Restaurant or bar

Voice-interactive marketplace providing promotion and promotion tracking, loyalty reward and redemption, and other features

6934684

Abstract

The invention provides a system, method, and business model for an information system and service having business self-promotion, promotion and promotion tracking, loyalty or frequent participant rewards and redemption, audio coupon, ratings, and other features. A business or organization in which consumers call into a service using ordinary telephone, PC, PDA, or other information appliance, and make requests in plain speech for information on goods and/or services, and the service provides responses to the request in plain speech in real-time. Provides operating model for a telephone-based audio-interfaced goods and services information and referral service having merchant self-promotion features, including database provider storing merchant information; an interface for inputting merchant information into the database and for retrieving and editing the information; and an interface for inputting voice commands and data and for receiving merchant information and processed information from the database in response to the input voice commands and data.


Claims

1. An operating model for a telephone-based audio-interfaced goods and services information service, comprising:

an information database provider storing merchant information including a merchant identity information, at least one good or service associated with said merchant, at least one merchant audio voice coupon associated with the at least one good or service, and an end-consumer notification service data set;

an audio merchant interface including a first telephone for inputting said merchant information into said database;

a second telephone for inputting end-consumer spoken voice commands making a request for information and for receiving said merchant information in audio form stored in said database in response to said input spoken voice commands making said request for information, said inputting end-consumer spoken voice commands making a request for information occurring without a conversion of a text command into a spoken voice command and without the use of a computer; and

at least one speech server separate from said merchant interface and said end-consumer second telephone and operable to: (i) receive said input spoken end-consumer voice commands in audio form and translate said received input spoken voice commands into a first symbolic command form using a speech-to-text conversion engine so that said symbolic command form may be used to search said information database and retrieve an information item in a second symbolic form therefrom, and (ii) convert said retrieved second symbolic form information item into speech using a text-to-speech conversion engine for communication to said end user in spoken form.

2. The operating model in claim 1, wherein said second telephone comprises a cellular wireless telephone and said consumer also inputs non-voice commands and data from a keypad on said telephone handset in addition to said spoken voice commands in association with said request for information.

3. A system comprising:

a speech server receiving a spoken voice telephone call from an external telephone including spoken voice input commands requesting information on a good or service from an end consumer without requiring said end consumer to provide any text or symbolic command representation;

a speech-to-text conversion engine converting said received spoken voice input commands from said external telephone separate from said speech-to-text conversion engine over a wired or wireless telephone line to generate output text-based or symbol-based commands and data;

a database storing a plurality of data items including a merchant identity information, at least one good or service associated with said merchant, at least one merchant promotional audio voice coupon associated with the at least one aood or service, and an end-consumer notification service data set; p1 a database search engine searching the database for a particular data item in response to said generated output text-based command and data, said generated output-text-based commands and data being used to query said database to service said request for information by retrieving said particular data item;

a text-to-speech conversion engine generating a speech-based audio representation of said retrieved text-based particular data item identified in said database search; and

a server separate from said end-consumer telephone for communicating said speech-based audio representation of said particular data item to said end-consumer external telephone; and

means for communicatina and validating the promotional merchant audio coupon, said means for validating including means for inserting a spoken message to the merchant after the call has been connected to identify the caller as a valid service user and to validate the audio coupon.

4. The system in claim 3, further comprising a device selected from the group consisting of a personal computer, notebook computer, personal data assistant (PDA), information appliance, or combination thereof.

5. A system comprising:

a speech-to-text conversion engine converting speech-based audio input commands and data received from an external telephone separate from said speech-to-text conversion engine over a wired or wireless telephone line into output text-based commands and data;

a database storing a plurality of data items including a merchant identity infonnation and at least one good or service associated with said merchant;

a database search engine searching. the database for a particular data item in response to said output text-based command and data;

a text-to-speech conversion engine generating a speech-based audio representation of said text-based particular data item identified in said database search; a server separate from said telephone for communicating said speech-based audio representation of said particular data item to said telephone; and

means for communicating and validating a promotional audio coupon, said means for validating including means for inserting a spoken message to the merchant after the call has been connected to identify the caller as a valid service user and to validate the audio coupon.

6. A business model for a business in which consumers call directly into a service using an ordinary telephone and make spoken requests in plain speech for information and referrals on goods or services available from merchants, the service receiving a spoken voice telephone call from an external telephone including spoken voice input commands requesting information on a good or service from an end consumer without requiring the end consumer to provide any text or symbolic command representation for the request, merchants access the service to create and edit merchant information in real-time including editing a merchant audio voice couoon, and the service provides responses to the spoken consumer request in plain speech in real-time over the same ordinary telephone and presents an audio voice coupon for a merchant good or service, the service using an automated speech driven query and response to reduce cost of operation as compared to non-automated speech driven query and response services.

7. The business model in claim 6, further including providing a facility for a business to communicate a self-promotion of the business to the requestor consumer, said facility including a process for the business to create, change and edit a promotional message for an audio coupon and communicate/publish this audio coupon promotion message to the consumer user either in real time upon their request or when the consumer user makes an information inquiry.

8. A method comprising:

receiving a speech utterance in the form of an electronic audio signal directly from an end user consumer from a telephone, the speech utterance including spoken voice input commands requesting information on a merchant good or service from the end user consumer without requiring the end user consumer to provide any text or symbolic command representation for the request;

converting the speech utterance to text and extracting commands and optional data from said converted text;

searching a database storing a plurality of data items including a merchant data items and at least one good or service data item associated with said merchant for a particular one of said plurality of said data items in response to said converted text-based command and data;

generating a speech-based audio representation of said particular data item identified in said database search for playback over a telephone;

serving said speech-based representation of said particular data item including said audio voice coupon to said telephone

providing an audio processed merchant good or service rating to an end user consumer requesting information with said speech utterance; validating a promotional audio coupon or discount offering by a merchant; and generating a referral to a merchanl having a oredetermined rating.

9. The method of claim 8, further comprising: providing an audio processed merchant good or service rating to an end user consumer requesting information with said speech utterance.

10. The method of claim 8, further comprising: validating a promotional audio coupon or discount offering by a merchant.

11. The method of claim 8, further comprising: generating a referral to a merchant having a predetermined rating.

12. The method in claim 8, wherein said received speech utterance comprises natural human speech, and said converting comprises natural language speech processing to extract said commands and data into a text or symbolic command and data form.

13. A computer program product for use in conjunction with a computer system, the computer program product comprising a computer readable storage medium and a computer program mechanism embedded therein, the computer program mechanism, comprising a program module, the program module including instructions for:

receiving a speech utterance from a user from an audio-enabled communication device;

converting the speech utterance to text and extracting commands and optional data from said converted text;

searching a database storing a plurality of data items including a merchant data items and at least one good or service data item associated with said merchant for a particular one of said plurality of said data items in response to said converted text-based command and data;

generating a speech-based representation of said particular data item identified in said database search;

serving said speech-based representation of said particular data item to said audio-enabled communication device; and

at least one or any combination of: (i) providing an audio processed merchant good or service rating to an end user consumer requesting information with said speech utterance; (ii) validating a promotional audio coupon or discount offering by a merchant; and (iii) generating a referral to a merchant having a predetermined rating.

14. The method in claim 8, wherein the voice coupons are purchased by the merchant and delivered to consumers on a real-time basis.

15. The method in claim 8, wherein merchants can each create a plurality of coupon types including a lead coupon that is played when a user hears the merchant business address and phone number, and the user may optionally audibly browse the other merchant coupons.

16. The method in claim 8, wherein the system will generate a voice coupon reference number that can be used by the merchants and their customers to refer to the voice coupon during voice coupon redemption.

17. The method in claim 8, wherein merchants can target coupons to users in a certain geographical area, and wherein users will hear an audio voice coupon only if they call from a certain area.


Description

FIELD OF INVENTION

This invention pertains generally to voice-recognition based or speech-recognition-based interactive electronic commerce, and more particularly to systems, methods, and methods of doing business for providing automated interactive directory assistance information from a business or organization to a consumer in need of goods and/or services. The invention pertains even more particularly to systems, methods, and methods of doing business for providing automated speech-recognition driven query and response with business or event self-promotion features relative to businesses and events over ordinary wired or wireless telephone systems, PC systems, Personal Data Assistants (PDAs), and other communication and information appliances and devices.

BACKGROUND

Locating business establishments, such as for example a restaurant satisfying the particular need of a customer, has hereto for generally required access to printed directory listings, or more recently access to the World Wide Web using a personal computer. The availability of such references is frequently quite limited at the time the consumer desires to avail themselves of particular goods or services. For example, an out-of-town visitor driving in their automobile and approaching San Francisco might decide to stop and have dinner in a fine Italian restaurant and more particularly might like to have dinner in a fine Italian restaurant located in the particular area of the city, or to partake of a particular gastronomic delicacy. That visitor would likely not have a printed directory in their automobile or mobile access to the Internet to search for a restaurant satisfying their current need. Therefore, the visitor would likely either have to stop and asked for recommendations or drive around until a restaurant satisfying their needs might be located. Perhaps tens of minutes or hours later than desired. This approach is clearly inefficient, and the visitor may not have the dining experience expected if the restaurant they happen to see while driving turns out to have poor quality food, poor service, or both.

An analogous dilemma arises for other goods and services, whether provided to the local residents or to a visitor from out of the area. Frequently information is not available to a consumer (perspective purchaser) when he or she needs such information, and with the proliferation of a fast mobile lifestyle, there exists and need to provide such consumer information with readily available information appliances, such as conventional telephones, cellular phones, or other pocket or mobile devices that can provide connectivity to a service at minimum cost.

Frequently such device will have only sparse input/output capabilities. For example, a cellular telephone will typically have only a few display lines presenting text or symbolic data to a user, but has substantial audio input and audio output capability that can be used by the consumer.

Heretofore, speech-to-text conversion has generally been limited to word processing and or computer or control applications as the has required fairly substantial processing power and memory within a computer device. For example, speech to text conversion products made by Dragon Systems (Lernout & Hauspie, Speech Products U.S.A., Inc., 52 Third Avenue, Burlington, Mass. 01803) generally require an Intel Pentium II or Pentium III microprocessor, AMD K-6 or Athlon processor, or the like running in excess of 450 MHz and 128 MB of memory. This technology is not available in conventional or mobile telephones at this time. Text-to-speech conversion has been known but has not been utilized to provide an interactive interface between consumers and consumer information from telephone systems. Such continuous speech recognition systems also usually require voice training with the ultimate user to provide satisfactory results.

