Automated video ratings

Patent metadata

Field	Value
Publication number	US-10643074-B1
Application number	US-201816003791-A
Country	US
Kind code	B1
Filing date	Jun 8, 2018
Priority date	Jun 8, 2018
Publication date	May 5, 2020
Grant date	May 5, 2020

Abstract

Techniques are described for a content rating system that allows for automatic assignment of maturity ratings for media content.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving first media content;
generating a first feature set based on the first media content, wherein generating the first feature set includes generating a feature subset for each of a plurality of different temporal portions of the first media content, excluding irrelevant values from the feature subsets that are unrelated to maturity levels of the first media content, and aggregating the feature subsets to generate the first feature set by selecting a greatest value from each of the feature subsets;
determining that a second feature set of a plurality of feature sets is similar to the first feature set;
identifying a first maturity rating associated with the second feature set; and
assigning the first maturity rating to the first media content.

2. The method of claim 1 , wherein generating the first feature set based on the first media content includes generating one or more of a first value based on video associated with the first media content, a second value based on audio associated with the first media content, or a third value based on subtitles associated with the first media content.

3. The method of claim 1 , wherein the first maturity rating corresponds to a first category of a plurality of pre-defined categories of a ratings system for videos or television.

4. The method of claim 1 , wherein the plurality of feature sets are generated based on training media content.

5. The method of claim 1 , further comprising determining that a third feature set of the plurality of feature sets is similar to the first feature set, wherein the first maturity rating is associated with both the second feature set and the third feature set.

6. The method of claim 1 , wherein the first media content is live content, and wherein the first feature set represents a first portion of the live content, the method further comprising:
generating a third feature set based on a second portion of the live content subsequent to the first portion of the live content;
determining that a fourth feature set of the plurality of feature sets is similar to the third feature set;
identifying a second maturity rating associated with the fourth feature set; and
assigning the second maturity rating to the second portion of the live content.

7. The method of claim 1 , further comprising identifying a second maturity rating associated with the second feature set and assigning the second maturity rating to the first media content, the first maturity rating being associated with a first ratings system and the second maturity rating being associated with a second ratings system different from the first ratings system.

8. A system, comprising one or more computing devices configured to:
receive first media content;
generate a first feature set based on the first media content, wherein the one or more computing devices are configured to generate the first feature set by generating a feature subset for each of a plurality of different temporal portions of the first media content, excluding irrelevant values from the feature subsets that are unrelated to maturity levels of the first media content, and aggregating the feature subsets to generate the first feature set by selecting a greatest value from each of the feature subsets;
determine that a second feature set of a plurality of feature sets is similar to the first feature set;
identify a first maturity rating associated with the second feature set; and
assign the first maturity rating to the first media content.

9. The system of claim 8 , wherein the one or more computing devices are configured to generate the first feature set based on the first media content by generating one or more of a first value based on video associated with the first media content, a second value based on audio associated with the first media content, or a third value based on subtitles associated with the first media content.

10. The system of claim 8 , wherein the first maturity rating corresponds to a first category of a plurality of pre-defined categories of a ratings system for videos or television.

11. The system of claim 8 , wherein the one or more computing devices are configured to generate the plurality of feature sets based on training media content.

12. The system of claim 8 , wherein the one or more computing devices are further configured to determine that a third feature set of the plurality of feature sets is similar to the first feature set, and wherein the first maturity rating is associated with both the second feature set and the third feature set.

13. The system of claim 8 , wherein the first media content is live content, wherein the first feature set represents a first portion of the live content, and wherein the one or more computing devices are further configured to:
generate a third feature set based on a second portion of the live content subsequent to the first portion of the live content;
determine that a fourth feature set of the plurality of feature sets is similar to the third feature set;
identify a second maturity rating associated with the fourth feature set; and
assign the second maturity rating to the second portion of the live content.

14. The system of claim 8 , wherein the one or more computing devices are further configured to identify a second maturity rating associated with the second feature set and assign the second maturity rating to the first media content, the first maturity rating being associated with a first ratings system and the second maturity rating being associated with a second ratings system different from the first ratings system.

15. A computer program product, comprising one or more non-transitory computer-readable media having computer program instructions stored therein, the computer program instructions being configured such that, when executed by one or more computing devices, the computer program instructions cause the one or more computing devices to:
receive first media content;
generate a first feature set based on the first media content, wherein the computer program instructions are configured to cause the one or more computing devices to generate the first feature set by generating a feature subset for each of a plurality of different temporal portions of the first media content, excluding irrelevant values from the feature subsets that are unrelated to maturity levels of the first media content, and aggregating the feature subsets to generate the first feature set by selecting a greatest value from each of the feature subsets;
determine that a second feature set of a plurality of feature sets is similar to the first feature set;
identify a first maturity rating associated with the second feature set; and
assign the first maturity rating to the first media content.

16. The method of claim 1 , wherein each of the plurality of feature sets corresponds to previously classified media content, wherein the previously classified media content is separated into a plurality of groups based on corresponding classifications, wherein determining that the second feature set is similar to the first feature set includes identifying k feature sets included among the plurality of feature sets that are most similar to the first feature set, and wherein identifying the first maturity rating includes identifying the classification most common among the previously classified media content corresponding to the k feature sets.

17. The system of claim 8 , wherein each of the plurality of feature sets corresponds to previously classified media content

Assignees

• Amazon Tech Inc

Inventors

• Mcaninly Emily Evon
• Pepik Bojan
• Cheung Benjamin Chung Yen
• Germano Vernon
• Kanchana Sivakumar Kripa
• Orme Eric
• Bazzani Loris
• Shah Prateek Ramesh Chandra
• Norman Matthew J
• Donoser Michael

Classifications

• G06N20/10

  using kernel methods, e.g. support vector machines [SVM] · CPC title

• H04N21/8456

  by decomposing the content in the time domain, e.g. in time segments · CPC title

• H04N21/26603

  for automatically generating descriptors from content, e.g. when it is not made available by its provider, using content analysis techniques · 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

• H04N21/23418 Primary

  involving operations for analysing video streams, e.g. detecting features or characteristics (television picture signal circuitry for scene change detection H04N5/147; filtering for image enhancement G06T5/00; methods or arrangements for recognising scenes G06V20/00; arrangements characterised by components specially adapted for monitoring, identification or recognition of video in broadcast systems H04H60/59) · CPC title