DETERMINING RELEVANT INFORMATION FOR DOMAINS OF INTEREST

• US 20130066887A1
• Filed: 05/03/2012
• Published: 03/14/2013
• Est. Priority Date: 02/25/2008
• Status: Active Grant

• Current Assignee: Veritone Media
• Original Assignee: Atigeo LLC
• Inventors: Downs, Oliver B., Sandoval, Michael, Branzan, Claudiu Alin, Iovanov, Vlad Mircea, Khalsa, Sopurkh Singh, Bisca, Radu Ioan, Milos, Catalin Teodor
• Granted Patent: US 8,706,664 B2
• Time in Patent Office: Days
• US Class Current: 707/749
• CPC Class Codes: G06F 16/3326 using relevance feedback from the user, e.g. relevance feedback on documents, documents sets, document terms or passages
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/355 Class or cluster creation or modification

Abstract

Techniques are described for determining and using relevant information related to domains of interest. In at least some situations, the techniques include automatically analyzing documents, terms and other information related to a domain of interest in order to automatically determine information about relevant themes within the domain and/or about which documents have contents that are relevant to such themes. Such automatically determined information related to a domain may then be used in various ways, including to assist users in specifying themes of interest and/or in obtaining documents and/or document fragments with contents that are relevant to specified themes. In addition, information about how the automatically determined information is used by users may be tracked and used as feedback for learning improved determinations of relevant themes and relevant documents within the domain, such as by using automated machine learning techniques.

Claims

1-51. -51. (canceled)

52. A computer-implemented method comprising:

analyzing, by one or more configured computing systems, associated information for a plurality of content items in order to identify one or more themes and to assess relevance of at least one of the plurality of content items to at least one of the identified themes;

updating, by the one or more configured computing systems, the assessed relevance of the at least one content items to the at least one identified theme based at least in part on feedback obtained from one or more actions of one or more entities related to one or more of the plurality of content items; and

providing information that is based at least in part on the updated assessed relevance of the at least one content items.

54. A configured computing system comprising:

one or more processors; and

one or more modules that are configured to, when executed by the one or more processors, perform the method of claim 52.

53. A non-transitory computer-readable medium having stored contents that configure a computing system to perform a method, the method comprising:

analyzing, by the configured computing system, associated information for a plurality of content items in order to identify one or more themes and to assess relevance of at least one of the plurality of content items to at least one of the identified themes;

updating, by the configured computing system, the assessed relevance of the at least one content items to the at least one identified theme based at least in part on feedback obtained from one or more actions of one or more entities related to the at least one identified theme; and

providing information that is based at least in part on the updated assessed relevance of the at least one content items.