System and method for performing automated dynamic dialogue generation

• US 6,418,440 B1
• Filed: 06/15/1999
• Issued: 07/09/2002
• Est. Priority Date: 06/15/1999
• Status: Expired due to Term

• Current Assignee: Nokia of America Corporation (Nokia Corporation)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: Pargellis, Andrew Nason, Kuo, Hong-Kwang Jeff, Lee, Chin-hui
• Primary Examiner(s): Trammell, James P.
• Assistant Examiner(s): CHEUNG, MARY DA ZHI WANG
• Application Number:
  US09/334,000
• Time in Patent Office: 1,120 Days
• Field of Search: 707/1-7, 704/1-4, 704/9-10, 704/200, 704/208, 704/231, 704/246, 704/257, 704/270, 704/275
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems

Abstract

A customized method or algorithm for holding an interactive dialogue session between a (human) user and a machine (hereinafter referred to simply as a “dialogue”) is generated, such that the resulting dialogue advantageously responds to the user'"'"'s requests and wherein the system'"'"'s capability (i.e., the dialogue) is automatically modified thereafter based on dynamically changing external databases. Specifically, a computer system acts as a Dialogue Generator agent by creating such a customized dialogue consisting of services that are organized and presented in a form that is a combination of the user'"'"'s expectations and the system'"'"'s capabilities. In particular, the system'"'"'s capabilities advantageously include the information content of database/service providers (such as, for example, a distributed information source such as the World Wide Web or a corporate file system), and the Dialogue Generator advantageously modifies the dialogue periodically in response to this dynamically changing external environment.

Claims

1. A computer based automated method for generating a dynamic human-machine dialogue comprising the steps of:

receiving user profile information for a user;

receiving a user request comprising at least one topic of interest;

retrieving from an external database at a first point in time, a first set of documents comprising information relating to the at least one topic of interest;

generating a user-customized human-machine dialogue based in part on the user profile information and in part on the information comprised in said first set of documents, said user-customized human-machine dialogue including an automatically generated dialogue flow specification;

retrieving from the external database at a second point in time later than said first point in time, a second set of documents comprising information relating to the at least one topic of interest, the information comprised in said second set of documents having at least one difference from the information comprised in said first set of documents; and

automatically modifying the dialogue flow specification of the human-machine dialogue based on the information comprised in said second set of documents so that said dialogue has a new organizational form that includes a set of latest services requested by the user, new information content downloaded from the external database, and a new grammar that specifically addresses said at least one difference.

2. The method of claim 1 wherein the external database comprises the World Wide Web.

3. The method of claim 1 wherein the user request further comprises information relating to a desired presentation format of said information comprised in said first and second sets of documents, and wherein said information comprised in said first and second sets of documents is formatted based on said desired presentation format.

4. The method of claim 1 wherein said second set of documents comprises one or more modified versions of said first set of documents.

5. The method of claim 1 wherein said second set of documents comprises at least one document which was not included in said first set of documents.

6. The method of claim 1 wherein the human-machine dialogue comprises a text-based input interface.

7. The method of claim 1 wherein the human-machine dialogue comprises a voice-based input interface and includes speech recognition capability.

8. The method of claim 1 wherein the human-machine dialogue comprises a text-based output interface.

9. The method of claim 1 wherein the human-machine dialogue comprises a speech-based output interface and includes speech synthesis capability.

10. The method of claim 1 wherein the user request further comprises one or more keywords related to said at least one topic of interest.

11. The method of claim 1 wherein each of the steps of generating and modifying the human-machine dialogue comprises the creation of one or more grammars.

12. The method of claim 1 wherein the human-machine dialogue comprises a tree-based dialogue session.

13. The method of claim 1 wherein the human-machine dialogue comprises a form-based dialogue session.

14. The method of claim 1 wherein the human-machine dialogue comprises a connected graph-based dialogue session.

15. The method of claim 1 wherein the human-machine dialogue comprises a dynamic stateless engine-based dialogue session.

16. An automated human-machine dialogue system comprising:

a profile manager which receives a user request comprising at least one topic of interest;

an information services manager which retrieves from an external database at a first point in time, a first set of documents comprising information relating to the at least one topic of interest, and which further retrieves from the external database at a second point in time later than said first point in time, a second set of documents comprising information relating to the at least one topic of interest, the information comprised in said second set of documents having at least one difference from the information comprised in said first set of documents;

an auto dialogue generator which generates a human-machine dialogue based on the information comprised in said first set of documents, and which further modifies the human-machine dialogue based on the information comprised in said second set of documents so that said dialogue has a new organizational form that includes a set of latest services requested by the user, new information content downloaded from the external database, and a new grammar that specifically addresses said at least one difference; and

a dialogue manager which manages the human-machine dialogue.

