GENERATING DISTINCT ENTITY NAMES TO FACILITATE ENTITY DISAMBIGUATION

• US 20150331950A1
• Filed: 05/16/2014
• Published: 11/19/2015
• Est. Priority Date: 05/16/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: LI, JINGFENG, KE, YAN, CHANG, HUNG-AN, ZHAUNG, WEI
• Granted Patent: US 10,838,995 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/24575 using context
• CPC Class Codes: G06F 16/338 Presentation of query results
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Computer-readable media, computer systems, and computing methods for facilitating generation of entity names for entities are provided. The method includes determining a set of previously submitted queries that are associated with an entity. The most frequently used query within the set of previously submitted queries associated with the entity can be identified and, thereafter, designated as the entity name for the entity. The entity name can distinguish the entity from other entities. Such an entity name can be provided for presentation to a user, for example, as a related search suggestion via a search results page.

Claims

1. A method of facilitating generation of entity names, the method comprising:

determining a set of previously submitted queries that are associated with an entity;

identifying, via a computing device, the most frequently used query within the set of previously submitted queries associated with the entity; and

designating the most frequently used query as an entity name for the entity, the entity name distinctly identifying the entity from other entities.

2. The method of claim 1, wherein the entity is a head entity that is associated with rich information pertaining to the entity.

3. The method of claim 1, wherein the previously submitted queries are determined to be associated with the entity based on content of web documents selected in association with the previously submitted queries.

4. The method of claim 1 further comprising storing the entity name for subsequent use in identifying the entity.

5. The method of claim 1 further comprising providing the entity name to distinctly identify the entity within a search engine web page in response to a user query.

6. The method of claim 1, wherein determining the set of previously submitted queries, identifying the most frequently used query, and designating the most frequently used query as an entity name for an entity occur in real-time upon issuance of a query to a search engine.

7. The method of claim 1 further comprising comparing the entity name to additional candidate entity names to select one entity name to distinctly represent the entity.

8. A method for facilitating generation of entity names comprising:

recognizing an indication to generate a unique entity name for an entity;

determining whether the entity is associated with at least a threshold number of queries, wherein

when the entity is associated with at least the threshold number of queries, using a first entity-name generating approach to generate an entity name for the entity, and

when the entity is not associated with the at least the threshold number of queries, using a second entity-name generating approach to generate the entity name for the entity.

9. The method of claim 8 further comprising providing a plurality of approaches to generate entity names for entities.

10. The method of claim 8, wherein the indication to generate the unique entity name for the entity is recognized upon submission of a user query.

11. The method of claim 8, wherein the first entity-name generating approach comprises a query log basis that utilizes frequently used query terms associated with the entity to generate the entity name.

12. The method of claim 8, wherein the second entity-name generating approach comprises a decision tree basis that traverses a decision tree to generate the entity name.

13. The method of claim 8 further comprising providing the entity name for presentation to the user in response to a user query.

14. One or more computer-readable storage media having embodied thereon computer-executable instructions that, when executed by a processor in a computing device, cause the computing device to perform a method of facilitating generation of entity names, the method comprising:

generating a plurality of candidate entity names for an entity using a plurality of entity-name generating techniques;

selecting a most distinct human-readable entity name for the entity from among the plurality of candidate entity names, wherein the selection is based at least in part on the entity-name generating techniques used to generate the corresponding candidate entity names; and

providing the selected entity name for presentation via a search results page to unambiguously represent the entity.

15. The media of claim 14, wherein the plurality of entity-name generating techniques comprises at least a query log basis that utilizes frequently used query terms associated with the entity to generate the entity name.

16. The media of claim 14, wherein the plurality of entity-name generating techniques comprises at least a decision tree basis that traverses a decision tree to generate the entity name.

17. The media of claim 14, wherein the plurality of entity-name generating techniques comprises a rule basis that uses one or more rules to generate the entity name for the entity based on a type of entity.

18. The media of claim 14, wherein the plurality of entity-name generating techniques comprises an entity relation basis that uses relationships between entities to generate the entity name for the entity.

19. The media of claim 14, wherein the selection of the most distinct human-readable entity name for the entity uses prioritization of the entity-name generating techniques based on a type of entity.

20. The media of claim 19, wherein the type of entity comprises a head entity, a tail entity, or a sub-entity.