Method and apparatus for providing active help to a user of a voice-enabled application

• US 6,560,576 B1
• Filed: 04/25/2000
• Issued: 05/06/2003
• Est. Priority Date: 04/25/2000
• Status: Expired due to Term

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Cohen, Michael H., Ghosh, Debajit, Balogh, Jennifer E., Wax, Tracy D., Thirumalai, Madhavan S.
• Primary Examiner(s): MCFADDEN, SUSAN IRIS
• Application Number:
  US09/557,988
• Time in Patent Office: 1,106 Days
• Field of Search: 704/270, 704/275, 379/88.22, 379/93.12
• US Class Current: 704/270
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 2015/0631 Creating reference templates; Clustering
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A voice-enabled application, which may be a voice browser, is configured to provide active help to a user. The application maintains a usage history of each user with respect to dialog states. The usage history includes various user-specific variables, some of which are valid across multiple sessions. The application maintains a number of active help prompts capable of being played to a user as speech, each containing information on a different, specific help topic. The application further maintains a number of sets of conditions, each set corresponding to a different one of the active help prompts. The application monitors dialog states during a session of a user and generates an event based on the dialog states. The application applies certain ones of the conditions to certain ones of the user-specific variables in response to the event. The application then plays a active help prompt containing information on a specific help topic to the user if the applied conditions are satisfied.

Claims

1. A method of providing active help to a user of a voice-enabled application, the method comprising:

maintaining a usage history of the user, the usage history including a plurality of user-specific variables;

monitoring dialog states during a session of the user;

generating an event in response to a specified transition between two dialog states corresponding to speech from the user;

checking a set of conditions using a set of the plurality of user-specific variables in response to the event; and

playing a prompt containing information on a specific help topic to the user in response to the set of conditions being satisfied.

2. A method as recited in claim 1, wherein at least some of the user-specific variables are applicable across a plurality of sessions.

3. A method as recited in claim 2, wherein said checking the set of conditions comprises checking the set of conditions using at least one of the user-specific variables that is applicable across a plurality of sessions.

4. A method as recited in claim 1, wherein the usage history comprises a history of use of the voice-enabled application by the user.

5. A method as recited in claim 4, wherein the usage history comprises a history of dialog states.

6. A method as recited in claim 5, wherein the voice-enabled application is a voice browser.

7. A method as recited in claim 1, wherein the set of conditions includes the condition that the user has engaged in at least a predetermined number of sessions.

8. A method as recited in claim 1, wherein the set of conditions includes:

the condition that the active help prompt has previously been played to the user no more than a predetermined number of times; and

the condition that the user has engaged in at least a predetermined number of sessions.

9. A method as recited in claim 1, wherein said playing the prompt comprises playing an audio prompt as speech.

10. A method of providing active help to a user of a voice-enabled application, the method comprising, in the voice-enabled application:

maintaining a history of dialog states of the user, wherein said maintaining the history includes maintaining a plurality of user-specific variables, at least some of the user-specific variables being applicable across a plurality of sessions for the user, each of the sessions characterized by one or more dialog states;

monitoring dialog states during a session;

detecting an event based on the dialog states;

checking a set of conditions using a set of the plurality of user-specific variables in response to detecting the event; and

playing an audio prompt containing information on a specific help topic to the user in response to the set of conditions being satisfied.

11. A method as recited in claim 10, wherein the voice-enabled application is a voice browser for providing the user with access to voice-enabled content on a network of voice-enabled sites.

12. A method as recited in claim 10, wherein said checking the set of conditions comprises checking the set of conditions using at least one of the user-specific variables that is applicable across a plurality of sessions.

13. A method as recited in claim 10, wherein the set of conditions includes the condition that the active help prompt has previously been played to the user no more than a configurable, predetermined number of times.

14. A method as recited in claim 10, wherein the set of conditions includes the condition that the user has engaged in at least a predetermined number of sessions.

15. A method as recited in claim 10, wherein the set of conditions includes:

the condition that the active help prompt has previously been played to the user no more than a configurable, predetermined number of times; and

the condition that the user has engaged in at least a predetermined number of sessions.

