System and method for verification of user identification based on multimedia content elements

• US 9,529,984 B2
• Filed: 10/01/2013
• Issued: 12/27/2016
• Est. Priority Date: 10/26/2005
• Status: Active Grant

• Current Assignee: Cortica Ltd.
• Original Assignee: Cortica Ltd.
• Inventors: Raichelgauz, Igal, Odinaev, Karina, Zeevi, Yehoshua Y.
• Primary Examiner(s): CHANNAVAJJALA, SRIRAMA T
• Application Number:
  US14/043,230
• Publication Number:
  US 20140033300A1
• Time in Patent Office: 1,183 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 16/31 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/316 Indexing structures
• CPC Class Codes: G06F 16/33 Querying
• CPC Class Codes: G06F 16/332 Query formulation
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/40 of multimedia data, e.g. slideshows comprising image and additional audio data retrieval of still image data G06F16/50; retrieval of audio data G06F16/60; retrieval of video data G06F16/70
• CPC Class Codes: G06F 16/41 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/483 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/50 of still image data
• CPC Class Codes: G06F 16/535 Filtering based on additional data, e.g. user or group profiles
• CPC Class Codes: G06F 16/60 of audio data
• CPC Class Codes: G06F 16/65 Clustering; Classification
• CPC Class Codes: G06F 16/70 of video data
• CPC Class Codes: G06F 16/75 Clustering; Classification
• CPC Class Codes: G06F 21/31 User authentication
• CPC Class Codes: H04W 12/06 Authentication

Abstract

A method and system for verifying an identity of a user accessing a user device are provided. The method includes receiving a request to verify the user identity accessing the user device; receiving a plurality of multimedia identification signals from the user device; querying a deep-content-classification (DCC) system to find a match between at least one concept structure associated with the user and the plurality of received multimedia identification signals, wherein the concept structure is created during a sign-in procedure; and sending an authentication notification upon determination of a match between the at least one concept structure and the plurality of received multimedia identification signals.

Claims

1. A method for verifying an identity of a user accessing a user device, comprising:

receiving a request to verify the identity of the user accessing the user device;

receiving a current set of multimedia identification signals from the user device in accordance with the verification request;

querying a deep-content-classification (DCC) system to find a match between at least one pre-stored concept structure associated with the user to be verified and the current set of received multimedia identification signals, wherein the at least one concept structure is created during a sign-in procedure and is based on a grouping of associated clusters, wherein each cluster includes a compressed set of similar signatures generated from an initial set of previously received multimedia identification signals received during the sign-in procedure; and

sending an authentication notification to the user upon finding a match between the at least one concept structure and the current set of received multimedia identification signals.

2. The method of claim 1, further comprising:

generating at least one signature to each of the initial set of multimedia identification signals prior to querying the DCC system.

3. The method of claim 1, wherein each of the initial set of multimedia identification signals is at least one of:

an image, a graphic, a video stream, a video clip, an audio stream, an audio clip, a video frame, a photograph, and images of signals.

4. The method of claim 3, wherein the images of signals are at least one of:

medical signals, geophysical signals, subsonic signals, supersonic signals, electromagnetic signals, infrared signals, an audio signal, a video signal, coordinates, and a sonography signal.

5. The method of claim 1, wherein each of the current set of multimedia identification signals received from the user device is at least one of:

captured by the user device, and stored in the user device.

6. The method of claim 1, wherein the request to verify the user identity accessing the user device further includes supplemental information, wherein the supplemental information comprises at least one of an Internet Protocol (IP) address of the user computing device, a time, a date, and a browser type of the user computing device.

7. The method of claim 6, wherein the supplemental information is used to create metadata from the at least one concept structure.

8. The method of claim 7, wherein the sign-in procedure further comprises:

receiving the initial set of multimedia identification signals from the user device;

generating at least one signature for each multimedia identification signal in the initial set of multimedia identification signals received from the user device;

creating the at least one concept structure associated with the user using the at least one generated signature;

associating the metadata with the created at least one concept structure; and

saving the created at least one concept structure in a database.

9. The method of claim 7, wherein the current set of received multimedia identification signals corresponds to the initial set of multimedia identification signals.

10. The method of claim 8, wherein the matching between the at least one concept structure and the current set of received multimedia identification signals further includes:

matching signatures in the at least one concept structure to signatures of the initial set of received multimedia identification signals.

11. The method of claim 8, wherein the at least one concept structure is created using the DCC system, wherein the DCC system includes:

an attention processor configured to generate a plurality of items from a multimedia identification signal and to determine which of the generated items are of interest for signature generation;

a signature generator configured to generate at least one signature responsive to at least one item of interest; and

a concept generator configured to match between the at least one signature generated responsive to at least one of the items of interest and a set of signature reduced clusters associated with a plurality of cluster structures.

12. 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.

13. The method of claim 1, wherein each signature is generated by a signature generator system, 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.

14. A server for verifying an identity of a user accessing a user device, comprising:

an interface to a network for receiving a request to verify the identity of the user accessing the user device and for receiving a current set of multimedia identification signals from the user device;

a processor; and

a memory connected to the processor, the memory contains instructions that, when executed by the processor, configure the server to;

query a deep-content-classification (DCC) system to find a match between at least one concept structure associated with the user and a current set of multimedia identification signals, wherein the concept structure is created during a sign-in procedure and is based on a grouping of associated clusters, where each cluster includes a compressed set of similar signatures generated from an initial set of multimedia identification signals received during the sign-in procedure; and

send an authentication notification upon finding a match between the at least one concept structure and the current set of received multimedia identification signals.

15. The server of claim 14, wherein the server is further configured to:

generate at least one signature to each of the initial set of multimedia identification signals prior to querying of the DCC system.

16. The server of claim 14, wherein each of the initial set of multimedia identification signals is at least one of:

an image, a graphic, a video stream, a video clip, an audio stream, an audio clip, a video frame, a photograph, and images of signals.

17. The server of claim 14, wherein the initial set of multimedia identification signals is at least one of:

captured by the user device, and stored in the user device.

18. The server of claim 14, wherein the request further includes supplemental information, wherein the supplemental information comprises at least one of an Internet protocol (IP) address of the user computing device, a time, a date, and a browser type of the IP address of the user computing device, wherein the supplemental information is used to create a metadata of the concept structure.

19. The server of claim 18, wherein the server is further configured to:

receive an initial set of multimedia identification signals from the user device;

generate at least one signature for each signal in the initial set of multimedia identification signals;

create the at least one concept structure associated with the user based on the generated signatures;

associate the metadata with the created at least one concept structure; and

save the created concept structure in a database.

20. The server of claim 19, wherein the current set of received multimedia identification signals correspond to the initial set of multimedia identification signals, wherein further the current set of received multimedia identification signals is a subset of the initial set of multimedia identification signals.

21. The server of claim 19, wherein the DCC system is further configured to match signatures in the at least one concept structure to signatures of the received set of current multimedia identification signals.

22. The server of claim 19, wherein the at least one concept structure is created using the DCC system, wherein the DCC system includes:

an attention processor configured to generate a current set of items from a multimedia identification signal and to determine which of the generated items are of interest for signature generation;

a signature generator configured to generate at least one signature responsive to at least one item of interest; and

a concept generator configured to match between the at least one signature generated responsive to at least one of the items of interest and a current set of signature reduced clusters associated with a current set of cluster structures.

23. The server of claim 14, wherein the DCC system is integrated in the server.