SYSTEM AND METHOD FOR MANAGING CONVERSATION

• US 20150058014A1
• Filed: 01/18/2013
• Published: 02/26/2015
• Est. Priority Date: 05/17/2012
• Status: Active Grant

• Current Assignee: Postech Academy-Industry Foundation
• Original Assignee: Postech Academy-Industry Foundation
• Inventors: Lee, Gary Geunbae, Noh, Hyungjong, Lee, Kyusong
• Granted Patent: US 9,514,742 B2
• Time in Patent Office: Days
• US Class Current: 704/243
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G09B 19/06 Foreign languages with audible presentation of material to be studied G09B5/04
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 2015/0633 using lexical or orthographic knowledge sources

Abstract

A conversation management system includes: a training unit that generates an articulation speech act and an entity name of a training corpus, that generates a lexical syntactic pattern, and that estimates a speech act and an entity name of a training corpus; a database that stores the articulation speech act, the entity name, and the lexical syntactic pattern of the training corpus; an execution unit that generates an articulation speech act and an entity name of a user, that generates a user lexical syntactic pattern, that estimates a speech act and an entity name of a user, that searches for an articulation pair corresponding to a user articulation at the database using a search condition including the estimated user speech act and the generated user lexical syntactic pattern, and that generates a final response by selecting an articulation template using a restriction condition including an estimated entity name among the found articulation pair; and an output unit that outputs a final response that is generated by the execution unit.

Claims

1. A conversation management system, comprising:

a training unit that generates an articulation speech act and an entity name of a training corpus, that generates a lexical syntactic pattern, and that estimates a speech act and an entity name of a training corpus;

a database that stores the articulation speech act, the entity name, and the lexical syntactic pattern of the training corpus;

an execution unit that generates an articulation speech act and an entity name of a user, that generates a user lexical syntactic pattern, that estimates a speech act and an entity name of a user, that searches for an articulation pair corresponding to a user articulation at the database using a search condition comprising the estimated user speech act and the generated user lexical syntactic pattern, and that generates a final response by selecting an articulation template using a restriction condition comprising an estimated entity name among the found articulation pair; and

an output unit that outputs a final response that is generated by the execution unit.

2. The conversation management system of claim 1, wherein the training unit displays entity name information in a word of the training corpus, and attaches a symbol when the entity name cannot be replaced.

3. The conversation management system of claim 1, wherein the training unit analyzes a part of speech of the training corpus, defines a priority of parts of speech, and generates a lexical syntactic pattern from the part of speech.

4. The conversation management system of claim 1, wherein the execution unit comprises a search relieving unit,

wherein the search relieving unit enlarges a search range to a plurality of speech acts comprising the estimated speech act, and searches again for an articulation pair when there is no articulation that is selected by the execution unit.

5. The conversation management system of claim 1, wherein the execution unit comprises a search relieving unit,

wherein the search relieving unit enlarges a search range by reducing a range of the user lexical syntactic pattern, and searches again for an articulation pair when no articulation is selected by the execution unit.

6. The conversation management system of claim 1, wherein the execution unit comprises a search relieving unit,

wherein the search relieving unit enlarges a search range by reducing a range of the user lexical syntactic pattern and a plurality of speech acts comprising the estimated speech act, and searches again for an articulation pair when there is no articulation selected by the execution unit.

7. The conversation management system of claim 1, wherein the training unit comprises:

a machine learning model generator that estimates an articulation speech act and an entity name;

an entity name information display unit that displays an articulation speech act and entity name information, and that displays information between the displayed entity name and articulation;

an articulation part of speech analysis unit that analyzes an articulation part of speech;

a lexical syntactic pattern generator that generates a lexical syntactic pattern from the analyzed part of speech; and

an entity name information display unit that displays entity name information.

8. The conversation management system of claim 1, wherein the execution unit comprises:

a speech act analysis unit that estimates an articulation speech act;

an entity name recognition unit that recognizes an entity name of an articulation;

an articulation pair search unit that searches for an articulation pair corresponding to a user articulation using a speech act, a user lexical syntactic pattern, and an entity name; and

a restriction condition applying unit that searches for an articulation pair satisfying an entity name restriction among articulation pairs that are found in the articulation pair search unit.

9. The conversation management system of claim 1, wherein the database indexes and stores an articulation speech act, an entity name, and a lexical syntactic pattern.

10. The conversation management system of claim 1, wherein the training unit comprises a machine learning model generator,

wherein the machine learning model generator estimates a speech act of the training corpus articulation through a classifier that is generated according to a machine learning algorithm.

11. A method of managing a conversation, the method comprising:

a training step of generating an articulation speech act and an entity name of a training corpus, generating a lexical syntactic pattern, and estimating a speech act and an entity name of a training corpus;

storing the articulation speech act, the entity name, and the lexical syntactic pattern of the training corpus at a database;

an execution step of generating an articulation speech act and an entity name of a user, generating a user lexical syntactic pattern, estimating a speech act and an entity name of a user, searching for an articulation pair corresponding to a user articulation at the database using a search condition comprising the estimated user speech act and the generated user lexical syntactic pattern, and selecting an articulation template and generating a final response using a restriction condition comprising an estimated entity name among the found articulation pairs; and

outputting a final response that is generated at the execution step.

12. The method of claim 11, wherein the training step comprises:

displaying entity name information in a word of the training corpus;

displaying information between an entity name and an articulation in the training corpus; and

training a classifier that estimates an articulation speech act and an entity name in the training corpus.

13. The method of claim 11, wherein the training step comprises:

analyzing a part of speech of the training corpus;

defining a priority of the parts of speech; and

generating a lexical syntactic pattern from the part of speech.

14. The method of claim 11, wherein the execution step comprises relieving a search,

wherein the relieving of a search comprises searching again for, if there is no articulation selected at the execution step, an articulation pair by enlarging a search range to a plurality of speech acts comprising the estimated speech act.

15. The method of claim 11, wherein the execution step comprises relieving a search,

wherein the relieving of a search comprises searching again for, if there is no articulation selected at the execution step, an articulation pair by enlarging a search range by reducing a range of the user lexical syntactic pattern.

16. The method of claim 11, wherein the execution step comprises relieving a search,

wherein the relieving of a search comprises searching again for, if there is no articulation selected at the execution step, an articulation pair by enlarging a search range by reducing a range of the user lexical syntactic pattern and a plurality of speech acts comprising the estimated speech act.

17. The method of claim 11, wherein the training step comprises:

estimating an articulation speech act and an entity name;

displaying an articulation speech act and entity name information and displaying information between the displayed entity name and articulation;

analyzing an articulation part of speech;

generating a lexical syntactic pattern from the analyzed part of speech; and

displaying entity name information.

18. The method of claim 11, wherein the execution step comprises:

estimating an articulation speech act;

recognizing an entity name of an articulation;

searching for an articulation pair corresponding to a user articulation using a speech act, a user lexical syntactic pattern, and an entity name; and

searching for an articulation pair satisfying an entity name restriction among the found articulation pairs.

19. The method of claim 11, wherein the storing of the articulation speech act comprises indexing and storing an articulation speech act, an entity name, and a lexical syntactic pattern.

20. The method of claim 11, wherein the training step comprises generating a machine learning model,

wherein the generating of a machine learning model comprises estimating a speech act of the training corpus articulation through a classifier that is generated according to a machine learning algorithm.