16. A method as recited in claim 10, wherein said playing the audio prompt comprises playing the audio prompt as speech.

17. A method as recited in claim 10, further comprising throwing the event in response to entry to or exit from a specified dialog state.

18. A method as recited in claim 10, further comprising throwing the event in response to a specified transition between two dialog states.

19. A method of providing a user with access to voice-enabled content on a network of voice-enabled sites, the method comprising:

providing a voice browser application to allow a user to access voice-enabled content on the voice-enabled sites using voice commands;

maintaining a history of dialog states associated with the user, wherein said maintaining the history includes maintaining a plurality of user-specific variables, at least some of the user-specific variables being applicable across a plurality of sessions for the user, each of the sessions characterized by one or more dialog states;

maintaining a plurality of active help prompts capable of being played to a user as speech, each active help prompt containing information on a different, specific help topic;

maintaining a plurality of sets of conditions, each set of conditions corresponding to a different one of the active help prompts;

monitoring dialog states during a session;

detecting an event based on the dialog states in response to speech from the user;

checking a set of conditions of said plurality of sets of conditions using a set of the plurality of user-specific variables in response to detecting the event; and

in response to the applied set of conditions being satisfied, playing to the user the active help prompt corresponding to the applied set of conditions.

20. A method as recited in claim 19, wherein said checking a set of conditions comprises checking the set of conditions using at least one of the user-specific variables that is applicable across a plurality of sessions.

21. A method as recited in claim 19, wherein said monitoring dialog states comprises operating a listener to detect a thrown event.

22. A method as recited in claim 19, wherein the applied set of conditions includes the condition that the active help prompt has previously been played to the user no more than a configurable, predetermined number of times.

23. A method as recited in claim 19, wherein the set of conditions includes the condition that the user has engaged in at least a predetermined number of sessions.

24. A method as recited in claim 19, wherein the set of conditions includes:

the condition that the active help prompt has previously been played to the user no more than a configurable, predetermined number of times; and

the condition that the user has engaged in at least a predetermined number of sessions.

25. A method as recited in claim 19, wherein the plurality of active help prompts are categorized into a plurality of categories, including an expert help category and a novice help category, and wherein the prompts within each category have one or more conditions in common.

26. A method as recited in claim 25, wherein each active help prompt in the expert help category has associated therewith the condition that the user has engaged in at least a predetermined number of sessions.

27. A method as recited in claim 19, further comprising throwing the event in response to entry to or exit from a specified dialog state.

28. A method as recited in claim 19, wherein further comprising throwing the event in response to a specified transition between two dialog states.

29. A method of providing active help to a user of a voice browser, the voice browser for providing the user with access to voice-enabled content on a network of voice-enabled sites, the method comprising, in the voice browser:

maintaining a history for the user, wherein said maintaining the history includes maintaining a plurality of user-specific variables, at least some of the user-specific variables being applicable across a plurality of sessions for the user, each of the sessions characterized by one or more dialog states;

maintaining a plurality of active help prompts capable of being played to a user as speech, each active help prompt containing information on a different, specific help topic, wherein the plurality of active help prompts are categorized into a plurality of categories, including an expert help category and a novice help category;

maintaining a plurality of sets of conditions, each set of conditions corresponding to a different one of the active help prompts, wherein the active help prompts within each said category share one or more conditions of said sets of conditions, and wherein each active help prompt in the expert help category has the condition that the user has engaged in at least a predetermined number of sessions;

monitoring dialog states during a session;

detecting an event based on the dialog states in response to speech from the user;

checking a set of conditions of said plurality of sets of conditions using a set of the plurality of user-specific variables in response to detecting the event, including checking the set of conditions using at least one of the user-specific variables that is applicable across a plurality of sessions; and

in response to the applied set of conditions being satisfied, playing to the user the active help prompt corresponding to the applied set of conditions.

30. A method as recited in claim 29, wherein said monitoring dialog states comprises operating a listener to detect the event.

31. A method as recited in claim 29, wherein the applied set of conditions includes

the condition that the active help prompt has previously been played to the user no more than a configurable, predetermined number of times.

32. A method as recited in claim 29, further comprising generating the event in response to entry to or exit from a specified dialog state.

