System and method for identifying social trends

Patent metadata

Field	Value
Publication number	US-11657079-B2
Application number	US-201916699037-A
Country	US
Kind code	B2
Filing date	Nov 28, 2019
Priority date	Oct 26, 2005
Publication date	May 23, 2023
Grant date	May 23, 2023

Abstract

A method and system for identifying social trends are provided. The method includes collecting multimedia content from a plurality of data sources; gathering environmental variables related to the collected multimedia content; extracting visual elements from the collected multimedia content; generating at least one signature for each extracted visual element; generating at least one cluster of visual elements by clustering at least similar signatures generated for the extracted visual elements; correlating environmental variables related to visual elements in the at least one cluster; determining at least one social trend by associating the correlated environmental variables with the at least one cluster.

First claim

What is claimed is:

1. A method for identifying social trends, comprising:
collecting multimedia content from a plurality of data sources; wherein the multimedia content comprises multiple images, the multiple images are acquired by multiple cameras;
sensing, by one or more sensors that differ from the multiple cameras, one or more environmental variables related to acquisitions of the multiple images;
extracting, by a server, visual elements from the multiple images;
generating at least one signature for each extracted visual element;
generating at least one cluster of visual elements by clustering at least similar signatures generated for the extracted visual elements;
collecting, by the server, the one or more environmental variables related to the acquisition of the multiple images only when a predetermined threshold of a repetitive signature related to a certain extracted visual element sensed at a certain location is generated;
correlating environmental variables related to visual elements in the at least one cluster; and
determining at least one social trend by associating the correlated environmental variables with the at least one duster.

2. The method of claim 1 , wherein the one or more environmental variables are sensed by a weather information service or geo location system.

3. The method of claim 1 , wherein the one or more environmental variables related to an image of the multiple images comprise a motion variable of a camera that captured the image, the camera belongs to the multiple cameras.

4. The method of claim 1 , wherein the one or more environmental variables is a time of acquisition of an image of the multiple images.

5. The method of claim 1 , wherein correlating the environmental variables further comprises: checking if the correlated environmental variables meet a predefined correlation threshold.

6. The method of claim 1 , wherein the at least one cluster is a concept, wherein the concept is a collection of signatures representing visual elements and metadata describing the concept.

7. The method of claim 1 , further comprising: evaluating the determined social trend over time.

8. The method according to claim 1 wherein the one or more environmental variables comprise locations, sensed by one or more GPS sensors, from which the multiple images were uploaded.

9. The method according to claim 1 wherein the one or more environmental variables are sensed by an accelerator.

10. The method according to claim 1 wherein the generating at least one signature for each extracted visual element is performed by independent computational cores that are implemented in hardware.

11. The method according to claim 1 wherein the generating of the at one cluster of visual elements comprises generating a signature reduced cluster by removing at least one signature from the cluster.

12. The method according to claim 1 wherein the predefined threshold is one hundred.

13. The method according to claim 1 wherein the at least one environmental variables comprises a time in which an image was stored in a data source.

14. The method according to claim 1 wherein the at least one environmental variables comprises a location from where an image of the multiple images is shared.

15. A non-transitory computer readable medium having stored thereon instructions for
collecting multimedia content from a plurality of data sources; wherein the multimedia content comprises multiple images, the multiple images are acquired by multiple cameras;
sensing, by one or more sensors that differ from the multiple cameras, one or more environmental variables related to acquisitions of the multiple images;
extracting, by a server, visual elements from the multiple images;
generating at least one signature for each extracted visual element
generating at least one cluster of visual elements by clustering at least similar signatures generated for the extracted visual elements;
collecting, by the server, the one or more environmental variables related to the acquisition of the multiple images only when a predetermined threshold of a repetitive signature related to a certain extracted visual element sensed at a certain location is generated;
correlating environmental variables related to visual elements in the at least one cluster; and
determining at least one social trend by associating the correlated environmental variables with the at least one cluster.

16. The non-transitory computer readable medium according to claim 15 wherein the one or more environmental variables are sensed by a weather information service or geo location system.

17. The non-transitory computer readable medium according to claim 15 , wherein the one or more environmental variables related to an image of the multiple images comprise a motion variable of a camera that captured the image, the camera belongs to the multiple cameras.

18. The non-transitory computer readable medium according to claim 15 , wherein the one or more environmental variables comprise locations, sensed by one or more GPS sensors, from which the multiple images were uploaded.

19. The non-transitory computer readable medium according to claim 15 , wherein the one or more environmental variables are sensed by an accelerator.

20. The non-transitory computer readable medium according to claim 15 , wherein the at least one environmental variables comprises a location from where an image of the multiple images is shared.

Assignees

• Raichelgauz Igal
• Odinaev Karina
• Zeevi Yehoshua Y
• Cortica Ltd

Inventors

• Raichelgauz Igal
• Odinaev Karina
• Zeevi Yehoshua Y

Classifications

• G06F16/45

  Clustering; Classification · CPC title

• G06F16/48

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06F16/43

  Querying · CPC title

• H04H20/93

  which locates resources of other pieces of information, e.g. URL [Uniform Resource Locator] · CPC title

• G06F16/285

  Clustering or classification · CPC title