Ranking Videos for a User

• US 20140250180A1
• Filed: 03/04/2013
• Published: 09/04/2014
• Est. Priority Date: 03/04/2013
• Status: Active Grant

• Current Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Original Assignee: Meta Platforms, Inc. (f/k/a Facebook, Inc.)
• Inventors: Tseng, Erick
• Granted Patent: US 9,165,069 B2
• Time in Patent Office: Days
• US Class Current: 709/204
• CPC Class Codes: G06F 16/70 of video data
• CPC Class Codes: G06F 16/738 Presentation of query results
• CPC Class Codes: G06F 16/7867 using information manually generated, e.g. tags, keywords, comments, title and artist information, manually generated time, location and usage information, user ratings
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46
• CPC Class Codes: H04N 21/251 Learning process for intelligent management, e.g. learning user preferences for recommending movies details of learning user preferences for the retrieval of video data in a video database G06F16/739; computer systems using learning methods G06N3/08
• CPC Class Codes: H04N 21/4668 for recommending content, e.g. movies

Abstract

In one embodiment, a method includes determining by a computing device a set of videos that a user may watch. For each video, a coefficient value is determined for each of one or more coefficient factors. At least one of the coefficient factors has a value that would be coincident with the user watching the video. A video coefficient for each video is calculated based on the coefficient values of its coefficient factors, and the videos are ranked based on their video coefficients. The rankings are then provided for presentation to the user.

Claims

1. A method comprising:

by one or more computing devices, determining a plurality of videos a user may watch;

by one or more computing devices, for each of the videos;

determining a coefficient value for each of one or more coefficient factors, at least one of the coefficient factors having a value that would be coincident with the user watching the video; and

calculating a video coefficient based on the coefficient values of the coefficient factors;

by one or more computing devices, ranking the videos based on their video coefficients; and

by one or more computing devices, providing the ranking of the videos for presentation to the user.

2. The method of claim 1, wherein a coefficient factor having a value that would be coincident with the user watching the video comprises:

a number of others users currently watching the video that are connected to the user within a social-networking system;

a number of any other users, regardless of connection to the user within the social-networking system, that are currently watching the video;

an immediacy of the video;

or

a current value to an entity of the user watching the video.

3. The method of claim 2, wherein:

the user and other users are users of a social-networking system that comprises a graph comprising a plurality of nodes and edges connecting the nodes, at least one node in the graph corresponding to the user, at least one node in the graph corresponding to each of one or more of the other users; and

a connection of another user to the user comprises at least one node in the graph corresponding to the user and at least one node corresponding to the other user being connected to each other by one or more edges.

4. The method of claim 1, wherein at least one of the coefficient factors has a value that would not be coincident with the user watching the video.

5. The method of claim 4, wherein a coefficient factor having a value that would not be coincident with the user watching the video comprises:

a number of others users that are connected to the user within a social-networking system that have liked the video;

a number of any other users, regardless of connection to the user within the social-networking system, that have liked the video;

a trend of users'"'"' actions related to the video;

or

a taste factor based on one or more preferences of the user.

6. The method of claim 5, wherein:

the user and other users are users of a social-networking system that comprises a graph comprising a plurality of nodes and edges connecting the nodes, at least one node in the graph corresponding to the user, at least one node in the graph corresponding to each of one or more of the other users; and

a connection of another user to the user comprises at least one node in the graph corresponding to the user and at least one node corresponding to the other user being connected to each other by one or more edges.

7. The method of claim 5, wherein:

the user is a user of a social-networking system that comprises a graph comprising a plurality of nodes and edges connecting the nodes, with at least one node in the graph corresponding to the user; and

at least one of the preferences the taste factor is based on is determined from information associated with at least one of the plurality of nodes or edges in the social-networking system.

8. The method of claim 1, wherein at least one of the plurality of videos comprises a television program.

9. The method of claim 8, wherein the television program is a live television program.

10. The method of claim 8, wherein:

at least one first coefficient factor comprises a number of others users currently watching the television program that are connected to the user within a social-networking system;

at least one second coefficient factor comprises a number of any other users, regardless of connection to the user within the social-networking system, that are currently watching the television program;

at least one third coefficient factor comprises an immediacy of the television program;

at least one fourth coefficient factor comprises a current value to an entity of the user watching the television program;

at least one fifth coefficient factor comprises a number of others users that are connected to the user within a social-networking system that have liked the television program;

at least one sixth coefficient factor comprises a number of any other users, regardless of connection to the user within the social-networking system, that have liked the television program;

at least one seventh coefficient factor comprises a trend of users'"'"' actions related to the video;

at least one eighth coefficient factor comprises a relevance of the television program to the user based on social-networking information associated with the user;

each coefficient factor has an associated weight; and

calculating a video coefficient based on the coefficient values of the coefficient factors comprises calculating the video coefficient using a linear combination of each coefficient factor'"'"'s value multiplied by the coefficient factor'"'"'s associated weight.

