IP Library Granted Patent US 10,691,642
Granted Patent B2
US 10,691,642 · App. 15/698,317 · Granted Jun 23, 2020

System and method for enriching a concept database with homogenous concepts

Inventors: Adam Harel (Tel Aviv, IL); Igal Raichelgauz (Tel Aviv, IL); Karina Odinaev (Tel Aviv, IL); Yehoshua Y Zeevi (Haifa, IL)
Assignee: CORTICA LTD
G06F16/1748G06F16/215G06F16/2228G06F16/285G06F16/41G06F16/43G06F16/48Y10S707/99943Y10S707/99948
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,691,642
App. No.
15/698,317
Granted
Jun 23, 2020
Kind
B2
Abstract

A system and method for enriching a concept database with homogenous concepts. The method includes determining, based on signatures of a first multimedia content element (MMCE) and signatures of a plurality of existing concepts in the concept database, at least one first concept; generating a reduced representation of the first MMCE, wherein the reduced representation excludes the signatures of the first MMCE that match the at least one first concept; comparing the reduced representation to signatures representing a plurality of second MMCEs to select a first plurality of top matching second MMCEs; generating, based on the reduced representation and the first plurality of top matching second MMCEs, at least one second concept; determining, for each second concept, whether the second concept is a homogenous concept, wherein each homogenous concept uniquely represents the same content; and adding each homogenous concept to the concept database.

Claims (47)

1. A method for enriching a concept database, comprising:

determining, based on signatures of a first multimedia content element (MMCE) and signatures of a plurality of existing concepts in the concept database, at least one first concept, wherein each first concept matches at least a portion of the signatures of the first MMCE;

generating a reduced representation of the first MMCE, wherein the reduced representation excludes the signatures of the first MMCE that match the at least one first concept;

comparing the reduced representation to signatures representing a plurality of second MMCEs to select a first plurality of top matching second MMCEs;

generating, based on the reduced representation and the first plurality of top matching second MMCEs, at least one second concept;

determining, for each second concept, whether the second concept is a homogenous concept, wherein each homogenous concept uniquely represents the same content; and

adding each homogenous concept to the concept database; and

wherein each MMCE is at least one of: an image, a graphic, a video stream, a video clip, a video frame, a photograph, and an image of signals; wherein the image of signals is an image of any of medical signals, geophysical signals, subsonic signals, supersonic signals, electromagnetic signals, and infrared signals.

2. The method of claim 1 , wherein each second concept includes a plurality of signatures, wherein determining whether each second concept is a homogenous concept further comprises:

determining, based on the plurality of signatures of the second concept, a homogeneity score for the second concept, wherein the determining includes matching among the plurality of signatures of the second concept, wherein whether the second concept is homogenous is determined based on the homogeneity score for the second concept.

3. The method of claim 2 , wherein determining whether each second concept is a homogenous concept further comprises: determining whether the homogeneity score for the second concept is above a homogeneity threshold.

4. The method of claim 1 , further comprising, for each second concept that is determined as not homogenous:

selecting a second plurality of top matching MMCEs, wherein the second plurality of top matching MMCEs includes fewer MMCEs than the first plurality of top matching MMCEs;

generating a third concept based on the second plurality of top matching MMCEs; and

determining whether the third concept is a homogenous concept.

5. The method of claim 1 , wherein determining the at least one first concept further comprises: performing a cleaning process, wherein the cleaning process includes removing at least one signature of the first MMCE, wherein each removed signature matches signatures of one of the at least one first concept above a predetermined threshold.

6. The method of claim 3 comprising determining the homogeneity threshold based on a portion of the plurality of second MMCEs .

7. The method of claim 6 , wherein the portion of the plurality of second MMCEs comprises second MMCEs that follow the first plurality of top matching second MMCEs.

8. The method of claim 1 , wherein each concept is a collection of signatures and metadata representing the concept.

9. The method of claim 1 , wherein each signature is generated by a signature generator system, wherein the signature generator system includes a plurality of at least statistically independent computational cores, wherein the properties of each core are set independently of the properties of each other core.

10. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to execute a process for enriching a concept database, the process comprising:

determining, based on signatures of a first multimedia content element (MMCE) and signatures of a plurality of existing concepts in the concept database, at least one first concept, wherein each first concept matches at least a portion of the signatures of the first MMCE;

generating a reduced representation of the first MMCE, wherein the reduced representation excludes the signatures of the first MMCE that match the at least one first concept;

comparing the reduced representation to signatures representing a plurality of second MMCEs to select a first plurality of top matching second MMCEs;

generating, based on the reduced representation and the first plurality of top matching second MMCEs, at least one second concept;

determining, for each second concept, whether the second concept is a homogenous concept, wherein each homogenous concept uniquely represents the same content; and

adding each homogenous concept to the concept database; and

wherein each MMCE is at least one of: an image, a graphic, a video stream, a video clip, a video frame, a photograph, and an image of signals; wherein the image of signals is an image of any of medical signals, geophysical signals, subsonic signals, supersonic signals, electromagnetic signals, and infrared signals.

