METHOD OF AND SYSTEM FOR INFERRING USER INTENT IN SEARCH INPUT IN A CONVERSATIONAL INTERACTION SYSTEM

• US 20160342702A1
• Filed: 08/04/2016
• Published: 11/24/2016
• 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
• Granted Patent: US 10,592,575 B2
• Time in Patent Office: Days
• 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 inferring user intent in search input in a conversational interaction system is disclosed. A method of inferring user intent in a search input includes providing a user preference signature that describes preferences of the user, receiving search input from the user intended by the user to identify at least one desired item, and determining that a portion of the search input contains an ambiguous identifier. The ambiguous identifier is intended by the user to identify, at least in part, a desired item. The method further includes inferring a meaning for the ambiguous identifier based on matching portions of the search input to the preferences of the user described by the user preference signature and selecting items from a set of content items based on comparing the search input and the inferred meaning of the ambiguous identifier with metadata associated with the content items.

Claims

1-29. -29. (canceled)

30. A computer-implemented method of inferring user intent in a search input, the method comprising:

receiving information for a set of content items, each of the content items being associated with metadata that describes the corresponding content item, and each of the content items being associated with at least one information domain;

receiving the search input from a user at one or more of the processors, the search input being intended by the user to identify at least one desired content item;

inferring by the one or more of the processors that a first portion of the search input contains a phrase of at least one word that has a plurality of possible meanings, wherein each possible meaning of the plurality of possible meanings is associated with a corresponding information domain;

determining by the one or more of the processors at least one information domain relevant to the search input based in part on a second portion of the search input and not based on the first portion of the search input;

selecting by the one or more of the processors one possible meaning for the phrase from the plurality of possible meanings based on the search input and the at least one information domain determined to be relevant to the search input; and

selecting by the one or more of the processors a result for the search input based on the search input, the one possible meaning for the phrase, and metadata associated with the content items, wherein the result comprises at least one content item from the set of content items.

31. The method of claim 30, the at least one information domain including media entertainment and the metadata including at least one of crew, characters, actors, teams, leagues, tournaments, athletes, composers, music artists, performers, albums, songs, news personalities, and content distributors.

32. The method of claim 30, the at least one information domain including electronic mail and the metadata including at least one of electronic mail threads, contacts, senders, recipients, company names, business departments, business units, electronic mail folders, and office location information.

33. The method of claim 30, the at least one information domain including travel-related information and the metadata including at least one of cities, hotels, hotel brands, individual points of interest, categories of points of interest, retail chains, car rental websites, and car rental company names.

34. The method of claim 30, the at least one information domain including electronic commerce and the metadata including at least one of product items, product categories, product subcategories, product brand, and retail stores.

35. The method of claim 30, the at least one information domain including network-based documents and the metadata including at least one of domain names, internet media types, filenames, directories, and filename extensions.

36. The method of claim 30, the at least one information domain including address book information and the metadata including at least one of contact names, electronic mail address, telephone number, address, and employer.

37. The method of claim 30, further comprising providing a user preference signature, the user preference signature describing preferences of the user for at least one of (i) particular content items and (ii) metadata associated with the content items, wherein the selecting the one possible meaning for the phrase is further based on comparing portions of the search input to the preferences of the user described by the user preference signature.

38. The method of claim 30, further comprising:

providing a user preference signature, the user preference signature describing preferences of the user for at least one of (i) particular content items and (ii) metadata associated with the content items; and

ordering the at least one content item based on the preferences of the user described by the user preference signature.

39. The method of claim 30, the metadata associated with the content items including a mapping of relationships between entities associated with the content items, and the determining by the one or more processors the at least one information domain relevant to the search input being based in part on the mapping of relationships and the search input.

40. The method of claim 30, wherein the one possible meaning for the phrase from the plurality of possible meanings is selected by one or more of the processors based in part on a previous search input.

41. A system for inferring user intent in a search input, the system comprising:

a processor configured to;

receive information for a set of content items, each of the content items being associated with metadata that describes the corresponding content item, and each of the content items being associated with at least one information domain;

receive the search input from a user, the search input being intended by the user to identify at least one desired content item;

infer that a first portion of the search input contains a phrase of at least one word that has a plurality of possible meanings, wherein each possible meaning of the plurality of possible meanings is associated with a corresponding information domain;

determine at least one information domain relevant to the search input based in part on a second portion of the search input and not based on the first portion of the search input;

select one possible meaning for the phrase from the plurality of possible meanings based on the search input and the at least one information domain determined to be relevant to the search input; and

select a result for the search input based on the search input, the one possible meaning for the phrase, and metadata associated with the content items, wherein the result comprises at least one content item from the set of content items.

42. The system of claim 41, the at least one information domain including media entertainment and the metadata including at least one of crew, characters, actors, teams, leagues, tournaments, athletes, composers, music artists, performers, albums, songs, news personalities, and content distributors.

43. The system of claim 41, the at least one information domain including electronic mail and the metadata including at least one of electronic mail threads, contacts, senders, recipients, company names, business departments, business units, electronic mail folders, and office location information.

44. The system of claim 41, the at least one information domain including travel-related information and the metadata including at least one of cities, hotels, hotel brands, individual points of interest, categories of points of interest, retail chains, car rental websites, and car rental company names.

45. The system of claim 41, the at least one information domain including electronic commerce and the metadata including at least one of product items, product categories, product subcategories, product brand, and retail stores.

46. The system of claim 41, the at least one information domain including network-based documents and the metadata including at least one of domain names, internet media types, filenames, directories, and filename extensions.

47. The system of claim 41, the at least one information domain including address book information and the metadata including at least one of contact names, electronic mail address, telephone number, address, and employer.

48. The system of claim 41, wherein the processor is further configured to provide a user preference signature, the user preference signature describing preferences of the user for at least one of (i) particular content items and (ii) metadata associated with the content items, wherein the selecting the one possible meaning for the phrase is further based on comparing portions of the search input to the preferences of the user described by the user preference signature.

49. The system of claim 41, wherein the processor is further configured to:

provide a user preference signature, the user preference signature describing preferences of the user for at least one of (i) particular content items and (ii) metadata associated with the content items; and

order the at least one content item based on the preferences of the user described by the user preference signature.

50. The system of claim 41, the metadata associated with the content items including a mapping of relationships between entities associated with the content items, and wherein the processor is further configured to determine the at least one information domain relevant to the search input based in part on the mapping of relationships and the search input.

51. The system of claim 41, wherein the processor is further configured to select the one possible meaning for the phrase from the plurality of possible meanings based in part on a previous search input.