17. The system of claim 16 wherein the external database from which the information services manager retrieves said first and second sets of documents comprises the World Wide Web.

18. The system of claim 16 wherein the user request received by the profile manager further comprises information relating to a desired presentation format of said information comprised in said first and second sets of documents, and wherein said information comprised in said first and second sets of documents is formatted based on said desired presentation format.

19. The system of claim 16 wherein said second set of documents comprises one or more modified versions of said first set of documents.

20. The system of claim 16 wherein said second set of documents comprises at least one document which was not included in said first set of documents.

21. The system of claim 16 wherein the dialogue manager comprises a text-based input interface.

22. The system of claim 16 wherein the dialogue manager comprises a voice-based input interface and includes a speech recognizer.

23. The system of claim 16 wherein the dialogue manager comprises a text-based output interface.

24. The system of claim 16 wherein the dialogue manager comprises a speech-based output interface and includes a speech synthesizer.

25. The system of claim 16 wherein the user request received by the profile manager further comprises one or more keywords related to said at least one topic of interest.

26. The system of claim 16 wherein the auto dialogue generator creates one or more grammars.

27. The system of claim 16 wherein the auto dialogue generator generates a human-machine dialogue which is comprised of a tree-based dialogue session.

28. The system of claim 16 wherein the auto dialogue generator generates a human-machine dialogue which is comprised of a form-based dialogue session.

29. The system of claim 16 wherein the auto dialogue generator generates a human-machine dialogue which is comprised of a connected graph-based dialogue session.

30. The system of claim 16 wherein the auto dialogue generator generates a human-machine dialogue which is comprised of a dynamic stateless engine-based dialogue session.

31. An apparatus for automatically generating a human-machine dialogue comprising:

means for receiving a user request comprising at least one topic of interest;

means for retrieving from an external database at a first point in time, a first set of documents comprising information relating to the at least one topic of interest;

means for generating a human-machine dialogue based on the information comprised in said first set of documents;

means for retrieving from the external database at a second point in time later than said first point in time, a second set of documents comprising information relating to the at least one topic of interest, the information comprised in said second set of documents having at least one difference from the information comprised in said first set of documents; and

means for modifying the human-machine dialogue based on the information comprised in said second set of documents so that said dialogue has a new organizational form that includes a set of latest services requested by the user, new information content downloaded from the external database, and a new grammar that specifically addresses said at least one difference.

32. The apparatus of claim 31 wherein the external database comprises the World Wide Web.

33. The apparatus of claim 31 wherein the user request further comprises information relating to a desired presentation format of said information comprised in said first and second sets of documents, and wherein said information comprised in said first and second sets of documents is formatted based on said desired presentation format.

34. The apparatus of claim 31 wherein said second set of documents comprises one or more modified versions of said first set of documents.

35. The apparatus of claim 31 wherein said second set of documents comprises at least one document which was not included in said first set of documents.

36. The apparatus of claim 31 wherein the human-machine dialogue comprises a text-based input interface means.

37. The apparatus of claim 31 wherein the human-machine dialogue comprises a voice-based input interface means and includes means for performing speech recognition.

38. The apparatus of claim 31 wherein the human-machine dialogue comprises a text-based output interface means.

39. The apparatus of claim 31 wherein the human-machine dialogue comprises a speech-based output interface means and includes means for performing speech synthesis.

40. The apparatus of claim 31 wherein the user request further comprises one or more keywords related to said at least one topic of interest.

41. The apparatus of claim 31 wherein the means for generating and modifying the human-machine dialogue each comprise means for creating one or more grammars.

42. The apparatus of claim 31 wherein the human-machine dialogue comprises means for performing a tree-based dialogue session.

43. The apparatus of claim 31 wherein the human-machine dialogue comprises means for performing a form-based dialogue session.

44. The apparatus of claim 31 wherein the human-machine dialogue comprises means for performing a connected graph-based dialogue session.

45. The apparatus of claim 31 wherein the human-machine dialogue comprises means for performing a dynamic stateless engine-based dialogue session.