Methods for identifying audio or video content

• US 10,007,723 B2
• Filed: 03/18/2016
• Issued: 06/26/2018
• Est. Priority Date: 12/23/2005
• Status: Active Grant

• Current Assignee: Digimarc Corporation
• Original Assignee: Digimarc Corporation
• Inventors: Conwell, William Y.
• Primary Examiner(s): McNally, Michael S
• Application Number:
  US15/074,967
• Publication Number:
  US 20160246878A1
• Time in Patent Office: 830 Days
• Field of Search: 713176
• 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 16/43 Querying
• CPC Class Codes: G06F 16/489 using time information
• CPC Class Codes: G06F 16/58 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/683 using metadata automatically derived from the content
• CPC Class Codes: G06F 16/783 using metadata automatically derived from the content
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06Q 10/00 Administration; Management
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G06Q 50/18 Legal services
• CPC Class Codes: G06Q 50/265 Personal security, identity or safety
• CPC Class Codes: H04L 63/08 for authentication of entities cryptographic mechanisms or cryptographic arrangements for entity authentication H04L9/32
• CPC Class Codes: H04L 9/3247 involving digital signatures

Abstract

The disclosed technology generally relates to methods for identifying audio and video entertainment content. One claim recites network server comprising: an input for receiving data representing audio uploaded to said network server; memory for storing the data representing audio; one or more processors configured for processing the data representing audio to yield fingerprint data; memory for storing fingerprint data; one or more processors configured for: determining whether the fingerprint data incurs a potential match with the stored fingerprint data, the potential match indicating an unreliability in the match below a predetermined threshold; and issuing a call, upon a condition of unreliability in the match, requesting at least a first reviewer and a second reviewer to review the data representing audio; an interface for receiving results from the first reviewer and results from the second reviewer; and one or more processors configured for weighting results from the first reviewer differently than results from the second reviewer, and determining whether to allow public access to the data representing audio based at least in part on weighted results. Of course other combinations and claims are provided.

Claims

1. A system associated with an online content distribution site, comprising:

an input to receive user uploaded audio or visual content, the user uploaded audio or visual content having been uploaded by a user to the online content distribution site for distribution from the online content distribution site to the public;

one or more memory modules storing data representing a universe of reference content associated with the online content distribution site;

one or more processors programmed for;

i. generating query fingerprint data from data associated with the user uploaded audio or visual content;

ii. determining candidate reference content, from the data representing the universe of reference content, that is a possible match of the user uploaded audio or visual content, in which the possible match comprises a non-identical match between the candidate reference content and the user uploaded audio or visual content, said determining being based on the query fingerprint data;

iii. providing a computer controlled interface associated with the online content distribution site through which a queue is obtained, the queue for review by a first party, the queue providing access to the candidate reference content and the user uploaded audio or visual content;

iv. soliciting through the computer controlled interface an indication from the first party, the indication confirming whether the uploaded audio or audio content corresponds to the candidate reference content;

v. in response to the soliciting, obtaining the indication through the computer controlled interface;

vi. controlling distribution of the user uploaded audio or visual content from the online content distribution site to the public based on the indication, in which the user uploaded audio or visual content remains publically accessible on the online content distribution site pending receipt of the indication; and

vii. in response to the indication, updating the data representing the universe of reference content with the query fingerprint data to more quickly enable future recognition of the user uploaded audio or visual content without review by the first party.

2. The system of claim 1 in which the query fingerprint data comprises a hash, and in which the non-identical match for the candidate reference content comprises a non-identical match based on the query fingerprint data hash with a hash corresponding to the candidate reference content.

3. The system of claim 1 in which said generating query fingerprint data comprises analyzing a transformed representation of the user uploaded audio or visual content, and in which said generating query fingerprint data utilizes hashing.

4. The system of claim 1 in which the queue comprises a link to the candidate reference content.

5. The system of claim 1 in which said determining candidate reference content utilizes a hamming distance.

6. The system of claim 1 in which the query fingerprint data comprises first plural hashes, and fingerprint data associated with the candidate reference content comprises second plural hashes, in which the possible match is determined by a distance function comparing the first plural hashes with the second plural hashes.

