Generating and using social brains with complimentary semantic brains and indexes

• US 8,788,516 B1
• Filed: 03/15/2013
• Issued: 07/22/2014
• Est. Priority Date: 03/15/2013
• Status: Active Grant

• Current Assignee: Brainspace Corporation (Reveal Data Corp.)
• Original Assignee: PureDiscovery Corporation (Reveal Data Corp.)
• Inventors: Jakubik, Paul A.
• Primary Examiner(s): Ruiz, Angelica
• Application Number:
  US13/842,144
• Time in Patent Office: 494 Days
• Field of Search: None
• US Class Current: 707/758
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A method includes determining a plurality of social interactions associated with a plurality of people, generating a social object matrix using the determined social interactions, and generating a social brain by performing Singular Value Decomposition (SVD) on the social object matrix. The method further includes determining text from the social objects of the determined social interactions, generating a term-document matrix (TDM) using the determined text, generating a semantic brain by performing SVD on the TDM, generating an index using the determined text, and performing a query using the social brain, the semantic brain, and the index. The social brain is a singular value representation of the social object matrix and the semantic brain is a singular value representation of the TDM. Each social interaction is a particular person interacting with a particular social object.

Claims

1. A system, comprising:

one or more memory units; and

one or more processors operable to;

determine a plurality of social interactions associated with a plurality of people, each social interaction comprising a particular person interacting with a particular social object of a plurality of social objects;

generate a social object matrix using the determined social interactions;

generate a social brain by performing Singular Value Decomposition (SVD) on the social object matrix, the social brain comprising a singular value representation of the social object matrix;

determine text from the social objects of the determined social interactions;

generate a term-document matrix (TDM) using the determined text;

generate a semantic brain by performing SVD on the TDM, the semantic brain comprising a singular value representation of the TDM;

generate an index using the determined text; and

perform a query using the social brain, the semantic brain, and the index.

2. The system of claim 1, wherein determining text from the social objects of the determined social interactions comprises:

capturing text from the plurality of social objects that are textual social objects; and

determining proxies for the plurality of social objects that are non-textual social objects and capturing text from the determined proxies.

3. The system of claim 1, wherein performing the query using the social brain, the semantic brain, and the index comprises:

determining, using the semantic brain and the index, one or documents in the social brain that are semantically related to a query document;

creating a pseudo-document using the determined one or more semantically related documents; and

determining one or more social recommendations using the social brain and the created pseudo-document.

4. The system of claim 1, wherein the one or more processors are further operable to group the determined social interactions into the plurality of groups according to the plurality of people or the plurality of social objects.

5. The system of claim 1, wherein generating the social object matrix comprises:

determining a number of occurrences of each social object for each of the plurality of people;

determining a number of occurrences of each social object across all of the plurality of people;

determining a subset of the plurality of social objects;

determining a weighting for each social object of the subset of social objects, the weighting based at least in part on a distribution of the social objects across all of the plurality of people; and

creating the plurality of vectors based on the determined number of occurrences of each social object for each of the plurality of people and the determined weighting for each social object.

6. The system of claim 1, wherein the social object matrix comprises a person-by-social object matrix.

7. The system of claim 1, wherein the social object matrix comprises a social object-by-person matrix.

8. A computer-implemented method, comprising:

determining, by one or more computing systems, a plurality of social interactions associated with a plurality of people, each social interaction comprising a particular person interacting with a particular social object of a plurality of social objects;

generating, by the one or more computing systems, a social object matrix using the determined social interactions;

generating, by the one or more computing systems, a social brain by performing Singular Value Decomposition (SVD) on the social object matrix, the social brain comprising a singular value representation of the social object matrix;

determining, by the one or more computing systems, text from the social objects of the determined social interactions;

generating, by the one or more computing systems, a term-document matrix (TDM) using the determined text;

generating, by the one or more computing systems, a semantic brain by performing SVD on the TDM, the semantic brain comprising a singular value representation of the TDM;

generating, by the one or more computing systems, an index using the determined text; and

performing, by the one or more computing systems, a query using the social brain, the semantic brain, and the index.

9. The computer-implemented method of claim 8, wherein determining text from the social objects of the determined social interactions comprises:

capturing text from the plurality of social objects that are textual social objects; and

determining proxies for the plurality of social objects that are non-textual social objects and capturing text from the determined proxies.

10. The computer-implemented method of claim 8, wherein performing the query using the social brain, the semantic brain, and the index comprises:

determining, using the semantic brain and the index, one or documents in the social brain that are semantically related to a query document;

creating a pseudo-document using the determined one or more semantically related documents; and

determining one or more social recommendations using the social brain and the created pseudo-document.

11. The computer-implemented method of claim 8, further comprising grouping, by the one or more computing systems, the determined social interactions into the plurality of groups according to the plurality of people or the plurality of social objects.

12. The computer-implemented method of claim 8, wherein generating the social object matrix comprises:

determining a number of occurrences of each social object for each of the plurality of people;

determining a number of occurrences of each social object across all of the plurality of people;

determining a subset of the plurality of social objects;

determining a weighting for each social object of the subset of social objects, the weighting based at least in part on a distribution of the social objects across all of the plurality of people; and

creating the plurality of vectors based on the determined number of occurrences of each social object for each of the plurality of people and the determined weighting for each social object.

13. The computer-implemented method of claim 8, wherein the social object matrix comprises a person-by-social object matrix.

14. The computer-implemented method of claim 8, wherein the social object matrix comprises a social object-by-person matrix.

15. A non-transitory computer-readable medium comprising software, the software when executed by one or more processors operable to perform operations comprising:

determining a plurality of social interactions associated with a plurality of people, each social interaction comprising a particular person interacting with a particular social object of a plurality of social objects;

generating a social object matrix using the determined social interactions;

generating a social brain by performing Singular Value Decomposition (SVD) on the social object matrix, the social brain comprising a singular value representation of the social object matrix;

determining text from the social objects of the determined social interactions;

generating a term-document matrix (TDM) using the determined text;

generating a semantic brain by performing SVD on the TDM, the semantic brain comprising a singular value representation of the TDM;

generating an index using the determined text; and

performing a query using the social brain, the semantic brain, and the index.

16. The non-transitory computer-readable medium of claim 15, wherein determining text from the social objects of the determined social interactions comprises:

capturing text from the plurality of social objects that are textual social objects; and

determining proxies for the plurality of social objects that are non-textual social objects and capturing text from the determined proxies.

17. The non-transitory computer-readable medium of claim 15, wherein performing the query using the social brain, the semantic brain, and the index comprises:

determining, using the semantic brain and the index, one or documents in the social brain that are semantically related to a query document;

creating a pseudo-document using the determined one or more semantically related documents; and

determining one or more social recommendations using the social brain and the created pseudo-document.

18. The non-transitory computer-readable medium of claim 15, the operations further comprising grouping the determined social interactions into the plurality of groups according to the plurality of people or the plurality of social objects.

19. The non-transitory computer-readable medium of claim 15, wherein generating the social object matrix comprises:

determining a number of occurrences of each social object for each of the plurality of people;

determining a number of occurrences of each social object across all of the plurality of people;

determining a subset of the plurality of social objects;

determining a weighting for each social object of the subset of social objects, the weighting based at least in part on a distribution of the social objects across all of the plurality of people; and

creating the plurality of vectors based on the determined number of occurrences of each social object for each of the plurality of people and the determined weighting for each social object.

20. The non-transitory computer-readable medium of claim 15, wherein the social object matrix comprises a person-by-social object matrix or a social object-by-person matrix.