Watch-time clustering for video searches
Abstract
This document describes, among other things, systems, methods, devices, and other techniques for using information about how long various videos were presented at client devices to determine subsequent video recommendations and search results. In some implementations, a computing can include a modeling apparatus, a front-end server, a request manager, one or more video file storage devices, a video selector, or a combination of some or all of these. The video selector can select video content for a particular digitized video among a plurality of digitized videos to serve to a computing device responsive to a request. The selection can be based at least in part on how long the particular digitized video has been presented at client devices associated with users having characteristics that match one or more characteristics of the user that submitted the request for video content, as indicated by the modeling apparatus.
Claims
exact text as granted — not AI-modified1 . (canceled)
2 . A computer-implemented method, comprising:
identifying an opportunity to display a video to a user; determining that the user is a member of a particular viewer category group based at least on the user previously viewing a first video corresponding to the particular viewer category group for at least a threshold amount of time; in response to determining that the user is a member of the particular viewer category group, selecting one or more second videos for the user based on the particular viewer category group; and providing video content of the one or more second videos to a computing device of the user.
3 . The computer-implemented method of claim 2 , wherein determining that the user is a member of a particular viewer category group comprises determining that characteristics of the user match user characteristics for the particular viewer category group.
4 . The computer-implemented method of claim 2 , wherein providing the video content of the one or more second videos comprises sending the one or more second videos to the computing device of the user.
5 . The computer-implemented method of claim 2 , wherein providing the video content of the one or more second videos comprises sending indications of the one or more second videos to the computing device of the user.
6 . The computer-implemented method of claim 2 , wherein:
identifying the opportunity to display the video to the user comprises receiving a video content request comprising one or more keywords; and selecting the one or more second videos comprises selecting the one or more second videos based on selection criteria comprising the one or more keywords and one or more user characteristics of the user.
7 . The computer-implemented method of claim 2 , wherein selecting the one or more second videos for the user based on the particular viewer category group comprises selecting at least one video previously assigned to the particular video category group.
8 . The computer-implemented method of claim 2 , further comprising:
obtaining data that indicates, for each respective user among a plurality of users to which at least a portion of the first video was served, a respective watch time for the first video that occurred at a respective computing device of the respective user; and generating, by the computing system a plurality of viewer category groups that each include a set of users having a common set of one or more characteristics, the one or more characteristics for each viewer category group including a respective minimum watch time for the first video.
9 . The computer-implemented method of claim 8 , further comprising:
selecting, based on the respective minimum watch time for each view category group, one or more view category groups to receive video content of the one or more second videos; and providing the video content of the one or more second videos to computing devices of one or more users in each selected view category group.
10 . A system, comprising:
one or more processors; and one or more computer-readable media having instructions stored thereon that, when executed by the one or more processors, cause performance of operations comprising:
identifying an opportunity to display a video to a user;
determining that the user is a member of a particular viewer category group based at least on the user previously viewing a first video corresponding to the particular viewer category group for at least a threshold amount of time;
in response to determining that the user is a member of the particular viewer category group, selecting one or more second videos for the user based on the particular viewer category group; and
providing video content of the one or more second videos to a computing device of the user.
11 . The system of claim 10 , wherein determining that the user is a member of a particular viewer category group comprises determining that characteristics of the user match user characteristics for the particular viewer category group.
12 . The system of claim 10 , wherein providing the video content of the one or more second videos comprises sending the one or more second videos to the computing device of the user.
13 . The system of claim 10 , wherein providing the video content of the one or more second videos comprises sending indications of the one or more second videos to the computing device of the user.
14 . The system of claim 10 , wherein:
identifying the opportunity to display the video to the user comprises receiving a video content request comprising one or more keywords; and selecting the one or more second videos comprises selecting the one or more second videos based on selection criteria comprising the one or more keywords and one or more user characteristics of the user.
15 . The system of claim 10 , wherein selecting the one or more second videos for the user based on the particular viewer category group comprises selecting at least one video previously assigned to the particular video category group.
16 . The system of claim 10 , wherein the operations comprise:
obtaining data that indicates, for each respective user among a plurality of users to which at least a portion of the first video was served, a respective watch time for the first video that occurred at a respective computing device of the respective user; and generating, by the computing system a plurality of viewer category groups that each include a set of users having a common set of one or more characteristics, the one or more characteristics for each viewer category group including a respective minimum watch time for the first video.
17 . The system of claim 16 , wherein the operations comprise:
selecting, based on the respective minimum watch time for each view category group, one or more view category groups to receive video content of the one or more second videos; and providing the video content of the one or more second videos to computing devices of one or more users in each selected view category group.
18 . A non-transitory computer-readable media having instructions stored thereon that, when executed by the one or more processors, cause performance of operations comprising:
identifying an opportunity to display a video to a user; determining that the user is a member of a particular viewer category group based at least on the user previously viewing a first video corresponding to the particular viewer category group for at least a threshold amount of time; in response to determining that the user is a member of the particular viewer category group, selecting one or more second videos for the user based on the particular viewer category group; and providing video content of the one or more second videos to a computing device of the user.
19 . The non-transitory computer-readable media of claim 18 , wherein determining that the user is a member of a particular viewer category group comprises determining that characteristics of the user match user characteristics for the particular viewer category group.
20 . The non-transitory computer-readable media of claim 18 , wherein providing the video content of the one or more second videos comprises sending the one or more second videos to the computing device of the user.
21 . The non-transitory computer-readable media of claim 18 , wherein providing the video content of the one or more second videos comprises sending indications of the one or more second videos to the computing device of the user.Join the waitlist — get patent alerts
Track US2023105846A1 — get alerts on status changes and closely related new filings.
We store only your email — no account needed. See our privacy policy.