Furthermore, even for systems which provided some degree of consumer information over the telephone, such systems have either not attempted to generate business revenues through their operation, or have been unsuccessful in generating significant revenue in this manner. In part the lack of revenue success has been due to a low level of business participation in such systems, the inability of a business to control or modify their message in response to short-term business needs or to sell promote their businesses, as well as the lack of a particular incentive for a consumer to par take all of the information offered by the service. In fact, there may frequently have been a cost associated access to conventional information and referral services by consumers, even if only by virtue of the directory assistance by local telephone service providers.

Some conventional systems and methods have been limited to playback of recorded audio or audio playback corresponding to the content of web pages; but such systems have not integrated Internet or web-based interactions with voice or telephone based information provision. They have also frequently provided inferior voice interfaces that have annoyed callers rather than having provided a useful information experience.

Local as well as national businesses (really any business, merchant, marketing, or other organization) and their customers have made significant sacrifices in order to find each other and conduct a transaction for goods or services. These sacrifices result at least in part from the nature of the information resources available to match businesses and their customers, primary among these information sources are the printed Yellow Pages, on-line Yellow Pages, conventional 411 directory assistance, print media coupons, and on-line coupons.

Businesses (particularly local businesses) make sacrifices when relying on printed Yellow Pages because they are expensive, difficult to sort prices and options, cannot be changed once in print, and their effectiveness cannot readily be determined without additional time consuming and expensive surveys. From customers, or potential customers, perspective sacrifices are made because they are too heavy to carry, present too many choices so that it is difficult for a customer to figure out which one to call as they usually lack the information that may effectively provide the decision criteria, the information is usually stale (12-16 months old is typical), and many customers may forget to take advantage of coupon offers even when available. Printed Yellow Pages and related types of large bulky paper directories clearly have other problems and limitations.

Even on-line or Internet Yellow Pages or directories have limitations that present sacrifices for both merchants and their potential customers. From the merchant's perspective, for example, there are many different on-line directory providers and a business must make a decision as to which one or ones to associate with, a personal computer is required to access and update such directories and may not be available when and where needed, updating may require payment to an ISP or programmer, the directory reaches only those with an Internet connection, and additional fees must normally be paid to place ad banners. From a customer's perspective, the information provided is frequently inaccurate and limited, an interne connection is required to access the information, and either a personal computer or WAP enabled device is required to access.

Local directory assistance and more recently national directory assistance through either a 411 type information service is also limited. From a local merchant's perspective, even when a potential customer receives a correct number the connection may not be made because either the customer must redial to get the number or pay an additional fee to be connected. From a customer's perspective, there is relatively easy access but at a cost of between about $0.50 and $1.00 per call. The directory, particularly when using the wireless directory assistance, is notorious for providing wrong numbers and there is no ability to get the correct number without re-dialing and paying an additional fee. Additional charges are also typically billed for requesting address information if available.

Reliance on print media coupons also entail sacrifices. For example, they are static and cannot be changed once in print. It takes a relatively long period of time between developing the coupon promotion and getting feedback as to its success or failure. Redemption dates cannot be changed, and one merchants coupons frequently get lost in the noise of other unrelated or competing coupons. Customers find it difficult to identify relevant coupons, find it a hassle and hardly worth the time or effort to cut them out or save them, and have a difficult time keeping tract of expiration dates. in some social settings, they present a questionable social image, and cannot always be carried with the person so they are not available when an occasion to use them arises.

On-line coupons are somewhat of an improvement however they still present issues. They are expensive to place at high traffic portals for local merchants, and may still be lost in the noise of other promotions. There is low traffic at coupon only sites and their reach is limited due to the need for an Internet connection. The use of coupons may also be favored by groups that may not have ready access to the Internet. Customers also find them hard to locate and a hassle to pint, copy, or cut out. Access by many groups of persons, or by persons at the time they consider making a purchase may be limited.

In addition to the limitations and sacrifices made by merchants and customers relative to establishing a contact for the provision of goods or services, there currently exist additional problems and limitations relative to wireless data communication of advertising information. For example, infrastructure and methods have not been established or are in their infancy and must be developed before true wireless advertising can become widely available and accepted. Data ready telephone handsets exist but are in the minority and typically represent higher-end and more expensive models. Mobile phones in the hands of the majority of consumers do not provide for wireless interaction with merchants or for the receipt of audio advertising, marketing, or promotional information. Nor are they typically used for voice recognition applications. Merchants have been hesitant to participate in wireless data transactions and the lack of consumer interest in marketing messages generally have contributed to lack of development and progress in this area.

Techniques for building speech recognition applications are some what in their early development stage, however, some information is provided in the reference How to Build a Speech Recognition Application-A Style Guide for Telephony Dialogues, by Bruce Balentine et al., ISBN 0-9671278-1-5, published in 1999 by Enterprise Integration Group, Inc., 2410 San Ramon Valley Blvd., Suite 225, San Ramone, Calif. 94583; which reference text is hereby incorporated by reference.

Therefore there remains a need for a system, method, and business operating model and method that overcome these and other limitations. More particularly, there remains a need for a method of doing business, an information, directory assistance service and referral service providing easy access by businesses and consumers, as well as providing business self promotion and consumer feedback features that encourage use, generate revenues, and provide incentives for use by both businesses and consumers. Such services should advantageously provide more information than traditional 411 type directory assistance in terms of greater amounts of information, greater accuracy and currency of information, award programs, and other features that encourage businesses to participate and consumers to call and utilize such systems.

SUMMARY

The invention provides a system, method, and business model for an information system and service having business self-promotion features, including voice coupons, discounts, sales promotions or other special deals, ratings, and different categories of sponsorship and visibility to the calling public. In one aspect, the inventive business model is directed to a business in which consumers call into a service using an ordinary telephone, PC, PDA, or other information appliance, and make requests in plain speech for information and positive referrals on goods and/or services, and the service provides responses to the request in plain speech in real-time over the same telephone, PC, PDA, or other information appliance. The business model may further include providing a facility for a business to communicate a self-promotion of the business to the requester, as well as providing an audio promotional coupon (or other promotional item) to a requestor when the requestor completes a call to a business using the service.

In another aspect the inventive system extends these features to the Internet and inter-operates with the Internet in a web page based embodiment to provide an additional portal and greater interactive capability.

In another aspect, the invention provides an operating model for a telephone-based audio or speech recognition and text to voice interfaced information, enhanced 411 type directory assistance and referral service having merchant self-promotion features, comprising: an information database provider storing merchant information; a merchant interface for inputting merchant information into the database and for retrieving and editing the information; and a consumer interface for inputting voice commands and data and for receiving merchant information and processed information from the database in response to the input voice commands and data. The operating method may provide that the consumer interface comprises a telephone handset, and/or that the consumer also inputs non-voice commands and data from a keypad on the telephone handset. The operating model may also provide that the telephone handset comprises a mobile telephone.

In another aspect, the invention provides a system comprising: a speech-to-text conversion engine converting speech-based input commands and data received from an external device over a communication link into text-based commands and data; a data base storing a plurality of data items; a database search engine searching the database for a particular data item in response to the text-based command and data; a text-to-speech conversion engine generating a speech-based representation of the particular data item identified in the database search; and a speech server for communicating the speech-based representation of the particular data item to the external device.

In another aspect the invention provides audio coupons that operate as incentives for consumers to use the inventive system.

In still another aspect, the invention provides system and methods for submitting and retrieving ratings for goods and/or services.

In yet another aspect, the inventive system and method assists in providing directory driven wireless commerce.

In yet another aspect, the inventive system and method provide a promotion and advertising channel that has geographical and sociological reach and the speed needed in today's dynamic financial and commercial markets.

In still another aspect, the inventive system and method provide a voice-interactive dynamic market place where individuals (particularly locals) call to save and businesses (particularly local merchants) call to publish sales promotions in real-time or near real-time.

In still another aspect, the inventive system and method communicate information on an as requested basis that goes beyond the telephone number.

In yet another aspect, the inventive system and method provide instant savings with voice coupons published by local merchants.

In still another aspect, the inventive system and method provide an advertising free initial experience where voice or audio coupons are only heard attached to businesses that the caller has requested or searched for.

In even another aspect, the inventive system and method provide for hands-free navigation with voice commands on any telephone or device supporting telephony.

In yet another aspect, the invention provides a low cost 411 directory assistance with added informational features that is easy to access.

In yet another aspect, the invention provides benefits to merchants including but not limited to targeted reach, instant promotion, instant or near-term feedback, and an optional free Internet web presence.

In still another aspect, the invention provides benefits to common carriers and telephone companies who save conventional 411 costs, process higher call volumes, and attract new customers.

In yet another aspect, the invention provides a business model in which voice coupons are sold for distribution, a monthly fee is charged for subscription to the basic service, and additional charges are levied and collected for business category sponsorship.

In still another aspect, the invention provides a business model in which the providing organization partners with a print yellow page or other business directory publisher and/or with direct marketing organizations to subscribe merchants, businesses, individual professionals, or other organizations.

In a further aspect, the invention provides a business model in which the providing organization partners with a yellow page, wireless providers, telephone companies, and conventional 411 call centers to generate call traffic and thereby increase revenue.

In yet another aspect, the invention provides a business model in which conventional 411 directory assistance providers are replaced by the inventive system to save carriers 411 costs and to offer a new shared revenue channel and business model.

In another aspect, the invention provides a business model in which new customers are solicited and provided with value added services.

In still another aspect, the invention provides a business model in which direct marketers are provided with a new coupon or promotion distribution channel.

In still another aspect, the invention provides a business model in which new business is brought to direct marketing organizations through the voice channel of the inventive system.

In still another aspect, the invention provides a business model in which direct marketing organizations are provided with rapid marketing feedback for their clients and customers.

In still another aspect, the invention provides a business model in which print yellow page and print business directory publishers increase their existing revenues by increasing the yellow page or directory ad size sold by virtue of ad space required by a trademark and/or "voice coupon" icon or logo.

In still another aspect, the invention provides a business model in which print yellow page or other print directory publishers are provided with increased usage of the yellow pages or directory to show which vendors provide immediate savings.

In still another aspect, the invention provides a business model in which yellow page or other print directory publishers are provided with an enhancement in their market positioning by virtue of their providing an more complete and compelling offering.

In still another aspect, the invention provides the closest locations for a particular requested category where the location of the caller is known from a caller location input, cellular signal triangulation, GPS position determination, or other position or proximity location means.

In still another aspect, the invention provides means for a merchant to interact with the system using either voice or web interface and select templates for the type of social, economic, political, age, gender, profession, or other image the merchant wants to portray and the type of promotion message the merchant wants to publish with a small number of mouse clicks, key strokes, or voice commands and prompts.

