SYSTEMS AND METHODS FOR AUTOMATED LABELING OF SOCIAL CONNECTIONS

• US 20130097237A1
• Filed: 10/17/2011
• Published: 04/18/2013
• Est. Priority Date: 10/17/2011
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Kothari, Pankaj, Sahni, Saurabh
• Granted Patent: US 8,959,148 B2
• Time in Patent Office: Days
• US Class Current: 709/204
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

First data relating to a first user and second data relating to a second user are retrieved from a plurality of sources. A social connection is identified, by a computing device, between the first user and the second user using the first data and the second data. A label that describes the social connection is identified, by the computing device, using the first data and the second data. A first profile relating to the first user and a second profile relating to the second user is updated by the computing device to reflect the social connection and the label for the social connection.

Claims

1. A method comprising:

retrieving, over a network, first data relating to a first user and second data relating to a second user from a plurality of sources;

identifying, by the computing device, a label that describes a social connection using the first data and the second data; and

updating, by the computing device, a first profile relating to the first user and a second profile relating to the second user to reflect the social connection and the label.

2. A method comprising:

retrieving, over a network, user data relating to a plurality of users, the user data being retrieved from a plurality of websites, the user data comprising social graph data, profile data, interest data and interaction data relating to each user of the plurality of users;

identifying, by a computing device, a plurality of social connections using the social graph data, each social connection of the plurality of social connections reflecting a connection between a respective first user of the plurality of users and a respective second user of the plurality of users; and

labeling, by the computing device, each social connection of the plurality of social connections with a respective first set of labels, each respective label of the respective first set of labels being based on respective profile data and respective interest data for the respective first user of the plurality of users and the respective second user of the plurality of users associated with the respective social connection, such that the respective label represents respective interest data or profile data for the respective first user that matches respective interest or profile data for the respective second user.

3. The method of claim 2 additionally comprising:

clustering, by the computing device, the plurality of social connections into a plurality of clusters of social connections, where each cluster of social connections comprises a respective subset of the plurality of social connections having mutual connections; and

labeling, by the computing device, each social connection of the plurality of social connections with a respective second set of labels, each respective label of the respective second set of labels being based on a respective cluster of social connections of the plurality of clusters of social connections that the respective social connection is associated with.

4. The method of claim 3 additionally comprising:

labeling, by the computing device, each social connection of the plurality of social connections with a respective third set of labels, each respective label of the respective third set of labels being based on respective interaction data reflecting communications between the respective first user of the plurality of users and the respective second user of the plurality of users associated with the respective social connection.

5. The method of claim 4 additionally comprising:

analyzing, by the computing device, each social connection of the plurality of social connections to determine a respective strength of the respective social connection, where the respective strength of the connection is based on respective profile data, respective interest data, respective interaction data and mutual connections for the respective first user of the plurality of users and the respective second user of the plurality of users associated with the respective social connection.

6. The method of claim 3 wherein the plurality of social connections are clustered using k-means clustering.

7. The method of claim 3 wherein each respective second set of labels are based on collaborative filtering of the respective cluster of social connections of the plurality of clusters with which the respective second set of labels is associated.

8. The method of claim 4 wherein the respective strength of the respective social connection is based on temporal aspects of the respective profile data, the respective interest data, the respective interaction data and the mutual connections for the respective first user of the plurality of users and the respective second user of the plurality of users associated with the respective social connection.

9. The method of claim 4 wherein at least some of the labels on the plurality of social connections are transient.

10. The method of claim 4 wherein the at least some of the labels on the plurality of social connections expire after a predetermined period.

11. The method of claim 5 wherein a respective label on a respective social connection of the plurality of social connections expires when the respective strength of the respective social connection falls below a threshold.

12. The method of claim 5 wherein a respective social connection of the plurality of social connections expires when the respective strength of the respective social connection falls below a threshold.

13. The method of claim 2 wherein the social graph data comprises explicit connections between at least some users of the plurality of users.

