Identifying related videos based on relatedness of elements tagged in the videos

Patent metadata

Field	Value
Publication number	US-9639634-B1
Application number	US-201414166548-A
Country	US
Kind code	B1
Filing date	Jan 28, 2014
Priority date	Jan 28, 2014
Publication date	May 2, 2017
Grant date	May 2, 2017

Abstract

Systems and methods for identifying related videos based on elements tagged in the videos are presented. In an aspect, a system includes an identification component configured to identify tagged elements in a video, a matching component configured to identify other videos that include one or more of the tagged elements, and a recommendation component configured to recommend the other videos for viewing based on a current or past request to play the video.

First claim

What is claimed is:

1. A system, comprising:
a memory that stores computer executable components;
a processor that executes at least the following computer executable components stored in the memory:
an identification component configured to identify tagged elements in a video, wherein the tagged elements include a person appearing in the video;
a social component configured to identify one or more videos associated with a user identity of the person;
a privacy component configured to determine whether the person appearing in the video has authorized recommending, to another user, the one or more videos associated with the user identity of the person; and
a recommendation component configured to recommend the one or more videos for viewing based on a current or past request to play the video and in response to a determination that the person appearing in the video has authorized recommending to the other user.

2. The system of claim 1 , wherein the one or more videos associated with the user identity of the person include at least one of: a video liked by the person, a video watched by the person, a video uploaded by the person, a video endorsed by the person, a video shared by the person, a video commented on by the person, or a video in which the person appears.

3. The system of claim 1 , wherein the recommendation component is further configured to provide information describing how the one or more videos are associated with the user identity of the person in association with recommending the one or more videos.

4. The system of claim 1 , wherein
the social component is further configured to identify one or more videos associated with a user identity of the person based on a social relationship between the person appearing in the video and a user to which the one or more videos will be recommended, wherein the recommendation component is further configured to recommend the one or more videos based on the current or past request to play the video.

5. The system of claim 1 , further comprising:
a ranking component configured to rank the one or more videos based on number of matching tagged elements included in the video and respective ones of the one or more videos; and
a filter component configured to identify a subset of the one or more videos for recommending based on the ranking.

6. The system of claim 1 , further comprising:
a ranking component configured to rank the one or more videos based on types of matching tagged elements included in the video and respective ones of the one or more videos, and preferences of a user to which the one or more videos will be recommended; and
a filter component configured to identify a subset of the one or more videos for recommending based on the ranking.

7. The system of claim 1 , further comprising:
a playback component configured to track playback of the video in response to a request to play the video, wherein the recommendation component is further configured to recommend a subset of the one or more videos based on tagged elements appearing in the video prior to a point in the video where playback is stopped.

8. The system of claim 1 , further comprising:
a playback component configured to track playback of the video in response to a request to play the video, wherein the recommendation component is further configured to recommend a subset of the one or more videos during the playback of the video based elements appearing in the video at or near a current point in the video.

9. A method comprising:
using a processor to execute the following computer executable instructions stored in a memory to perform the following acts:
identifying tagged elements in a video, wherein the tagged elements include a person appearing in the video;
identifying one or more videos associated with a user identity of the person;
determining whether the person appearing in the video has authorized recommending, to another user, the one or more videos associated with the user identity of the person; and
recommending the one or more videos for viewing based on a current or past request to play the video and in response to a determination that the person appearing in the video has authorized recommending to the other user.

10. The method of claim 9 , wherein the one or more videos associated with the user identity of the person include at least one of: a video liked by the person, a video watched by the person, a video uploaded by the person, a video endorsed by the person, a video shared by the person, or a video commented on by the person.

11. The method of claim 9 , wherein
the one or more videos associated with the user identity of the person are identified based on a social relationship between the person appearing in the video and a user to which the one or more videos will be recommended.

12. The method of claim 9 , further comprising:
ranking the one or more videos based on number of matching tagged elements included in the video and respective ones of the one or more videos; and
identifying a subset of the one or more videos for recommending based on the ranking.

13. The method of claim 9 , further comprising:
ranking the one or more videos based on types of matching tagged elements included in the video and respective ones of the one or more videos, and preferences of a user to which the one or more videos will be recommended; and
identifying a subset of the one or more videos for recommending based on the ranking.

14. The method of claim 9 , further comprising:
tracking playback of the video in response to a request to play the video; and
recommending a subset of the one or more videos based on tagged elements appearing in the video prior to a point in the video where playback is stopped.

15. A non-transitory computer-readable storage medium comprising computer-readable instructions that, in response to execution, cause a computing system to perform operations, comprising:
identifying tagged elements in a video, wherein the tagged elements include a person appearing in the video;
identifying one or more videos associated with a user identity of the person;
determining whether the person appearing in the video has authorized recommending, to another user, the one or more videos associated with the user identity of the person; and
recommending the one or more videos for viewing based on a current or past request to play the video and in response to a determination that the person appearing in the video has authorized recommending to the other user.

16. The non-transitory computer-readable storage medium of claim 15 , wherein
the one or more videos associated with the user identity of the person are identified based on a social relationship between the person appearing in the video and a user to which the one or more videos will be recommended.

Assignees

• Google Inc

Inventors

• Greene Kevin
• Lewis Justin

Classifications

• G06F17/30029

  Physics · mapped topic

• G06F17/30053

  Physics · mapped topic

• G06F17/30973 Primary

  Physics · mapped topic

• G06F16/784 Primary

  the detected or recognised objects being people · CPC title

• G06F16/7837

  using objects detected or recognised in the video content · CPC title