Identifying and labeling segments within video content

Patent metadata

Field	Value
Publication number	US-12457382-B2
Application number	US-202218546386-A
Country	US
Kind code	B2
Filing date	Jan 21, 2022
Priority date	Feb 16, 2021
Publication date	Oct 28, 2025
Grant date	Oct 28, 2025

Abstract

In one aspect, an example method includes (i) obtaining fingerprint repetition data for a portion of video content, with the fingerprint repetition data including a list of other portions of video content matching the portion of video content and respective reference identifiers for the other portions of video content; (ii) identifying the portion of video content as a program segment rather than an advertisement segment based at least on a number of unique reference identifiers within the list of other portions of video content relative to a total number of reference identifiers within the list of other portions of video content; (iii) determining that the portion of video content corresponds to a program specified in an electronic program guide using a time stamp of the portion of video content; and (iv) storing an indication of the portion of video content in a data file for the program.

First claim

The invention claimed is:

1. A method comprising:
obtaining, by a computing system, fingerprint repetition data for a portion of video content, wherein the fingerprint repetition data comprises a list of other portions of video content matching the portion of video content and respective reference identifiers for the other portions of video content, each reference identifier corresponding to a respective different time the other portion of video content was presented;
identifying, by the computing system, the portion of video content as a program segment rather than an advertisement segment based at least on a number of unique reference identifiers within the list of other portions of video content relative to a total number of reference identifiers within the list of other portions of video content, wherein the total number of reference identifiers within the list of other portions of video content further includes a plurality of reference identifiers that are the same; and
based at least on the identifying of the portion of video content as a program segment, storing, by the computing system, an indication of the portion of video content in a data file for a corresponding program.

2. The method of claim 1 , wherein obtaining the fingerprint repetition data comprises searching for matches to fingerprints of the portion of video content within a video database so as to obtain the list of other portions of video content.

3. The method of claim 1 , wherein identifying the portion of video content as a program segment rather than an advertisement segment based at least on the number of unique reference identifiers relative to the total number of reference identifiers comprises determining that a ratio of the number of unique reference identifiers to the total number of reference identifiers satisfies a threshold.

4. The method of claim 1 , further comprising obtaining logo coverage data for the portion of video content,
wherein the logo coverage data is indicative of a percent of time that a logo overlays the portion of video content, and
wherein the identifying the portion of video content as a program segment rather than an advertisement segment is further based on the logo coverage data.

5. The method of claim 4 , wherein the identifying the portion of video content as a program segment rather than an advertisement segment is further based on a number of portions of video content in the list of other portions of video content and a length of the portion of video content.

6. The method of claim 1 , further comprising:
obtaining transition data for a section of video content that includes the portion of video content; and
identifying boundaries of the portion of video content using the transition data.

7. The method of claim 1 , further comprising after identifying the portion of video content as a program segment, merging the portion of video content with an adjacent portion of video content that is identified as a program segment.

8. The method of claim 7 , wherein merging the portion of video content with the adjacent portion of video content comprises:
obtaining a first list of matching portions for the portion of video content;
obtaining a second list of matching portions for the adjacent portion of video content;
identifying correspondences between the first list and the second list using timestamps for matching portions of the first list of matching portions and timestamps for matching portions of the second list of matching portions; and
based on the correspondences, merging the portion of video content with the adjacent portion of video content.

9. The method of claim 1 , further comprising generating a copy of the program using the data file for the program.

10. The method of claim 1 , further comprising obtaining closed captioning repetition data for the portion of video content,
wherein the identifying the portion of video content as a program segment rather than an advertisement segment is further based on the closed captioning repetition data.

11. The method of claim 10 , further comprising:
generating features using the closed captioning repetition data; and
providing the features as input to a classification model, wherein the classification model is configured to output classification data indicative of a likelihood of the features being characteristic of a program segment,
wherein the identifying the portion of video content as a program segment rather than an advertisement segment is further based on the classification data.

12. The method of claim 1 , further comprising:
obtaining fingerprint repetition data for another portion of video content;
identifying the other portion of video content as an advertisement segment rather than a program segment using the fingerprint repetition data;
identifying metadata for the other portion of video content; and
storing an indication of the other portion of video content and the metadata in another data file.

13. A non-transitory computer-readable medium having stored thereon program instructions that upon execution by a processor, cause performance of a set of acts comprising:
obtaining fingerprint repetition data for a portion of video content, wherein the fingerprint repetition data comprises a list of other portions of video content matching the portion of video content and respective reference identifiers for the other portions of video content, each reference identifier corresponding to a respective different time the other portion of video content was presented;
identifying the portion of video content as a program segment rather than an advertisement segment based at least on a number of unique reference identifiers within the list of other portions of video content relative to a total number of reference identifiers within the list of other portions of video content, wherein the total number of reference identifiers within the list of other portions of video content further includes a plurality of reference identifiers that are the same; and
based at least on the identifying of the portion of video content as a program segment, storing an indication of the portion of video content in a data file for a corresponding program.

14. The non-transitory computer-readable medium of claim 13 , wherein obtaining the fingerprint repetition data comprises searching for matches to fingerprints of the portion of video content within a video database so as to obtain the list of other portions of video content.

15. The non-transitory computer-readable medium of claim 13 , wherein identifying the portion of video content as a program segment rather than an advertisement segment based at least on the number of unique reference identifiers relative to the total number of reference identifiers comprises determining that a ratio of the number of unique reference identifiers to the total number of reference identifiers satisfies a threshold.

16. A computing system configured for performing a set of acts comprising:
obtaining fingerprint repetition data for a portion of video content, wherein the fingerprint repetition data comprises a list of other portions of video content matching the portion of video content and respective reference identifiers for the other portions of video content, each reference identifier corresponding to a respective different time the other portion of video content was presented;
identifying the portion of video content as a program segment rather than an advertisement segment based at least on a number of unique reference identifiers within the list of other portions of video content relative to a total

Assignees

• Gracenote Inc

Inventors

• Garg Amanmeet
• Gupta Sharmishtha
• Schmidt Andreas
• Balasuriya Lakshika
• Vartakavi Aneesh

Classifications

• G06F18/253

  of extracted features · CPC title

• G06V20/41 Primary

  Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49) · CPC title

• H04N21/8352

  involving content or source identification data, e.g. Unique Material Identifier [UMID] · CPC title

• H04N21/44008 Primary

  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

• G06V20/46

  Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames · CPC title