11. One or more computer-readable non-transitory storage media embodying software that is operable when executed to:

determine a plurality of videos a user may watch;

for each of the videos;

determine a coefficient value for each of one or more coefficient factors, at least one of the coefficient factors having a value that would be coincident with the user watching the video; and

calculate a video coefficient based on the coefficient values of the coefficient factors;

rank the videos based on their video coefficients; and

provide the ranking of the videos for presentation to the user.

12. The media of claim 11, wherein a coefficient factor having a value that would be coincident with the user watching the video comprises:

a number of others users currently watching the video that are connected to the user within a social-networking system;

a number of any other users, regardless of connection to the user within the social-networking system, that are currently watching the video;

an immediacy of the video;

or

a current value to an entity of the user watching the video.

13. The media of claim 12, wherein:

the user and other users are users of a social-networking system that comprises a graph comprising a plurality of nodes and edges connecting the nodes, at least one node in the graph corresponding to the user, at least one node in the graph corresponding to each of one or more of the other users; and

a connection of another user to the user comprises at least one node in the graph corresponding to the user and at least one node corresponding to the other user being connected to each other by one or more edges.

14. The media of claim 11, wherein at least one of the coefficient factors has a value that would not be coincident with the user watching the video.

15. The media of claim 14, wherein a coefficient factor having a value that would not be coincident with the user watching the video comprises:

a number of others users that are connected to the user within a social-networking system that have liked the video;

a number of any other users, regardless of connection to the user within the social-networking system, that have liked the video;

a trend of users'"'"' actions related to the video;

or

a taste factor based on one or more preferences of the user.

16. The media of claim 15, wherein:

the user and other users are users of a social-networking system that comprises a graph comprising a plurality of nodes and edges connecting the nodes, at least one node in the graph corresponding to the user, at least one node in the graph corresponding to each of one or more of the other users; and

a connection of another user to the user comprises at least one node in the graph corresponding to the user and at least one node corresponding to the other user being connected to each other by one or more edges.

17. The media of claim 15, wherein:

the user is a user of a social-networking system that comprises a graph comprising a plurality of nodes and edges connecting the nodes, with at least one node in the graph corresponding to the user; and

at least one of the preferences the taste factor is based on is determined from information associated with at least one of the plurality of nodes or edges in the social-networking system.

18. The media of claim 11, wherein at least one of the plurality of videos comprises a television program.

19. The media of claim 18, wherein:

at least one first coefficient factor comprises a number of others users currently watching the television program that are connected to the user within a social-networking system;

at least one second coefficient factor comprises a number of any other users, regardless of connection to the user within the social-networking system, that are currently watching the television program;

at least one third coefficient factor comprises an immediacy of the television program;

at least one fourth coefficient factor comprises a current value to an entity of the user watching the television program;

at least one fifth coefficient factor comprises a number of others users that are connected to the user within a social-networking system that have liked the television program;

at least one sixth coefficient factor comprises a number of any other users, regardless of connection to the user within the social-networking system, that have liked the television program;

at least one seventh coefficient factor comprises a trend of users'"'"' actions related to the video;

at least one eighth coefficient factor comprises a relevance of the television program to the user based on social-networking information associated with the user;

each coefficient factor has an associated weight; and

software that is operable when executed to calculate a video coefficient based on the coefficient values of the coefficient factors comprises software that is operable when executed to calculate the video coefficient using a linear combination of each coefficient factor'"'"'s value multiplied by the coefficient factor'"'"'s associated weight.

20. A system comprising:

one or more processors; and

a memory coupled to the processors comprising instructions executable by the processors, the processors being operable when executing the instructions to;

determine a plurality of videos a user may watch;

for each of the videos;

determine a coefficient value for each of one or more coefficient factors, at least one of the coefficient factors having a value that would be coincident with the user watching the video; and

calculate a video coefficient based on the coefficient values of the coefficient factors;

rank the videos based on their video coefficients; and

provide the ranking of the videos for presentation to the user.