Development system for a dialog system

• US 20060203980A1
• Filed: 09/05/2003
• Published: 09/14/2006
• Est. Priority Date: 09/06/2002
• Status: Active Grant

• Current Assignee: Telstra Corporation Limited (Telstra Group Ltd.)
• Original Assignee: Telstra Corporation Limited (Telstra Group Ltd.)
• Inventors: Starkie, Bradford Craig
• Granted Patent: US 8,046,227 B2
• Time in Patent Office: Days
• US Class Current: 379/88.180
• CPC Class Codes: G06F 16/3329 Natural language query formulation or dialogue systems
• CPC Class Codes: G06F 2209/545 Gui
• CPC Class Codes: G06F 8/30 Creation or generation of source code
• CPC Class Codes: G06F 8/38 for implementing user interfaces
• CPC Class Codes: G06F 8/65 Updates security arrangements therefor G06F21/57
• CPC Class Codes: H04M 2203/355 Interactive dialogue design tools, features or methods
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00
• CPC Class Codes: Y10S 715/978 Audio interaction as part of an operator interface

Abstract

A development system, including a scenario generator for generating a plurality of sample interactions representative of interactions between a dialog system and a user of the dialog system on the basis of definition data for the dialog system. The definition data includes state machine code, prompt data, and recognition data. A simulator generates prompts of sample interactions on the basis of the prompt data, and the scenario generator generates responses to the prompts on the basis of the recognition data. A scenario editor allows a user to modify the sample interactions. A grammar learner then updates the prompt data and the recognition data on the basis of the modified sample interactions. An application builder generates the definition data from specification data provided by a developer, an application template, and/or an existing dialog application.

Claims

1. A process for developing a dialog system, including generating a plurality of sample interactions representative of interactions between said dialog system and a user of said dialog system on the basis of definition data for said dialog system.

2. The process of claim 1, wherein said step of generating includes automatically generating a plurality of prompts on the basis of said definition data, providing said prompts to a user, and receiving responses to said prompts from said user.

3. The process of claim 1, wherein said step of generating includes automatically generating a plurality of prompts on the basis of said definition data, and automatically generating responses to said prompts on the basis of said definition data.

4. The process of claim 1, wherein said sample interactions include interaction text and application data.

5. The process of claim 3, wherein said step of generating a plurality of sample interactions includes generating first sample interactions, each of said first sample interactions including interaction text and one item of application data;

and subsequently generating second sample interactions, each of said second sample interactions including interaction text and two or more items of application data.

6. The process of claim 3, wherein said step of generating a plurality of sample interactions includes generating a plurality of prompts and respective lists of possible responses to said prompts, and selecting responses from said lists.

7. The process of claim 6, wherein said step of selecting includes randomly selecting unselected responses from said lists.

8. The process of claim 6, including identifying a dialog state with at least one unselected response, and determining a sequence of events for entering said dialog state.

9. The process of claim 8, wherein said sequence of events is determined on the basis of sample interactions.

10. The process of claim 8, wherein said step of determining includes determining a first sequence of events for reaching an end dialog state and a second sequence of events for reaching said dialog state from an initial dialog state.

11. The process of claim 8, including determining two or more sequences of events for entering said dialog state and selecting from said two or more sequences to determine an event sequence with the least number of events.

12. The process of claim 8, wherein said step of determining a sequence of events for entering said dialog state includes providing one or more prompts to a user and receiving one or more responses from said user.

13. The process of claim 8, including generating events on the basis of said sequence to enter said dialog state.

14. The process of claim 3, wherein said step of automatically generating a plurality of prompts includes selecting grammar rules of said definition data to generate prompts that are likely to have responses having the largest numbers of items of information.

15. The process of claim 1, including modifying said sample interactions on the basis of interaction data received from a developer.

16. The process of claim 15, wherein said definition data includes prompt data, and the process includes modifying said prompt data on the basis of said interaction data.

17. The process of claim 16, wherein said prompt data is in a grammar format.

18. The process of claim 1, including using grammar learning to update prompt data of said definition data on the basis of said sample interactions.

19. The process of claim 18, including updating prompts of said sample interactions on the basis of the updated prompt data.

20. The process of claim 19, including selecting prompts of said sample interactions for updating if said prompts have not been modified by a developer.

21. The process of claim 1, including generating said definition data on the basis of specification data received from a developer.

22. The process of claim 21, wherein said definition data is generated on the basis of said specification data and one of a predetermined dialog application and at least one dialog application template.

23. The process of claim 1, wherein said definition data includes dialog state machine code, at least one recognition grammar and prompt data.

24. The process of claim 23, wherein said prompt data includes at least one prompt grammar.

25. A development system having components for executing the process of claim 1.

26. A computer readable storage medium having stored thereon program instructions for executing the process of claim 1.

27. A dialog application generated by executing the process of claim 1.

28. A development system, including a scenario generator for generating a plurality of sample interactions representative of interactions between a dialog system and a user of said dialog system on the basis of definition data for said dialog system.

29. The development system of claim 28, wherein said definition data includes state machine code, prompt data, and recognition data.

30. The development system of claim 29, including a simulator for generating prompts of said sample interactions on the basis of said prompt data, and wherein said scenario generator is adapted to generate responses to said prompts on the basis of said recognition data.

31. The development system of claim 29, including a scenario editor for modifying said sample interactions.

32. The development system of claim 31, wherein said scenario generator generates graphical user interface components for modifying said sample interactions.

33. The development system of claim 31, including at least one learning component for updating at least one of said prompt data and said recognition data on the basis of the modified sample interactions.

34. The development system of claim 28, including an application builder for generating said definition data on the basis of at least one of specification data provided by a developer, an application template, and an existing application.

35. A dialogue application generated by The development system of claim 28.

36. A graphical user interface for use in developing a dialog system, said interface including graphical user interface components for modifying sample interactions representative of interactions between said dialog system and a user of said dialog system.

37. The graphical user interface of claim 36, wherein said graphical user interface components include a component for deleting a selected sample interaction.

38. The graphical user interface of claim 37, wherein said graphical user interface components include a component for a developer to select a predetermined reason why said selected sample interaction was deleted.

39. The graphical user interface of claim 36, wherein said graphical user interface components include a component for defining a question and an answer to said question for display to a user of said dialog system.

40. The graphical user interface of claim 39, wherein said graphical user interface components include a question text component for defining question text and an answer text component for defining answer text.

41. The graphical user interface of claim 39, wherein said graphical user interface components include a component for selecting from a list of predetermined answers to said question.

42. The graphical user interface of claim 39, wherein said graphical user interface components include a component for specifying whether said question can be asked at any time.

43. The graphical user interface of claim 39, wherein said graphical user interface components include a component for specifying that said question can be asked during a selected sample interaction.