33. A method as recited in claim 29, further comprising generating the event in response to a specified transition between two dialog states.

34. An apparatus for providing active help to a user of a voice-enabled application, the apparatus comprising:

means for maintaining a usage history of the user, the usage history including a plurality of user-specific variables;

means for monitoring dialog states during a session of the user;

means for generating an event in response to a specified transition between two dialog states corresponding to speech from the user;

means for checking a set of conditions using a set of the plurality of user-specific variables in response to the event; and

means for playing a prompt containing information on a specific help topic to the user in response to the set of conditions being satisfied.

35. An apparatus as recited in claim 34, wherein at least some of the user-specific variables are applicable across a plurality of sessions for the user.

36. An apparatus as recited in claim 35, wherein said means for checking the set of conditions comprises means for checking the set of conditions using at least one of the user-specific variables that is applicable across a plurality of sessions.

37. An apparatus as recited in claim 34, wherein said usage history comprises a history of use of the voice-enabled application by the user.

38. An apparatus as recited in claim 34, wherein the voice-enabled application is a voice browser.

39. An apparatus as recited in claim 34, wherein the set of conditions includes the condition that the user has engaged in at least a predetermined number of sessions.

40. An apparatus as recited in claim 34, wherein the set of conditions includes:

the condition that the active help prompt has previously been played to the user no more than a configurable, predetermined number of times; and

the condition that the user has engaged in at least a predetermined number of sessions.

41. An apparatus as recited in claim 34, wherein said means for playing the prompt comprises means for playing an audio prompt as speech.

42. A processing system connected on a network of voice-enabled sites, the processing system comprising:

a processor;

a network interface to connect the processing system to the network;

an audio interface through which speech from a user is received and audio prompts to the user are played; and

a storage facility having stored therein sequences of instructions which, when executed by the processor, result in the processing system;

providing a voice browser application to allow a user to access voice-enabled content on the voice-enabled sites using voice commands;

maintaining a history of use of the application by the user, including maintaining a plurality of user-specific variables, at least some of the user-specific variables being applicable across a plurality of sessions for the user, each of the sessions characterized by one or more dialog states;

monitoring dialog states during a session;

detecting an event based on the dialog states;

checking a set of conditions using a set of the plurality of user-specific variables in response to detecting the event; and

playing an audio prompt containing information on a specific help topic to the user in response to the set of conditions being satisfied.

43. A processing system as recited in claim 42, wherein said checking the set of conditions comprises checking the set of conditions using at least one of the user-specific variables that is applicable across a plurality of sessions.

44. A processing system as recited in claim 42, wherein said monitoring dialog states comprises operating an event listener to detect the event.

45. A processing system as recited in claim 42, wherein the history of use comprises a history of dialog states.

46. A processing system as recited in claim 42, wherein the set of conditions includes the condition that the user has engaged in at least a predetermined number of sessions.

47. A processing system as recited in claim 42, wherein the set of conditions includes:

the condition that the active help prompt has previously been played to the user no more than a configurable, predetermined number of times; and

the condition that the user has engaged in at least a predetermined number of sessions.

48. A processing system as recited in claim 42, wherein said playing the audio prompt comprises playing the audio prompt as speech.

49. A processing system as recited in claim 42, further comprising throwing the event in response to entry to or exit from a specified dialog state.

50. A processing system as recited in claim 42, further comprising throwing the event in response to a specified transition between two dialog states.

51. A machine-readable program storage medium having stored therein sequences of instructions which, when executed by a machine, cause the machine to perform a method of providing active help to a user of a voice browser, the voice browser for providing the user with access to voice-enabled content on a network of voice-enabled sites, the method comprising, in the voice browser:

maintaining a history of dialog states associated with the user, wherein said maintaining the history includes maintaining a plurality of user-specific variables, at least some of the user-specific variables being applicable across a plurality of sessions for the user, each of the sessions characterized by one or more dialog states;

monitoring dialog states during a session;

generating an event based on the dialog states;

detecting the event;

checking a set of conditions using a set of the plurality of user-specific variables in response to detecting the event; and

playing an audio prompt containing information on a specific help topic to the user in response to the set of conditions being satisfied.