11. A system for enriching a concept database, comprising:

a processing circuitry; and

a memory connected to the processing circuitry, the memory containing instructions that, when executed by the processing circuitry, configure the system to:

determine, based on signatures of a first multimedia content element (MMCE) and signatures of a plurality of existing concepts in the concept database, at least one first concept, wherein each first concept matches at least a portion of the signatures of the first MMCE;

generate a reduced representation of the first MMCE, wherein the reduced representation excludes the signatures of the first MMCE that match the at least one first concept;

compare the reduced representation to signatures representing a plurality of second MMCEs to select a first plurality of top matching second MMCEs;

generate, based on the reduced representation and the first plurality of top matching second MMCEs, at least one second concept;

determine, for each second concept, whether the second concept is a homogenous concept, wherein each homogenous concept uniquely represents the same content; and

add each homogenous concept to the concept database; and

wherein each MMCE is at least one of: an image, a graphic, a video stream, a video clip, a video frame, a photograph, and an image of signals; wherein the image of signals is an image of any of medical signals, geophysical signals, subsonic signals, supersonic signals, electromagnetic signals, and infrared signals.

12. The system of claim 11 , wherein each second concept includes a plurality of signatures, wherein the system is further configured to: determine, based on the plurality of signatures of the second concept, a homogeneity score for the second concept, wherein the determining includes matching among the plurality of signatures of the second concept, wherein whether the second concept is homogenous is determined based on the homogeneity score for the second concept.

13. The system of claim 12 , wherein the system is further configured to: determine whether the homogeneity score for the second concept is above a homogeneity threshold.

14. The system of claim 11 , wherein the system is further configured to, for each second concept that is determined as not homogenous:

select a second plurality of top matching MMCEs, wherein the second plurality of top matching MMCEs includes fewer MMCEs than the first plurality of top matching MMCEs;

generate a third concept based on the second plurality of top matching MMCEs; and determine whether the third concept is a homogenous concept.

15. The system of claim 11 , wherein the system is further configured to: perform a cleaning process, wherein the cleaning process includes removing at least one signature of the first MMCE, wherein each removed signature matches signatures of one of the at least one first concept above a predetermined threshold.

16. The system of claim 11 , wherein each concept is a collection of signatures and metadata representing the concept.

17. The system of claim 11 , wherein each signature is generated by a signature generator system, wherein the signature generator system includes a plurality of at least statistically independent computational cores, wherein the properties of each core are set independently of the properties of each other core.

18. The system of claim 11 , wherein the system further comprises the concept database.

Assignments (3)
LICENSE Recorded Jan 31, 2022
From: CORTICA LTD.
To: CORTICA AUTOMOTIVE
Reel/Frame 058917/0479 →
AMENDMENT TO LICENSE Recorded Jan 31, 2022
From: CORTICA LTD.
To: CARTICA AI LTD.
Reel/Frame 058917/0495 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 12, 2019
From: RAICHELGAUZ, IGAL; ODINAEV, KARINA; ZEEVI, YEHOSHUA Y
To: CORTICA LTD
Reel/Frame 047978/0792 →
Priority Claims (3)
IL 171577 · Oct 26, 2005 · national
IL 173409 · Jan 29, 2006 · national
IL 185414 · Aug 21, 2007 · national
Continuity (18)
Continuation In Part 15296551 · Oct 18, 2016
Continuation In Part 14643694 · Mar 10, 2015
Continuation 13766463 · Feb 13, 2013
Continuation In Part 13602858 · Sep 4, 2012
Continuation 12603123 · Oct 21, 2009
Continuation In Part 12084150
Continuation In Part 12195863 · Aug 21, 2008
Continuation In Part 12084150 · Apr 7, 2009
Continuation In Part 12348888 · Jan 5, 2009
Continuation In Part 12084150 · Apr 7, 2009
Continuation In Part 12195863 · Aug 21, 2008
Continuation In Part 12538495 · Aug 10, 2009
Continuation In Part 12084150 · Apr 7, 2009
Continuation In Part 12195863 · Aug 21, 2008
Continuation In Part 12348888 · Jan 5, 2009
Provisional Application 62384207 · Sep 7, 2016
Provisional Application 62310742 · Mar 20, 2016
Related Publication 20170371893A1 · Dec 28, 2017