SYSTEM AND METHOD FOR CONTENT BASED SOCIAL RECOMMENDATIONS AND MONETIZATION THEREOF

• US 20150032535A1
• Filed: 07/25/2013
• Published: 01/29/2015
• Est. Priority Date: 07/25/2013
• Status: Abandoned Application

• Current Assignee: Excalibur IP, LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Li, Jia, Shamma, David
• Application Number:
  US13/951,078
• Publication Number:
  US 20150032535A1
• Time in Patent Office: Days
• US Class Current: 705/14.53
• CPC Class Codes: G06Q 30/0255 based on user history
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Disclosed is a system and method for automatically detecting social relationships from consumer image collections. The disclosed systems and methods provide the ability to infer relationships between people thereby creating dynamic social networks from the occurrences of people appearing in digital images. Occurrences of people in pictures can be detected based on known or to be known facial recognition technology. These inferences enable relationship determinations regarding whether the people are family members, friends, acquaintances or merely strangers who happen to be in the same place at the same time. The disclosed detection of such relationships enables the building of intelligent image management systems. Furthermore, based on the detected social relationships, advertisements can be served not solely to a single person, but to multiple people within the scope of the social relationship

Claims

1. A method comprising:

identifying, via a computing device, an image collection associated with a first user within a photo-sharing network;

parsing, via the computing device, each image in the image collection to identify content of each image;

determining, via the computing device, a first content category based on the content of each image;

grouping, via the computing device, each image associated with the first content category into a first image cluster;

analyzing, via the computing device, each image of the first cluster to determine an occurrence of a digital representation of a second user within the first cluster;

providing, via the computing device, a recommendation to the first user and the second user, said recommendation facilitating a social relationship between the first user and the second user within the photo-sharing network; and

serving, via the computing device, an advertisement to the first user and the second user in accordance with the recommendation and based on the first content category.

2. The method of claim 1, wherein said recommendation is an invitation for the first user to accept the second user as a friend on the photo-sharing network.

3. The method of claim 1, wherein said recommendation is an invitation to the first user and the second user to join a group, said group based on the first content category.

4. The method of claim 1, wherein said determination of said digital representation of the second user is based on profile information of the second user within the photo-sharing network.

5. The method of claim 1, further comprising:

determining a plurality of content categories based on said parsing of each image in the image collection; and

categorizing each image based on each determined content category.

6. The method of claim 5, further comprising:

determining whether each determined content category comprises a number of images equal to or above a threshold; and

creating an image cluster for each determined content category having the number of images equal to or above the threshold.

7. The method of claim 6, wherein said analyzing step is performed for each created image cluster.

8. The method of claim 1, wherein said occurrence of said digital representation of said second user satisfies a threshold by occurring at least a predetermined number of times.

9. The method of claim 1, wherein said social relationship between the first user and the second user is based, in part, on profile information of the first user.

10. The method of claim 1, further comprising:

identifying a connection between the second user and a third user within the photo-sharing network, said connection based upon the first content category; and

providing a second recommendation to the first user and the third user based on the connection between the second user and the third user.

11. The method of claim 1, wherein said analysis comprises applying a facial recognition algorithm to each image of the first image cluster.

12. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions, that when executed by a processor of a computing device, perform a method comprising:

identifying an image collection associated with a first user within a photo-sharing network;

parsing each image in the image collection to identify content of each image;

determining a first content category based on the content of each image;

grouping each image associated with the first content category into a first image cluster;

analyzing each image of the first cluster to determine an occurrence of a digital representation of a second user within the first cluster;

providing a recommendation to the first user and the second user, said recommendation facilitating a social relationship between the first user and the second user within the photo-sharing network; and

serving an advertisement to the first user and the second user in accordance with the recommendation and based on the first content category.

13. The non-transitory computer-readable storage medium of claim 12, wherein said recommendation is an invitation for the first user to accept the second user as a friend on the photo-sharing network.

14. The non-transitory computer-readable storage medium of claim 12, wherein said recommendation is an invitation to the first user and the second user to join a group, said group based on the first content category.

15. The non-transitory computer-readable storage medium of claim 12, wherein said determination of said digital representation of the second user is based on profile information of the second user within the photo-sharing network.

16. The non-transitory computer-readable storage medium of claim 12, further comprising:

determining a plurality of content categories based on said parsing of each image in the image collection;

categorizing each image based on each determined content category;

determining whether each determined content category comprises a number of images equal to or above a threshold; and

creating an image cluster for each determined content category having the number of images equal to or above the threshold, wherein said analyzing step is performed for each created image cluster.

17. The non-transitory computer-readable storage medium of claim 12, wherein said occurrence of said digital representation of said second user satisfies a threshold by occurring at least a predetermined number of times.

18. The non-transitory computer-readable storage medium of claim 12, further comprising:

identifying a connection between the second user and a third user within the photo-sharing network, said connection based upon the first content category; and

providing a second recommendation to the first user and the third user based on the connection between the second user and the third user.

19. A system comprising:

at least one computing device comprising;

memory storing computer-executable instructions; and

one or more processors for executing said computer-executable instructions, comprising;

identifying an image collection associated with a first user within a photo-sharing network;

parsing each image in the image collection to identify content of each image;

determining a first content category based on the content of each image;

grouping each image associated with the first content category into a first image cluster;

analyzing each image of the first cluster to determine an occurrence of a digital representation of a second user within the first cluster;

providing a recommendation to the first user and the second user, said recommendation facilitating a social relationship between the first user and the second user within the photo-sharing network; and

serving an advertisement to the first user and the second user in accordance with the recommendation and based on the first content category.

20. The system of claim 19, further comprising:

determining a plurality of content categories based on said parsing of each image in the image collection;

categorizing each image based on each determined content category;

determining whether each determined content category comprises a number of images equal to or above a threshold; and

creating an image cluster for each determined content category having the number of images equal to or above the threshold, wherein said analyzing step is performed for each created image cluster.