Automatic gleaning of semantic information in social networks

• US 20100114989A1
• Filed: 10/30/2008
• Published: 05/06/2010
• Est. Priority Date: 10/30/2008
• Status: Active Grant

• Current Assignee: LYFT Incorporated
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Krishnamurthy, Balachander, Cormode, Graham
• Granted Patent: US 8,386,534 B2
• Time in Patent Office: Days
• US Class Current: 707/808
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Disclosed are method and apparatus for identifying members of a social network who have a high likelihood of providing a useful response to a query. A query engine examines the personal pages of a set of members and automatically gleans semantic information relevant to the query. From the automatically-gleaned semantic information, a score indicative of the likelihood that the member may provide a useful response is calculated.

Claims

1. A method for generating a set of candidates who may provide at least one useful response to a query submitted by a querier in a first social networking site associated with a first social network, comprising the steps of:

receiving the query;

automatically gleaning semantic information from a first personal page in the first social networking site, said first personal page associated with a member of the first social network;

calculating a first score based at least in part on the semantic information automatically gleaned from the first personal page; and

adding the member to the set of candidates based at least in part on said calculated first score.

2. The method of claim 1, further comprising the step of:

sending the query to at least one candidate in said set of candidates.

3. The method of claim 2, wherein said step of sending the query to at least one candidate in said set of candidates comprises the step of:

sending an e-mail containing the query from a querier to said at least one candidate.

4. The method of claim 2, wherein said step of sending the query to at least one candidate in said set of candidates comprises the step of:

automatically sending a message containing the query to said at least one candidate.

5. The method of claim 1, wherein said step of adding the member to the set of candidates based at least in part on said calculated first score comprises the steps of:

comparing said calculated first score to a threshold score; and

adding the member to the set of candidates if said calculated first score is greater than said threshold score.

6. The method of claim 1, further comprising the step of:

rank-ordering said set of candidates based on the specific calculated first score associated with each specific candidate in said set of candidates.

7. The method of claim 1, wherein said member is an addressee in a set of addressees.

8. The method of claim 7, wherein said set of addressees is based at least in part on said query.

9. The method of claim 7, wherein said set of addressees is a predetermined set of addressees.

10. The method of claim 9, wherein said predetermined set of addressees comprises at least one of:

a set of friends associated with said querier;

a group associated with said querier; and

a set of specific addressees specified by said querier.

11. The method of claim 7, further comprising the steps of:

for each of the specific addressees in said set of addressees;

automatically gleaning semantic information from the specific first personal page associated with the specific addressee;

calculating the specific first score associated with the specific addressee, said specific first score based at least in part on the semantic information automatically gleaned from the specific first personal page associated with the specific addressee; and

adding the specific addressee to said set of candidates based at least in part on the calculated specific first score associated with the specific addressee.

12. The method of claim 1, further comprising the steps of:

finding at least one additional friend on said first personal page associated with said member;

automatically gleaning semantic information from at least one second personal page in the first social networking site, said at least one second personal page associated with the found at least one additional friend;

calculating at least one second score based at least in part on the semantic information automatically gleaned from the at least one second personal page; and

adding the found at least one additional friend to said set of candidates based at least in part on said calculated at least one second score.

13. The method of claim 1, further comprising the steps of:

finding at least one uniform resource locator on said first personal page, said at least one uniform resource locator identifying at least one second personal page associated with said member in at least one second social networking site;

automatically gleaning semantic information from said identified at least one second personal page;

calculating at least one second score based at least in part on the semantic information automatically gleaned from the identified at least one second personal page; and

adding said member to said set of candidates based at least in part on the calculated at least one second score.

14. An apparatus for generating a set of candidates who may provide at least one useful response to a query submitted by a querier in a first social networking site associated with a first social network, comprising:

means for receiving the query;

means for automatically gleaning semantic information from a first personal page in the first social networking site, said first personal page associated with a member of the first social network;

means for calculating a first score based at least in part on the semantic information automatically gleaned from the first personal page; and

means for adding the member to the set of candidates based at least in part on said calculated first score.

15. The apparatus of claim 14, further comprising:

means for sending the query to at least one candidate in said set of candidates.

16. The apparatus of claim 14, wherein said means for adding the member to the set of candidates based at least in part on said calculated first score comprises:

means for comparing said calculated first score to a threshold score; and

means for adding the member to the set of candidates if said calculated first score is greater than said threshold score.

17. The apparatus of claim 14, further comprising:

means for rank-ordering said set of candidates based on the specific calculated first score associated with each candidate in said set of candidates.

