Systems and methods for analyzing video data and generating scoring data

Patent metadata

Field	Value
Publication number	US-12567254-B2
Application number	US-202318346623-A
Country	US
Kind code	B2
Filing date	Jul 3, 2023
Priority date	Jul 3, 2023
Publication date	Mar 3, 2026
Grant date	Mar 3, 2026

Abstract

System, process and device configurations are provided for analyzing video data, such as electronic game data, and generating scoring data for video data. Processes and device configurations include training a video data analysis model to generate scoring parameters, and for an evaluation tool for video data. Highly viewed and popular videos may be used as training input to the video analysis model. At least one score parameter may be determined for scoring videos. For electronic games, at least one score may be associated with a game scene, gameplay storylines, and for scoring video data in general. Analysis of game titles and game design may be performed during design to ensure that game scenes will have a high likelihood of user interest. Embodiments may also include modifying gameplay and gameplay storylines, and evaluating game promotional videos.

First claim

What is claimed is:

1 . A method for analyzing video data and generating scoring data, the method comprising:
receiving, by a device, input video data; providing, by the device, the input video data as input to a video analysis model that is trained to generate video analysis score parameters; obtaining, as output from the video analysis model, at least one video analysis score parameter for the input video data; and modifying, by the device, the input video data based on the at least one video analysis score parameter to generate modified video data, the modifying including removing or rearranging at least one frame of the input video data.

2 . The method of claim 1 , wherein the input video data includes a rendered video segment for an electronic game.

3 . The method of claim 1 , wherein the at least one video analysis score parameter is related to a likely popularity rating of the input video data.

4 . The method of claim 3 , wherein modifying the input video data is responsive to determining that the likely popularity rating of the input video data does not satisfy a threshold popularity rating.

5 . The method of claim 1 , comprising:
converting the input video data to a text stream representation, the text stream representation including a description of the input video data, and providing the text stream representation of the input video data as input to the video analysis model to obtain the at least one video analysis score parameter.

6 . The method of claim 1 , wherein the video analysis model is trained to generate the video analysis score parameters at least in part by comparing the input video data to a video input data reference.

7 . The method of claim 1 , comprising obtaining, as output from the video analysis model, at least one tag word and a preview image of input video data.

8 . The method of claim 1 , comprising providing the at least one video analysis score parameter for display.

9 . The method of claim 1 , comprising:
determining that the at least one video analysis score parameter does not satisfy a predetermined threshold; and obtaining, as output from the video analysis model, information identifying at least one element of the input video data as a cause of the at least one video score parameter not satisfying the predetermined threshold.

10 . The method of claim 9 , wherein modifying the input video data comprises removing at least one frame of the input video data that is associated with the at least one element of the input video data identified as a cause of the at least one video score parameter not satisfying the predetermined threshold.

11 . The method of claim 1 , wherein modifying the input video data comprises removing at least one frame of the input video data.

12 . The method of claim 1 , wherein modifying the input video data comprises rearranging at least one frame of the input video data.

13 . A device configured for analyzing video data and generating scoring data, the device comprising:
an interface; a memory storing executable instructions; and a controller coupled to the interface and the memory, wherein the controller is configured to perform operations comprising:
receiving input video data;
providing the input video data as input to a video analysis model that is trained to generate video analysis score parameters;
obtaining, as output from the video analysis model, at least one video analysis score parameter for the input video data;
and
modifying the input video based on the at least one video analysis score parameter to generate modified video data, the modifying including removing or rearranging at least one frame of the input video data.

14 . The device of claim 13 , wherein the input video data includes a rendered video segment for a game.

15 . The device of claim 13 , wherein the at least one video analysis score parameter is related to a likely popularity of the input video data.

16 . The device of claim 13 , comprising:
converting the input video data to a text stream representation, the text stream representation including a description of the input video data, and providing the text stream representation of the input video data as input to the video analysis model to obtain the at least one video analysis score parameter.

17 . The device of claim 13 , wherein the video analysis model is trained to generate the video analysis score parameters at least in part by comparing the input video data to a video input data reference.

18 . The device of claim 13 , comprising obtaining, as output from the video analysis model, at least one tag word and a preview image of input video data.

19 . The device of claim 13 , comprising providing the at least one video analysis score parameter for display.

20 . The device of claim 13 , comprising obtaining, as output from the video analysis model, information identifying at least one element of the input video data associated with a low score.

Assignees

• Sony Interactive Entertainment Inc

Inventors

• Bashkirov Sergey
• Bean Celeste
• Krishnamurthy Sudha
• Omote Masanori
• Sudhakara Sagar

Classifications

• G06V10/774

  Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title

• G06F40/40

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title

• A63F13/46

  Computing the game score · CPC title

• A63F13/67

  adaptively or by learning from player actions, e.g. skill level adjustment or by storing successful combat sequences for re-use · 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