News results through query expansion

• US 9,646,062 B2
• Filed: 06/10/2013
• Issued: 05/09/2017
• Est. Priority Date: 06/10/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Ormont, Justin, Davis, Marc Eliot
• Primary Examiner(s): To, Baoquoc N
• Application Number:
  US13/913,835
• Publication Number:
  US 20140365468A1
• Time in Patent Office: 1,429 Days
• Field of Search: 707705, 707706, 705 1449, 705 1403
• CPC Class Codes: G06F 16/245 Query processing
• CPC Class Codes: G06F 16/2455 Query execution
• CPC Class Codes: G06F 16/248 Presentation of query results
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

Systems and methods for providing improved news results to a news query according to entity expansion are presented. In response to receiving a news query from a computer user, a news engine identifies one or more interest entities of the computer user. Expanded entity data corresponding to the one or more interest entities is obtained, the expanded entity data identifying related entities to the one or more interest entities. The expanded entity data also includes category data corresponding to the categories of the one or more interest entities. Expanded news queries are generated according to the interest entities, the related entities, and category entities corresponding to the categories. News results are obtained according to the expanded news queries and a news presentation is generated and returned to the computer user.

Claims

1. A computer implemented method for providing news to a computer user in response to receiving a news query from the computer user, the method comprising:

identifying an interest entity of the computer user, wherein the interest entity is associated with a category;

obtaining expanded entity data corresponding to the interest entity from a related entity source, the expanded entity data comprising related entity data identifying a plurality of related entities that are related to the interest entity;

generating an expanded news query for news content according to the interest entity and the expanded entity data, wherein generating the expanded news query for news content according to the interest entity and the expanded entity data comprises generating the expanded news query to include a request for the interest entity and the plurality of related entities;

obtaining a plurality of references to news content according to the news query and the expanded news query, wherein the obtained plurality of references to news content comprise interest entity references to news content related to the interest entity and general references to news content not related to the interest entity;

generating a news presentation according to the obtained references to news content, wherein generating the news presentation according to the obtained references to news content comprises grouping the interest entity references to news content and presenting the interest entity references to news content as being associated with the category of the interest entity; and

providing the news presentation to the computer user.

2. The computer implemented method of claim 1, wherein the expanded entity data further comprises category data corresponding to the category associated with the interest entity, wherein the category data comprises category entities identifying all of the bases of relationships that an interest entity associated with the category may have with related entities, each category entity identifying a basis of a relationship that an interest entity associated with the category may have with a related entity.

3. The computer implemented method of claim 2, wherein the bases of the relationships between the interest entity and the plurality of related entities identified in the related entity data is a subset of the bases of relationships between an interest entity associated with the category and related entities as identified by the category data.

4. The computer implemented method of claim 3, wherein generating the expanded news query for news content according to the interest entity and the expanded entity data comprises generating the expanded news query to include a request for the interest entity, the plurality of related entities, and the category entities.

5. The computer implemented method of claim 4, wherein the obtained plurality of references to news content comprise interest entity references to news content related to the interest entity and general references to news content not related to the interest entity;

and

wherein generating a news presentation according to the obtained references to news content comprises grouping the interest entity references to news content and presenting the interest entity references to news content as being associated with the category of the interest entity.

6. The computer implemented method of claim 4 further comprising:

identifying a plurality of interest entities of the computer user, each of the plurality of interest entities being associated with a category;

obtaining expanded entity data for each of the plurality of interest entities;

generating a plurality of expanded news queries corresponding to each of the plurality of interest entities;

obtaining references to news content for each of the plurality of expanded news queries; and

generating a news presentation according to the obtained references to news content, wherein at least a portion of the obtained references to news content is organized according to categories associated with the plurality of interest entites.

7. The computer implemented method of claim 1, wherein obtaining expanded entity data corresponding to the interest entity comprises obtaining the expanded entity data corresponding to the interest entity from a plurality of related entity sources.

8. The computer implemented method of claim 1, wherein subject matter of the expanded news query comprises the interest entity, related entities, and category entities.

9. The computer implemented method of claim 1, wherein the interest entity is identified explicitly or implicitly for the computer user.

10. A computer readable storage medium bearing computer executable instructions which, when executed on a computing system comprising at least a processor executing the instructions retrieved from the medium, carry out a method for providing news to a computer user in response to receiving a news query from the computer user, the method comprising:

identifying a plurality of interest entities of the computer user, each of the plurality of interest entities being associated with a category;

obtaining expanded entity data for each of the plurality of interest entities from a related entity source, the expanded entity data comprising;

related entity data identifying a set of related entities that are related to the interest entity; and

category data corresponding to the category associated with the interest entity, the category data comprising a set of category entities identifying all of the bases of relationships that an interest entity associated with the category may have with related entities, each category entity identifying a basis of a relationship that an interest entity associated with the category may have with a related entity;

generating a plurality of expanded news queries corresponding to each of the plurality of interest entities according to the plurality of interest entities and the expanded entity data;

obtaining a plurality of references to news content for each of the plurality of expanded news queries;

generating a news presentation according to the obtained references to news content, wherein at least a portion of the obtained references to news content are organized according to the categories associated with the plurality of interest entities; and

providing the news presentation to the computer user.

11. The computer readable storage medium of claim 10, wherein generating the expanded news query for news content according to the interest entity and the expanded entity data comprises generating the expanded news query to include a request for the interest entity, the plurality of related entities, and the category entities.

12. The computer readable storage medium of claim 11, wherein generating a news presentation according to the obtained references to news content comprises grouping a portion of the interest entity references to news content according to the category associated with the interest entity.

13. The computer readable storage medium of claim 10, wherein the method further comprises obtaining expanded entity data corresponding to the interest entity from a plurality of related entity sources.

14. The computer readable storage medium of claim 10, each of the plurality of interest entities is identified explicitly or implicitly for the computer user.

15. A computer system for providing news results in response to receiving a news query from a computer user, the system comprising a processor and a memory, wherein the processor executes instructions stored in the memory as part of or in conjunction with additional components to respond to the news query, the additional components comprising:

an interest entity retrieval component configured to obtain interest entity information identifying a plurality of interest entities of the computer user, each interest entity being associated with a category;

an expanded data retrieval component configured to obtain related entity data identifying related entities for the plurality of interest entities and category data corresponding to the associated categories;

an expanded query generator that generates an expanded news query for each of the plurality of interest entities and corresponding related entity data;

an expanded query merger component that combines the expanded news queries of interest entities of the same category to generate one or more combined expanded news queries;

a news retrieval component configured to obtain references to news content from a news content store according to the one or more combined expanded news queries; and

a news presentation generator that generates a news presentation for the computer user according to the obtained references to news content and provides the news presentation to the computer user.

16. The computer system of claim 15, wherein subject matter of the expanded news query comprises the interest entity, related entities, and category entities.

17. The computer system of claim 15, wherein the expanded data retrieval component is configured to obtain related entity data identifying related entities for the plurality of interest entities and category data corresponding to the associated categories from a plurality of related entity sources.

18. The computer system of claim 15, wherein the news presentation generator is configured to generate the news presentation for the computer user according to the obtained references to news content and including a grouping of the interest entity references to news content and present the interest entity references as being associated with the category of the interest entity.

19. The computer system of claim 15, wherein interest entity retrieval component is configured to obtain interest entity information identifying a plurality of interest entities of the computer user, each interest entity being associated with a category, from a plurality of interest entity sources.

20. The computer system of claim 15, wherein each of the plurality of interest entities is identified explicitly or implicitly for the computer user.