SOCIAL NETWORK BASED CONTEXTUAL RANKING

• US 20120209832A1
• Filed: 03/08/2011
• Published: 08/16/2012
• Est. Priority Date: 02/10/2011
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Neystadt, Eugene (John), Karidi, Ron, Varshavsky, Roy, Oron, Avigad, Radinsky, Kira, Weisfeld, Yitzhak Tzahi
• Granted Patent: US 9,870,424 B2
• Time in Patent Office: Days
• US Class Current: 707/723
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 16/9536 Search customisation based on social or collaborative filtering
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

A ranked set of users may be calculated from an expertise categorization for each user and a person'"'"'s trust in the users for specific categories. The ranked set of users may be used for presenting search results, recommendations, social marketing, or other uses. A person'"'"'s reputation may be determined through various online activities. A person'"'"'s trust in another person may be related to their proximity and activity in one or more social networks.

Claims

1. A method performed on a computer processor, said method comprising:

receiving a plurality of usage context;

receiving a request comprising a first category and a first user;

searching a social network comprising said first user to identify a first set of persons having a reputation level associated with said first category;

for each person in said first set of persons;

determining a influence factor for said first category based at least in part on relationships within said social network between said first user and said person in said first set of persons;

ranking said first set of persons based at least in part on said influence factor.

2. The method of claim 1, said ranking being further calculated as a product of said reputation level and said influence factor for each of said persons in said first set of persons.

3. The method of claim 2, said determining a reputation level being performed prior to said receiving a request.

4. The method of claim 1 further comprising:

searching a second social network for said first user to identify a second set of persons associated with said first category;

for each person in said second set of persons;

determining a influence factor based at least in part on relationships within said second social network between said first person and said person in said first set of persons;

said ranking being based on said trust factor determined from said second social network.

5. The method of claim 1, said first set of persons comprising a plurality of levels of said social network.

6. The method of claim 5, said method being performed in an iterative fashion comprising expanding said first set of persons.

7. The method of claim 1 further comprising:

for each of said plurality of usage context;

searching a set of documents for a usage context to identify a plurality of persons associated with said usage context;

for each of said plurality of persons, determining an reputation level for a person based on said set of documents; and

storing said reputation level in a reputation database;

said first set of persons being selected from said reputation database.

8. A system comprising:

an reputation scorer that searches for a first category to identify persons related to said first category and determines a reputation rating for said persons relating to said first category;

an influencer analyzer that;

searches a social network for persons having said reputation rating for said first category;

determines an influence score for said persons; and

ranks said persons based in part on said influence score.

9. The system of claim 8, said social network aggregator that further ranks said persons based at least in part on said reputation rating.

10. The system of claim 9, said reputation scorer that determines a reputation rating based on express actions performed by said persons.

11. The system of claim 10, said reputation scorer that further determines a reputation rating based on a reputation determination.

12. The system of claim 11, said reputation determination being determined by actions performed by other persons relating to said person for whom a reputation determination is being made.

13. The system of claim 12, said actions being feedback.

14. The system of claim 12, said actions comprising social network connections.

15. The system of claim 8, said social network aggregator that searches said social network to identify a minimum number of said persons.

16. The system of claim 8, said social network aggregator that searches a maximum number of nodes away from said user.

17. A method performed on a computer processor, said method comprising:

receiving a plurality of categories;

for each of said plurality of categories;

searching a set of documents for a category to identify a plurality of persons associated with said category;

for each of said plurality of persons, determining a reputation level for a person after searching online references for said person, said reputation level being based on explicit actions performed by said person and feedback performed by other persons relating to said person;

receiving a request comprising a first category and a first user;

searching a social network comprising said first user to identify a first set of persons having said reputation level associated with said first category;

for each person in said first set of persons;

determining a trust factor based at least in part on relationships within said social network between said first person and said person in said first set of persons;

ranking said first set of persons based at least in part on said trust factor.

18. The method of claim 17, said ranking being further based in part on said reputation rating.

19. The method of claim 18, said first set of persons comprising both natural persons and organizational entities.

20. The method of claim 19, said social network comprising a plurality of social networks.