System for identifying content of digital data

• US 10,181,015 B2
• Filed: 10/09/2017
• Issued: 01/15/2019
• Est. Priority Date: 07/27/2007
• Status: Active Grant

• Current Assignee: Audible Magic Corporation
• Original Assignee: Audible Magic Corporation
• Inventors: Wold, Erling
• Primary Examiner(s): Chai, Longbit
• Application Number:
  US15/728,481
• Publication Number:
  US 20180032705A1
• Time in Patent Office: 463 Days
• Field of Search: 726 32
• CPC Class Codes: G06F 16/7834 using audio features
• CPC Class Codes: G06F 16/785 using colour or luminescence
• CPC Class Codes: G06F 21/10 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 Class Codes: G06F 21/16 Program or content traceability, e.g. by watermarking

Abstract

A processor receives a first list comprising a plurality of events from a portion of digital data of an unknown work and one or more metrics between each pair of adjacent events from the plurality of events. The processor compares the first list to a second list comprising events and metrics between events for a known work to determine a first quantity of hits and a second quantity of misses. The processor determines whether the first list matches the second list based on the first quantity of hits and the second quantity of misses. The processor determines that the unknown work is a copy of the known work responsive to determining that the first list matches the second list.

Claims

1. A method comprising:

receiving a first list comprising

     1) a plurality of events from a portion of digital data of an unknown work and

     2) one or more metrics between each pair of adjacent events from the plurality of events, wherein each of the plurality of events comprises a visually or audibly perceptual occurrence at a time location in the unknown work;

determining associated pairs of elements, wherein an associated pair of elements comprises an element from the first list and an element from a second list, the second list comprising events and metrics between events for a known work;

determining a first quantity of hits and a second quantity of misses based at least in part of the associated pairs of elements, wherein a hit is determined for at least a first degree of correspondence between an event or metric in the first list and an event or metric in the second list and a miss is determined for less than the first degree of correspondence between an event or metric in the first list and an event or metric in the second list;

determining a miss ratio based on the associated pairs of elements, wherein the miss ratio is a ratio of the first quantity of hits to the second quantity of misses;

determining whether the miss ratio is less than a miss ratio threshold;

making a determination, by a hardware processor, as to whether the first list matches the second list based on whether the miss ratio is less than the miss ratio threshold; and

determining, by the hardware processor, whether the unknown work is a copy of the known work responsive to determining whether the first list matches the second list.

2. The method of claim 1, further comprising:

determining a hit threshold;

determining that the first quantity of hits is at least equal to the hit threshold;

determining that the first list matches the second list; and

determining that the unknown work is a copy of the known work.

3. The method of claim 1, further comprising:

determining a hit threshold;

determining that the first quantity of hits is below the hit threshold;

determining that the first list does not match the second list; and

determining that the unknown work is not a copy of the known work.

4. The method of claim 1, further comprising:

determining a hit threshold;

determining a miss threshold;

determining that the first quantity of hits is at least equal to the hit threshold;

determining that the second quantity of misses exceeds the miss threshold;

determining that the first list does not match the second list; and

determining that the unknown work is not a copy of the known work.

5. The method of claim 1, further comprising:

determining a hit threshold;

determining a miss threshold;

determining that the first quantity of hits is at least equal to the hit threshold;

determining that the second quantity of misses is below the miss threshold;

determining that the first list matches the second list; and

determining that the unknown work is a copy of the known work.

6. The method of claim 1, further comprising:

determining that the miss ratio is less than the miss ratio threshold;

determining that the first list matches the second list; and

determining that the unknown work is a copy of the known work.

7. The method of claim 1, wherein the miss ratio is a weighted miss ratio.

8. The method of claim 1, further comprising performing the following for each event:

determining a strength of the event; and

determining a weight to associate with the event based on the strength of the event.

9. The method of claim 8, wherein the first quantity of hits is a weighted quantity of hits and the first quantity of misses is a weighted quantity of misses.

10. The method of claim 1, wherein the unknown work comprises an unknown video work, and wherein the plurality of events comprises visually perceptual occurrences at the time locations in the unknown video work, the plurality of events comprising at least one of a scene change between neighboring scenes in the portion of digital data, a blank frame preceding or following a non-blank frame, or a first frame having pixels with a first color distribution preceding a second frame having pixels with a second color distribution that differs from the first color distribution by a threshold amount.

