Contextual connection recommendation in a social network

Patent metadata

Field	Value
Publication number	US-9595069-B2
Application number	US-201514985964-A
Country	US
Kind code	B2
Filing date	Dec 31, 2015
Priority date	Jan 30, 2015
Publication date	Mar 14, 2017
Grant date	Mar 14, 2017

Abstract

A system and method for contextual connection recommendation includes obtaining, with a processor from a database, contextual data and social graph data related to a pair of members of a social network who are not currently connected on the social network. A connection base score between the pair of members is generated based on the social graph data. A recommendation modifier is generated based on the contextual data. A connection recommendation modified score is determined by applying the recommendation modifier to the base score. A connection recommendation is provided to at least one of the pair of members based, at least in part, on the connection recommendation modified score.

First claim

What is claimed is:

1. A method, comprising:
obtaining, with a processor from a database, contextual data and social graph data related to a pair of members of a social network who are not currently connected on the social network;
generating, with the processor, a connection base score between the pair of members based on the social graph data;
generating, with the processor, a recommendation modifier based on the contextual data;
determining, with the processor, a plurality of connection recommendation modified scores, individual ones of the plurality of connection recommendation modified scores corresponding to one of a plurality of pairs of members, each of the plurality of pairs of members including the first member, each one of the plurality of connection recommendation modified scores determined based on a connection base score between members of an associated one of the plurality of pairs of members and a recommendation modifier between the members of the associated one of the plurality of pairs of members;
ranking, with the processor, the plurality of connection recommendation modified scores; and
providing, via a network interface, connection recommendations ranked based on the plurality of connection recommendation modified scores;
wherein the contextual data is profile data of each of the pair of members and activity data of each of the pair of members;
wherein the profile data includes individual data points for each of the pair of members; and
wherein generating the recommendation modifier is based, at least in part, on a similarity between pairs of the individual data points.

2. The method of claim 1 , wherein each pair of the individual data points is assigned a score based on the similarity of the data points of the pair; and
wherein generating the recommendation modifier is based, at least in part, on a combination of the score of each pair of the individual data points.

3. The method of claim 1 , wherein the activity data includes activities on the social network by the pair of members; and
wherein generating the recommendation modifier is based, at last in part, on related activities by the pair of members.

4. The method of claim 3 , wherein the related activities are based, at least in part, on an interaction by one of the pair of members with an action by another one of the pair of members.

5. The method of claim 1 , wherein generating the connection base score is based on common connections within the social network between the members of the pair of members and other members of the social network.

6. A non-transitory computer readable medium, comprising instructions which, when implemented by a processor, cause the processor to perform operations comprising:
obtaining, with a processor from a database, contextual data and social graph data related to a pair of members of a social network who are not currently connected on the social network;
generating, with the processor, a connection base score between the pair of members based on the social graph data;
generating, with the processor, a recommendation modifier based on the contextual data;
determining, with the processor, a plurality of connection recommendation modified scores, individual ones of the plurality of connection recommendation modified scores corresponding to one of a plurality of pairs of members, each of the plurality of pairs of members including the first member, each one of the plurality of connection recommendation modified scores determined based on a connection base score between members of an associated one of the plurality of pairs of members and a recommendation modifier between the members of the associated one of the plurality of pairs of members;

ranking, with the processor, the plurality of connection recommendation modified scores; and
providing, via a network interface, connection recommendations ranked based on the plurality of connection recommendation modified scores;
wherein the contextual data is profile data of each of the pair of members and activity data of each of the pair of members;
wherein the profile data includes individual data points for each of the pair of members; and
wherein generating the recommendation modifier is based, at least in part, on a similarity between pairs of the individual data points.

7. The non-transitory computer readable medium of claim 6 , wherein each pair of the individual data points is assigned a score based on the similarity of the data points of the pair; and
wherein generating the recommendation modifier is based, at least in part, on a combination of the score of each pair of the individual data points.

8. The non-transitory computer readable medium of claim 6 , wherein the activity data includes activities on the social network by the pair of members; and
wherein generating the recommendation modifier is based, at last in part, on related activities by the pair of members.

9. The non-transitory computer readable medium of claim 8 , wherein the related activities are based, at least in part, on an interaction by one of the pair of members with an action by another one of the pair of members.

10. The non-transitory computer readable medium of claim 6 , wherein generating the base score is based on common connections within the social network between the members of the pair of members and other members of the social network.

11. A system, comprising:
a computer readable medium, comprising instructions which, when implemented by a processor, cause the processor to perform operations comprising:
obtaining, from a database, contextual data and social graph data related to a pair of members of a social network who are not currently connected on the social network;
generating a connection base score between the pair of members based on the social graph data;
generating a recommendation modifier based on the contextual data;
determining a plurality of connection recommendation modified scores, individual ones of the plurality of connection recommendation modified scores corresponding to one of a plurality of pairs of members, each of the plurality of pairs of members including the first member, each one of the plurality of connection recommendation modified scores determined based on a connection base score between members of an associated one of the plurality of pairs of members and a recommendation modifier between the members of the associated one of the plurality of pairs of members;
ranking the plurality of connection recommendation modified scores; and
providing, via a network interface, connection recommendations ranked based on the plurality of connection recommendation modified scores;

wherein the contextual data is profile data of each of the pair of members and activity data of each of the pair of members;
wherein the profile data includes individual data points for each of the pair of members; and
wherein generating the recommendation modifier is based, at least in part, on a similarity between pairs of the individual data points.

12. The system of claim 11 , wherein each pair of the individual data points is assigned a score based on the similarity of the data points of the pair; and
wherein generating the recommendation modifier is based, at least in part, on a combination of the score of each pair of the individual data points.

13. The system of claim 11 , wherein the activity data includes activities on the social network by the pair of members; and
wherein generating the recommendation modifier is based, at last in part, on related activities by the pair of members.

14. The system of claim 13 , wherein the related activities are ba

Assignees

• Linkedin Corp

Inventors

• Tiwari Mitul
• Wang Curtis
• Jain Aastha

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06F16/24578 Primary

  using ranking · CPC title

• G06Q50/01 Primary

  Physics · mapped topic

• G06F17/30867

  Physics · mapped topic

• G06Q30/02 Primary

  Marketing; Price estimation or determination; Fundraising · CPC title