Methods and apparatus for providing context and experience sensitive help in voice applications

• US 20050177373A1
• Filed: 02/05/2004
• Published: 08/11/2005
• Est. Priority Date: 02/05/2004
• Status: Abandoned Application

• Current Assignee: Avaya Incorporated
• Original Assignee: Avaya Technology Corporation Miami Lakes FLA US
• Inventors: Sanders, Derek, Tokarev, Vladimir Sergeyevich, Cooper, Robert S.
• Application Number:
  US10/772,483
• Publication Number:
  US 20050177373A1
• Time in Patent Office: Days
• US Class Current: 704/275
• CPC Class Codes: G06F 9/453 Help systems
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/227 of the speaker; Human-factor methodology
• CPC Class Codes: G10L 2015/228 of application context

Abstract

Systems and techniques for improved user prompting in the event of voice recognition failures. A system according to one aspect of the invention includes a central server hosting various modules employing voice recognition in order to interpret user inputs. When a module fails to recognize an input, it invokes a help application that selects an appropriate help prompt. The help application has access to user information including information indicating the user'"'"'s experience with each function of each module. The help application receives notification of the module and function being used when the unrecognized input was received and examines the user information to determine the user'"'"'s experience with the module and function. The help application categorizes a user as belonging to an experience category, such as novice, intermediate and expert based on the user'"'"'s experience with the function and selects a help prompt associated with the user'"'"'s experience with the function.

Claims

1. A voice recognition system comprising:

a plurality of modules for receiving voice inputs from a user and performing services based on the user response to the voice inputs; and

a help application for selecting a help prompt for presentation to a user upon receipt of an unrecognized or erroneous input, the help application being operative to identify an experience level of a user and select a help prompt appropriate to the user'"'"'s experience level.

2. The system of claim 1, wherein a function and module being employed upon receipt of an unrecognized or erroneous input is identified to the help application and the help prompt selected is chosen based on stored user information relating to the user.

3. The system of claim 2, wherein the user information includes information indicating the user'"'"'s proficiency in using the system.

4. The system of claim 3, wherein the information indicating the user'"'"'s proficiency includes information indicating the user'"'"'s proficiency with each function available to the user.

5. The system of claim 4, wherein the information indicating a user'"'"'s proficiency with each function includes a function usage tally for each function, the function usage tally for a function indicating a number of times the user has successfully employed the function.

6. The system of claim 5, wherein the help application employs the function usage tally for the function being used when an unrecognized or erroneous input was detected, in order to determine a user experience category for the user with respect to the function.

7. The system of claim 6, wherein the help application determines the user experience category by selecting an experience category associated with a range of function usage tally values within which the user'"'"'s function usage tally for the function falls.

8. The system of claim 7, wherein the help application tracks consecutive errors and recognition failures and selects appropriate help prompts in the case of consecutive errors and recognition failures.

9. The system of claim 8, wherein the user'"'"'s function usage tally for a function is updated upon each successful use of that function.

10. A method of help prompt selection, comprising the steps of:

identifying a function being employed when an unrecognized input was received;

identifying a user experience level for the function; and

selecting a help prompt appropriate for the user experience level for the function.

11. The method of claim 10, wherein the step of identifying the user experience level comprises assigning the user to a particular experience category and wherein the step of selecting a help prompt includes selecting a prompt associated with the experience category to which the user belongs.

12. The method of claim 11, wherein the step of identifying the user as belonging to a particular experience category includes examining user information indicating the experience category to which the user should be assigned.

13. The method of claim 11, wherein the step of examining user information includes examining a function usage tally for the function being employed when an unrecognized input was received and assigning the user to an experience category associated with a range of function usage tally values within which the user'"'"'s function usage tally for the function falls.

14. The method of claim 13, further comprising the steps of:

detecting consecutive errors or recognition failures; and

upon detection of consecutive errors or recognition failures, selecting a prompt appropriate for the user'"'"'s experience level and for the number of consecutive errors or recognition failures detected.

15. The method of claim 14, wherein the selection of a prompt is more dependent on the number of errors or recognition failures detected as the number of consecutive errors or recognition failures increases.

16. The method of claim 15, further comprising a step of updating the user'"'"'s function usage tally for a function upon each successful use of that function.