In still another aspect, the invention provides system and method for establishing user groups ("My" . . . group) and communities based on lifestyles, usage patterns, interests and interest levels so that a registered user can subscribe to a group of multiple groups where merchant listings and other relevant information is given a priority. Such group or community may include a bicycling enthusiast who can subscribe to the bicycling group and when he calls, he says "My bike" and will then be offered services that has something to do with biking.

In still another aspect, the invention provides means for obtaining ratings, in which once a caller gets connected to the business through the talk411 service system, after a period of time measured in hours the service calls back the caller to ask for ratings or to collect feedback to improve service, where the caller has either registered to permit this inquiry or does not have caller ID blocked.

In still another aspect, the invention provides system and method for merchants to post customer testimonials so that future callers can hear these messages as a reference that may help make a choice of which merchant they want to be connected with, and optionally, as the service gets used callers can leave testimonial messages which the business can choose to post for other users access.

In still another aspect, the invention provides system and method for merchants to post key words on the voice system or internet site which can be used as a search term by the caller and that will be used as a navigation pointer to the posting merchant. In a further aspect, this key word or phrase based search may be used in connection with a new product or service (new movie, new CD, new restaurant, or any other product or service) so that the caller may speak (or otherwise input) this key word and be matched with one or more merchants offering it. In an even further aspect, priority use of such key word may be auctioned to merchants for priority playback to callers.

In still another aspect, the invention provides system and method allowing merchants to post their promotional message or company information in multiple ways including to record their own, select from a voice talent who would record the text the merchant put in the system using voice, a personal computer, or in any other way; or just type in an let a text-to-speech processor convert it.

In still another aspect, the invention provides a coupon aggregation and translation engine and service allowing aggregation of different formatted coupons from online sites and reformat such coupons to a standard Dialsurf or other format that allows them to be played over the telephone phone.

In still another aspect, the invention provides user call back to remind the user to rate a recently used local merchant service.

In still another aspect, the invention provides means for an over the telephone offer for a user to become an instant member to a community or coupon distribution list using email or other communication means once the user asks for a specific category. In a further aspect, if the user is registered and set up "my411" features, the user gets coupons for this category delivered to his "my411" voice box.

In still another aspect, the invention provides merchants the ability to identify specials in their "additional information" or "coupon message" that is used to find that merchant when those words are used over the phone in the key word search mode

In still another aspect, the invention provides system and method for publishing secret words in local newspapers, Internet chat rooms and other community oriented online and offline boards, where they can be used on the phone or on our web site as a password to enter a sweepstake or win a prize, and to thereby provide a beneficial marketing tactic to increase sales of print papers and increase traffic to online portals

In still another aspect, the invention provides voice coupon targeting based on area code and prefix, city, geocoded location, GPS location, zip code, cross streets, vicinity of a milestone, major tourist areas, major landmarks, airports, night clubs, entertainment centers, shopping malls, restaurants, and the like.

In still another aspect, the invention provides means and business model for facilitating spread of secret words through the word of mouth initiating from someone in the company to provide access to privileged information, prizes, etc. to enhance the repeat user experience

In still another aspect, the invention provides the use of live agent interaction on a random call basis to provide a surprise element to enhance the user experience, where live agents can be celebrities.

In still another aspect, the invention provides user choice or automatic choice of voice of the Talk411 attendant based on gender, age, interest, and other selection criteria.

In still another aspect, the invention provides user choice to select synthesized voice of a celebrity as the automated attendant.

In still another aspect, the invention provides system and method for insertion of trivia questions where correct answer wins a prize from a local merchant.

In still another aspect, the invention provides a business model in which 411 directory assistance call centers are provided with an added revenue stream to improve slim profit margins, to increase call volume by providing a desirable information service, to keep their current carrier customers with value added services, to decrease their operating costs and overhead by reducing the number of human employees, and by overcoming severe local competition on wireless carriers.

The invention also provides further apparatus, system, method, operating model and business method, computer program and software, and computer software program products that interoperate with the inventive systems and methods.

BRIEF DESCRIPTION OF THE DRAWINGS

Additional advantages and features of the invention will become readily apparent upon reading the following detailed description and appended claims when taken in conjunction with reference to the following drawings, in which:

FIG. 1 is a diagrammatic illustration showing an exemplary embodiment of the inventive system.

FIG. 2 is a diagrammatic illustration showing an exemplary embodiment of speech server functionality.

FIG. 3 is a diagrammatic illustration showing an exemplary embodiment of a new business user (merchant) interaction with the inventive system.

FIG. 4 is a diagrammatic illustration showing an exemplary embodiment of an existing registered business user interaction with the inventive system.

FIG. 5 is a diagrammatic illustration showing an embodiment of a general consumer user interaction with the inventive system.

FIG. 6 is a diagrammatic illustration showing an exemplary implementation of the inventive directory service on the Web.

FIG. 7 is a diagrammatic illustration of a flow-chart for a method of interaction between the inventive system and a caller, including call flow procedures and procedures for articulating messages to the caller and for receiving inputs from the caller.

FIG. 8 is a diagrammatic illustration showing an embodiment of an alternative call handing procedure by the inventive system and service call center.

FIG. 9 is a diagrammatic illustration showing an exemplary coupons web page.

FIG. 10 is a diagrammatic illustration showing an exemplary get business web page.

FIG. 11 is a diagrammatic illustration showing an exemplary member menu web page.

FIG. 12 is a diagrammatic illustration showing an exemplary member registration web page.

FIG. 13 is a diagrammatic illustration showing the relationships of several web pages to each other.

FIG. 14 is a diagrammatic illustration showing an exemplary Internet web page according to invention for a Home page.

FIG. 15 is a diagrammatic illustration showing an exemplary Internet web page according to invention for a Directory page.

FIG. 16 is a diagrammatic illustration showing an exemplary Internet web page according to invention for an Alerts page.

FIG. 17 is a diagrammatic illustration showing an exemplary Internet web page according to invention for a Surveys page.

FIG. 18 is a diagrammatic illustration showing an exemplary Internet web page according to invention for a Rewards page.

FIG. 19 is a diagrammatic illustration showing an exemplary Internet web page according to invention for a Ratings page.

FIG. 20 is a diagrammatic illustration showing an exemplary Internet web page according to invention for a Hot Deals page.

FIG. 21 is a diagrammatic illustration showing an exemplary Internet web page according to invention for an Events page.

FIG. 22 is a diagrammatic illustration showing an exemplary Internet web page according to invention for a Cool Idea page.

FIG. 23 is a diagrammatic illustration showing an exemplary Internet web page according to invention for a Voices page.

DETAILED DESCRIPTION OF EMBODIMENTS OF THE INVENTION

It will be appreciated that conventional methods and approaches to matching a consumer with a merchant, business, or other individual or organization are unsatisfactory at best, and severely lacking, in many situations. The limitations and sacrifices are described in the Background section of this specification. Even with approaches that are more modem than conventional printed yellow pages or telephone number providing only 411-type directory assistance, the actual improvement measured in terms of merchant, consumer, or industry adoption has been minimal. A combination of technological, philosophical, and psychological needs and forces has conspired against the success of such attempted improvements.

Attention is therefore first directed to an overview of the inventive system, method, computer programs and procedures, and Talk411 service and then to a discussion of certain needs and goals that are desirably satisfied for such an information system to meet the needs of merchants, consumers, and service providers as well. These goals do not rise to the level of requirements, as a system that fails to meet all of the goals may nevertheless provide advantageous utility, but arguably the more goals that are satisfied, the more satisfying the implementation may be. Many of the features described in the following paragraphs are also clearly optional and although they provide great utility and many benefits, would not be required in a basic system or method.

Talk411 is a one-stop fresh information source that offers instant promotion capabilities to local businesses using the telephone or the web. The information service is free for consumers. It is a promotion service for local businesses similar to the Yellow Pages, except it can be accessed with voice interaction on the phone or with display devices equipped with an Internet browser.

The information database (content) may be acquired in any number of ways, including from one or more of the following ways: (i) Purchased from local telephone operators, such as Pacific Bell or other operator, (ii) Input from local businesses who subscribe to the service, or (iii) Content partners who provide local information on the web.

The local businesses can subscribe, access and maintain the information they want to communicate to the consumers in at least the following two ways: (i) Call the Talk411 service and voice navigate/input, and (ii) Browse the Talk411.com and input by typing the information, uploading business information such as logo, etc. The consumers can access the information in several ways as well, including: (i) Call the Talk411 service and voice navigate and speak naturally, and (ii) Browse the Talk411.com web site.

Selected features that a business may user are now described. These are examples to illustrate some interesting aspects of the invention and are not limitations or requirements of any particular embodiment.

Businesses can, for example: (i) Subscribe, register, and input their business information and promotional messages using the telephone or the web site. (ii) Become a member to the standard service, where they pay a low monthly fee in exchange for extended business information prepared specifically for the category they belong. This information is provided upon information request about that specific business. (iii) Become a Category Sponsor, where a message is played/displayed when a caller request businesses in a category, prior to playing the choices. (iv) Purchase Category positions for an additional monthly fee, where they purchase the right to be announced/displayed at a priority level when the callers/browsers request businesses in a specific category. Category Level 2 position for the month will ensure that the promotional message is announced/displayed in second place when the caller requests businesses in that category. If no Category position is purchased, information will be pulled from the database on a random basis. (v) Become a General Sponsor for a larger fee, where their message gets heard as the first message as the call gets answered. (vi) Purchase Audio Coupons, where the callers get a discount on products/services if they call Talk411 service and request information about the specific businesses, upon hearing a prompt from Talk411 or in any of the promotional messages mentioned above. Audio Coupons can be purchased with a credit card on the Talk411.com web site, or on the Talk411 telephone service. (vi) Get reports on access/call patterns in their category. (vii) Get consumer ratings of their businesses upon participation in the "BayHits" discount program. This program allows registered users to get discounts from participating businesses in return for feedback on products/services delivered.

Consumers can, for example: (i) Obtain free of service charges, unlike the 411 directory services which cost about $0.46 to about $0.95 (local phone charges still apply) get local business information. (ii) Have hassle free navigation with voice on the telephone, focused web site with local business information on the Talk411.com web site. (iii) Obtain more information than just the number and address for the local businesses. More relevant information, since the business chooses the type of info they want to communicate. (iv) Locate businesses of interest by speaking naturally and specifying a category. (v) Locate a business by specifying zip code, name, street, phone number or other relevant information. (vi) Get discounts with Audio Coupons from promoting businesses. (vii) Become a Reviewer by registering to the "BayHits" service and get discounts in exchange for rating businesses on the Talk411 service.

