US 12,192,550 B2
Time marking of media items at a platform using machine learning
Dongeek Shin, San Jose, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on May 17, 2022, as Appl. No. 17/746,818.
Prior Publication US 2023/0379520 A1, Nov. 23, 2023
Int. Cl. H04N 21/25 (2011.01); H04N 21/472 (2011.01); H04N 21/845 (2011.01)
CPC H04N 21/251 (2013.01) [H04N 21/47217 (2013.01); H04N 21/8455 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
identifying a media item to be provided to users of a platform, wherein the media item comprises a plurality of content segments;
providing an indication of the identified media item as input to a machine learning model;
obtaining one or more outputs of the machine learning model, wherein the one or more obtained outputs comprise event data identifying each of the plurality of content segments of the media item and, for each of the plurality of content segments, an indication of a level of confidence that a respective content segment depicts an event of interest to a first plurality of users of the platform;
responsive to determining that at least one of the plurality of content segments is associated with a level of confidence that satisfies a level of confidence criterion, associating the at least one of the plurality of content segments with a bookmark for a timeline of the media item; and
responsive to a request from a client device associated with a second user outside of the first plurality of users of the platform for access to the media item, providing the media item and an indication of the bookmark for presentation via a user interface of the client device.