Granted Patent B2

US 9,953,032 · App. 14/302,487 · Granted Apr 24, 2018

Inventors: Igal Raichelgauz (New-York, NY); Karina Odinaev (New-York, NY); Yehoshua Y. Zeevi (Haifa, IL)

Assignee: Cortica, Ltd.

G06F17/3002

Abstract

Claims (39)

1. A system for characterization of multimedia content inputs using a plurality of computational cores of a natural liquid architecture, comprising:

a processing element, wherein the processing element further comprises an ensemble of randomly and independently generated heterogeneous computational cores;

a signature data base (SDB) for storing at least one signature for a multimedia content input and a concept database (CDB) for storing at least one concept, wherein the concept includes a collection of signatures, each signature representing a multimedia content input, and metadata describing the concept;

an interface coupled to the processing element, wherein the interface is configured to receive at least one multimedia content input; and

a memory communicatively connected to the processing element, wherein the memory contains instructions that, when executed by the processing element, configure the system to:

receive a multimedia content input;

generate a signature respective of the multimedia content input;

match the signature to at least one signature from the SDB;

identify a cluster respective of the generated signatures;

identify at least one concept respective of the cluster in the CDB; and

characterize the multimedia content input based in part on metadata describing the at least one identified concept.

2. The system of claim 1 , wherein the at least one multimedia content input is at least one of: a digital representation of an audio signal, and a direct feed from at least one microphone device.

3. The system of claim 2 , wherein a plurality of audio signals is received respective of a single source.

4. The system of claim 2 , wherein the signature is generated respective of the entire audio signal, a part of the audio signal, or a combination of entire or partial audio signals.

5. The system of claim 1 , wherein the at least one multimedia content input is at least one of: a digital representation of a video signal, and a direct feed from at least one camera device.

6. The system of claim 5 , wherein a plurality of video signals is received respective of a single source.

7. The system of claim 5 , wherein the signature is generated respective of the entire video signal, a part of the video signal, or a combination of entire or partial video signal.

8. The system of claim 1 , wherein the signature is either partially matched or fully matched to at least one signature from the SDB.

9. A method for characterization of multimedia content inputs using cores of a natural liquid architecture, comprising:

receiving at least one multimedia content input;

generating at least a signature respective of the multimedia content input, wherein the at least a signature is generated by an ensemble of randomly and independently generated heterogeneous computational cores;

matching the generated at least a signature respective of the multimedia content input to at least a signature from a Signature Database;

identifying a cluster respective of the generated at least a signature; and

identifying in a Concept Database (CDB) a concept respective of the cluster, wherein the concept includes a collection of signatures, each signature representing an a multimedia content input, and metadata describing the concept; and

characterizing the multimedia content input based in part on metadata describing the at least one identified concept.

10. The method of claim 9 , wherein the at least one multimedia content input is at least one of: a digital representation of an audio signal, and a direct feed from at least one microphone device.

11. The method of claim 10 , wherein a plurality of audio signals is received respective of a single source.

12. The method of claim 10 , wherein the signature is generated respective of the entire audio signal, a part of the audio signal, or a combination of entire or partial audio signal.

13. The method of claim 9 , wherein the at least one multimedia content input is at least one of: a digital representation of a video signal, and a direct feed from at least one camera device.

14. The method of claim 13 , wherein a plurality of video signals is received respective of a single source.

15. The method of claim 13 , wherein the signature is generated respective of the entire video signal, a part of the video signal, or a combination of entire or partial video signal.

16. The method of claim 9 , wherein the signature is either partially matched or fully matched to at least one signature from the SDB.

17. A non-transitory computer readable medium having stored thereon instructions for causing a processing circuitry to execute a process, the process comprises:

receiving at least one multimedia content input;

generating at least a signature respective of the multimedia content input, wherein the at least a signature is generated by an ensemble of randomly and independently generated heterogeneous computational cores;

matching the generated at least a signature respective of the multimedia content input to at least a signature from a Signature Database;

identifying a cluster respective of the generated at least a signature; and

identifying in a Concept Database (CDB) a concept respective of the cluster, wherein the concept includes a collection of signatures, each signature representing a multimedia content input, and metadata describing the concept; and

characterizing the multimedia content input based in part on metadata describing the at least one identified concept.

Assignments (4)

Priority Claims (3)

Continuity (15)