Apparatus and method for determining user attention using a deep-content-classification (DCC) system

• US 10,210,257 B2
• Filed: 05/23/2016
• Issued: 02/19/2019
• Est. Priority Date: 10/26/2005
• Status: Expired due to Fees

• Current Assignee: Cortica Ltd.
• Original Assignee: Cortica Ltd.
• Inventors: Raichelgauz, Igal, Odinaev, Karina, Zeevi, Yehoshua Y
• Primary Examiner(s): Le, Uyen T
• Application Number:
  US15/162,042
• Publication Number:
  US 20160267186A1
• Time in Patent Office: 1,002 Days
• Field of Search: None
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/41 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 30/0241 Advertisements
• CPC Class Codes: G06Q 30/0251 Targeted advertisements
• CPC Class Codes: H04L 61/5007 Internet protocol [IP] addresses
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]

Abstract

A method and system for determining a user attention to a multimedia data element (MMDE) displayed in a web-page over a user computing device. The method includes generating, based on at least one sensory signal captured by at least one sensor communicatively connected to the computing device, at least one signature; querying, using the generated at least one signature, a deep-content-classification (DCC) system for at least one concept structure matching the received at least one sensory signal, wherein each of the at least one concept structure includes metadata associated with a plurality of signature reduced clusters representing MMDEs; identifying the metadata of the matching at least one concept structure; and analyzing the identified metadata to determine an attention of a user to the MMDE.

Claims

1. A method for determining a user attention to a multimedia data element (MMDE) displayed in a web-page over a computing device, comprising:

generating, based on at least one sensory signal captured by at least one sensor communicatively connected to the computing device, at least one signature;

querying, using the generated at least one signature, a deep-content-classification (DCC) system for at least one concept structure matching the received at least one sensory signal, wherein each of the at least one concept structure includes metadata associated with a plurality of signature reduced clusters representing MMDEs;

identifying the metadata of the matching at least one concept structure; and

analyzing the identified metadata to determine an attention of a user to the MMDE.

2. The method of claim 1, further comprising:

querying the DCC system to find a match between at least one other concept structure and the MMDE;

identifying metadata of the at least one other concept structure; and

correlating the metadata of the at least one other concept structure with the determined user attention.

3. The method of claim 2, further comprising:

generating at least one signature to the MMDE, wherein the match between the at least one other concept structure and the MMDE is found based on the at least one signature generated to the MMDE.

4. The method of claim 1, wherein the at least one sensory signal is at least one of:

an audio signal, a video signal, coordinates, and a sonography signal.

5. The method of claim 1, wherein the MMDE is at least one of:

an image, graphics, a video stream, a video clip, an audio stream, an audio clip, a video frame, a photograph, images of signals, medical signals, geophysical signals, subsonic signals, supersonic signals, electromagnetic signals, and infrared signals.

6. The method of claim 1, further comprising:

associating the determined user attention with supplemental information, wherein the supplemental information of the computing device, wherein the supplemental information includes at least one of;

an IP address of the computing device, a time, a date, and a browser type of the IP address of the computing device.

7. The method of claim 1, wherein the DCC system includes:

an attention processor for generating a plurality of items from the received at least one sensory signal and determining at least one item of interest for signature generation;

a signature generator for generating at least one signature to the at least one item of interest determined by the sensory signal; and

a concept generator for matching between the at least one signature to the at least one item of interest and a plurality of signature reduced clusters associated with a plurality of cluster structures to identify at least the first set of metadata.

8. The method of claim 7, wherein the signature generator system includes a plurality of computational cores configured to receive a plurality of unstructured data elements, each computational core of the plurality of computational cores having properties that are at least partly statistically independent of other of the computational cores, the properties are set independently of each other core.

9. The method of claim 1, wherein the at least one sensory signal is captured when the web-page is uploaded on a browser of the computing device.

10. A non-transitory computer readable medium having stored thereon instructions for causing one or more processing units to execute the method according to claim 1.

11. A system for determining a user attention to a multimedia data element (MMDE) displayed in a web-page over a user computing device, comprising:

a signature generator system;

a processing system; and

a memory connected to the processing system, the memory contains instructions that, when executed by the processing system, configured the system to;

generate, based on at least one sensory signal captured by a sensor of the computing device, at least one signature via the signature generator system;

query, using the generated at least one signature, a deep-content-classification (DCC) system for at least one concept structure matching the received at least one sensory signal, wherein each of the at least one concept structure includes metadata associated with a plurality of signature reduced clusters representing MMDEs;

identify the metadata of the matching at least one concept structure; and

analyze the identified metadata to determine an attention of a user to the MMDE.

12. The system of claim 11, wherein the system is further configured to:

query the DCC system to find a match between at least one other concept structure and the MMDE;

identify metadata of the at least one other concept structure; and

correlate the metadata of the at least one other concept structure with the determined user attention.

13. The system of claim 12, wherein the system is further configured to:

generate at least one signature to the MMDE, wherein the match between the at least one other concept structure and the MMDE is found based on the at least one signature generated to the MMDE.

14. The system of claim 11, wherein the at least one sensory signal is at least one of:

an audio signal, a video signal, coordinates, and a sonography signal.

15. The system of claim 11, wherein the MMDE is at least one of:

an image, graphics, a video stream, a video clip, an audio stream, an audio clip, a video frame, a photograph, images of signals, medical signals, geophysical signals, subsonic signals, supersonic signals, electromagnetic signals, and infrared signals.

16. The system of claim 11, wherein the system is further configured to:

associate the determined user attention with supplemental information, wherein the supplemental information of the computing device, wherein the supplemental information includes at least one of;

an IP address of the computing device, a time, a date, and a browser type of the IP address of the computing device.

17. The system of claim 11, wherein the DCC system includes:

an attention processor for generating a plurality of items from the received at least one sensory signal and determining at least one item of interest for signature generation;

a signature generator for generating at least one signature to the at least one item of interest determined by the sensory signal; and

a concept generator for matching between the at least one signature to the at least one item of interest and a plurality of signature reduced clusters associated with a plurality of cluster structures to identify at least the first set of metadata.

18. The system of claim 17, wherein the signature generator of the DCC system includes a plurality of computational cores configured to receive a plurality of unstructured data elements, each computational core of the plurality of computational cores having properties that are at least partly statistically independent of other of the computational cores, the properties are set independently of each other core.

19. The system of claim 11, wherein the signature generator system includes a plurality of computational cores configured to receive a plurality of unstructured data elements, each computational core of the plurality of computational cores having properties that are at least partly statistically independent of other of the computational cores, the properties are set independently of each other core.

20. The system of claim 11, wherein the at least one sensory signal is captured when the web-page is uploaded on a browser of the computing device.