Image recommendations for thumbnails for online media items based on user activity

1. A method comprising:

collecting user activity data for a first online media item of a plurality of online media items, the user activity data comprising data for a user consuming the first online media item;

identifying a ranking of the plurality of online media items, wherein the ranking is based on a click rate of a corresponding online media item of the plurality of online media items;

identifying, based on at least the ranking of the plurality of online media items, a second online media item of the plurality of online media items for thumbnail analysis;

segmenting the second online media item into a plurality of segments, wherein each segment comprises a corresponding set of frames of a plurality of frames of the second online media item, wherein a set of frames comprises more than one of the plurality of frames;

identifying a segment of the plurality of segments with user activity data satisfying one or more criteria uniquely associated with the user activity data of the user, the identified segment comprising a set of frames of the plurality of frames of the second online media item;

selecting a frame from the set of frames of the identified segment from the second online media item; and

sending, to a client device, a recommendation of the selected frame as a thumbnail for the second online media item, wherein the recommendation comprises a point in time of the second online media item corresponding to the selected frame.

2. The method of claim 1 , wherein the user activity data comprises measurements that are based on time of a presentation of the first online media item to the user.

3. The method of claim 1 , wherein identifying one or more of the plurality of segments with user activity data satisfying one or more criteria comprises:

identifying one or more features from each segment of the plurality of segments;

comparing the one or more features to the user activity data; and

based on the comparing, identifying one or more of the plurality of segments that has one or more features in common with the user activity data.

4. The method of claim 1 , wherein the one or more criteria comprise at least one of geography, language, or topic.

5. The method of claim 1 , wherein the user activity data for the first online media item comprises at least one of user data, geography data, a consumption time, replay data, recommend data, content change data, or view data.

6. The method of claim 1 , wherein selecting the frame from the set of frames from the second online media item comprises:

determining frame data for each frame in the set of frames, the frame data comprising at least one of color analysis information or a consumption rate; and

identifying the frame from the set of frames that has frame data satisfying one or more criteria.

7. The method of claim 1 , wherein sending the recommendation of the selected frame as the thumbnail for the second online media item further comprises:

specifying one or more frames of the set of frames to not use as the thumbnail for the second online media item.

8. A system comprising:

a memory; and

a processing device operatively coupled with the memory to:

collect user activity data for a first online media item of a plurality of online media items, the user activity data comprising data for a user consuming the first online media item;

identify a ranking of the plurality of online media items, wherein the ranking is based on a click rate of a corresponding online media item of the plurality of online media items;

identify, based on at least the ranking of the plurality of online media items, a second online media item of the plurality of online media items for thumbnail analysis;

segment the second online media item into a plurality of segments, wherein each segment comprises a corresponding set of frames of a plurality of frames of the second online media item, wherein a set of frames comprises more than one of the plurality of frames;

identify a segment of the plurality of segments with user activity data satisfying one or more criteria uniquely associated with the user activity data of the user, the identified segment comprising a set of frames of the plurality of frames of the second online media item;

select a frame from the set of frames of the identified segment from the second online media item; and

send, to a client device, a recommendation of the selected frame as a thumbnail for the second online media item, wherein the recommendation comprises a point in time of the second online media item corresponding to the selected frame.

9. The system of claim 8 , wherein the user activity data comprises measurements that are based on time of a presentation of the first online media item to the user.

10. The system of claim 8 , wherein to identify one or more of the plurality of segments with user activity data satisfying one or more criteria, the processing device is to:

identify one or more features from each segment of the plurality of segments;

compare the one or more features to the user activity data; and

based on the comparing, identify one or more of the plurality of segments that has one or more features in common with the user activity data.

11. The system of claim 8 , wherein the one or more criteria comprise at least one of geography, language, or topic.

12. The system of claim 8 , wherein the user activity data for the first online media item comprises at least one of user data, geography, data, a consumption time, replay data, recommend data, content data, or view data.

13. The system of claim 8 , wherein to select the frame from the set of frames from the second online media item, the processing device is to:

determining frame data for each frame in the set of frames, the frame data comprising at least one of color analysis information or a consumption rate; and

identifying the frame from the set of frames that has frame data satisfying one or more criteria.

14. The system of claim 8 , wherein to send the recommendation of the selected frame as the thumbnail for the second online media item, the processing device is to:

specify one or more frames of the set of frames to not use as the thumbnail for the second online media item.

15. A non-transitory computer readable storage medium encoding instructions thereon that, in response to execution by a processing device, cause the processing device to perform operations comprising:

collecting user activity data for a first online media item of a plurality of online media items, the user activity data comprising data for a user consuming the first online media item;

identifying a ranking of the plurality of online media items, wherein the ranking is based on a click rate of a corresponding online media item of the plurality of online media items;

identifying, based on at least the ranking of the plurality of online media items, a second online media item of the plurality of online media items for thumbnail analysis;

segmenting the second online media item into a plurality of segments, wherein each segment comprises a corresponding set of frames of a plurality of frames of the second online media item, wherein a set of frames comprises more than one of the plurality of frames;

identifying a segment of the plurality of segments with user activity data satisfying one or more criteria uniquely associated with the user activity data of the user, the identified segment comprising a set of frames of the plurality of frames of the second online media item;

selecting a frame from the set of frames of the identified segment from the second online media item; and

sending, to a client device, a recommendation of the selected frame as a thumbnail for the second online media item, wherein the recommendation comprises a point in time of the second online media item corresponding to the selected frame.

16. The non-transitory computer readable storage medium of claim 15 , wherein the user activity data comprises measurements that are based on time of a presentation of the first online media item to the user.

17. The non-transitory computer readable storage medium of claim 15 , wherein identifying one or more of the plurality of segments with user activity data satisfying one or more criteria comprises:

identifying one or more features from each segment of the plurality of segments;

comparing the one or more features to the user activity data; and

based on the comparing, identifying one or more of the plurality of segments that has one or more features in common with the user activity data.

18. The non-transitory computer readable storage medium of claim 15 , wherein the one or more criteria comprise at least one of geography, language, or topic.

19. The non-transitory computer readable storage medium of claim 15 , wherein the user activity data for the first online media item comprises at least one user data, geography data, a consumption of time, replay data, recommend data, content change data, or view data.

20. The non-transitory computer readable storage medium of claim 15 , wherein selecting the frame from the set of frames from the second online media item comprises:

determining frame data for each frame in the set of frames, the frame data comprising at least one of color analysis information or a consumption rate; and

identifying the frame from the set of frames that has frame data satisfying one or more criteria.