DYNAMIC DIALOG SYSTEM AGENT INTEGRATION

• US 20140278427A1
• Filed: 03/13/2013
• Published: 09/18/2014
• Est. Priority Date: 03/13/2013
• Status: Abandoned Application

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Cheung, Chun Shing, Riviere Escobedo, Christopher M.
• Application Number:
  US13/802,448
• Publication Number:
  US 20140278427A1
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A method for dialog agent integration comprises discovering a dialog agent required for a dialog request including dialog information comprising terms required for audio feedback in a service domain required for the dialog request, extracting the dialog information from the discovered dialog agent, integrating the dialog information to existing dialog information of a dialog system (DS) that provides dialog functionality for an electronic device, and expanding the service domain dialog functionality of the DS with the integrated dialog information.

Claims

1. A method for dialog agent integration, comprising:

discovering a dialog agent required for a dialog request, the dialog agent including dialog information comprising terms required for audio speech feedback in a service domain required for the dialog request;

extracting the dialog information from the discovered dialog agent;

integrating the dialog information to existing dialog information of a dialog system (DS) that provides dialog speech functionality for an electronic device; and

expanding service domain dialog functionality of the DS with the integrated dialog information.

2. The method of claim 1, wherein the existing dialog information comprises natural language understanding (NLU) information, natural language generation (NLG) information, and dialog manager (DM) information for one or more existing service domains.

3. The method of claim 2, wherein the dialog information of the dialog agent comprises NLU information, NLG information, and DM information for the service domain required for the dialog request.

4. The method of claim 3, wherein the expanded dialog functionality comprises the one or more existing service domains and the service domain required for the dialog request.

5. The method of claim 4, wherein NLU information comprises context-free grammar (CFG) provided in a notation form.

6. The method of claim 5, wherein a CFG parser detects an utterance based on locating a production rule for a respective dialog agent.

7. The method of claim 6, wherein each production rule is associated with a probabilistic CFG (PCFG), wherein probability of each possible parse is used for identifying a most likely interpretation of speech input to the DS from an automatic speech recognition (ASR) engine.

8. The method of claim 5, wherein NLG information comprises a list of possible grammatical feedback responses associated with supported actions, and the DM information comprises an ordered structure for progressing through a dialog conversation once selected for execution.

9. The method of claim 8, wherein the ordered structure comprises a dialog tree including nodes representing user requested actions and branches connected to the nodes representing speech responses.

10. The method of claim 8, wherein integrating the dialog information of the dialog agent to the existing dialog information of the DS comprises:

adding the NLU information from the dialog agent to the NLU information of the existing dialog information;

adding the NLG information from the dialog agent to the NLG information of the existing dialog information; and

adding the DM information from the dialog agent to the DM information of the existing dialog information.

11. The method of claim 2, wherein the electronic device comprises a mobile phone, and the dialog agent is provided over a network.

12. A system for dialog agent integration, comprising:

an electronic device including a microphone for receiving speech signals and an automatic speech recognition (ASR) engine that converts the speech signals into words; and

a dialog system (DS) that receives the words from the ASR engine and provides dialog functionality for the electronic device, the dialog system comprising a DS agent interface that integrates dialog information from a dialog agent to existing dialog information of the DS for expanding service domain dialog functionality of the DS.

13. The system of claim 12, wherein the existing dialog information of the DS comprises natural language understanding (NLU) information, natural language generation (NLG) information, and dialog manager (DM) information for one or more existing service domains, and the dialog information of the dialog agent comprises NLU information, NLG information, and DM information for a particular service domain of the dialog agent.

14. The system of claim 13, wherein the expanded dialog functionality comprises the one or more existing service domains and the service domain of the dialog agent.

15. The system of claim 13, wherein NLU information comprises context-free grammar (CFG) provided in a notation form, and the DS further comprises a CFG parser that detects a request based on the words by locating a production rule for a respective domain.

16. The system of claim 15, wherein each production rule is associated with a probabilistic CFG (PCFG), wherein probability of each possible parse by the CFG parser is used for identifying a most likely interpretation of the words input to the DS from the ASR engine.

17. The system of claim 16, wherein NLG information comprises a list of possible grammatical feedback responses associated with supported actions, and the DM information comprises an ordered structure for progressing through a dialog conversation once selected for execution.

18. The system of claim 17, wherein the ordered structure comprises a dialog tree including nodes representing user requested actions and branches connected to the nodes representing speech responses.

19. The system of claim 17, wherein the DS agent interface integrates dialog information from the dialog agent to the existing dialog information of the DS based on:

adding the NLU information from the dialog agent to the NLU information of the existing dialog information;

adding the NLG information from the dialog agent to the NLG information of the existing dialog information; and

adding the DM information from the dialog agent to the DM information of the existing dialog information.

20. The system of claim 19, wherein the electronic device comprises a mobile phone, and the dialog agent is provided over a network.

21. A non-transitory computer-readable medium having instructions which when executed on a computer perform a method comprising:

discovering a dialog agent required for a dialog request, the dialog agent including dialog information comprising feedback terms required for audio feedback in a service domain required for the dialog request;

extracting the dialog information from the discovered dialog agent;

integrating the dialog information to existing dialog information of a dialog system (DS) that provides dialog functionality for of an electronic device; and

expanding service domain dialog functionality of the DS with the integrated dialog information.

22. The medium of claim 21, wherein the existing dialog information of the DS comprises natural language understanding (NLU) information, natural language generation (NLG) information, and dialog manager (DM) information for one or more existing service domains, and the dialog information of the dialog agent comprises NLU information, NLG information, and DM information for a particular service domain of the dialog agent.

23. The medium of claim 22, wherein the expanded dialog functionality comprises one or more existing service domains and the service domain required for the dialog request.

24. The medium of claim 23, wherein NLU information comprises context-free grammar (CFG) provided in a notation form, and the DS further comprises a CFG parser that detects a request based on the words by locating a production rule for a respective service domain.

25. The medium of claim 24, wherein each production rule is associated with a probabilistic CFG (PCFG), wherein probability of each possible parse is used for identifying a most likely interpretation of speech input to the DS from an automatic speech recognition (ASR) engine of the electronic device.

26. The medium of claim 24, wherein NLG information comprises a list of possible grammatical feedback responses associated with supported actions, and the DM information comprises an ordered structure for progressing through a dialog conversation once selected for execution.

27. The medium of claim 26, wherein the ordered structure comprises a dialog tree including nodes representing user requested actions and branches connected to the nodes representing speech responses.

28. The medium of claim 26, wherein integrating the dialog information of the dialog agent to the existing dialog information of the DS comprises:

adding the NLU information from the dialog agent to the NLU information of the existing dialog information;

adding the NLG information from the dialog agent to the NLG information of the existing dialog information; and

adding the DM information from the dialog agent to the DM information of the existing dialog information.

29. The medium of claim 28, wherein the electronic device comprises a mobile phone, and the dialog agent is provided over a network.