USER INTERESTS FACILITATED BY A KNOWLEDGE BASE

• US 20150278691A1
• Filed: 04/01/2014
• Published: 10/01/2015
• Est. Priority Date: 04/01/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Cai, Ting, XIA, Minghui, PODLEPAEV, Evgeny, MAO, Qiaolin, RANFT, Eric Conrad, FAN, Xiaodong
• Granted Patent: US 9,754,210 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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 16/90344 by using string matching techniques
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

In one implementation, a computer-implemented method for determining user interests includes receiving user activity data that describes an interaction between a user and digital content. The method further includes generating first interest-level data that quantifies a first level of interest between the user and an entity that is a topic of the digital content, where the entity is of a plurality of entities included within a knowledge base. The knowledge base includes an ontology that indicates relationships between the plurality of entities. The method further includes identifying a candidate entity based on the candidate entity having one of the relationships to the entity within the knowledge base. Additionally, the method includes generating second interest-level data that quantifies a second level of interest between the user and the candidate entity based on an analysis of the one of the relationships of the candidate entity to the entity within the knowledge base.

Claims

1. A computer-implemented method for determining user interests, comprising:

receiving user activity data that describes an interaction between a user and digital content;

generating first interest-level data that quantifies a first level of interest between said user and an entity that is a topic of said digital content, wherein said entity is one of a plurality of entities included within a knowledge base, said knowledge base comprising an ontology that indicates relationships between said plurality of entities;

identifying a candidate entity based on said candidate entity having one of said relationships to said entity within said knowledge base; and

generating second interest-level data that quantifies a second level of interest between said user and said candidate entity based on an analysis of said one of said relationships of said candidate entity to said entity within said knowledge base.

2. The computer-implemented method of claim 1, wherein said entity and said candidate entity are each instance entities of said ontology.

3. The computer-implemented method of claim 1, wherein said one of said relationships comprises said candidate entity sharing at least one common concept entity with said entity.

4. The computer-implemented method of claim 1, wherein said candidate entity is not a topic of digital content the user has interacted with, and wherein the candidate entry is related to the entity through co-occurrence in one or more documents.

5. The computer-implemented method of claim 1, further comprising updating said first level of interest between said user and said entity based on a frequency of said entity being a topic of additional digital content that the user interacts with.

6. The computer-implemented method of claim 1, further comprising updating said first level of interest between said user and said entity that is said topic of said digital content based on a recency of said entity being a topic of digital content.

7. The computer-implemented method of claim 1, further comprising presenting additional digital content to said user on a user device based on said candidate entity being a topic of said additional digital content.

8. The computer-implemented method of claim 1, further comprising generating search results for said user that are relevance ranked using said second interest-level data.

9. The computer-implemented method of claim 1, further comprising exposing said second interest-level data for consumption by multiple applications.

10. The computer-implemented method of claim 1, further comprising presenting said candidate entity to said user on a user device based on said second interest-level data;

and

updating said second interest level between said user and said candidate entity based on feedback received from said user.

11. A computer-implemented method for determining user interests, comprising:

generating first interest-level data that quantifies a first level of interest between a user and a first entity that is a topic of a first digital content, wherein said first entity is one of a plurality of entities included within a knowledge base, said knowledge base comprising an ontology that indicates relationships between said plurality of entities;

generating second interest-level data that quantifies a second level of interest between said user and a second entity that is a topic of a second digital content, wherein said second entity is one of said plurality of entities included within said knowledge base; and

updating said first interest-level data by increasing said first level of interest between said user and said first entity based on said second entity being closely related to said first entity in one of said relationships of said knowledge base.

12. The computer-implemented method of claim 11, wherein the first interest-level data comprises identification information that allows the first level of interest to be linked to the first entity within the knowledge base.

13. The computer-implemented method of claim 11, wherein said one of said relationships comprises said first entity sharing at least one common concept entity with said second entity.

14. The computer-implemented method of claim 11, wherein said digital content comprises any of a webpage, a post on a social network, an email, a mobile text, an advertisement, a word processing document, a music file, a video file, an audio book, a spreadsheet, an electronic book, a news article, a game, and a blog post.

15. The computer-implemented method of claim 11, further comprising presenting said first entity to said user as a query to said user on a display of a user device based on said second interest-level data;

and

updating said first level of interest between said user and said first entity as quantified by said first interest-level data based on a response of said user to said query.

16. One or more computer-storage media storing computer-useable instructions that, when executed by a computing device, perform a method for determining user interests, comprising:

identifying a digital content in user activity data that describes an interaction between a user and said digital content;

identifying an entity that is matched to the digital content by mapping data, said entity being a topic of said digital content, wherein said entity is of a plurality of entities included within a knowledge base, said knowledge base comprising an ontology that indicates relationships between said plurality of entities;

generating first interest-level data that quantifies a first level of interest between said user and said entity;

identifying a candidate entity based on said candidate entity having one of said relationships to said entity within said knowledge base; and

generating second interest-level data that quantifies a second level of interest between said user and said candidate entity based on an analysis of said one of said relationships of said candidate entity to said entity within said knowledge base.

17. The one or more computer-storage media of claim 16, wherein said mapping data is of a plurality of mapping data in an index, said plurality of mapping data matching ones of said plurality of entities included within said knowledge base to corresponding digital content.

18. The one or more computer-storage media of claim 16, wherein said entity and said candidate entity are each instance entities of said ontology.

19. The one or more computer-storage media of claim 16, further comprising determining said entity as said topic of said digital content based on an analysis of said digital content.

20. The one or more computer-storage media of claim 16, wherein said one of said relationships comprises one or more relations of said ontology of said knowledge graph.