Method of and system for using conversation state information in a conversational interaction system

• US 9,477,643 B2
• Filed: 11/04/2013
• Issued: 10/25/2016
• Est. Priority Date: 07/20/2012
• Status: Active Grant

• Current Assignee: Veveo, Inc. (Adeia Inc.)
• Original Assignee: Veveo, Inc. (Adeia Inc.)
• Inventors: Barve, Rakesh, Aravamudan, Murali, Venkataraman, Sashikumar, Welling, Girish
• Primary Examiner(s): COLUCCI, MICHAEL C
• Application Number:
  US14/071,168
• Publication Number:
  US 20140058724A1
• Time in Patent Office: 1,086 Days
• Field of Search: 704/275, 704/753, 704/277, 704/270.1, 704/235, 715/764, 715/753, 715/752, 715/727, 709/207, 709/206, 709/204, 706/12, 455/414.1, 446/175, 434/308, 379/88.13, 370/352, 127/5, 175/3
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2457 with adaptation to user needs
• CPC Class Codes: G06F 16/24573 using data annotations, e.g. user-defined metadata
• CPC Class Codes: G06F 16/84 Mapping; Conversion
• CPC Class Codes: G06F 16/9558 Details of hyperlinks; Management of linked annotations
• CPC Class Codes: G06F 40/10 Text processing natural language analysis G06F40/20; semantic analysis G06F40/30; processing or translation of natural language G06F40/40
• CPC Class Codes: G06F 40/237 Lexical tools
• CPC Class Codes: G06F 40/295 Named entity recognition
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G06F 40/40 Processing or translation of natural language natural language analysis G06F40/20; semantic analysis G06F40/30

Abstract

A method of using conversation state information in a conversational interaction system is disclosed. A method of inferring a change of a conversation session during continuous user interaction with an interactive content providing system includes receiving input from the user including linguistic elements intended by the user to identify an item, associating a linguistic element of the input with a first conversation session, and providing a response based on the input. The method also includes receiving additional input from the user and inferring whether or not the additional input from the user is related to the linguistic element associated with the conversation session. If related, the method provides a response based on the additional input and the linguistic element associated with the first conversation session. Otherwise, the method provides a response based on the second input without regard for the linguistic element associated with the first conversation session.

Claims

1. A method of inferring a conversation session during continuous user interaction with an interactive content providing system having a processor, the method comprising:

providing access to a set of content items, each content item of the set of content items having associated metadata stored in an electronically readable medium that describes the corresponding content item;

receiving at the processor a first input from a user, the first input including linguistic elements that identify at least one desired content item from the set of content items;

associating by the processor at least one linguistic element of the first input with a first conversation session;

providing by the processor a first response based on the first input and based on metadata associated with the set of content items, wherein the first response comprises the at least one desired content item;

receiving at the processor a second input from the user;

inferring by the processor whether the second input from the user is related to the at least one linguistic element associated with the first conversation session; and

upon a condition in which the second input is inferred to relate to the at least one linguistic element associated with the first conversation session, providing by the processor a second response based on metadata associated with the at least one desired content item, the second input, and the at least one linguistic element of the first input associated with the first conversation session.

2. The method of claim 1, wherein the inferring by the processor whether the second input from the user is related to the at least one linguistic element associated with the first conversation session is based on a determination of whether the second input contains a linguistic linking element.

3. The method of claim 2, wherein the linguistic linking element is at least one of a pronoun and a syntactic expletive.

4. The method of claim 2, wherein the inferring by the processor concludes that the second input from the user is related upon a condition in which the second input contains a linguistic linking element.

5. The method of claim 4, wherein the linguistic linking element is at least one of a pronoun and a syntactic expletive.

6. The method of claim 2, further comprising, upon a condition in which the second input does not contain a linguistic linking element, the following:

determining by the processor a measure of relatedness between (i) linguistic elements of the second input and (ii) the at least one linguistic element associated with the first conversation session based on the metadata associated with the set of content items; and

upon a condition in which the measure of relatedness is equal to or greater than a threshold value, the inferring by the processor concludes that the second input is related to the at least one linguistic element associated with the first conversation session.

7. The method of claim 6, the metadata associated with the set of content items including a mapping of relationships between entities associated with the set of content items, and the determining by the processor the measure of relatedness including analyzing by the processor the mapping of relationships.