7. The system of claim 1 in which said one or more memory modules comprise one or more hard disks.

8. A method comprising:

obtaining uploaded visual or audio content, the uploaded visual or audio content having been uploaded to an online service for distribution from the online service to the public;

deriving query fingerprint data from the uploaded visual or audio content, said deriving query fingerprint data being performed by a configured computer system;

determining candidate reference content, from a universe of reference content, that is a possible match of the uploaded visual or audio content, in which the possible match comprises a non-identical match between the candidate reference content and the uploaded visual or audio content, said determining being based on the query fingerprint data and being performed by a configured computer system;

receiving an indication from a first party through an interface associated with the online service, the indication confirming that the uploaded visual or audio content corresponds to the candidate reference content;

controlling distribution of the user uploaded visual or audio content from the online service to the public based on the indication; and

based on the indication, updating the universe of reference content with the uploaded visual and audio content via the query fingerprint data to more quickly enable future recognition of the uploaded visual and audio content without review by the first party.

9. The method of claim 8 in which the query fingerprint data comprises a hash, and in which the non-identical match for the candidate reference content comprises a non-identical match between the query fingerprint data hash and a hash corresponding to the candidate reference content.

10. The method of claim 8 in which said deriving query fingerprint data comprises analyzing a transformed representation of the user uploaded visual or audio content, and in which said deriving query fingerprint data utilizes hashing.

11. The method of claim 8 further comprising queuing for review, the user uploaded visual or audio content item and data associated with the candidate reference content for review by the first party.

12. The method of claim 11 in which said queuing comprises providing a link to the candidate reference content.

13. The method of claim 8 in which the user uploaded visual or audio content is available for distribution to the public from the first party'"'"'s online service pending receipt of the indication.

14. The method of claim 8 in which said determining candidate reference content utilizes a hamming distance.

15. The method of claim 8 in which the query fingerprint data comprises first plural hashes, and fingerprint data associated with the candidate reference content comprises second plural hashes, in which the possible match is determined by a distance function comparing the first plural hashes with the second plural hashes.

16. A non-transitory computer readable medium on which is stored instructions, which when executed by one or more processors, perform a method of:

obtaining uploaded visual or audio content, the uploaded visual or audio content having been uploaded to an online service for distribution from the online service to the public;

deriving query fingerprint data from the uploaded visual or audio content;

determining candidate reference content, from a universe of reference content, that is a possible match of the uploaded visual or audio content, in which the possible match comprises a non-identical match between the candidate reference content and the uploaded visual or audio content, said determining being based on the query fingerprint data;

handling an indication from a first party through an interface associated with the online service, the indication confirming that the uploaded visual or audio content corresponds to the candidate reference content;

controlling distribution of the user uploaded visual or audio content from the online service to the public based on the indication; and

based on the indication, updating the universe of reference content with the uploaded visual and audio content via the query fingerprint data to more quickly enable future recognition of the uploaded visual and audio content without review by the first party.

17. The non-transitory computer readable medium of claim 16 in which the query fingerprint data comprises a hash, and in which the non-identical match for the candidate reference content comprises a non-identical match between the query fingerprint data hash and a hash corresponding to the candidate reference content.

18. The non-transitory computer readable medium of claim 16 in which the deriving query fingerprint data comprises analyzing a transformed representation of the user uploaded visual or audio content, and in which said deriving query fingerprint data utilizes hashing.

19. The non-transitory computer readable medium of claim 16 further comprising queuing for review, the user uploaded visual or audio content item and data associated with the candidate reference content for review by the first party.

20. The non-transitory computer readable medium of claim 19 in which the queuing comprises providing a link to the candidate reference content.

21. The non-transitory computer readable medium of claim 16 in which the user uploaded visual or audio content is available for distribution to the public from the first party'"'"'s online service pending receipt of the indication.

22. The non-transitory computer readable medium of claim 16 in which the determining candidate reference content utilizes a hamming distance.

23. The non-transitory computer readable medium of claim 16 in which the query fingerprint data comprises first plural hashes, and fingerprint data associated with the candidate reference content comprises second plural hashes, in which the possible match is determined by a distance function comparing the first plural hashes with the second plural hashes.