14. The method of claim 2 wherein the social graph data comprises mutual connections between at least some users of the plurality of users.

15. The method of claim 2 wherein the interaction data comprises messages between at least some users of the plurality of users.

16. The method of claim 2 wherein the interest data comprises behavior, activities, interests and real-time location data for at least some users of the plurality of users.

17. The method of claim 2 wherein the profile data comprises demographics, work address, home address, employer data for at least some users of the plurality of users.

18. The method of claim 2 wherein at least some of the plurality of social connections reflect direct connections between at least some of the plurality of users and wherein at least some of the plurality of social connections reflect indirect connections between at least some of the plurality of users.

19. A computing device comprising:

a processor;

a storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising;

logic executed by the processor for retrieving, over a network, user data relating to a plurality of users, the user data being retrieved from a plurality of websites, the user data comprising social graph data, profile data, interest data and interaction data relating to each user of the plurality of users;

logic executed by the processor for identifying a plurality of social connections using the social graph data, each social connection of the plurality of social connections reflecting a connection between a respective first user of the plurality of users and a respective second user of the plurality of users;

logic executed by the processor for labeling each social connection of the plurality of social connections with a respective first set of labels, each respective label of the respective first set of labels being based on respective profile data and respective interest data for the respective first user of the plurality of users and the respective second user of the plurality of users associated with the respective social connection, such that the respective label represents respective interest data or profile data for the respective first user that matches respective interest or profile data for the respective second user;

logic executed by the processor for clustering the plurality of social connections into a plurality of clusters of social connections, where each cluster of social connections comprises a respective subset of the plurality of social connections having mutual connections;

logic executed by the processor for labeling each social connection of the plurality of social connections with a respective second set of labels, each respective label of the respective second set of labels being based on a respective cluster of social connections of the plurality of clusters of social connections that the respective social connection is associated with;

logic executed by the processor for labeling each social connection of the plurality of social connections with a respective third set of labels, each respective label of the respective third set of labels being based on respective interaction data reflecting communications between the respective first user of the plurality of users and the respective second user of the plurality of users associated with the respective social connection; and

logic executed by the processor for analyzing each social connection of the plurality of social connections to determine a respective strength of the respective social connection, where the respective strength of the connection is based on respective profile data, respective interest data, respective interaction data and mutual connections for the respective first user of the plurality of users and the respective second user of the plurality of users associated with the respective social connection.

20. Computer-readable storage media for tangibly storing thereon computer-readable instructions for a method comprising:

retrieving, over a network, user data relating to a plurality of users, the user data being retrieved from a plurality of websites, the user data comprising social graph data, profile data, interest data and interaction data relating to each user of the plurality of users;

identifying a plurality of social connections using the social graph data, each social connection of the plurality of social connections reflecting a connection between a respective first user of the plurality of users and a respective second user of the plurality of users;

labeling each social connection of the plurality of social connections with a respective first set of labels, each respective label of the respective first set of labels being based on respective profile data and respective interest data for the respective first user of the plurality of users and the respective second user of the plurality of users associated with the respective social connection, such that the respective label represents respective interest data or profile data for the respective first user that matches respective interest or profile data for the respective second user;

clustering the plurality of social connections into a plurality of clusters of social connections, where each cluster of social connections comprises a respective subset of the plurality of social connections having mutual connections;

labeling each social connection of the plurality of social connections with a respective second set of labels, each respective label of the respective second set of labels being based on a respective cluster of social connections of the plurality of clusters of social connections that the respective social connection is associated with;

labeling each social connection of the plurality of social connections with a respective third set of labels, each respective label of the respective third set of labels being based on respective interaction data reflecting communications between the respective first user of the plurality of users and the respective second user of the plurality of users associated with the respective social connection; and

analyzing each social connection of the plurality of social connections to determine a respective strength of the respective social connection, where the respective strength of the connection is based on respective profile data, respective interest data, respective interaction data and mutual connections for the respective first user of the plurality of users and the respective second user of the plurality of users associated with the respective social connection.