Video data learning and prediction

Patent metadata

Field	Value
Publication number	US-10789990-B2
Application number	US-201816222876-A
Country	US
Kind code	B2
Filing date	Dec 17, 2018
Priority date	Dec 17, 2018
Publication date	Sep 29, 2020
Grant date	Sep 29, 2020

Abstract

A computer-implemented method for locating content corresponding to a recap segment includes determining whether a recap segment is present in video data corresponding to a video series. In response to determining that the recap segment is present, the method includes dividing the recap segment into clips corresponding to individual scenes in one or more previous episodes of the video series and, for each clip, comparing the clip to one or more of the episodes in the video series for determining a location of the clip in one of the episodes. The method also includes determining whether the clip is part of a larger scene in the episode corresponding thereto and determining a starting and ending time of the larger scene within the episode. The method includes storing the starting and ending time of the larger scene in correlation with the clip.

First claim

What is claimed is:

1. A computer-implemented method for locating content corresponding to a recap segment, the method comprising:
determining whether a recap segment is present in video data corresponding to a video series;
in response to determining that the recap segment is present, dividing the recap segment into clips corresponding to individual scenes in one or more previous episodes of the video series; and
for each clip:
comparing the clip to one or more of the episodes in the video series for determining a location of the clip in one of the episodes, wherein the comparing the clip to the one or more episodes includes analyzing speech-to-text data of the clip and the one or more episodes;
determining whether the clip is part of a larger scene in the episode corresponding thereto;
determining a starting and ending time of the larger scene within the episode; and
storing the starting and ending time of the larger scene in correlation with the clip.

2. The computer-implemented method of claim 1 , wherein the comparing the clip to the one or more episodes includes analyzing image data of the clip and the one or more episodes.

3. The computer-implemented method of claim 1 , wherein the comparing the clip to the one or more episodes includes analyzing audio data of the clip and the one or more episodes.

4. The computer-implemented method of claim 1 , wherein the clips are compared to episodes sequentially starting with a most recent episode.

5. A computer-implemented method, the method comprising:
determining whether a recap segment is present in video data corresponding to a video series;
in response to determining that the recap segment is present, identifying clips in the recap segment;
outputting an option to alter output of one of the clips of the recap segment as the clip is output;
in response to receiving selection of the option to alter the output of the clip, altering the clip according to the selection; and
in response to not receiving selection of the option to alter the output of the clip, outputting the unaltered clip, wherein the option to alter the output of the clip of the recap segment as the clip is not output if the clip is tagged for preventing altering of the output of the clip.

6. The computer-implemented method of claim 5 , wherein the clips in the recap segment correspond to individual scenes in the video series.

7. The computer-implemented method of claim 5 , wherein the option to alter the output of the clip includes skipping the clip.

8. The computer-implemented method of claim 5 , wherein the option to alter the output of the clip includes outputting at least a portion of a larger scene corresponding to the clip, the larger scene being from an episode of the video series.

9. The computer-implemented method of claim 5 , comprising executing a prediction algorithm for determining whether to output the option for at least some of the clips.

10. The computer-implemented method of claim 9 , wherein the prediction algorithm makes a prediction based on whether a user has rewound at least a portion of a previous episode.

11. The computer-implemented method of claim 9 , wherein the prediction algorithm makes a prediction to alter the output of the clip based on passage of a threshold amount of time since a user has watched the previous episode corresponding to the clip.

12. A computer program product for altering output of a clip, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to:
determine, by the computer, whether a recap segment is present in video data corresponding to a video series;
in response to determining that the recap segment is present, identify, by the computer, clips in the recap segment;
output, by the computer, an option to alter output of one of the clips of the recap segment as the clip is output;
in response to receiving selection of the option to alter the output of the clip, alter, by the computer, the clip according to the selection; and
in response to not receiving selection of the option to alter the output of the clip, output, by the computer, the unaltered clip; and
execute, by the computer, a prediction algorithm for determining whether to output the option to alter the output of the clip, wherein the prediction algorithm makes a prediction based on whether a user has rewound at least a portion of a previous episode.

13. The computer program product of claim 12 , wherein the clips in the recap segment correspond to individual scenes in the video series.

14. The computer program product of claim 12 , wherein the option to alter the output of the clip includes skipping the clip.

15. The computer program product of claim 12 , wherein the option to alter the output of the clip includes outputting at least a portion of a larger scene corresponding to the clip, the larger scene being from an episode of the video series.

16. The computer program product of claim 12 , wherein the prediction algorithm makes a prediction to alter the output of the clip based on passage of a threshold amount of time since a user has watched the previous episode corresponding to the clip.

Assignees

• IBM

Inventors

• Catalano Pasquale A
• Crimmins Andrew G
• Tsfasman Arkadiy O
• Werner John S

Classifications

• H04N21/8549 Primary

  Creating video summaries, e.g. movie trailer {(retrieval in video databases by using presentations in form of a video summary G06F16/739)} · CPC title

• G06V20/49

  Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes · CPC title

• G06V20/48

  Matching video sequences · CPC title

• G11B27/28

  by using information signals recorded by the same method as the main recording {(G11B27/22 takes precedence)} · CPC title

• G11B27/031

  Electronic editing of digitised analogue information signals, e.g. audio or video signals · CPC title