Methods and devices for customizing knowledge representation systems

• US 9,576,241 B2
• Filed: 12/07/2015
• Issued: 02/21/2017
• Est. Priority Date: 06/22/2010
• Status: Active Grant

• Current Assignee: Primal Fusion Inc.
• Original Assignee: Primal Fusion Inc.
• Inventors: Sweeney, Peter Joseph, Ilyas, Ihab Francis
• Primary Examiner(s): Holmes, Michael B
• Application Number:
  US14/961,819
• Publication Number:
  US 20160086085A1
• Time in Patent Office: 442 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

Techniques for customizing knowledge representation systems including identifying, based on a plurality of concepts in a knowledge representation (KR), a group of one or more concepts relevant to user context information, and providing the identified group of one more concepts to a user. The KR may include a combination of modules. The modules may include a kernel and a customized module customized for the user. The kernel may accessible via a second KR.

Claims

1. A computer-implemented method for providing content based on a knowledge representation (KR), the method comprising:

obtaining user context information associated with a user, wherein the user context information includes information regarding an attribute of the user, information regarding an activity of the user, and/or information provided by the user;

identifying a group of one or more concepts relevant to the user context by performing a synthesis operation on a user KR, wherein the user KR includes at least one kernel module combined with at least one user-specific customized module;

identifying content information corresponding to the identified group of one or more concepts; and

providing the identified content information to the user.

2. The computer-implemented method of claim 1, wherein the identified content includes documents, audiovisual information, tweets, emails, messages posted on a social networking platform, blog entries, and/or any combination thereof.

3. The computer-implemented method of claim 1, further comprising ranking the content information provided to the user based on relevance of the content information to the identified group of one or more concepts.

4. The computer-implemented method of claim 1, further comprising combining the at least one kernel module with the at least one user-specific customized module, the combining comprising an entity resolution act comprising:

identifying a first concept associated with the kernel module and identifying a second concept associated with the user-specific customized module;

matching the first concept with the second concept based on an identifier and/or pattern; and

merging the first concept and the second concept into a third concept.

5. The computer-implemented method of claim 1, wherein the user context information is part of an interest network corresponding to information provided by the user.

6. The computer-implemented method of claim 5, further comprising providing the interest network to an analysis engine for deconstruction.

7. At least one non-transitory computer-readable storage medium storing computer-executable instructions that, when executed, perform a method for providing content based on a knowledge representation (KR), the method comprising:

obtaining user context information associated with a user, wherein the user context information includes information regarding an attribute of the user, information regarding an activity of the user, and/or information provided by the user;

identifying a group of one or more concepts relevant to the user context by performing a synthesis operation on a user KR, wherein the user KR includes at least one kernel module combined with at least one user-specific customized module;

identifying content information corresponding to the identified group of one or more concepts; and

providing the identified content information to the user.

8. The at least one non-transitory computer-readable storage medium of claim 7, wherein the identified content includes documents, audiovisual information, tweets, emails, messages posted on a social networking platform, blog entries, and/or any combination thereof.

9. The at least one non-transitory computer-readable storage medium of claim 7, wherein the method further comprises ranking the content information provided to the user based on relevance of the content information to the identified group of one or more concepts.

10. The at least one non-transitory computer-readable storage medium of claim 7, wherein the method further comprises combining the at least one kernel module with the at least one user-specific customized module, the combining comprising an entity resolution act comprising:

identifying a first concept associated with the kernel module and identifying a second concept associated with the user-specific customized module;

matching the first concept with the second concept based on an identifier and/or pattern; and

merging the first concept and the second concept into a third concept.

11. The at least one non-transitory computer-readable storage medium of claim 7, wherein the user context information is part of an interest network corresponding to information provided by the user.

12. The at least one non-transitory computer-readable storage medium of claim 11, wherein the method further comprises providing the interest network to an analysis engine for deconstruction.

13. Apparatus comprising:

at least one processor; and

at least one storage medium storing processor-executable instructions that, when executed by the at least one processor, perform a method for providing content based on a knowledge representation (KR), the method comprising;

obtaining user context information associated with a user, wherein the user context information includes information regarding an attribute of the user, information regarding an activity of the user, and/or information provided by the user;

identifying a group of one or more concepts relevant to the user context by performing a synthesis operation on a user KR, wherein the user KR includes at least one kernel module combined with at least one user-specific customized module;

identifying content information corresponding to the identified group of one or more concepts; and

providing the identified content information to the user.

14. The apparatus of claim 13, wherein the identified content includes documents, audiovisual information, tweets, emails, messages posted on a social networking platform, blog entries, and/or any combination thereof.

15. The apparatus of claim 13, wherein the method further comprises ranking the content information provided to the user based on relevance of the content information to the identified group of one or more concepts.

16. The apparatus of claim 13, wherein the method further comprises combining the at least one kernel module with the at least one user-specific customized module, the combining comprising an entity resolution act comprising:

identifying a first concept associated with the kernel module and identifying a second concept associated with the user-specific customized module;

matching the first concept with the second concept based on an identifier and/or pattern; and

merging the first concept and the second concept into a third concept.

17. The apparatus of claim 13, wherein the user context information is part of an interest network corresponding to information provided by the user.

18. The apparatus of claim 17, wherein the method further comprises providing the interest network to an analysis engine for deconstruction.