Automatic identification of video series

1. A method of improving content distribution on a content platform using a trained machine learning model, comprising:

inputting a first video created by a user into a machine learning model, wherein the machine learning model is trained to identify any other video created by a same user that belongs to a same series as an input video, wherein the user is any user on the content platform, and wherein the content platform comprises a plurality of videos distributed to a plurality of client computing devices;

extracting data from the first video and from a subset of the plurality of videos by the machine learning model, wherein the subset of the plurality of videos comprise videos created by the same user;

computing vectors associated with the first video and the subset of the plurality of videos by the machine learning model based on the data, wherein each vector indicates information that is unique to a particular video corresponding to each vector;

determining at least a second video related to the first video by the machine learning model based on the vectors, wherein the at least a second video is among the subset of the plurality of videos on the content platform;

determining whether the at least a second video is connected in a series with the first video based at least in part on creation times of the first video and the at least a second video using the machine learning model, wherein the series of videos comprises the first video and the at least a second video;

storing information indicative of a connection among the series of videos comprising the first video and the at least a second video; and

causing to display an interface element indicative of the series of videos in an interface of playing any video in the series of videos on one of the plurality of client computing devices associated with a user who is viewing the any video in the series of videos, wherein the interface element is configured to enable the user to seamlessly view another video in the series of videos, and wherein the interface of playing the any video in the series of videos further comprises information indicating that the any video is a particular part of the series of videos.

2. The method of claim 1 , further comprising:

generating a playlist, wherein the playlist comprises identification information of the first video and identification information of the at least a second video.

3. The method of claim 2 , further comprising:

transmitting the playlist to the one of the plurality of client computing devices associated with the user who is viewing any video in the series of videos.

4. The method of claim 1 , further comprising:

recommending one or more other videos in the series of videos to a user in response to detecting that the user is viewing any video in the series of videos.

5. The method of claim 1 , further comprising:

determining similarities between the first video and the at least a second video based on processing their respective metadata, wherein the metadata comprise text associated with the first video and text associated with the at least a second video.

6. The method of claim 5 , wherein the metadata further comprise information indicating creation time of the first video and information indicating creation time of the at least a second video.

7. The method of claim 1 , further comprising:

determining similarities between the first video and the at least a second video based on processing their respective metadata, image data, and voice data.

8. The method of claim 1 , further comprising:

receiving a third video;

determining whether the third video is uploaded by the same creator; and

determining whether the third video belongs to the series of video based at least in part on processing text associated with the third video.

9. The method of claim 8 , further comprising:

adding the third video to an existing playlist comprising the first video and the at least a second video in response to determining that the third video belongs to the series of videos.

10. A system of improving content distribution on a content platform using a trained machine learning model, comprising:

at least one computing device in communication with a computer memory, the computer memory comprising computer-readable instructions that upon execution by the at least one computing device, configure the system to perform operations comprising:

inputting a first video created by a user into a machine learning model, wherein the machine learning model is trained to identify any other video created by a same user that belongs to a same series as an input video, wherein the user is any user on the content platform, and wherein the content platform comprises a plurality of videos distributed to a plurality of client computing devices;

extracting data from the first video and from a subset of the plurality of videos by the machine learning model, wherein the subset of the plurality of videos comprise videos created by the same user;

computing vectors associated with the first video and the subset of the plurality of videos by the machine learning model based on the data, wherein each vector indicates information that is unique to a particular video corresponding to each vector;

determining at least a second video related to the first video by the machine learning model based on the vectors, wherein the at least a second video is among the subset of the plurality of videos on the content platform;

determining whether the at least a second video is connected in a series with the first video based at least in part on creation times of the first video and the at least a second video using the machine learning model, wherein the series of videos comprises the first video and the at least a second video;

storing information indicative of a connection among the series of videos comprising the first video and the at least a second video; and

causing to display an interface element indicative of the series of videos in an interface of playing any video in the series of videos on one of the plurality of client computing devices associated with a user who is viewing the any video in the series of videos, wherein the interface element is configured to enable the user to seamlessly view another video in the series of videos, and wherein the interface of playing the any video in the series of videos further comprises information indicating that the any video is a particular part of the series of videos.

11. The system of claim 10 , the operations further comprising:

generating a playlist, wherein the playlist comprises identification information of the first video and identification information of the at least a second video; and

transmitting the playlist to the one of the plurality of client computing devices associated with the user who is viewing any video in the series of videos.

12. The system of claim 10 , the operations further comprising:

recommending one or more other videos in the series of videos to a user in response to detecting that the user is viewing any video in the series of videos.

13. The system of claim 10 , the operations further comprising:

determining similarities between the first video and the at least a second video based on processing their respective metadata, wherein the metadata comprise text associated with the first video and text associated with the at least a second video.

14. The system of claim 13 , wherein the metadata further comprise information indicating creation time of the first video and information indicating creation time of the at least a second video.

15. The system of claim 10 , the operations further comprising:

receiving a third video;

determining whether the third video is uploaded by the same creator; and

determining whether the third video belongs to the series of video based at least in part on processing text associated with the third video; and

adding the third video to an existing playlist comprising the first video and the at least a second video in response to determining that the third video belongs to the series of videos.

16. A non-transitory computer-readable storage medium, storing computer-readable instructions that upon execution by a processor cause the processor to implement operations comprising:

inputting a first video created by a user into a machine learning model, wherein the machine learning model is trained to identify any other video created by a same user that belongs to a same series as an input video, wherein the user is any user on the content platform, and wherein the content platform comprises a plurality of videos distributed to a plurality of client computing devices;

extracting data from the first video and from a subset of the plurality of videos by the machine learning model, wherein the subset of the plurality of videos comprise videos created by the same user;

computing vectors associated with the first video and the subset of the plurality of videos by the machine learning model based on the data, wherein each vector indicates information that is unique to a particular video corresponding to each vector;

determining at least a second video related to the first video by the machine learning model based on the vectors, wherein the at least a second video is among the subset of the plurality of videos on the content platform;

determining whether the at least a second video is connected in a series with the first video based at least in part on creation times of the first video and the at least a second video using the machine learning model, wherein the series of videos comprises the first video and the at least a second video;

storing information indicative of a connection among the series of videos comprising the first video and the at least a second video; and

causing to display an interface element indicative of the series of videos in an interface of playing any video in the series of videos on one of the plurality of client computing devices associated with a user who is viewing the any video in the series of videos, wherein the interface element is configured to enable the user to seamlessly view another video in the series of videos, and wherein the interface of playing the any video in the series of videos further comprises information indicating that the any video is a particular part of the series of videos.

17. The non-transitory computer-readable storage medium of claim 16 , the operations further comprising:

generating a playlist, wherein the playlist comprises identification information of the first video and identification information of the at least a second video; and

transmitting the playlist to the one of the plurality of client computing devices associated with the user who is viewing any video in the series of videos.

18. The non-transitory computer-readable storage medium of claim 16 , the operations further comprising:

recommending one or more other videos in the series of videos to a user in response to detecting that the user is viewing any video in the series of videos.

19. The non-transitory computer-readable storage medium of claim 16 , the operations further comprising:

determining similarities between the first video and the at least a second video based on processing their respective metadata, wherein the metadata comprise text associated with the first video and text associated with the at least a second video.

20. The non-transitory computer-readable storage medium of claim 16 , the operations further comprising:

receiving a third video;

determining whether the third video is uploaded by the same creator; and

determining whether the third video belongs to the series of video based at least in part on processing text associated with the third video; and

adding the third video to an existing playlist comprising the first video and the at least a second video in response to determining that the third video belongs to the series of videos.