Generating a Discussion Group in a Social Network Based on Similar Source Materials

• US 20130031100A1
• Filed: 10/13/2011
• Published: 01/31/2013
• 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
• Granted Patent: US 8,892,595 B2
• Time in Patent Office: Days
• US Class Current: 707/739
• 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 method for providing access to a discussion group in a social network based on different electronic images comprising:

receiving a first electronic image from a first user device;

performing a first visual search using the first electronic image to identify a first mixed media reality (MMR) object corresponding to a first source material;

identifying the discussion group associated with a cluster that includes the first MMR object and a second MMR object, the second MMR object corresponding to a second source material; and

providing the first user device with access to the discussion group.

2. The method of claim 1, further comprising:

receiving a second electronic image from a second user device, the second electronic image being different from the first electronic image;

performing a second visual search using the second electronic image to identify the second MMR object; and

providing the second user device with access to the discussion group.

3. The method of claim 1, wherein before the first electronic image is received further comprising:

indexing the first mixed media reality (MMR) object and the second MMR object; and

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

4. The method of claim 3, wherein the cluster is generated by using agglomerative clustering.

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

6. The method of claim 1, further comprising:

receiving a comment from a second user;

comparing the comment to the discussion group; and

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

7. 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.

8. The method of claim 3, wherein the cluster is a plurality of clusters and further comprising:

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

selecting a centroid MMR object from an MMR database for each of the k-clusters;

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

generating the k-clusters of MMR 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:

a mixed media reality (MMR) engine receiving a first electronic image from a first user device and performing a first visual search using the first electronic image to identify a first MMR object corresponding to a first source material; and

a social network application coupled to the MMR engine, the social network application identifying a discussion group associated with a cluster that includes the first MMR object and a second MMR object corresponding to a second source material and providing the first user device with access to the discussion group.

10. The system of claim 9, wherein the MMR engine receives a second electronic image from a second user device, the second electronic image being different from the first electronic image and performs a second visual search using the second electronic image to identify the second MMR object;

and

wherein the social network application provides the second user device with access to the discussion group.

11. The system of claim 9, further comprising:

a mixed media reality (MMR) database indexing the first MMR object and the second MMR object; and

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

12. The system of claim 11, wherein content management engine generates the cluster by using agglomerative clustering.

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

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

15. 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.

16. The system of claim 11, wherein the cluster is a plurality of clusters and wherein the content management engine determines a number of the plurality of clusters to be generated as k-clusters, selects a centroid MMR object from the MMR database for each of the k-cluster, computes a similarity vector between the centroid MMR object'"'"'s metadata and the other MMR objects metadata in the MMR database and generates the k-clusters of MMR objects based on the similarity vector.

17. A computer program product comprising a 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 from a first user device;

perform a first visual search using the first electronic image to identify a first mixed media reality (MMR) object corresponding to a first source material;

identify the discussion group associated with the cluster that includes the first MMR object and a second MMR object, the second MMR object corresponding to a second source material; and

provide the first user device with access to the discussion group.

18. The computer program product of claim 17, further comprising:

receiving a second electronic image from a second user device, the second electronic image being different from the first electronic image;

performing a second visual search using the second electronic image to identify the second MMR object; and

providing the second user device with access to the discussion group.

19. The computer program product of claim 18, wherein before the first electronic image is received further comprising:

indexing the first mixed media reality (MMR) object and the second MMR object, the first MMR object and the second MMR object each corresponding to a source material; and

generate the cluster that includes the first MMR object and the second MMR object based on 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.