Dynamic summaries for media content

Patent metadata

Field	Value
Publication number	US-10123095-B2
Application number	US-201715618447-A
Country	US
Kind code	B2
Filing date	Jun 9, 2017
Priority date	Mar 24, 2016
Publication date	Nov 6, 2018
Grant date	Nov 6, 2018

Abstract

Disclosed are various embodiments for providing dynamically generated summaries of media content, such as electronic books, audiobooks, audio series, video content series, and so on. An elapsed time since consumption of media content was ended is determined. A summary of a portion of the media content occurring prior to a point of resumption in the media content is dynamically generated. The content of the summary is selected according to a length of the elapsed time. The summary is presented via an output device.

First claim

Therefore, the following is claimed:

1. A system, comprising:
at least one computing device; and
at least one application executable in the at least one computing device, wherein when executed the at least one application causes the at least one computing device to at least:
determine an elapsed time since consumption of media content was ended;
dynamically generate a summary of a portion of the media content occurring prior to a point of resumption in the media content, wherein content of the summary is selected according to a length of the elapsed time and based at least in part on a popularity of dialogue searches relative to individual logical divisions of the portion of the media content; and
cause the summary to be presented via an output device.

2. The system of claim 1 , wherein when executed the at least one application further causes the at least one computing device to at least cause the media content to be presented via the output device at the point of resumption after presentation of the summary.

3. The system of claim 1 , wherein when executed the at least one application further causes the at least one computing device to at least:
determining a consumption history for the media content; and
wherein the content of the summary is selected based at least in part on the consumption history.

4. The system of claim 1 , wherein when executed the at least one application further causes the at least one computing device to at least:
analyze another portion of the media content after the point of resumption to determine at least one of: one or more cast members, one or more characters, one or more plot elements, one or more storyline elements, or one or more locations that occur in the other portion of the media content; and
wherein the content of the summary is selected based at least in part on at least one of: the one or more cast members, the one or more characters, the one or more plot elements, the one or more storyline elements, or the one or more locations that occur in the other portion of the media content.

5. The system of claim 1 , wherein when executed the at least one application further causes the at least one computing device to at least:
receive user feedback regarding the summary; and
modify a machine learning model used in dynamically generating the summary based at least in part on the user feedback.

6. The system of claim 1 , wherein the content of the summary is further selected according to a target summary length that is based at least in part on the elapsed time.

7. The system of claim 1 , wherein the media content is real-time media content.

8. The system of claim 1 , wherein the media content is an electronic book.

9. The system of claim 1 , wherein the summary is dynamically generated based at least in part on metadata indicating which logical divisions of the portion of the media content are associated with a relative significance meeting a threshold.

10. A method, comprising:
determining, by at least one computing device, a current position in media content being presented via an output device;
dynamically generating, by the at least one computing device, a summary of a portion of the media content beginning after the current position;
selecting, by the at least one computing device, content of the summary based at least in part on a popularity of dialogue searches relative to individual logical divisions of the portion of the media content; and
causing, by the at least one computing device, the summary of the portion of the media content to be presented via the output device.

11. The method of claim 10 , further comprising:
receiving, by the at least one computing device, a target length for the summary via a user interface; and
wherein the summary is dynamically generated to approximate the target length.

12. The method of claim 10 , further comprising:
receiving, by the at least one computing device, a request to end consumption of the media content; and
wherein the current position in the media content is determined in response to the request.

13. The method of claim 10 , further comprising identifying, by the at least one computing device, logical divisions of significance in the portion of the media content.

14. The method of claim 13 , wherein identifying the logical divisions of significance further comprises employing, by the at least one computing device, a machine learning model to select one or more logical divisions of the portion of the media content.

15. The method of claim 10 , wherein dynamically generating the summary further comprises inserting, by the at least one computing device, one or more predefined summaries of logical divisions of the portion of the media content in the summary.

16. The method of claim 10 , further comprising:
determining, by the at least one computing device, one or more user characteristics; and
selecting, by the at least one computing device, the content for the summary from the portion of the media content based at least in part on the one or more user characteristics.

17. A non-transitory computer-readable medium embodying a program executable in at least one computing device, wherein when executed the program causes the at least one computing device to at least:
determine a current position in media content being presented via an output device;
dynamically generate a summary of a portion of the media content beginning after the current position;
select content of the summary based at least in part on a popularity of dialogue searches relative to individual logical divisions of the portion of the media content; and
cause the summary of the portion of the media content to be presented via the output device.

18. The non-transitory computer-readable medium of claim 17 , wherein when executed the program further causes the at least one computing device to at least:
receive a target length for the summary via a user interface; and
wherein the summary is dynamically generated to approximate the target length.

19. The non-transitory computer-readable medium of claim 17 , wherein when executed the program further causes the at least one computing device to at least insert one or more predefined summaries of logical divisions of the portion of the media content in the summary.

20. The non-transitory computer-readable medium of claim 17 , wherein when executed the program further causes the at least one computing device to at least:
determine one or more user characteristics; and
select the content for the summary from the portion of the media content based at least in part on the one or more user characteristics.

Assignees

• Amazon Tech Inc

Inventors

• Mishra Pragyana K
• Goyal Dushyant

Classifications

• G06V10/84

  using probabilistic graphical models from image or video features, e.g. Markov models or Bayesian networks · CPC title

• G06V10/764

  using classification, e.g. of video objects · CPC title

• G06F18/29

  Graphical models, e.g. Bayesian networks · CPC title

• G06F18/24155

  Bayesian classification · CPC title

• 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