Systems, methods, and devices for determining an introduction portion in a video program

Patent metadata

Field	Value
Publication number	US-12374113-B2
Application number	US-202418642517-A
Country	US
Kind code	B2
Filing date	Apr 22, 2024
Priority date	Jul 15, 2020
Publication date	Jul 29, 2025
Grant date	Jul 29, 2025

Abstract

Systems, methods, and devices relating to determining an introduction portion in a video program are described herein. A method may determine first and second hard-matching pairs of video segments in first and second video content such that video fingerprints of the first hard-matching pair match and video fingerprints of the second hard-matching pair also match. The method may classify a third pair of video segments in the first and second video content, sequentially between the first and second hard-matching pairs, as a soft-matching pair of video segments of an introduction portion. The method may use the classification of the third pair of video segments as a soft-matching pair to determine a model configured to determine that a pair of video segments in two video content items are a soft-matching pair of video segments of an introduction portion.

First claim

What is claimed is:

1. A method comprising:
determining that one or more hard-matching pairs of video segments of a first video content and a second video content are associated with an introduction portion of at least one of the first video content or the second video content;
determining, based on a machine learning model, one or more soft-matching pairs of video segments of the first video content and the second video content that are associated with the introduction portion of the at least one of the first video content or the second video content;
determining, based on the machine learning model, that a pair of video segments of the first video content and the second video content following a contiguous sequence of the one or more hard-matching and the one or more soft-matching pairs of video segments are neither a hard-matching pair of video segments nor a soft-matching pair of video segments; and
determining, based on the determination that the pair of video segments of the first video content and the second video content is neither a hard-matching pair of video segments nor a soft-matching pair of video segments, that the pair of video segments of the first video content and the second video content are associated with a main body of video content of the at least one of the first video content or the second video content.

2. The method of claim 1 , wherein, for each hard-matching pair of video segments of the one or more hard-matching pairs of video segments, video fingerprints associated with the hard-matching pair of video segments match.

3. The method of claim 1 , wherein, for each soft-matching pair of video segments of the one or more soft-matching pairs of video segments, video fingerprints associated with the soft-matching pair of video segments do not match.

4. The method of claim 1 , wherein the one or more soft-matching pair of video segments comprises a transition from a first part of the introduction portion of the at least one of the first video content or the second video content to the main body of video content of the at least one of the first video content or the second video content.

5. The method of claim 1 , wherein the first video content comprises target video content in which the introduction portion is not known, and the second video content comprises reference video content in which the introduction portion is known.

6. The method of claim 1 , wherein for each hard-matching pair of video segments of the one or more hard-matching pairs of video segments, a difference between lengths of the hard-matching pair of video segments satisfies a length threshold.

7. The method of claim 1 , wherein for each soft-matching pair of video segments of the one or more soft-matching pairs of video segments, a difference between lengths of the soft-matching pair of video segments does not satisfy a length threshold.

8. The method of claim 1 , further comprising causing, based on the determining that the pair of video segments of the first video content and the second video content are associated with a main body of video content of the at least one of the first video content or the second video content, output of the at least the first video content or the second video content to skip to the main body of video content.

9. A method comprising:
determining, based on a machine learning model, that sequential pairs of video segments of a first video content and a second video content that follow contiguous hard-matching pairs of video segments of the first video content and second video content are either hard-matching pairs or soft-matching pairs until a next sequential pair of video segments of the first video content and the second video content is determined to be neither a hard-matching pair nor a soft-matching pair;
determining, based on the determination that the next sequential pair is neither a hard-matching pair nor a soft-matching pair, that the next sequential pair of video segments of the first video content and the second video content are associated with a main body of the at least one of the first video content or the second video content.

10. The method of claim 9 , wherein, for each hard-matching pair of video segments of the sequential pairs of video segments, video fingerprints associated with the hard-matching pair of video segments match.

11. The method of claim 9 , wherein, for each soft-matching pair of video segments of the sequential pairs of video segments, video fingerprints associated with the soft-matching pair of video segments do not match.

12. The method of claim 9 , wherein the first video content comprises target video content in which the introduction portion is not known, and the second video content comprises reference video content in which the introduction portion is known.

13. The method of claim 9 , wherein for each hard-matching pair of video segments the sequential pairs of video segments, a difference between lengths of the hard-matching pair of video segments satisfies a length threshold.

14. The method of claim 9 , wherein for each soft-matching pair of video segments the sequential pairs of video segments, a difference between lengths of the soft-matching pair of video segments does not satisfy a length threshold.

15. The method of claim 9 , further comprising causing, based on the determining that the next sequential pair of video segments of the first video content and the second video content are associated with a main body of video content of the at least one of the first video content or the second video content, output of the at least the first video content or the second video content to skip to the main body of video content.

16. A non-transitory computer-readable medium storing instructions that, when executed, cause:
determining that one or more hard-matching pairs of video segments of a first video content and a second video content are associated with an introduction portion of at least one of the first video content or the second video content;
determining, based on a machine learning model, one or more soft-matching pairs of video segments of the first video content and the second video content that are associated with the introduction portion of the at least one of the first video content or the second video content;
determining, based on the machine learning model, that a pair of video segments of the first video content and the second video content following a contiguous sequence of the one or more hard-matching and the one or more soft-matching pairs of video segments are neither a hard-matching pair of video segments nor a soft-matching pair of video segments; and
determining, based on the determination that the pair of video segments of the first video content and the second video content is neither a hard-matching pair of video segments nor a soft-matching pair of video segments, that the pair of video segments of the first video content and the second video content are associated with a main body of video content of the at least one of the first video content or the second video content.

17. The non-transitory computer-readable medium of claim 16 , wherein, for each hard-matching pair of video segments of the one or more hard-matching pairs of video segments, video fingerprints associated with the hard-matching pair of video segments match.

18. The non-transitory computer-readable medium of claim 16 , wherein, for each soft-matching pair of video segments of the one or more soft-matching pairs of video segments, video fingerprints associated with the soft-matching pair of video segmen

Assignees

• Comcast Cable Comm Llc

Inventors

• Younessian Ehsan
• Ishtiaq Faisal
• Braskich Anthony
• Spier Benjamin

Classifications

• 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

• H04N21/4394

  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

• H04N21/4665

  involving classification methods, e.g. Decision trees · CPC title

• H04N21/442

  Monitoring of processes or resources, e.g. detecting the failure of a recording device, monitoring the downstream bandwidth, the number of times a movie has been viewed, the storage space available from the internal hard disk {(arrangements for monitoring broadcast services or broadcast-related services H04H60/29; arrangements for identifying or recognising characteristics with a direct linkage to broadcast information H04H60/35; monitoring of user activities for profile generation for accessing a video database G06F16/739; monitoring in wireless networks H04W24/00)} · CPC title

• G06N20/00

  Machine learning · CPC title