Adaptive voice recognition menu method and system

• US 6,697,460 B2
• Filed: 04/30/2002
• Issued: 02/24/2004
• Est. Priority Date: 04/30/2002
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: SBC Technology Resources, Inc. (AT&T, Inc.)
• Inventors: Bushey, Robert R., Martin, John M., Joseph, Kurt M., Knott, Benjamin A.
• Primary Examiner(s): WEAVER, SCOTT LOUIS
• Application Number:
  US10/135,143
• Publication Number:
  US 20030202640A1
• Time in Patent Office: 665 Days
• Field of Search: 379/67.1, 379/88.01, 379/88.04, 379/88.05, 379/88.06, 379/88.11, 379/88.14, 379/88.16, 379/88.19, 379/88.22, 379/88.23, 379/88.24, 379/201.01, 379/201.03, 379/917, 704/270, 704/275
• US Class Current: 379/88.22
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals
• CPC Class Codes: H04M 3/5166 in combination with interactive voice response systems or voice portals, e.g. as front-ends
• CPC Class Codes: Y10S 379/917 Voice menus

Abstract

A method and system for automated speech-enabled responses to caller requests for information prompts caller requests for information from a menu that lists options based upon the frequency of requests for information and for automated collection and updating of content based upon the feedback provided by customers. For instance, a task analyzer classifies information requested by caller opening statements with the classifications based on the task the caller intends to accomplish. For a menu that provides information on telephone services, classifications may include instructions on how to use a service, pre-purchase information, identification of the services that the caller subscribes to, the cost of services, post-purchase information and identification of the caller'"'"'s long distance carrier.

Claims

1. A method for automated speech-enabled responses to information requests made through a telephone network, the method comprising:

analyzing plural opening statements made by callers to classify the information request associated with each opening statement;

determining the frequency of requests for each information request classification;

identifying information request classifications having a predetermined frequency level; and

defining an opening menu to respond to caller information requests, the opening menu listing the identified information request classifications and a DTMF tone associated with each information request classification, each information request classification selectable by stating a voice utterance or inputting the associated DTMF tone.

2. The method of claim 1 wherein analyzing plural opening statements further comprises analyzing subsequent menu selections associated with each opening statement to classify the information request associated with the opening statement.

3. The method of claim 1 wherein the information request classifications comprise telephone service information.

4. The method of claim 3 wherein the opening menu comprises selections for how to use a service, pre-purchase information, identification of caller services, cost of services, post-purchase information and identification of caller long distance service carrier.

5. The method of claim 1 further comprising:

analyzing subsequent caller requests for information to classify the subsequent information requests associated with one or more of the opening menu information request classifications;

determining the frequency of the subsequent information request classifications; and

defining a subsequent menu listing to respond to caller requests for information, the subsequent menu listing having the subsequent information request classifications and a DTMF tone associated with each subsequent information request classification.

6. The system of claim 5 wherein the subsequent menu listing provides the subsequent information request classifications in order from most to least frequent.

7. The system of claim 1 wherein the opening menu lists the identified information request classifications in order from most to least frequent.

8. The system of claim 1 further comprising re-defining the menu to adjust for changes in frequency of information requests for a classification.

9. The system of claim 1 wherein defining an opening menu comprises listing the information request classifications in the opening menu in an order based on information request frequency.

10. A system for providing information to callers over a telephone, the system comprising:

an interactive voice response unit operable to provide voice prompts to callers and to accept caller inputs as either voice utterances or DTMF tones;

a menu interfaced with the interactive voice response unit, the menu defining prompts to callers for information, the prompts based on information request frequency; and

a task analyzer interfaced with the interactive voice response unit and operable to classify caller opening statements by the information requested and to track information request frequency.

11. The system of claim 10 further comprising a menu graphical user interface in communication with the task analyzer and the menu for ordering the prompts in accordance with the information request frequency.

12. The system of claim 11 wherein the menu prompts are ordered from greatest to least frequent information request.

13. The system of claim 10 wherein the task analyzer is further operable to analyze subsequent caller requests for information to classify the subsequent information requests associated with one or more of the opening statement information request classifications.

14. The system of claim 10 wherein the menu defines prompts to request information about telephone services.

15. The system of claim 14 wherein the telephone service information comprises information describing how to use a telephone service, describing telephone pre-purchase information, identifying the telephone services subscribed by the caller, describing the cost of telephone services, describing post-purchase information and identifying the long distance carrier of the caller.

16. The system of claim 15 wherein selection of a menu option for information describing how to use a telephone service provides a subsequent menu for selection of a definition of the telephone service, an explanation of how to use the telephone service, an explanation of how to set up the telephone service and the cost of the telephone service.

17. A menu for a voice recognition enabled interactive voice response unit for providing information to callers, the menu comprising:

a voice greeting that describes the menu as responsive to both voice recognition and DTMF tone caller inputs;

an opening statement voice prompt that requests a caller statement identifying information requested by the caller; and

plural menu option voice prompts, each menu option voice prompt requesting a caller statement or a DTMF tone for the caller to receive information associated with the voice prompt;

wherein the plural menu option voice prompts list information determined by an analysis of the frequency of information requested by caller opening statements.

18. The menu of claim 17 wherein the information comprises information about telephone services.

19. The menu of claim 18 wherein the plural menu option voice prompts comprise prompts for information describing how to use a telephone service, describing telephone pre-purchase information, identifying the telephone services subscribed by the caller, describing the cost of telephone services, describing post-purchase information and identifying the long distance carrier of the caller.

20. The menu of claim 17 wherein the plural menu option voice prompts list information ordered from most frequently requested to least frequently requested.

21. A method for automated speech-enabled responses to information requests made through a telephone network, the method comprising:

analyzing plural opening statements made by callers to classify the information request associated with each opening statement;

determining the frequency of requests for each information request classification;

monitoring a feedback frequency of receiving feedback from callers, wherein the feedback relates to speech-enabled response content;

automatically modifying the speech-enabled response content, based on the feedback frequency.