From a certain perspective, for a system to be adopted and used by businesses and consumers, the system must not only be technically viable but must also satisfy the needs of the users. In this vain, the inventive system and method are designed to satisfy certain overall philosophical and subjective requirements as well as other more specific telephone service, Internet response, merchandising and marketing needs. In the paragraphs immediately below, some of the concepts and mechanisms that will facilitate providing a high quality of service and acceptance and adoption by the business, organization, and consumer communities are described. These should be interpreted as goals and guidelines rather than requirements of the inventive system or method, as they need not all be adopted or implemented to sustain a successful implementation. Rather they contribute to implementing a commercial system and method, and as such provide options for a commercially successful system, method, and business model.

A caller or user (whether the business or other organization providing talk411 information of a customer making an inquiry) needs to be able to interact with the system with the utmost ease and simplicity. Speed and simplicity should desirably only be compromised for accuracy.

The effectiveness of the system and service maybe assessed and measured with the ability of the caller/user getting information with no more than one phone call in most cases. A key benefit for the callers are convenience and savings from local merchants/businesses, hence improving the quality of their lives. Key benefits for the merchant/business/organization are the speed of deploying promotions (or other information) at a low cost, ability to get quick feedback from the marketplace and change their promotion or message dynamically, hence generating quality self-targeted leads. The first impression of the users should desirably be to fun, fast, accurate, and helpful information retrieval.

With these top-level needs in mind, attention is now directed to telephone service preferences. Prompts and menu designs, especially for audio prompts, menus, or other indicators. Sound may desirably be used as an indicator where possible to shorten the amount of words, and a minimum (or reduced) number of questions should be asked to get the answer. Where a response may not be clear, it may typically be beneficial to ask the user to confirm the input, in order to avoid providing incorrect or inappropriate information, and if still not clear, connect to live operator. As consumers are already familiar with U.S. nationwide basic 411 directory assistance, there may be desirability in emulating the basic 411 experience with additional courtesy and information. In some embodiments, limit the registration to phone number and password only, and direct potential member to web site to complete the registration, perhaps offering some incentives for such web based registration. Simple navigation using a limited number of intuitive key words to access information with a special lead phrase are desirably used. As a positive courtesy, a greeting at entry and hang-up may be provided. With respect to response time, it is desirable that the wait not exceed the typical time for operator assisted directory assistance, and a wait time of no longer than about 10 seconds (and preferably less than about 5 seconds) for information.

When a caller makes an inquiry, the phone number is retrieved based on the business (or organization) name and location, and the caller is then asked whether to connect to that phone number. The location can be any designation, for example any or all of an address, a city, a zip code, or major cross streets or other recognizable location. If a location is not specified, then various rules or policies may be used to select, for example, in one embodiment, three possibilities are deliver by city or street names. In the event that there is more than one of the business in the area searched, for example there may be three Radio Shack locations in the search area, then the caller may be presented with three alternatives and locations selected according to any scheme, and asked for a decision with which to connect. In either case, the selection may be made either by the number or by the location.

Embodiments of the inventive system and method provide optional features including "more" information, and a "bayhit" feature. The "more" feature is provided for business or organizations that prefer to provide additional information than standard phone number, address, type of business information. A "bayhit" feature relates to a rating popularity or recommendation feature as described elsewhere herein. Businesses or organization, or specific locations of a business or organization, having more information may be identified using a distinctive sound, tone, word, or other audible indicator to identify them as having "more" information that may be accessed. Use of a distinctive sound reduces the time required to communicate the information and also reduces the computational burden of delivering additional spoken words. The bayhit feature (or equivalent by another name) may be indicated by a different sound, tone, or word than the "more" feature, and businesses or organization that are both more and bayhit may be identified with some third set of audio indicators or hybrid or composite sounds.

Where an audio or voice coupon is involved, the audio coupon may advantageously be played or enunciated at the time the phone number is delivered. Alternatively, the caller may be given an option as to delivery of the audio coupon.

When a caller request or inquiry is processed by the system, the system advantageously retrieves a predetermined number of the closest matches to the requested category and location. In North American culture, three seems to be the appropriate number, however, providing one to 4 of the closest matches might represent the normal range. In some contexts, providing five or more or the closest matches might be appropriate with due consideration given to the brevity of delivering so many alternatives.

Advantageously, the names of the matches are delivered along with the availability of any coupons (when the coupon feature is implemented) and optionally the content of the coupon. Relevancy may be based on a user location input, this location input may be expected to optionally be provided automatically by caller identification based location determining mechanisms, cell phone base station triangulation mechanisms, or phone based Global Positioning System (GPS) location determining mechanisms. When such caller location information is available by whatever method, the search and relevancy may be a location sensitive search.

Upon delivering the predetermined number of matching (or most nearly matching businesses or organizations), the caller is requested to chose from these or to request delivery of additional matches. Either a predetermined number of additional matches may be delivered or the system may request the caller specify how many additional matches, with an optional limit imposed by the system to reduce the burden on system resources and the total connect time. In one embodiment, the number of matches delivered at each stage is three matches, and the total number of additional requests that can be made is four. More generally, the number of matches delivered for each request and the number of requests for additional matches for the same call may be limited to suit local markets and customs.

The system desirably recognize the caller's choice by business name or by either a vocalized queue number or phone keypad press corresponding to the number. IF one of the matches has more than one location in the relevant search area the caller may be presented with the alternative locations or address information when that business is selected. In this regard, the system may filter a business that has multiple locations so that the predetermined number of matches are to different businesses rather than to multiple locations of the same business entity. If the caller is interested in that business entity, then the caller is provided with information as to the multiple locations and asked to select or choose the desired location.

The phone number for the selected business or organization (and location) is then delivered and the caller is optionally but advantageously asked whether the caller wishes to be connected. The ability to be connected is particularly advantageous for a caller using a mobile phone where materials to write the phone number may not be readily available. Automatic connection is advantageously free to the caller and may be free to the business or may incur some additional fees. Various alternative credit, bonus, fee and non-fee based mechanisms may be implemented.

In some embodiments, it may be desirable for the caller to provide a phone number to a particular business name and location, and to have the system search and verify a business name by saying the phone number, and getting the business name back with the coupon if available. This feature may be referred to as a reverse search by phone number with optional coupon retrieval. This feature permits the caller to effectively make an inquiry as to the availability of a coupon offer at a particular business establishment, to make comparisons between business establishments, and to make a decision accordingly.

In a further embodiment, a coupon request may be made by the caller asking for a category alone, a category and location, or any other item or combination of items on which the database may be queried. Based on the results of such a category or other criteria search, the coupon may be provided. Note that although this and the above discussion focus on the voice based system, these coupon mechanisms (particularly the ability to perform directed searches on the basis of business identity and category) may also be implemented for the Internet based service.

Desirably, audio coupons delivered in this manner should have a maximum permitted length. For example, in one embodiment coupons are limited to 10 seconds and in another embodiment to 5 seconds or less. Caller consumers are not generally interested in receiving additional advertising, rather they want to know the essence of the offer, what discount, free item, cost saving, or other enticement is being offered, and no more. They are then free to make an inquiry once connected to the business, merchant, or other organization as to further information. Again, there is desirability of satisfying the needs of the caller consumer, the desires of the business, and the practicalities of system implementation where the number of lines, processors, servers, and other software and hardware infrastructure and impacted by call volume and duration.

Once the caller selects the matching business or organization with which to connect, the system dials and connects the call, checks for an answering machine tone, delivers a message that informs the business that this is a Talk411 call and identifies the coupon promised to the caller, and transfers connection with the business to the caller. Optionally, the caller may be connected to the business during this hand over or transfer process, but normally this is disadvantageous as it appears to add undue complexity to a process that the caller should view as transparent and effortless. Advantageously, in one embodiment of the inventive system and method, during some predetermined time interval following the connection to the selected business, the caller can take action to terminate the call with the business and reconnect with the talk411 system. This presupposes that a connection be retained with the talk411 system, or that a re-connection mechanism be provided. These mechanisms are readily available in the telephony art.

This predetermined time period is anticipated to be in the 15 second to 2 minute time frame, and nominally about 30 seconds so that if the caller determines the selected business does not satisfy the need of the caller, he or she can try again without undue difficulty or expense. In one embodiment, the caller action involves pressing a key or combination of keys so that commands to the system may be clearly distinguished from a verbal discussion with the proprietor or employee of the business. A tone signaling scheme will likely be more readily interpreted than a voice command, particularly if automated switching and routing is involved.

Embodiments of the system provide the ability for a caller to rate or otherwise provide positive or negative feedback regarding a talk411 member business or organization. Desirably, the rating of any particular member should be limited in some way to avoid the possibility of a single caller, unduly influencing a member rating in either an absolute or statistical sense. The limit may be rules that provide for a maximum total number of rating inputs for a business, a limited number per month or per year, or some other rating restriction rules. The goal is to provide other callers with a rating that fairly represents the opinion of all callers that have had an experience with the business, and not to allow either an individual that has had a bad experience to rate the business negatively multiple times. These limitations would also prevent an individual from inflating the rating of a member business by calling multiple times with a positive rating. Control mechanisms would also be desirable to keep the proprietor of the member business from self-rating in an unwarranted manner. These controls may involve technological mechanisms and/or legal contractual agreements with the member businesses.

In one embodiment, a caller desiring to rate a member business has to sign on or register in some manner so as to identify themselves. For example, the caller may sign on to the system by saying a phone number and a password. Individuals desiring to participate in rating member businesses may be provided with certain benefits, points in a points or award program, discounts, or other promotional and/or marketing enticements for their participation. In one embodiment, the system implements a Rate2save points program wherein a registered caller earns points that may be redeemed for goods or services in exchange for rating businesses of organizations. In another embodiment, registration is not required, however, the rating made is associated with the caller's telephone number if the system can determine the callers caller ID so that multiple ratings of the same business from a single telephone number cannot be made, or cannot be made within predetermined time intervals. In the desire to maintain privacy, a message may also be played indicating that the caller's telephone number will be examined and compared for the purpose of ratings control and requesting permission to continue.

A caller will say the name of the business, location or other information such as phone number to quickly identify the business and rate on some predetermined scale, such as for example, a scale of 1-10, or any other numerical or non-numerical scale that permits the caller to use other adjectives such as for example poor, good, great, exceptional, too expensive, no parking, or any rating information that would be of use to a later customer. Ratings in multiple areas may also be permitted. For example, a restaurant may be rated according to food quality, food portion, service, price, wine selection, parking availability, or other factors of interest to potential customers. As system evolves and direct or indirect feedback is obtained from businesses and consumers, particular rating categories and scales found to be useful will be identified for the various categories of business and the ratings categories may be updated and modified accordingly.