11. The method of claim 1, further comprising:

determining a regression line through a set of points (x,y), where each x is a time location of a particular event on the first list having a corresponding event on the second list and each y is a time location of the corresponding event on the second list;

determining a regression error for the regression line; and

comparing the regression error to a regression error threshold;

wherein determining whether the first list matches the second list comprises determining whether the regression error is lower than the regression error threshold, wherein the first list matches the second list if the regression error is lower than the regression error threshold.

12. The method of claim 1, further comprising:

determining that the first list matches the second list; and

performing a secondary test to verify an identity of the unknown work responsive to a determination that the first list matches the second list.

13. The method of claim 1, further comprising:

determining that the first list fails to match the second list; and

performing a secondary test to determine an identity of the unknown work.

14. The method of claim 1, further comprising:

determining that the first list matches the second list;

determining that the first list matches a third list associated with a second known work; and

performing a secondary test to determine whether the unknown work is a copy of the known work or a copy of the second known work.

15. A system comprising:

a memory; and

a hardware processor operatively coupled with the memory, the hardware processor to;

receive a first list comprising

     1) a plurality of events from a portion of digital data of an unknown work and

     2) one or more metrics between each pair of adjacent events from the plurality of events, wherein each of the plurality of events comprises a visually or audibly perceptual occurrence at a time location in the unknown work;

determine associated pairs of elements, wherein an associated pair of elements comprises an element from the first list and an element from a second list, the second list comprising events and metrics between events for a known work;

determine a first quantity of hits and a second quantity of misses based at least in part on the associated pairs of elements, wherein a hit is determined for at least a first degree of correspondence between an event or metric in the first list and an event or metric in the second list and a miss is determined for less than the first degree of correspondence between an event or metric in the first list and an event or metric in the second list;

determine a miss ratio based on the associated pairs of elements, wherein the miss ratio is a ratio of the first quantity of hits to the second quantity of misses;

determine whether the miss ratio is less than a miss ratio threshold;

make a determination, by the hardware processor, as to whether the first list matches the second list based on whether the miss ratio is less than the miss ratio threshold; and

determine, by the hardware processor, whether the unknown work is a copy of the known work responsive to determining whether the first list matches the second list.

16. The system of claim 15, wherein the hardware processor is further to:

determine a hit threshold;

determine a miss threshold;

determine that the first quantity of hits is at least equal to the hit threshold;

determine that the second quantity of misses exceeds the miss threshold;

determine that the first list does not match the second list; and

determine that the unknown work is not a copy of the known work.

17. The system of claim 15, wherein the hardware processor is further to:

determine that the miss ratio is less than the miss ratio threshold;

determine that the first list matches the second list; and

determine that the unknown work is a copy of the known work.

18. The system of claim 15, wherein the hardware processor is further to perform the following for each event:

determine a strength of the event; and

determine a weight to associate with the event based on the strength of the event, wherein the first quantity of hits is a weighted quantity of hits and the first quantity of misses is a weighted quantity of misses.

19. The system of claim 15, wherein the hardware processor is further to:

determine that the first list matches the second list;

determine that the first list matches a third list associated with a second known work; and

perform a secondary test to determine whether the unknown work is a copy of the known work or a copy of the second known work.

20. A non-transitory computer readable storage medium that provides instructions that, when executed on a hardware processor, cause the hardware processor to perform operations comprising:

determining associated pairs of elements, wherein an associated pair of elements comprises an element from a first list and an element from a second list, the second list comprising events and metrics between events for a known work;

receiving a first list comprising

     1) a plurality of events from a portion of digital data of an unknown work and

     2) one or more metrics between each pair of adjacent events from the plurality of events, wherein each of the plurality of events comprises a visually or audibly perceptual occurrence at a time location in the unknown work;

determining a first quantity of hits and a second quantity of misses based at least in part of the associated pairs of elements, wherein a hit is determined for at least a first degree of correspondence between an event or metric in the first list and an event or metric in the second list and a miss is determined for less than the first degree of correspondence between an event or metric in the first list and an event or metric in the second list;

determining a miss ratio based on the associated pairs of elements, wherein the miss ratio is a ratio of the first quantity of hits to the second quantity of misses;

determining whether the miss ratio is less than a miss ratio threshold;

making a determination, by the hardware processor, as to whether the first list matches the second list based on whether the miss ratio is less than the miss ratio threshold; and

determining, by the hardware processor, whether the unknown work is a copy of the known work responsive to determining whether the first list matches the second list.