US2020233891A1PendingUtilityA1

System and method for clustering multimedia content elements

77
Assignee: CORTICA LTDPriority: Oct 26, 2005Filed: Apr 8, 2020Published: Jul 23, 2020
Est. expiryOct 26, 2025(expired)· nominal 20-yr term from priority
G06V 20/48G06V 10/764G06F 16/41G06F 16/284G06N 7/01G06N 3/045G06N 3/048G06F 16/45G06F 16/48G06F 16/43H04L 67/63H04L 65/765H04L 67/535H04L 51/42G06V 2201/10G06V 40/171G06V 20/46G06V 20/40H04L 51/18H04L 67/02G06F 16/9535G06N 3/063G06F 17/16G06F 16/739G06N 20/00H04N 21/23418H04N 21/278H04N 21/26603G06Q 30/0261G06Q 30/0246G06N 3/088H04H 20/93G06F 3/0484H04H 60/58G06F 16/9558G06F 40/134H04H 60/33H04H 60/59H04H 20/103G06F 3/0488H04H 60/66G06F 16/783H04H 2201/90H04H 60/71H04H 60/49G09B 19/0092G06Q 30/0201G06N 5/04G06F 16/435H04L 67/306G06F 16/487G06F 16/14G06F 16/172G06F 16/152G06F 16/951G06F 16/2228G06F 16/1748G10L 25/51G06N 5/022Y10S707/99948Y10S707/99943H04N 21/8106H04N 21/466H04N 21/2668H04N 21/25891H04N 7/17318H04H 60/56H04H 60/46H04H 60/37H04H 20/26G06N 5/025G06N 5/02G06F 16/904G06F 16/51G06F 16/4393G06F 16/40G06F 16/35H04L 67/10G06F 16/285G06T 19/006G06F 16/438G06F 3/048G10L 15/32G10L 15/26G06F 16/7847G06F 16/683G06F 16/685G06F 16/433G06F 16/7844G06F 16/7834G06F 16/434G06F 16/483
77
PatentIndex Score
0
Cited by
0
References
0
Claims

Abstract

A system and method for clustering multimedia content. The method includes: detecting at least one clustering trigger event related to at least one multimedia content element to be clustered; generating at least one signature for the at least one multimedia content element, each signature representing at least a portion of the at least one multimedia content element; determining, based on the generated at least one signature, at least one multimedia content element cluster, wherein each multimedia content element cluster includes a plurality of clustered multimedia content elements sharing at least one common concept with the at least one multimedia content element; and adding, to each determined cluster, the at least one multimedia content element.

Claims

exact text as granted — not AI-modified
We claim: 
     
         1 . A method for clustering multimedia content, comprising:
 detecting at least one clustering trigger event related to at least one multimedia content element to be clustered;   generating at least one signature for the at least one multimedia content element, each signature representing at least a portion of the at least one multimedia content element;   following the generating of the at least one signature, generating, based on the generated at least one signature, at least one tag for the at least one multimedia content element;   determining, based on the generated at least one signature, at least one multimedia content element cluster, wherein each multimedia content element cluster includes a plurality of clustered multimedia content elements sharing at least one common concept with the at least one multimedia content element; and   adding, to each determined cluster, the at least one multimedia content element.   
     
     
         2 . The method of  claim 1 , wherein the at least one multimedia content element cluster is determined based further on the generated at least one tag. 
     
     
         3 . The method of  claim 2 , wherein each multimedia content element cluster includes a plurality of multimedia content elements associated with the generated at least one tag. 
     
     
         4 . The method of  claim 1 , further comprising:
 querying, with respect to the generated at least one signature, a deep content classification system to obtain at least one concept structure matching the at least one multimedia content element, each concept structure including a signature reduced cluster and metadata, and generating the at least one tag for the at least one multimedia content element based on the metadata of the at least one concept structure.   
     
     
         5 . The method of  claim 1 , wherein each multimedia content element cluster is associated with at least one portion of a signature that is common to the plurality of clustered multimedia content elements of the multimedia content element cluster and to the at least one multimedia content element. 
     