Once the caller rates the business, points or other benefits that the caller rater may be entitled to will be reported and the system will hang up. These ratings will then be compiled and made available to subscribed member merchants and businesses on the web as well as the telephone.

For embodiments of the invention that provide a hit or popular site (restaurants, night clubs, coffee shops, bookstores, etc), best sites, highly recommended sites, or the like listing or directory such hit sights are referred to as Bayhits after the San Francisco Bay/Silicon Valley region where the invention was developed. Other regional areas may adopt other names for such attractions, such as Twin-City Hits (Minneapolis-St. Paul Area), LAHits (Los Angeles), or any other title whether containing "hits" or not. Callers may make requests by category such that such BayHits (or equivalent) may also be found by category and delivered in the manner already described.

While many of the advantageous features of the inventive system and method are provided using voice recognition and text to speech processing over existing telephony infrastructure, other administrative facets may advantageously be taken care of using an Internet Web site or live agent. Live agents may also be occasionally used to set up and register. These administrative features may only be implemented where the clarity and preciseness of textual input and/or the volume of input increase the efficiency and accuracy of the process. These administrative procedures may also involve hybrid voice and Internet components. For example, an initial stage of registration or sign-up may be made over the telephone with minimal information provided over the telephone. The callers are then directed to a web site where registration may be completed. This form of registration may apply to either or both of businesses and consumers, for example consumers enrolled in the Rate2save points program. The advantage of such on-line or web based registration being that such registration does not tie up a phone line that might better be made available for responding to caller requests, and the accuracy associated with typed or menu driven registration may be somewhat greater given the current state of voice recognition technology. It is important that data entered into the database be accurate, and such accuracy is promoted by test input. This does not preclude the use of voiced or spoken input and it is likely that as voice recognition technology improves that the differences between text or character driven digital input and recognized and converted speech to digital inputs will lessen.

Merchants, businesses, and other organizations may register by providing their phone number and a password for a trial period. This may include a simple registration with minimal information obtained over the telephone and direct callers to the web site to complete the registration in order to take full advantage of all merchant and business services and options. In instances where further registration beyond the trial period are required, especially if the additional registration is required for the merchant or business to avail themselves of additional capabilities, such registration may be completed over the telephone, over the Internet, or through the use of paper document of electronic contracts or agreements.

After or as a component of registration, the basic information for the business, such as formal and common name of the business, business address, business phone number, are verified so that the business may subscribe to the inventive Talk411 service. If the business or organization is not in the database contact is made though a customer service representative or other means. Credit card or other bank or payment information is provided to initiate of continue subscription to the service. The business or organization is then provided with an opportunity to record a message to be heard by a caller when callers ask for more information about the business. In one embodiment, the duration of this business introductory message is limited to a predetermined period of time, usually between 10 seconds and 1 minute, and more typically not to exceed 20-30 seconds. An opportunity is given to review and re-record the message, to confirm the message, and ultimately to publish it. In one embodiment of the invention, provision is made to allow a celebrity or other talent to record the message. This optional service and feature is described in greater detail elsewhere in this specification.

Various levels of membership are supported and different optional features may be made available at the various membership levels. Membership and subscription fees may in some instances be tied to membership level or to options selected.

Whether provided as a membership level or an option within one or more membership levels, a business or organization once subscribed (or reg period), may purchase sponsorship for the category they belong to by specifying the category, number of months category sponsorship is desired, and level of sponsorship. In one embodiment of this category sponsorship feature, the sponsor business is put in an ordered list or queue (or random pool) along with others who have paid for the same level of sponsorship. When its turn comes (whether through a sequential ordering or via a random or statistically determined selection), the name and phone number (along with a attached coupon, if any) for that category sponsor business or organization will be heard if a caller asks for businesses by category.

In one embodiment, there are three levels of sponsorship. Level 1 consists of those sponsors who paid the highest to have a greater frequency of presentation to callers (a higher hit rate), level 2 with lower frequency or lower hit rate and cost, and level 3 with the lowest frequency and hit rate and cost. In another embodiment, a category sponsor may pay for a fixed number of placements per week or per month. Other placement parameters may pertain to geography, time of day, length of message, or other parameters that may tend to drive more business volume to the category sponsor. While category sponsorship is one type of sponsorship that may be implemented, sponsorship opportunities may exist for other aspects of the Talk411 service.

Voice or audio coupons may be created and purchased once a business or organization have subscribed or registered. Typically, a merchant will telephone and specify the number of coupons he or she wants to purchase and provide credit card information or other billing information and confirm the purchase. Usually, coupons will be bought in quantities in excess of 1000, though there are no limits on the quantity that may or must be purchased as any single transaction. The message that will be played in the form of a coupon is recorded (by the merchant or an agent of the merchant (such as a hired talent), along with the name and phone number of the business. This coupon message will not normally exceed a predefined duration, though different durations may be imposed for different types of business, membership entries, geographic regions, or other criteria. Typically the voice or audio coupon will not exceed 30 seconds in duration, more usually not exceed 15 seconds, and frequently will not exceed about five seconds. Some flexibility may be provided according to a minimum and/or maximum information that the merchant is entitled to record.

In one embodiment, once a caller asks for the business, hears the audio coupon and gets connected to the merchant, the merchant is notified by the system that this is a Talk411 call and play the same coupon message to remind the merchant (or an employee of the merchant) about their promotion so as to avoid any ambiguity or problem associated with an uniformed employee contesting the caller's (now customer's) entitlement to the coupon offering.

In one of the embodiments, providing for talk411 ratings, a simple cumulative rating that is compiled from the raw ratings of the users is delivered when the merchant calls to check the rating. Security protections such as password or numerical code may be required to access such ratings, particularly when greater detail is provided to the merchant than to the general public. There may also desirably be a ranking within the category to which the business belongs. These ratings will likely be adjusted from time to time and evolve to suit the needs for each category. In one embodiment, there is a simple 1-10 rating, where 1 is the lowest rating and 10 is the highest rating. Other embodiments provide for callers to rate the business on multiple criteria as may be relevant to the category.

It will be apparent to those workers having ordinary skill in the art that the inventive voice or speech based system provides numerous features, capabilities, and advantages over existing systems. The inventive system and method also provide for both separate Internet or world wide web based interface as well as to an integrated system providing both voice/telephone accessed and character/Internet based access. All, or nearly all, of the information described for the voice/telephone accessed features and capabilities are also available for access through a computer graphical user interface (GUI) over the web. It is not required to be able to interact with the web-based user interface with voice, or to connect the user to the merchant with the phone in this phase, however it is desirable to be able to play back the messages during an Internet web-based session that were recorded on the phone. It may even be desirable to allow a user to record a message using local available computer resources and upload the message to the system, however, this is not required.

In other embodiments of the invention, the user is provided with the capability to select a business and connect to the business using the Internet with Voice Over Internet Protocol based technology.

Desirably, the graphical user interface, provides a differentiation between a recorded message versus a text message prior to someone clicking the prompt, so the user expectation is set properly.

An embodiment of the Internet web-based graphical user interface is now described. For reasons of simple access, the web pages are desirably sized and formatted to display on a single viewing screen without the need to scroll. Advantageously, this is accomplished independently of the user's currently set screen resolution. Intuitive buttons and menus are advantageously provided where access and interaction is as simple as clicking on the available selections, and a single mouse click is used where possible. Quick page access is a high priority to encourage use without undue effort, therefore any graphics are desirably used judiciously only where necessary.

Simple and clear icons, tabs, drop downs, and the like features are used. Some space may be reserved for ad banners and other content that may provide useful information for the user or a source of revenue for the site, site operator, or talk411 provider. Coupons will desirably be highlighted so the user can easily understand that they are coupons, and provide facility for printing either as part of the web page or via a separate but readily available free program.

Information storage, search, and retrieval are desirably fast and efficient to minimize any delays. Search and retrieval of business/merchant information such as name, phone number, location, address (any elements of the address) from any of the known data above.

Search by category is supported, desirably with result priority given to category sponsors, and to those with coupons. Reserve a small section where BayHit businesses can be featured with a distinct graphic, linking to their business information.

The result of a search will yield a short list of found or matched (or closest match) businesses with the business information for a predetermined number of (typically 2-5 and usually 3), category sponsors visible in most of the page. The user may then click and select others in the list if not satisfied with the sponsors found. Each result page served with the next button should desirably serve the same format as above, except changing the sponsors and the short list.

For the business user, subscribed business users may be provided with one page where they can provide essential business information that will show as a result to a user search. They can select from an available selection of templates, upload their logo or graphics, and input their information. There will be a dedicated part for displaying their coupons if purchased. Custom pages not conforming to the template may be available as part of the standard subscription, available only to higher membership levels, or available at a higher fee. In one embodiment, customization is permitted but only within a certain range of options that preserve the talk411 look and feel.

A dedicated management page may optionally be made available for the subscribers. Subscribed business will be able to track their coupon promotions, category sponsorships, how they are rated in the category, and their account history. Other information may also be provided.

There will desirably be a provision to provide call volume, page hit rate, and comparative business results for businesses in the same category. This feature may be enabled when the volumes reach predetermined levels. Based on account activity and ratings, the talk411 service provider or an agent thereof will publish recommended action promoting our category sponsorship and coupon opportunities. Therefore it is desirable though not required that some space dedicated to Talk411 be reserved on every merchant page.

In one embodiment, a business, merchant, or organization are able to type in or otherwise enter or present the Coupon message or the Business information into the provided field which will then be translated into speech when a caller asks for the information over the telephone. Alternatively, Business/Merchant will be able to type in the information, and request the information to be recorded by a professional voice (or audio) talent from the list provided on the web site. This alternative feature is provided via an optional voice talent portal (VTP). Through this portal or other means, a user is able to select, such as by clicking on an icon or using a pull down menu, and hear a recorded clip of a message delivered by a registered voice talent as a preview. Each registered voice talent will have a private page where pending jobs will be posted and messages to be recorded displayed. Once the voice talent completes the recording of the job, he/she will be able to upload the wave file (or other file format) for the recording to their private page, and verify and publish it for review by the business. A phone alert with the recorded message will be made to the merchant or organization to confirm and publish the message.

