Customized handling of copied content based on owner-specified similarity thresholds

Patent metadata

Field	Value
Publication number	US-9654447-B2
Application number	US-201414258633-A
Country	US
Kind code	B2
Filing date	Apr 22, 2014
Priority date	Aug 29, 2006
Publication date	May 16, 2017
Grant date	May 16, 2017

Abstract

Making a determination of originality of content is disclosed. At least one originality factor related to the content is analyzed, wherein the originality factor is independent of a time when the content is detected. Based on the analysis of the at least one originality factor, automatically the determination is automatically made. The determination is outputted.

First claim

What is claimed is:

1. A method comprising the acts:
receiving a first item of content posted by a user to a web-based service, for distribution by said web-based service to the public;
computing first fingerprint data from the received first item of content, using a hardware processor configured to perform such act, said computing including determining spectral analysis, histogram, or wavelet data;
by reference to the first fingerprint data, identifying a first item of controlled content included in the first item of received content;
determining a first similarity score between the first item of received content and the first item of controlled content, based on matching between the computed first fingerprint data and fingerprint data for the first item of controlled content;
comparing the first similarity score with a first threshold value earlier-specified by an owner of the first item of controlled content, yielding a first comparison result;
selecting first usage rule data to apply to the first item of received content, based on the first comparison result;
applying the selected first usage rule data in governing distribution of the received first item of content by the web-based service;
receiving a second item of content posted by a user to the web-based service, for distribution by the web-based service to the public;
computing second fingerprint data from the received second item of content, using a hardware processor configured to perform such act, said computing including spectral analysis, histogram, or wavelet data;
by reference to the second fingerprint data, identifying a second item of controlled content included in the second item of received content;
determining a second similarity score between the second item of received content and the second item of controlled content, based on matching between the computed second fingerprint data and fingerprint data for the second item of controlled content;
comparing the second similarity score with a second threshold value earlier-specified by an owner of the second item of controlled content, yielding a second comparison result;
selecting second usage rule data to apply to the second item of received content, based on the second comparison result; and
applying the selected second usage rule data in governing distribution of the received second item of content by the web-based service;
wherein the second threshold value is different than the first threshold value, by which different content owners specified different, customized treatment of their items of controlled content by the web-based service.

2. The method of claim 1 wherein determination of the first similarity score depends, in part, on a percentage of the first controlled content that is included in the received first item of content.

3. The method of claim 1 that includes identifying the owner of the first controlled content, wherein said selecting of the first usage rule data is based, at least in part, on the identified owner of the first controlled content.

4. The method of claim 1 wherein determination of the first similarity score depends, in part, on a percentage of the first controlled content that is included in the received first item of content.

5. The method of claim 3 in which the owner of the first controlled content has established several stored usage rules, from which the applied first usage rule data is selected.

6. The method of claim 1 in which said selecting first usage rule data comprises selecting usage rule data from plural pre-defined usage rules.

7. The method of claim 6 that includes identifying the owner of the first controlled content, wherein said owner has pre-defined several usage rules.

8. The method of claim 1 that includes:
as a consequence of said applied first and second selected rule data:
for the first item of received content, preventing distribution of the content from the web service; and
for the second item of received content, allowing distribution of the content from the web service, with ad revenue related thereto shared with the owner of the second controlled content.

9. The method of claim 1 wherein the similarity score comprises a copying extent score.

10. The method of claim 1 wherein the similarity score comprises a copying density score.

11. The method of claim 1 that further includes presenting a graphical user interface to the owner of the first item of controlled content, said graphical user interface presenting plural alternative usage rules from which the owner can select, said graphical user interface further including a feature permitting the owner to specify the first threshold value.

12. The method of claim 1 that further includes presenting a graphical user interface to the owner of the first item of controlled content, said interface including a graphical representation of the first item of received content, adjacent a graphical representation of the identified first item of controlled content, the graphical user interface further presenting the first similarity score, wherein the presented user interface enables the owner of the first item of controlled content to review plural items of content received from users that are identified as including said owner's controlled content.

13. The method of claim 1 wherein computing the first fingerprint data includes determining spectral analysis data from said received first item of content.

14. The method of claim 1 wherein computing the first fingerprint data includes determining histogram data from said received first item of content.

15. The method of claim 1 wherein computing the first fingerprint data includes determining wavelet data from said received first item of content.

16. The method of claim 1 in which the act of identifying the first item of controlled content included in the first item of received content comprises plural staged processes:
in one stage, performing an initial analysis to identify a plurality of candidate items of controlled content that may be found in the received first item of content; and
in a subsequent stage, conducting a refined analysis to narrow said plurality of candidate items, to identify said first item of controlled content included in the first item of received content;
wherein resolution of the analysis is progressively enhanced by use of progressively more costly or complex operations.

17. The method of claim 16 in which said plurality of candidate items are identified using cosine similarity.

18. The method of claim 16 in which said plurality of candidate items are identified using latent semantic indexing.

19. The method of claim 1 in which the first similarity score is based on a Levinstein distance.

20. The method of claim 1 wherein the first item of content comprises video.

21. The method of claim 1 that further includes:
presenting a user interface through which an owner of the first item of controlled content can provide input confirming that the received first item of content is a match; and
feeding-back said user input for use in monitoring other user-posted content.

22. A system for distributing user-posted content to the public, comprising one or more hardware processors configured to perform actions including:
receiving a first item of content posted by a user;
computing first fingerprint data from the received first item of content, said computing including determining spectral analysis, histogram, or wavelet data;
by reference to the first fing

Assignees

• Brock James L
• Pitkow James E
• Digimarc Corp

Inventors

• Brock James L
• Pitkow James E

Classifications

• G06F21/10 Primary

  Protecting distributed programs or content, e.g. vending or licensing of copyrighted material (protection in video systems or pay television H04N7/16) {; Digital rights management [DRM]} · CPC title

• H04L63/0263 Primary

  Rule management · CPC title

• H04N21/2743

  Video hosting of uploaded data from client · CPC title

• H04N21/8358

  involving watermark {(protecting executable software by watermarking G06F21/16; image watermarking in general G06T1/0021; watermarks inserted in still images for transmission purposes H04N1/32144; inserting watermarks during video coding H04N19/467)} · CPC title

• H04N21/4627

  Rights management {associated to the content (security in data switching network management H04L41/28; security management or policies for network security H04L63/20; access security in wireless networks H04W12/08)} · CPC title