     
         6 . The method of  claim 1 , further comprising:
 determining, based on the generated at least one signature, whether an existing multimedia content element cluster sharing a common concept with the multimedia content element can be found; and   generating another multimedia content element cluster, when it is determined that an existing multimedia content element cluster sharing a common concept with the multimedia content element cannot be found.   
     
     
         7 . The method of  claim 1 , wherein the at least one signature is generated via a signature generator system, wherein the signature generator system includes a plurality of at least partially statistically independent computational cores, wherein the properties of each computational core are set independently of properties of each other computational core. 
     
     
         8 . The method of  claim 1 , wherein the detected at least one clustering trigger event includes receiving a request to cluster the at least one multimedia content element, wherein the request includes at least one of: the at least one multimedia content element, at least one identifier of the at least one multimedia content element, and at least one location of the at least one multimedia content element. 
     
     
         9 . The method of  claim 1 , further comprising: storing, in a data storage, the at least one cluster including the added at least one multimedia content element, wherein each cluster is stored in a separate location of the data storage. 
     
     
         10 . The method according to  claim 1  wherein the common concept represents a sub textual information out of (a) activities or actions being performed, and (b) relationships among individuals shown in the at least one multimedia content element. 
     
     
         11 . The method according to  claim 1  wherein the common concept represents a meta aspect indicating information about an acquisition of the at least one multimedia content element. 
     
     
         12 . The method according to  claim 1  wherein the common concept represents a user having a user device that captured the at least one multimedia content element. 
     
     
         13 . The method according to  claim 1  wherein the common concept differs from a textual tag. 
     
     
         14 . The method according to  claim 1  wherein the common concept represents an item captured in the at least one multimedia content element. 
     
     
         16 . A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to execute a process, the process comprising:
 detecting at least one clustering trigger event related to at least one multimedia content element to be clustered;   generating at least one signature for the at least one multimedia content element, each signature representing at least a portion of the at least one multimedia content element;   following the generating of the at least one signature, generating, based on the generated at least one signature, at least one tag for the at least one multimedia content element;   determining, based on the generated at least one signature, at least one multimedia content element cluster, wherein each multimedia content element cluster includes a plurality of clustered multimedia content elements sharing at least one common concept with the at least one multimedia content element; and   
       adding, to each determined cluster, the at least one multimedia content element. 
     
     
         16 . A system for clustering multimedia content, comprising:
 a processing circuitry; and   a memory, the memory containing instructions that, when executed by the processing circuitry, configure the system to:   detect at least one clustering trigger event related to at least one multimedia content element to be clustered;   generate at least one signature for the at least one multimedia content element, each signature representing at least a portion of the at least one multimedia content element;   generate, following a generating of the at least one signature, and based on the generated at least one signature, at least one tag for the at least one multimedia content element;   determine, based on the generated at least one signature, at least one multimedia content element cluster, wherein each multimedia content element cluster includes a plurality of clustered multimedia content elements sharing at least one common concept with the at least one multimedia content element; and   add, to each determined cluster, the at least one multimedia content element.   
     
     
         17 . The system of  claim 16 , wherein the at least one multimedia content element cluster is determined based further on the generated at least one tag. 
     
     
         18 . The system of  claim 17 , wherein each multimedia content element cluster includes a plurality of multimedia content elements associated with the generated at least one tag. 
     
     
         19 . The system of  claim 16 , wherein the system is further configured to: query, with respect to the generated at least one signature, a deep content classification system to obtain at least one concept structure matching the at least one multimedia content element, each concept structure including a signature reduced cluster and metadata, and generate the at least one tag for the at least one multimedia content element based on the metadata of the at least one concept structure. 
     
     
         20 . The system of  claim 16 , wherein each determined cluster is associated with at least one portion of a signature that is common to the clustered multimedia content elements of the cluster and to the at least one multimedia content element.

Cited by (0)

No later patents cite this yet.

References (0)

No backward citations on record.