US 11,669,951 B1
System for selecting content for a personalized video reel
Haotian Wu, New York, NY (US); Erin Kumari Pettigrew, San Francisco, CA (US); Adam Feldman, New York, NY (US); Zhengyu Su, Brooklyn, NY (US); Chengyan Qi, San Francisco, CA (US); and Joaquim Castella, Brooklyn, NY (US)
Assigned to Meta Platforms, Inc., Menlo Park, CA (US)
Filed by Meta Platforms, Inc., Menlo Park, CA (US)
Filed on Dec. 9, 2020, as Appl. No. 17/247,386.
Claims priority of provisional application 63/033,095, filed on Jun. 1, 2020.
Int. Cl. G06Q 50/00 (2012.01); G06T 7/00 (2017.01); G06F 3/04817 (2022.01); G06V 20/40 (2022.01)
CPC G06T 7/0002 (2013.01) [G06F 3/04817 (2013.01); G06Q 50/01 (2013.01); G06V 20/41 (2022.01); G06V 20/46 (2022.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/30168 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method comprising:
receiving, from a first device, a first content item associated with a first class of users, the first content item to be shared on a social networking system;
receiving, from a second device, a second content item associated with a second class of users, the second content item to be shared on the social networking system and the second class of users being different than the first class of users;
selecting the first content item for publication based at least in part on the first content item meeting or exceeding at least one first threshold and the first content item being associated with the first class of users;
in response to determining that the second content item is associated with the second class of users, determining, by the social networking system, that the second content item meets or exceeds at least one second threshold different from the first threshold;
inputting, based at least in part on determining that the second content item meets or exceeds the at least one second threshold, the second content item into a machine learned model to determine a content centric metric associated with the second content item, the content centric metric including an image quality metric, an audio quality metric, and a narrative quality metric;
receiving the content centric metric from the machine learned model;
selecting the second content item for publication based at least in part on the content centric metric; and
providing the second content item to a third device with an instruction to cause the third device to display at least an icon associated with the second content item in a user interface.