Upon completion with business approval, their credit card or other account will be charged or invoiced with a portion of it paid to the voice talent. Using the facilities available over the Internet, including the ability to use email and record, store and communicated high quality digital recordings, it is anticipated that such process should not take longer than 24-72 hours, and that for highly sought after talent, not more than one week. Additional fees and time may be required for premium talent. The ability to provide a quantity or volume of messages to a voice talent is a key value for merchants and businesses who want professional recording of their messages and don't want to pay the full hourly fee for such talent, or invent the overhead associated with contacting and negotiating a contract with the talent or their agent. Using the inventive system and method, talk411 aggregates the messages to be recorded and lets the merchants share the cost of voice talent recordings.

In one particular embodiment of the inventive Talk411 service, the design of the system is guided in part based on empirical results. These results suggest that the voice-recognition should desirably be highly accurate, preferably accurate better than 95% of the time. Automated announcements should desirably be a compelling and use consumer tested voice. Response time to voice inputs should ideally be no more than about 1 second in most cases, and typically no more than 3 seconds when searching. Some fine tuning of the input and search timing will occur when the system is fielded. Callers should desirably be able to interrupt any time and the system and method should desirably be able to deal with this. Transactions and identities should desirably be kept secure by the high standards. For consumer calls, when the system does not understand after two tries, it should desirably bounce to a live operator, or take other action in an attempt to understand the consumer. For example, if a live operator is not available, the system may use a more sophisticated (but possibly slower) processing algorithm to understand the speech. For business subscriber calls, when they say, "help" there should desirably be some automated help, and when they say "save me" they should desirably be connected to a customer service representative.

Various hardware and software configurations, computer program code constructs, procedures, and mechanisms, as well as a variety of different operating scenarios and protocols for accomplishing these and other goals are now described.

Having now described embodiments of the overall system as well as several operating scenarios, attention is now directed toward a description of two particular embodiments, an Internet web based embodiment and a voice processing based embodiment. Attention is first directed to a description of the voice processing based system including the voice processing hardware and software.

Voice Recognition Based System and Method

FIG. 1 shows the top or high level system architecture 102 and consumer user (or caller) 101 access points for a preferred embodiment of the invention. A cellular phone 106 (or other wireless device), standard telephone 118, either an analog (POTS) or digital, can be connected to the architecture 102 using a standard telecommunication link 120, such as a standard telephone line 122, ISDN line 124, cable 126 or DSL line 128. For a cellular phone 106, it is understood that there is a cellular base station 108 and a cellular switch 110 interposed between the cellular telephone 106 and the PSTN 112. The incoming call 130 from the cell phone 106 or the telephone 118 goes through a PSTN 112 and telephone switch 114 and gets picked up by the Speech server 116, which is connected on one side 117 to the telephone switch 115, and on the other side 119 to a computer network 130 such as for example the Internet.

Access maybe via the Internet, for example access using wireless devices using or compatible with the Wireless Access Protocol (WAP). Data may therefore be communicated in a WAP compatible format. WAP is a standard set of protocols for wireless Internet access which can deliver special Web pages to portable devices such as smartphones and palm-portables. In current versions it relies on the use of WML instead of HTML and so on. These systems generally support Java and Windows CE, among others. WAP Version 1.0 has been released and is hereby incorporated by reference along with variants and extensions thereof. Other versions are under development.

The user (or caller) 101 can access the information or data 132 that resides in a database 134 within the Information Center 136 and the Web Site 138 through interactive voice commands 140 and/or through keypad presses 142 on the caller's 101 device, such as on the cellular telephone 106 or standard wired telephone 118. In a preferred embodiment of the invention, only the caller's voice commands are used. The caller's voice commands 140 are recognized and translated into one of the variations of Voice Extensible Markup Language (VXML, VoiceXML, or VOXML) commands 144 by the Speech Server 116 using a speech-to-text conversion engine 146 and once translated into VXML are used to retrieve the information 132 from the Information Center 136 database 134. VXML is an extension or elaboration on the XML (Extensible Markup Language) standard known to workers in the art and not described in greater detail here. Information concerning the VXML Forum is available on the world-wide-web at http://www.vxmlforum.org/ and Version 1.0 of the VoiceXML specification dated 07 Mar. 2000 which is hereby incorporated by reference is available in Adobe Acrobat format at http://www.vxmlforum.org/specs/VoiceXML-100.pdf.

Once the data 132 is retrieved and transmitted back to the Speech Server 116, the text information from the data 132 is converted to speech using a text-to-speech conversion engine 148 within the speech server 116 and played back to the caller 101 using the caller's device 106, 118. Speech server 116 also generates and plays back (presents) pre-recorded or synthesized menu commands 150 to the caller. The system architecture connects 102 the information database 134 to the Internet 130 (or other local or global network of computers and/or information appliances) which can also be accessed with a display device 152 such as a personal computer (PC) equipped with a modem 154 (wired or wireless), a smart phone 156, other wireless phones or devices, a PDA or palmtop device 158 or any computer or other information appliance or device that can be connected to the Internet (or other local or global network) with the ability to display standard Hypertext Markup Language (HTML) pages or other formats interpretable by the computer 152. Access to such wireless devices may use the Wireless Access Protocol (WAP) and/or other protocols or standards.

It is noted that although reference is made to several current industry standard data and information formats and protocols, such as HTML, XML, and VXML, the inventive structure and method are not limited to these particular formats and/or protocols or to the versions of these protocols in existence at the time the invention was made as those workers having ordinary skill in the art will appreciate the capabilities and features provided by these formats and protocols may be provided in other ways and that future versions of these formats and protocols will also support the inventive structure and method.

Embodiments of the inventive system may desirably incorporate and utilize natural language speech recognition. In such implementations, the user can naturally speak and the system interprets the user's speech to extract the request or inquiry. The provides additional flexibility for a user as that user does not need to know any particular commands or request rules or syntax. Natural speech processing and artificial intelligence are known in the art and not described in greater detail here.

The system and/or method described herein may be deployed as a separate installation or deployed through application service providers (ASPs) who have the hardware and software deployed either nationally, or in the local areas. Teleron and Voiceeo are examples of such providers.

FIG. 2 shows an embodiment of Speech Server 116, some of its functions and functional connectivity to receive a switched telephone call and to interact with the Internet 130. Speech Server 116 performs several tasks such as the task of providing a Network Interface 160 to the analog or digital phone network that provides the switched phone call 162, Automatic Speech Recognition (ASR) 146 or speech-to-text conversion (STT), Text-to-Speech conversion (TTS) 148, runs the application or application program 164 that control and manages the phone calls 162 and the Interactive Voice Response (IVR) 166. IVR refers to the interactive voice response which is conventionally a menu driven response provided in response to an input. A user is asked to say something (for example, "Press or say 1 for marketing, press or say 2 for research", etc.) However, the inventors are not aware of any such conventional systems that provide ASR or text-to-speech in connection with IVR. In one embodiment of the invention, the Speech Server 116 is a personal computer equipped with Dialogic Antares automatic speech recognition boards and other products. Information regarding the Dialogic Antares boards are available from Dialogic Corporation, 1515 Route Ten, Parsippany, N.J. 07054-4596 U.S.A. and on their web site at http://www.dialogic.com/products/indx_abp.htm.

Operation of the exemplary Speech Server in the system is now described. The incoming call 162 is answered by a network interface card 160, such as for example a Dialogic network interface card (analog or digital). A prompt is played to the caller 101 over the caller's device 106, 118 asking the caller to say the selected item 170 from the available selections on a voice or audio menu. When the caller responds to the request, the application 164 passes the voice data to the auto speech recognition block 146, such as may be provided by a Dialogic Antares™ board loaded with an Automatic Speech Recognition (ASR) software. ASR software is available from several sources, including for example from Lernout & Hauspie (L&H) (LERNOUT & HAUSPIE Burlington, Mass., Phone: 1-781-203-5000, Fax: 1-781-238-0986, http://www.lhs.com) or SpeechWorks (SpeechWorks International, Inc., 695 Atlantic Avenue, Boston, Mass. 02111, Tel: 617.428.4444, Fax: 617.428.1122, http://www.speechworks.com).

A Dialogic Antares board-based automatic speech recognizer (speech-to-text) 146 translates the voice data into ASCII text (or another code or symbols) that identifies the spoken words and returns a text or other symbolic representation of the results to the application 164. The application 164 accesses, via for example a T-1 line or faster Internet connection, the database 134 of the Information Center 136. Real-time (or near-real-time), active vocabularies are generated at run-time using the database's 134 ASCII text or symbols. The application uses the ASCII text from the database 134, passes it to a second Antares board 148 running a text-to-speech (TTS) algorithm. The TTS algorithm generates the final voice or audio information that is played to the caller 101.

Voice processing hardware is now described relative to one practical embodiment of the invention, using a Dialogic Antares D41E printed circuit card configured for a Microsoft Windows based computer that supports up to four analog telephone lines and provides a telephony interface and voice processing functions such as playing and recording speech messages and collecting or dialing DTMF digits. The embodiment also utilizes a Dialogic Antares 2000/50 platform is used in one embodiment, and allows the Nuance Voice recognition system (or other voice recognition system with appropriate modification) to operate properly on the Dialogic platform by providing echo cancellation and end pointing services for the system). The installed card will support up to 16 channels of voice recognition.

The Antares 2000 family platform provides a standalone open digital signal processor platform for telecommunication applications. The Antares hardware platform provides four independent TI TMS320C31 32-bit floating-point DSPs running at 50 MHz, each with high-speed SRAM, enabling algorithms to be easily ported to the Antares™ board. Multiple memory options provide flexible solutions for different applications. For example, 512 KB (128 K words) or 2 MB (512 K words) local SRAM are available per DSP and 4 MB (1 M word) or 8 MB (2 M word) global DRAM memory are available per board. SCbus™ (or PEB™) connectivity allows standard access to off-the-shelf call processing products and provides the capability to build higher density systems. Up to 32-channel capability is available. Drivers are presently available for MS-DOS®, UNIX® (SCO®, UnixWare™, Solaris®, and AIX®), OS/2®, and Windows NT®.

The Antares platform open development environment uses the Antares board and an ANSI C Compiler and Assembler/Linker for the DSPs. SPOX support includes the run-time SPOX DSP operating system and SPOX-KNL kernel development kit. Additional software includes the Antares kernel , which integrates the DSPs into the SCbus system and a down loader to download software to the board.