18. The apparatus of claim 14, wherein said member is an addressee in a set of addressees.

19. The apparatus of claim 18, further comprising:

means for automatically gleaning semantic information from the specific first personal page associated with each specific addressee in said set of addressees;

means for calculating the specific first score associated with each specific addressee, said specific first score based at least in part on the semantic information automatically gleaned from the specific first personal page associated with each specific addressee; and

means for adding each specific addressee to said set of candidates based at least in part on the calculated specific first score associated with each specific addressee.

20. The apparatus of claim 14, further comprising:

means for finding at least one additional friend on said first personal page associated with said member;

means for automatically gleaning semantic information from at least one second personal page in the first social networking site, said at least one second personal page associated with the found at least one additional friend;

means for calculating at least one second score based at least in part on the semantic information automatically gleaned from the at least one second personal page; and

means for adding the found at least one additional friend to said set of candidates based at least in part on said calculated at least one second score.

21. The apparatus of claim 14, further comprising:

means for finding at least one uniform resource locator on said first personal page, said at least one uniform resource locator identifying at least one second personal page associated with said member in at least one second social networking site;

means for automatically gleaning semantic information from said identified at least one second personal page;

means for calculating at least one second score based at least in part on the semantic information automatically gleaned from the identified at least one second personal page; and

means for adding said member to said set of candidates based at least in part on the calculated at least one second score.

22. A computer readable medium storing computer program instructions for generating a set of candidates who may provide at least one useful response to a query submitted by a querier in a first social networking site associated with a first social network, said computer program instructions defining the steps of:

receiving the query;

automatically gleaning semantic information from a first personal page in the first social networking site, said first personal page associated with a member of the first social network;

calculating a first score based at least in part on the semantic information automatically gleaned from the first personal page; and

adding the member to the set of candidates based at least in part on said calculated first score.

23. The computer readable medium of claim 22, wherein said computer program instructions for generating a set of candidates who may provide at least one useful response to a query submitted by a querier in a first social networking site associated with a first social network further comprise computer instructions defining the step of:

sending the query to at least one candidate in said set of candidates.

24. The computer readable medium of claim 22, wherein said computer program instructions defining the step of adding the member to the set of candidates based at least in part on said calculated first score comprise computer instructions defining the steps of:

comparing said calculated first score to a threshold score; and

adding the member to the set of candidates if said calculated first score is greater than said threshold score.

25. The computer readable medium of claim 22, wherein said computer program instructions for generating a set of candidates who may provide at least one useful response to a query submitted by a querier in a first social networking site associated with a first social network further comprise computer instructions defining the step of:

rank-ordering said set of candidates based on the specific calculated first score associated with each specific candidate in said set of candidates.

26. The computer readable medium of claim 22, wherein said member is an addressee in a set of addressees.

27. The computer readable medium of claim 26, wherein said computer program instructions for generating a set of candidates who may provide at least one useful response to a query submitted by a querier in a first social networking site associated with a first social network further comprise computer instructions defining the steps of:

for each of the specific addressees in said set of addressees;

automatically gleaning semantic information from the specific first personal page associated with the specific addressee;

calculating the specific first score associated with the specific addressee, said specific first score based at least in part on the semantic information automatically gleaned from the specific first personal page associated with the specific addressee; and

adding the specific addressee to said set of candidates based at least in part on the calculated specific first score associated with the specific addressee.

28. The computer readable medium of claim 26, wherein said computer program instructions for generating a set of candidates who may provide at least one useful response to a query submitted by a querier in a first social networking site associated with a first social network further comprise computer instructions defining the steps of:

finding at least one additional friend on said first personal page associated with said member;

automatically gleaning semantic information from at least one second personal page on the first social networking site, said at least one second personal page associated with the found at least one additional friend;

calculating at least one second score based at least in part on the semantic information automatically gleaned from the at least one second personal page; and

adding the found at least one additional friend to said set of candidates based at least in part on the calculated at least one second score.

29. The computer readable medium of claim 26, wherein said computer program instructions for generating a set of candidates who may provide at least one useful response to a query submitted by a querier in a first social networking site associated with a first social network further comprise computer instructions defining the steps of:

finding at least one uniform resource locator on said first personal page, said at least one uniform resource locator identifying at least one second personal page associated with said member in at least one second social networking site;

automatically gleaning semantic information from said identified at least one second personal page;

calculating at least one second score based at least in part on the semantic information automatically gleaned from the identified at least one second personal page; and

adding said member to said set of candidates based at least in part on the calculated at least one second score.