US 12,273,568 B2
Social video platform for generating and experiencing content
Matthew Gordon Davis, New York City, NY (US); and Jesse I. Redniss, Westport, CT (US)
Assigned to Warner Bros. Entertainment Inc., Burbank, CA (US)
Filed by WARNER BROS. ENTERTAINMENT INC., Burbank, CA (US)
Filed on Aug. 27, 2021, as Appl. No. 17/460,159.
Claims priority of provisional application 63/071,089, filed on Aug. 27, 2020.
Prior Publication US 2022/0070501 A1, Mar. 3, 2022
Int. Cl. H04N 21/2187 (2011.01); H04N 21/234 (2011.01); H04N 21/854 (2011.01)
CPC H04N 21/2187 (2013.01) [H04N 21/23418 (2013.01); H04N 21/854 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for automatically producing live video content received from one or more collaborators, the method comprising:
receiving, by at least one processor, disparate live input video streams from multiple user devices associated with different user accounts, the disparate live input video streams providing different views of an event occurring at a definite place and time, wherein the disparate live input video streams include a plurality of video frames or a plurality of videos;
analyzing, by the at least one processor, the disparate live input video streams to obtain a context of the plurality of video frames or the plurality of videos;
processing, by the at least one processor, the disparate live input video streams based on the context, the processing including using at least one of artificial intelligence (AI), machine learning (ML), and natural language processing (NLP) for selecting a plurality of scenes from the disparate live input video streams to include in a sequence of video clips to be generated from at least two user devices of the multiple user devices;
obscuring, by the at least one processor, content included in the at least one of the plurality of selected scenes, wherein the obscured content includes at least one of: unauthorized branding information, at least one inappropriate message, and at least one inappropriate gesture;
generating, by the at least one processor, the sequence of video clips from the disparate live input video streams, wherein the sequence of video clips includes the obscured content that includes at least one of: unauthorized branding information, the obscured at least one inappropriate message, and the obscured at least one inappropriate gesture, based on the processing and the obscuring of the at least one of the plurality of selected scenes from the disparate live input video streams; and
sending, by the at least one processor, the sequence of video clips to at least one client device.