A single Antares board can process up to 32 channels of digital voice and digital telephony information received from a network interface board via the SCbus. The SCbus bit stream from the network interface board can contain both audio (digitized voice) and telephony signaling information. The bit stream is applied to a SC2000 ASIC chip which has an internal switching matrix. Under firmware control,. the SC2000 chip can connect any external bus time slot (1024 for the SCbus or 32 for the PEB) to any TDM (time division multiplexed) bus time slot on the Antares board. The Antares board uses four C31 DSPs, each with its own Static RAM (SRAM) to separate and process data for any assigned time slot. Each DSP processes data based on downloaded firmware stored in its SRAM. After processing the incoming data, each DSP communicates with the host PC via global Dynamic RAM (DRAM). Kernel services are available on every DSP. The Antares local kernel provides all the necessary tools to read and write data to and from the TDM bus, which operates as a PCM (pulse code modulated) highway. By using the DSP's internal DMA (direct memory address) capability, the kernel can bring multiple frames of PCM data (up to 32 time slots each) into DSP SRAM from the TDM bus. Each DSP connects to the local TDM bus via a serial interface. The TDM bus is implemented with 32 time slots that are mapped into 1024 external SCbus time slots by the SC2000 chip. Each SRAM contains the downloaded firmware that controls DSP processing and also provides the DSP with dedicated RAM for its data processing operations.

A control port on the Antares platform accepts operational commands from the host PC and monitors DSP-to-host PC interrupt status. This control port controls Antares platform operations such as: DSP reset; communications with and firmware downloading from the host PC via shared global DRAM read/write operations; the transmission of interrupts, control, and status information to and from the Antares platform via the global resource circuits. When the system is initialized, firmware to control each DSP's processing is downloaded from the host PC to the DSP's SRAM. This downloadable firmware enables feature enhancement, application changes, and upgrades.

Additional information on this item as well as on other products that may be used in conjunction with the inventive system may be obtained from Dialogic Corporation is an Intel company, with world headquarters at 1515 Route Ten, Parsippany, N.J. 07054-4596 U.S.A.

The above described Dialogic hardware and the computer system in which it is installed, inter-operates with an operating system (such as for example, a Microsoft Windows operating system, a Linux operating system, a Unix operating system) and application program software including device drivers.

In one embodiment, the Talk411 system is an integration of commercially available software applications and custom applications. These commercial software and custom software components include operation under a Windows NT Workstation (v4.0 Service Patch 4) operating system environment which is available from Microsoft Corporation of Redmond, Wash., U.S.A. The software may alternatively be adopted to interoperate with any of the other commercially available operating systems such as earlier and later versions of Microsoft Windows, such as for example Windows 2000 Professional; or non-Windows operating systems such as Linux, Unix, and others as are known in the art.

The core voice processing application is Parity software's VOS Version 6W (Version 6 for Windows). Parity VOS (V6W dated 07-1999) is available from Parity Software, Three Harbor Drive, Suite 110, Sausalito, Calif. 94965. Parity Software is a Dialogic company which is owned by Intel Corporation of Santa Clara, Calif. Parity Active Data Objects RLL (ADO RLL) is also used and is available from Parity Software, Three Harbor Drive, Suite 110, Sausalito, Calif. 94965. The Nuance voice recognition support the voice recognition requirements. Nuance Speech Recognition Software (v6.2.1) is available from Nuance, 1005 Hamilton Court, Menlo Park, Calif. 94025. A VOS-Nuance integration Run-Time Link Library (RLL) provides an interface between the Parity VOS software and the Nuance speech recognition system. An embodiment of a VOS-Nuance Integration Run-Time Link Library (RLL) is available from TeleVoice, Inc., 11767 Katy Freeway-Suite 425, Houston, Tex. 77079. These software and system features are described in greater detail below.

The Parity VOS system includes a VOS Script file or files which have been compiled to binary code which can be executed by the VOS runtime-engine. In Version 6W, VOS licenses are required both to run the system (a run time license) and to compile the VOS script (a developer license), both of which are available from Parity Software. (A developer license can be used as a run-time license but a run-time license cannot be used as a developer license.) Licenses are controlled by a hardware-key ("software sentinel" or "dongle") that plugs into the parallel port of the system.

Additional functionality to the basic Parity VOS script language may be achieved by external modules known as Run-Time Link Libraries or RLLs. Parity Software provides some RLLs with Parity VOS and other RLLs which may be desired to implement additional features are available from third-party vendors. RLLs are used for example, to enhance the VOS capabilities to include such features as voice recognition, text-to-speech, access to ODBC-compliant databases and convert numeric, date and currency values to speech.

The application specific program modules used for the inventive Talk411 system and method include a Nuance voice recognition interface module and a SpeechPro module which converts numeric, date and currency values to speech. Other providers of the broad class of text-to-speech converters (of which numerals-to-speech conversion is a simple subset) are known in the art. For example, Parity VOS provides a similar RLL called SmoothTalker with the VOS application. Those workers having ordinary skill in the art will appreciate that there are a number of competitive commercial products that may be utilized and that the rapid development in this technology area will likely result in a proliferation of software and hardware products that may be used in conjunction with the inventive system and method.

In Windows environments (such as in Microsoft Windows NT, Windows 2000, or the like environments), RLLs take the form of DLLs or Dynamic Link Libraries. RLLs are normally specified in a file (such as for example in a RLLS.TXT file) which must be referenced both when compiling and when executing. These programming and compilation conventions and procedures are known in the art and not described in greater detail herein.

By convention, script files used by the application are designated by a".vs" (vos script) or ".vh" extension, and compiled VOS scripts are designated by a ".vx" extension. Exemplary embodiments of selected ones of the files are summarized below. Additional detail is available in programming manuals and user documentation from the vendor, either by mail at the address provided elsewhere herein or via an Internet web site provided by each of the vendors.

TABLE I
Exemplary VOS Configuration Files
cpb.def Stores Dialogic specific configuration information
(Channel Parameter Block)
CPB.PAR Compiled cpb.def file
hedge=2 Detect greeting on trailing edge for outbound calls
nbrdna=6 Rings before no answer signal given on outbound
intflg=8 Specifies to use full Call Progress Analysis for outbound
calls
init.def Stores VOS initialization settings
INIT.PAR Compiled VOS initialization settings
sc_pcpa=1 Use Call Progress Analysis
sc_words=20 Maximum words in a phrase (used by SpeechPro)
sc_gtdterm=1 Let hang-up tones terminate any voice functions
fil_buf=16 File copy buffer size (in Kilobytes)
pr.def Defines indexed speech files
PR.PAR Compiled pr.def file
tone.def Stores PBX specific Tone configurations (generated by
Dialogic PBXpert prog.)
TONE.PAR Compiled tone.def
(Note that ".def" files are the source files, ".par" files are the compiled version of the ".def" file)


Parity VOS configuration files are listed and briefly described in Table I. Parity VOS Source and Executable code files are listed and briefly described in Table II. Table III lists and describes various Other VOS related files. Additional description is provided relative to files and procedures that have been developed to support the inventive system and method and are not part of the commercial software programs.

It is noted that although Parity VOS is used in the particular exemplary embodiment, the inventive system and method are not so limited and that those workers having ordinary skill in the art will appreciate that other programming language and methodological constructs may be used to achieve the invention, such as for example implementations using VoiceXML, C++, or other scripting or programming language or languages.
TABLE II
Aspects of VOS Source and Executable code
master.vs This file "kicks off" the Talk411 application for each voice
line
master.vx Compiled "start" file
Spro.vh Header file for SpeechPro commands and constants
spro.vs VOS source code for SpeechPro functions
talk411.vs This is the main application file
talk411.vx Compiled main application file
VrCmd.vh Header file for VR commands and constants
(Note that ".vs" and ".vh" are source code, and ".vx" is executable code)
TABLE III
Other VOS Related Files
directory2.mdb Microsoft Database file used to store demo business info.
LocalRlls.txt File used to specify VOS RLLs for compilation
Rlls.txt File used to specify VOS RLLs for Run-Time


The master.vs file is the file specified when launching the Parity VOS run-time engine. It contains all of the code necessary to open up the database, initialize and configure the voice lines and the voice recognition channels and spawn or launch the Talk411 application for each voice line. The presence and general structure of master.vs (and it's compiled partner master.vx) are known to workers using Parity VOS and other such commercial programs. Master.vs for the talk411 system is a file that does some set up, such as, determining how many phone lines are installed, and launches one talk411.vs application for each of the installed lines. It is somewhat like a computer system startup file and initializes some variables, establishes connection to the database that stores the business/merchant/organization information that will be retrieved in response to caller's requests, and then spawns one copy of talk411.vx for each line that it detected as being installed. Master.vs is specific to the talk411 application but it is generic in that each application would usually have a master. Several of the specific tasks performed by master are now described in somewhat greater detail.

Master.vx first determines and defines the number of voice lines installed. This represents the number of simultaneous callers (usually use function that detects number of hardware channels of lines installed, but where the number is stable, this may be hard coded). (Restrictions may also be applied where the number of lines is greater than the number of software licenses.)

Master.vx then opens a connection to the database in master that is shared by the applications. This database can be a local database either within the same physical box, co-located in a separate box or device, or located remotely. In one embodiment, the database is a Microsoft Access (Access 97) compatible database, however other database types and formats may be used. Advantageously, Parity VOS includes database functionality, so that a database created in Access may be used by VOS without requiring Microsoft Access or separate database application program. In one embodiment, the same data base file (dictionary32.mdb) is used to store and retrieve all of the business, merchant, individual, or other organizational material for both the voice recognition based talk411 and the Internet based talk411.

Master.vx code instructions then initialize the Nuance voice recognition that sets up the mapping between the inbound call line and the Nuance resources. It also maps (or sets up an association or routing of) the Nuance processing channels to the voice caller channels.

Master.vx then spawns or launches one copy of talk411.vx application for every line installed (subject to the number of licenses). There is an iterative loop that increments for the number of lines available. Operation then continues under the control of each talk411.vx compiled application.

The Talk411.vs script defines how the actual call handling and processing happens. The general flow of the call from the talk411 code perspective is as follows. First, a code procedure module "Initialize( )" sets up the telephone line or communication channel specific parameters and prepares the line or channel to accept a call. This line or channel may be wired or wireless and so the term line or channel is used in its broadest sense. Next, a "WaitForCall( )" procedure waits for a ring signal on the line and when it arrives, takes the line off-hook and prepares it for processing. An "InitializeVoice( )" procedure module sets up the voice recognition parameters for this line and prepares for a recognition.

A "MainMenu( )" procedure is where the call originates after the above initialization. At this point we set the Nuance Engine to the ".MainMenu" grammar and wait for a result. It returns a series of "slots" each with a valid keyword. The call is then processed based on the result of this recognition. If the caller said the name of a business, we give them the business information. For example, if the caller spoke a "Type" of business, the caller is provided with information on business of that type. Alternatively, the caller may either have spoken a command (such as help, quit, member information, or the like), in which case the command is handled, or the spoken utterance may not have matched any options in the grammar. Failure to match may be due, for example to the intended spoken utterance not being defined in the grammar, or the quality of the received utterance may have precluded matching. Various programmatic options are available requesting the caller to re say the utterance or to provide a different command or utterance. The talk411.vx file is the compiled version of the talk411.vs file.