8. The method of claim 1, wherein the inferring by the processor whether the second input from the user is related to the at least one linguistic element associated with the first conversation session includes:

identifying by the processor a linguistic element associated with the first conversation session that identifies at least one entity;

identifying by the processor a linguistic linking element of the second input;

determining by the processor whether the linguistic linking element of the second input is a suitable link to the linguistic element associated with the first conversation session that identifies at least one entity; and

upon a condition in which the linguistic linking element of the second input is a suitable link, concluding by the processor that the second input from the user is related to the at least one linguistic element associated with the first conversation session.

9. The method of claim 8, wherein the linguistic element associated with the first conversation session that identifies at least one entity is at least one of a noun and a gerund.

10. The method of claim 8, wherein the linguistic linking element of the second input is at least one of a pronoun and a syntactic expletive.

11. The method of claim 1, wherein the inferring by the processor whether the second input from the user is related to the at least one linguistic element associated with the first conversation session includes:

determining by the processor whether the second input includes a linguistic element that identifies at least one entity;

upon a condition in which the second input does not include a linguistic element that identifies at least one entity, determining by the processor whether the second input is an appropriate response to the first response; and

upon a condition in which the second input is an appropriate response to the first response, concluding by the processor that the second input from the user is related to the at least one linguistic element associated with the first conversation session.

12. The method of claim 11, wherein the linguistic element included in the second input that identifies at least one entity is at least one of a noun and a gerund.

13. The method of claim 1, upon the condition in which the second input is inferred to relate to the at least one linguistic element associated with the first conversation session, the providing by the processor the second response including substituting by the processor the at least one linguistic element associated with the first conversation session in place of at least one linguistic element of the second input.

14. The method of claim 1, further comprising:

associating by the processor at least one linguistic element of the first response with the first conversation session; and

upon a condition in which the second input is inferred to relate to the at least one linguistic element of the first response associated with the first conversation session, further basing the second response on the at least one linguistic element of the first response associated with the first conversation session.

15. The method of claim 14, upon the condition in which the second input is inferred to relate to the at least one linguistic element of the first response associated with the first conversation session, the providing by the processor the second response including substituting the at least one linguistic element of the first response associated with the first conversation session in place of at least one linguistic element of the second input.

16. The method of claim 1, the metadata associated with the set of content items including a mapping of relationships between entities associated with the set of content items.

17. The method of claim 1, further comprising:

determining by the processor that a portion of at least one of the first input from the user and the second input from the user contains an ambiguous identifier, the ambiguous identifier intended by the user to identify, at least in part, the at least one desired content item from the set of content items; and

inferring by the processor a meaning for the ambiguous identifier based on matching portions of the at least one of the first input from the user and the second input from the user to preferences of the user described by a user preference signature;

the providing by the processor the second response including selecting content items from the set of content items based on comparing the inferred meaning of the ambiguous identifier with the metadata associated with the set of content items.

18. The method of claim 1, further comprising, upon a condition in which the second input is inferred to not relate to the at least one linguistic element associated with the first conversation session, providing by the processor a second response based on the metadata associated with the set of content items and the second input.

19. The method of claim 1, wherein at least one of the first response and the second response includes machine-generated speech.

20. The method of claim 19, wherein the machine-generated speech relates to at least one of the first input and the second input.

21. The method of claim 1, wherein at least one of the first response and the second response is supplemented by machine-generated speech.

22. The method of claim 21, wherein the machine-generated speech relates to at least one of the first input and the second input.

23. A system for inferring a conversation session during continuous user interaction with an interactive content providing system, the system comprising:

a processor configured to;

provide access to a set of content items, each content item of the set of content items having associated metadata stored in an electronically readable medium that describes the corresponding content item;

receive a first input from a user, the first input including linguistic elements that identify at least one desired content item from the set of content items;

associate at least one linguistic element of the first input with a first conversation session;

provide a first response based on the first input and based on metadata associated with the set of content items, wherein the first response comprises the at least one desired content item;

receive a second input from the user;

infer whether the second input from the user is related to the at least one linguistic element associated with the first conversation session; and

upon a condition in which the second input is inferred to relate to the at least one linguistic element associated with the first conversation session, provide a second response based on metadata associated with the at least one desired content item, the second input, and the at least one linguistic element of the first input associated with the first conversation session.