Generating a discussion group in a social network based on similar source materials

• US 8,892,595 B2
• Filed: 10/13/2011
• Issued: 11/18/2014
• Est. Priority Date: 07/27/2011
• Status: Active Grant

• Current Assignee: Ricoh Company Limited
• Original Assignee: Ricoh Company Limited
• Inventors: Graham, Jamey, Bailloeul, Timothee, Gupta, Adit
• Primary Examiner(s): Tran, Anh Tai
• Application Number:
  US13/273,186
• Publication Number:
  US 20130031100A1
• Time in Patent Office: 1,132 Days
• US Class Current: 707/769
• CPC Class Codes: G06F 16/438 Presentation of query results
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 51/52 for supporting social networking services

Abstract

The present invention includes a system and method for generating a discussion group based on different electronic images. A mixed media reality database receives MMR objects that correspond to source material and indexes the MMR objects. A content management engine generates a cluster that includes MMR objects based on a similarity of source material. An MMR engine receives an electronic image from a user device, performs a visual search and identifies an MMR object that is associated with the electronic image. A social network application identifies a discussion group associated with the cluster that includes the MMR object and provides the user device with access to the discussion group.

Claims

1. A computer-implemented method for providing access to a discussion group in a social network based on different electronic images comprising:

receiving, with one or more processors, a first electronic image of a first source material from a first user device at a first location;

performing, with the one or more processors, a first visual search using the first electronic image to identify a first object corresponding to the first source material;

receiving, with the one or more processors, a second electronic image of a second source material from a second user device at a second location, the second electronic image being different from the first electronic image;

performing, with the one or more processors, a second visual search using the second electronic image to identify a second object corresponding to the second source material, the second source material being related to the first source material;

determining, with the one or more processors, a location proximity of the first location and the second location;

identifying in the social network, with the one or more processors, the discussion group associated with a cluster that includes the first object and the second object and based on the location proximity of the first location and the second location satisfying a threshold distance, the discussion group including one or more discussion threads associated with each of the first object and the second object, the one or more discussion threads each including comments and replies received based on the comments; and

providing, with the one or more processors, the first user device and the second user device with access to the discussion group in the social network.

2. The method of claim 1, further comprising:

determining statistics associated with the discussion group; and

providing the first and the second user devices with access to the statistics associated with the discussion group.

3. The method of claim 1, wherein the discussion group comprises a plurality of conversations.

4. The method of claim 1, further comprising:

receiving a comment from a third user device;

comparing the comment to the discussion group; and

granting the third user device access to the discussion group based on a relationship between the comment and the discussion group.

5. The method of claim 1, further comprising:

tracking a time of adding content to the discussion group; and

removing a member of the discussion group based on the time that elapsed since the content was added to the discussion group.

6. The method of claim 1, further comprising:

indexing metadata associated with the first object and the second object; and

generating the cluster that includes the first object and the second object based on relatedness of the metadata and a similarity of the first and second source materials.

7. The method of claim 6, wherein the cluster is generated by using agglomerative clustering.

8. The method of claim 6, further comprising:

determining a number of a plurality of clusters to be generated as k-clusters;

selecting a centroid object for each of the k-clusters;

computing a similarity vector between the centroid object'"'"'s metadata and the other objects'"'"' metadata; and

generating the k-clusters of objects based on the similarity vector.

9. A system for providing access to a discussion group in a social network based on different electronic images comprising:

one or more processors;

an engine stored on a memory and executable by the one or more processors, the engine configured to receive a first electronic image of a first source material from a first user device at a first location, to perform a first visual search using the first electronic image to identify a first object corresponding to the first source material, to receive a second electronic image of a second source material from a second user device at a second location, the second electronic image being different from the first electronic image, to perform a second visual search using the second electronic image to identify a second object corresponding to the second source material, the second source material being related to the first source material and to determine a location proximity of the first location and the second location; and

a social network application stored on the memory and executable by the one or more processors, the social network application coupled to the engine and configured to identify in the social network a discussion group associated with a cluster that includes the first object and the second object and based on the location proximity of the first location and the second location satisfying a threshold distance, the discussion group including one or more discussion threads associated with each of the first object and the second object, the one or more discussion threads each including comments and replies received based on the comments and to provide the first user device and the second user device with access to the discussion group in the social network.

10. The system of claim 9, wherein the social network application determines statistics associated with the discussion group and provides the first and the second user devices with access to the statistics associated with the discussion group.

11. The system of claim 9, wherein the discussion group comprises a plurality of conversations.

12. The system of claim 9, wherein the social network application receives a comment from a third user device, compares the comment to the discussion group and grants the third user device access to the discussion group based on a relationship between the comment and the discussion group.

13. The system of claim 9, wherein the social network application tracks a time of adding content to the discussion group and removes a member of the discussion group based on the time that elapsed since the content was added to the discussion group.

14. The system of claim 9, further comprising:

a database indexing metadata associated with the first object and the second object; and

a content management engine coupled to the database, the content management engine generating the cluster that includes the first object and the second object based on relatedness of the metadata and a similarity of the first and second source materials.

15. The system of claim 14, wherein content management engine generates the cluster by using agglomerative clustering.

16. The system of claim 14, wherein the content management engine determines a number of a plurality of clusters to be generated as k-clusters, selects a centroid object for each of the k-clusters, computes a similarity vector between the centroid object'"'"'s metadata and the other objects'"'"' metadata and generates the k-clusters of objects based on the similarity vector.

17. A computer program product comprising a non-transitory computer useable medium including a computer readable program, wherein the computer readable program when executed on a computer causes the computer to:

receive a first electronic image of a first source material from a first user device at a first location;

perform a first visual search using the first electronic image to identify a first object corresponding to the first source material;

receive a second electronic image of a second source material from a second user device at a second location, the second electronic image being different from the first electronic image;

performing a second visual search using the second electronic image to identify a second object corresponding to the second source material, the second source material being related to the first source material;

determining a location proximity of the first location and the second location;

identify in a social network a discussion group associated with a cluster that includes the first object and the second object and based on the location proximity of the first location and the second location satisfying a threshold distance, the discussion group including one or more discussion threads associated with each of the first object and the second object, the one or more discussion threads each including comments and replies received based on the comments; and

provide the first user device and the second user device with access to the discussion group in the social network.

18. The computer program product of claim 17, wherein the computer readable program when executed on the computer further causes the computer to:

determine statistics associated with the discussion group; and

provide the first and the second user devices with access to the statistics associated with the discussion group.

19. The computer program product of claim 18, wherein the computer readable program when executed on the computer further causes the computer to:

index metadata associated with the first object and the second object; and

generate the cluster that includes the first object and the second object based on relatedness of the metadata and a similarity of the first and second source materials.

20. The computer program product of claim 19, wherein the cluster is generated by using agglomerative clustering.