CONTENT RECOMMENDATION BASED ON COLLECTIONS OF ENTITIES

• US 20110282888A1
• Filed: 03/01/2011
• Published: 11/17/2011
• Est. Priority Date: 03/01/2010
• Status: Active Grant

• Current Assignee: VCVC III LLC (Vulcan, Inc.)
• Original Assignee: EVRI Incorporated
• Inventors: Roseman, Neil, Liang, Jisheng, Koperski, Krzysztof
• Granted Patent: US 9,710,556 B2
• Time in Patent Office: Days
• US Class Current: 707/752
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Techniques for content recommendation are described. Some embodiments provide a content recommendation system (“CRS”) configured to recommend content items that are related to a collection of entities. A content item may be considered related to a collection of entities based on various factors, including whether and how often the article references or otherwise covers the entities of the collection, the size of the article, other entities that are covered by the article but that are not in the collection, article recency, or article credibility. Recommending content items may also or instead include determining entities that are related to a collection. An entity can be considered related to a collection based on various factors, such as whether the entity is of the same or similar type to entities of the collection, or whether the entity appears in some article in a relationship with one or more entities of the collection.

Claims

1. A method in a content recommendation system, the method comprising:

defining a collection including indications of multiple entities that are each referenced by one or more of multiple content items indexed by the content recommendation system and that are each electronically represented in the content recommendation system;

processing the collection to determine one or more of the multiple content items that are related to at least some of the multiple entities, the one or more content items including an article and/or an entity; and

recommending the content items.

2. The method of claim 1 wherein defining the collection includes presenting a user interface control that suggests one or more entities to add to an existing collection.

3. The method of claim 1 wherein defining the collection includes presenting a user interface control configured to create a new collection in response to received user specification of one or more entities.

4. The method of claim 1 wherein processing the collection includes determining multiple articles that each reference at least one of the entities of the collection.

5. The method of claim 1 wherein processing the collection includes determining multiple entities that are each related to at least one of the entities of the collection.

6. The method of claim 1 wherein processing the collection includes determining whether an entity appears in an article in a relationship with a facet common to entities of the collection and in the article in context with one of the common key terms.

7. The method of claim 1 wherein processing the collection includes determine whether an entity appears in an article in a relationship with one of the multiple entities and in the article in context with another one of the multiple entities.

8. The method of claim 1 wherein recommending the content items includes ordering the multiple content items based on at least one of relevance, recency, or credibility.

9. The method of claim 1 further comprising providing a code module configured to perform the method in a third-party application context.

10. The method of claim 1 wherein recommending the content items includes causing at least some of the recommended content items to be displayed.

11. A method in a content recommendation system, the method comprising:

receiving indications of multiple entities that are each referenced by one or more indexed articles and that are each electronically represented in the content recommendation system;

determining multiple articles that each include references to at least two of the multiple entities; and

storing the multiple articles.

12. The method of claim 11 wherein determining the multiple articles includes constructing a query configured to obtain indications of one or more of the articles indexed by the content recommendation system.

13. The method of claim 12 wherein constructing the query includes determine whether one of the multiple entities is a known disambiguated entity or a known non-disambiguated entity.

14. The method of claim 12 wherein constructing the query includes constructing a query that includes a unique identifier for the one entity when the one entity is a known disambiguated entity.

15. The method of claim 12 wherein constructing the query includes constructing a query that includes, when the one entity is a known non-disambiguated entity, a name for the entity along with one or more disambiguating terms.

16. The method of claim 11 further comprising:

ordering the multiple articles based on article recency and/or article relevance.

17. The method of claim 16 wherein ordering the multiple articles includes ordering a first article before a second article, the first article having a more recent publishing date than the second article.

18. The method of claim 16 wherein ordering the multiple articles includes ordering a first article before a second article, the first article, the first article referencing more of the multiple entities than the second article.

19. The method of claim 16 wherein ordering the multiple articles includes ordering the multiple articles based at least in part on term document frequency and/or inverse term document frequency.

20. The method of claim 16 wherein ordering the multiple articles includes ordering the multiple articles based at least in part on source credibility.

21. A method in a content recommendation system, the method comprising:

receiving an indication of a collection including multiple entities;

determining shared characteristics of the multiple entities, the shared characteristics including common facets and common key terms;

determining a plurality of entities that are each related to one of the multiple entities, wherein each of the plurality of entities

appear in an article in a relationship with one or more of the common facets and in the article in context with one of the common key terms, and/or

appear in an article in a relationship with one of the multiple entities and in the article in context with another one of the multiple entities; and

storing the plurality of entities.

22. The method of claim 21 wherein determining the plurality of entities includes determining a plurality of entities that each appear in a subject-verb-object relationship described in an article and that includes one of the multiple entities.

23. The method of claim 21 wherein determining the plurality of entities includes determining a plurality of entities that each appear in an article in a relationship with one or more of the common facets and in the article in context with one of the common key terms.

24. The method of claim 21 wherein determining the plurality of entities includes determining a plurality of entities that each appear in an article in a relationship with one of the multiple entities and in the article in context with another one of the multiple entities.

25. The method of claim 21 wherein determining the plurality of entities includes constructing a query configured to discover relationships expressed in articles.

26. The method of claim 21 wherein receiving the indication of the collection includes at least one of:

receiving indication of an entity selected from an entity store, receiving indication of a keyterm, and/or receiving an indication of facet.

27. The method of claim 21, further comprising ordering the plurality of entities based at least in part on how many facets are shared between each of the plurality of entities and the multiple entities.

28. The method of claim 21, further comprising ordering the plurality of entities based at least in part on how frequently each of the plurality the entities appear in one or more articles that reference the entity.

29. A computer-readable medium whose contents enable a computing system to recommend content, by performing a method comprising:

defining a collection including indications of multiple entities that are each referenced by one or more of multiple content items indexed by a content recommendation system and that are each electronically represented in the content recommendation system;

processing the collection to determine one of the multiple content items that is related to at least some of the multiple entities, the one content item including an article and/or an entity; and

recommending the content items.

30. The computer-readable medium of claim 29 wherein the method further comprises:

determining shared characteristics of the multiple entities, the shared characteristics including common facets and common key terms;

determining at least one entity that is related to one of the multiple entities; and

recommending the at least one entity.

31. The computer-readable medium of claim 30 wherein the at least one entity appears in an article in a relationship with one or more of the common facets and in the article in context with one of the common key terms, and/or appears in an article in a relationship with one of the multiple entities and in the article in context with another one of the multiple entities.

32. The computer-readable medium of claim 29 wherein the computer-readable medium is at least one of a memory in a computing device or a data transmission medium transmitting a generated signal containing the contents.

33. The computer-readable medium of claim 29 wherein the contents are instructions that when executed cause the computing system to perform the method.

34. A computing system configured to recommend content, comprising:

a memory;

a module stored on the memory that is configured, when executed, to;

define a collection including indications of multiple entities that are each referenced by one or more of multiple content items indexed by a content recommendation system and that are each electronically represented in the content recommendation system;

process the collection to determine one or more content items of the multiple content items that are related to at least some of the multiple entities, the one or more content items including an article and/or an entity; and

recommend the content items.

35. The computing system of claim 34 wherein the module is configured to recommend at least one of an article, image, advertisement, audio, video, and/or document.

36. The computing system of claim 34 wherein the module is configured to recommend content items to at least one of a desktop computing system, a personal digital assistant, a smart phone, a mobile application, a laptop computer, and/or a third-party application.