Methods and apparatus for optimizing station reference fingerprint loading using reference watermarks

Patent metadata

Field	Value
Publication number	US-12184397-B2
Application number	US-202318482945-A
Country	US
Kind code	B2
Filing date	Oct 9, 2023
Priority date	Dec 26, 2018
Publication date	Dec 31, 2024
Grant date	Dec 31, 2024

Abstract

Methods, apparatus, systems and articles of manufacture are disclosed selectively generating and storing hashed reference signatures. An example method disclosed herein determining whether watermark coverage of a first media segment satisfies a dropout constraint, the first media segment corresponding to a first monitoring time interval of a media source feed and, when the watermark coverage of the first media segment does not satisfy the dropout constraint hashing first media signatures associated with the first media segment to generate corresponding first hashed signatures and generating first reference data for the first media segment, the first reference data including the first hashed signatures and the first media signatures. The example method further includes, when the watermark coverage of the first media segment satisfies the dropout constraint, generating second reference data for the first media segment, the second reference data including the first media signatures.

First claim

What is claimed is:

1. An audience measurement computing system, comprising:
at least one processor; and
memory having stored therein machine readable instructions that, upon execution by the at least one processor, cause the audience measurement computing system to perform a set of operations comprising:
obtaining reference watermarks and linear reference signatures associated with a media source feed including a plurality of media segments;
for a first media segment of the plurality of media segments corresponding to a first monitoring time interval of the media source feed, storing ones of the linear reference signatures associated with the first media segment;
making a determination that watermark coverage of the first media segment failed to satisfy a threshold; and
based on making the determination that watermark coverage of the first media segment failed to satisfy the threshold: (i) hashing the ones of the linear reference signatures associated with the first media segment to determine hashed reference signatures associated with the first media segment, and (ii) storing the hashed reference signatures.

2. The audience measurement computing system of claim 1 , wherein the hashed reference signatures are used to credit viewership of the first media segment based on matching a monitoring signature with at least one of the hashed reference signatures.

3. The audience measurement computing system of claim 1 , wherein the operations further include:
determining at least one watermark-extraction timestamp indicated by a given one of the reference watermarks extracted from a portion of the media source feed;
determining at least one signature-generation timestamp associated with a given one of the linear reference signatures generated from another portion of the media source feed; and
aligning the at least one watermark-extraction timestamp and the at least one signature-generation timestamp.

4. The audience measurement computing system of claim 3 , wherein the operations further include making the determination that watermark coverage of the first media segment failed to satisfy the threshold by determining, based on the aligned at least one watermark-extraction timestamp and at least one signature-generation timestamp that the first monitoring time interval corresponding to the first media segment does not include a threshold extent of extracted watermarks.

5. The audience measurement computing system of claim 3 , wherein the operations further include storing the hashed reference signatures in association with the determined at least one signature-generation timestamp corresponding to the first monitoring time interval.

6. The audience measurement computing system of claim 1 , wherein the threshold is a watermark dropout threshold indicating a threshold percentage of watermarks extracted from the media source feed during the first monitoring time interval.

7. The audience measurement computing system of claim 6 , wherein the operations further include:
extracting the reference watermarks from the media source feed, and
making the determination that watermark coverage of the first media segment failed to satisfy the threshold by determining that a percentage of the reference watermarks extracted during the first monitoring time interval is less than the threshold percentage.

8. The audience measurement computing system of claim 1 , wherein the operations further include:
populating a reference database for the media source feed including, for the first media segment corresponding to the first monitoring time interval, the hashed reference signatures, and, for at least one other media segment of the plurality of media segments, reference watermarks extracted from the at least one other media segment and not hashed reference signatures; and
wherein the reference database is used in crediting media impressions to ones of the plurality of media segments based on monitoring information that matches corresponding portions of the reference database.

9. A method of selectively populating a media reference database with reference signatures, the method comprising:
obtaining reference watermarks and linear reference signatures associated with a media source feed including a plurality of media segments;
for a first media segment of the plurality of media segments corresponding to a first monitoring time interval of the media source feed, storing ones of the linear reference signatures associated with the first media segment;
making a determination that watermark coverage of the first media segment failed to satisfy a threshold; and
based on making the determination that watermark coverage of the first media segment failed to satisfy the threshold: (i) hashing the ones of the linear reference signatures associated with the first media segment to determine hashed reference signatures associated with the first media segment, and (ii) storing the hashed reference signatures.

10. The method of claim 9 , further including:
determining at least one watermark-extraction timestamp indicated by a given one of the reference watermarks extracted from a portion of the media source feed;
determining at least one signature-generation timestamp associated with a given one of the linear reference signatures generated from another portion of the media source feed; and
aligning the at least one watermark-extraction timestamp and the at least one signature-generation timestamp.

11. The method of claim 10 , further including making the determination that watermark coverage of the first media segment failed to satisfy the threshold by determining, based on the aligned at least one watermark-extraction timestamp and at least one signature-generation timestamp that the first monitoring time interval corresponding to the first media segment does not include a threshold extent of extracted watermarks.

12. The method of claim 10 , further including storing the hashed reference signatures in association with the determined at least one signature-generation timestamp corresponding to the first monitoring time interval.

13. The method of claim 9 , wherein the threshold is a watermark dropout threshold indicating a threshold percentage of watermarks extracted from the media source feed during the first monitoring time interval, and wherein the method further includes:
extracting the reference watermarks from the media source feed, and
making the determination that watermark coverage of the first media segment failed to satisfy the threshold by determining that a percentage of the reference watermarks extracted during the first monitoring time interval is less than the threshold percentage.

14. The method of claim 9 , further including:
populating a reference database for the media source feed including, for the first media segment corresponding to the first monitoring time interval, the hashed reference signatures, and, for at least one other media segment of the plurality of media segments, reference watermarks extracted from the at least one other media segment and not hashed reference signatures; and
wherein the reference database is used in crediting media impressions to ones of the plurality of media segments based on monitoring information that matches corresponding portions of the reference database.

15. A non-transitory computer-readable storage medium having stored thereon computer-readable instructions that, when executed by at least one processor, cause performance of operations comprising:
obtaining reference watermarks and linear reference signatures associated with a media source feed including a plurality of media s

Assignees

• Nielsen Co Us Llc

Inventors

• Petro James
• Nelson Dan
• Cross Deborah
• Ranganathan Raghuram

Classifications

• H04H60/58

  of audio {(determination or detection of speech characteristics in general G10L25/00; speech recognition in general G10L15/00)} · CPC title

• H04N21/4394 Primary

  involving operations for analysing the audio stream, e.g. detecting features or characteristics in audio streams (arrangements characterised by components specially adapted for monitoring, identification or recognition of audio in broadcast systems H04H60/58) · CPC title

• H04H60/59

  of video {(recognising characters or patterns in general G06F18/00, G06V20/00)} · CPC title

• H04N21/44008

  involving operations for analysing video streams, e.g. detecting features or characteristics in the video stream (arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59) · CPC title

• H04H60/37

  for identifying segments of broadcast information, e.g. scenes or extracting programme ID · CPC title