A exemplary embodiment of the talk411.vs is now described. The talk411.vs script file and its compiled version talk411.vx is application program that controls how a telephone call to the talk411 service is processed. An interface exists which permits signals sent from any telephone handset or other telephony capable device to be received and recognized by a computer or more precisely by a circuit or PC board designed to handle and process such signals. Telephony-to-computer and computer-to-telephony products made by Dialogic that provide this signaling and call processing capability are described elsewhere herein. In the recent past, interaction between telephone systems and computers primarily relied on touch tone frequency signaling, such as may be accomplished by pressing a series telephone keypad buttons to generate readily recognizable signals, or equivalently to have a computer program generate such tones. More recently, new technology supports spoken voice command and data in a system that provides voice recognition to interpret the electronic signal generated from the spoken voice, interpret that signal, and convert that interpreted signal into one or more commands or data items that can be processed by the computer. Effectively, voice is used to give or respond to an inquiry. These hardware and voice recognition components are known in the art and therefore are not described here in greater detail. References are also provided to companies and organizations providing this type of technology as standard off-the-shelf commercial products.

The talk411.vs, talk411.vx, and other associated or related files provide an additional layer or layers on top of the conventional telephony hardware and software, the voice recognition software and possible optional hardware or DSPs (voice-to-computer), and computer-to-voice (also referred to as text-to-voice), that direct the system in handling a call in a particular way and to provide particular features. The inventive software and system configuration used in conjunction with existing or customized voice recognition features constitute a novel computing and information processing machine and method.

As stated elsewhere in this specification, the Parity Software VOS Version 6 for Microsoft Windows is used as a foundation platform. In its native uncustomized form, it supports only touch tone signaling, and does not support voice processing or recognition in its native form. Nuance has provided a voice recognition software (Version 6.2.1) available from Nuance at www.nuance.com, but this software is not directly compatible with the Parity VOS software. Therefore, a third major software component integrates the Nuance voice recognition software with the Parity VOS software so that the three components accept voice or speech input, interpret it, create a character or a string of characters, and provide that character of character string in the manner of one or more computer keystrokes or other digital data stream that is readily interpretable by the computer.

More specifically, the Parity VOS software handles the interface to the phone system (including how to answer a call when a phone ring indicator signal appears, how to play messages to the caller after it answers, and how to accept touch tone signals form the caller. It also handles branching to further alternative processing based on what action is selected by user, and handles hang-up or call termination by hanging up the line, and resetting the line and the system and software to receive the next call. In essence is it responsible for call control. In many applications it is the only application software that is needed, particularly if the system is a touch tone based systems. The Parity VOS software version 6W does not have native voice recognition built in. Parity VOS version 7 is available, and it is anticipated that Version 8 will be released shortly. Version 8 may provide some additional voice processing or recognition capability, or provide an interface or other integration with Nuance Voice Recognition (and possibly including others, such as SpeechWorks software). The interface software is presently a piece of software that permits use of Nuance Voice Recognition software and returns a result from that software to VOS for processing.

Parity Software also provides a developers toolkit in the form of a programing language and compiler for that language, so that software code, including data structures and executable instructions, can be developed to tell the VOS software and other components of the system what to do. These developer tool kits and documentation for their use are available from Parity Software and are not described in greater detail here. The talk411.vs script is developed using this VOS toolkit and compiled into talk411.vx. This script and its compiled version executes within the hardware to provide control the particular manner in which call flow is handled, what inquiries and responses are permitted (in conjunction with various dictionary and grammar filed described elsewhere herein), how to interpret specif commands and situations. In essence, the talk411.vs and talk411.vx files control the life of a call. Note that multiple phone lines and interactions on a shared personal computer or server are permitted. In one embodiment, twenty-four simultaneous calls on twenty-four different lines are supported. With additional hardware boards and an appropriate configured computer, additional lines and calls are supported. Portions of an exemplary talk411.vs file are set forth in the specification. Selected components of the talk411.vs script file are listed and described and it is expected that those workers having ordinary skill in the art in light of the description provided herein, including the description of the function and operation, the commercial availability of Dialogic, Parity and Nuance Software and Hardware, will understand how particular aspects of call handling are implemented without detailed exposition of all portions of the script, dictionary, and/or grammar source or executable files.

The exemplary talk411.vs file includes the following components or functions: main menu {MainMenu( )}, business information {BusinessInfo( )}, connect to business {ConnectToBusiness( )}, more business information {MoreBusinessInfo( )}, recommend others {RecommendOthers( )}, type menu {TypeMenu( )}, modifier menu {ModifierMenu( )}, rate business {RateBusiness( )}, member entry {MemberEntry( )}, play promotional message {PlayPromo(ID)}, play coupon message {PlayCoupon(ID)}, record promotional message {RecordPromoMessage( )}, purchase coupons {PurchaseCoupons( )}, record coupon message {RecordCouponMessage( )}, check score {CheckScore( )}, category sponsor {CategorySponsor( )}, get credit card information {GetCreditCard( )}, confirm information {Confirm( )}, get voice response {GetVoiceResponse(Grammar, FirstPrompt, SecondPrompt)}, parse input string {ParseString(InputString)}, process slot {ProcessSlot( )}, remove input string spaces {(RemoveSpaces(InputString)}, remove input string dashes {RemoveDash(InputString)}, remove input string parenthesis {RemoveParens(InputString)}, save recording {SaveRecording( )}, set end time in seconds {SetEndSeconds(seconds)}, initialize {Initialize( )}, wait for incoming call {WaitForCall( )}, initialize voice {InitializeVoice( )}, terminate voice {TerminateVoice( )}, play message {Play(MessageName)}, play message b {Playb(MessageName)}, speech process the phone number {SproPhone(Number)}, and, play speech message that can be interpreted by the caller {PlayI(Prompt)}.

These functions are largely self explanatory by their name. For example, the MainMenu( ) function lets the caller select a business, a type of business or enter the member area. The BusinessInfo( ) function reads the business information from the database and speaks the business Name, Phone Number, and any optional features such as the BayHit Message, Promotional Message, and Coupon Message. The ModifierMenu( ) menu function is used if the caller only said a modifier such as Coupons or BayHits. The PlayI(Prompt) function will play a speech message that can be interrupted by the caller speaking, where the result of their speech is thrown away, and where the function returns true if the message was not interrupted and false if the message was interrupted.

By way of further example, the MainMenu( ) function portion of the talk411.vs file is duplicated in Table IV. Exemplary portions of talk411.grammar code are also providd in Tables V and VI. As will be appreciated from the syntax of the MainMenu function in the table, this function lets the caller select a business, a type of business or, entry to the member area. Variables used by the function are reset, a greeting is optionally played, and a voice response is received from the caller. A determination is then made as to whether they spook the name of a recognized business, or of a business type, and whether any business type modifiers were spoken. The function also monitors to determine if any commands were spoken, such as for example "Help", "Quit", or "Member".

In particular, the GetVoiceResponse(".MainMenu", Prompt, "MainMenu") syntax results in playing a prompt entitled "MainMenu" that speaks: "Thank you for calling talk 411, please speak the name of a business or a type of business and we will get the information for you." Note that in one embodiment of the invention, the words or phrases are played back from earlier recordings, and that in a different embodiment they are synthesized based on the words or text. Either approach may be utilized and some implementations may utilize a combination of the two. In general, the speech quality is better using pre-recorded speech and is preferred.
TABLE IV
Exemplary embodiment of Main Menu from talk411.vs script file.
func MainMenu( )
#===============================================
# This function lets the caller select a business, a type of business or
# if enter the member area
#===============================================
do
voslog("Line: ", Line, " Main Menu");
# if Reset the VR Variables before getting the next VR
Business="";
Modifier=""
Type=""
Command="";
if (GreetingPlayed)
Prompt = "MainMenu";
else
Prompt = "Greeting";
GreetingPlayed = true;
endif
# if Get a Voice Response from the caller
GetVoiceResponse (" .MainMenu", Prompt, "MainMenu") ;
voslog ("Business=", Business);
voslog ("Modifier=", Modifier);
voslog ("Type=", Type);
voslog ("Command=",Command) ;
# if Did they speak the name of a business?
if (Business strneq "")
BusinessInfo ( );
else
# Did they speak a business type?
if (Type strneq "")
TypeMenu ( );
else
if (Modifier strneq "")
ModifierMenu ( );
else
# Did they speak a command
switch (Command)
case "Help":
Play ("Help") ;


case "Quit":
Play ("Goodbye") ;
TerminateVoice ( ) ;
case "Member":
MemberEntry ( ) ;
default:
Play ("Help") ;
endswitch
endif
endif
endif
until (Command streg "Quit") ;
endfunc
TABLE V
Exemplary .MainMenu Grammar from talk411.grammar
Nuance Voice Recognition Component
. . .
.MainMenu
[
Business
Type
(Modifier Type)
(Type Modifier)
Modifier
Commands
]
. . .


Assuming the caller spoke something the system detect what they said. If they spoke the name of a business then the string returned would not be empty. If the string is not empty, it is processed as if the caller spoke the name of a business. If the type variable has been set, the system knows the caller spoke a type of business and we process that. The program and system parse through and analyze the results that come back from the voice recognition process (Nuance) and process it. Note that the voslog operation merely displays to a display screen. It is further noted that this exemplary main menu is taken from a simple example of a talk411 script file used for demonstration purposes.

In connection with the get voice response (GetVoiceResponse) operation, the ".mainmenu" parameter is a reference to a Nuance voice recognition grammar file that will be used in processing the voice response. When programming Nuance, Nuance requires the identification or definition of each symbol, word, number, or phrase that a caller may say in response to the prompt. Many or even most common words and numbers, as well as common phrases are defined in files provided by Nuance; however, current versions of the software do not allow unlimited words such as might be supported by desktop voice recognition applications. That additional level of flexibility and sophistication invariably require prior training by the speaker so that the speaker's voice characteristics are understood by the speech or voice processing software.

Within the ".MainMenu" portion of the talk411.grammar file are six top-level grammars: Business, Type, Modifier Type, Type Modifier, Modifier, and Commands. Anything with a capital letter as the first letter, such as capitalized "Type" means that the item or type is defined later on in the file or in another file. Further down in the same talk411.grammar file appears a block