US 11,704,585 B2
System and method to determine outcome probability of an event based on videos
Humphrey Chen, Norwood, NJ (US); Cindy Chin, New York, NY (US); and Aaron Sloman, Costa Mesa, CA (US)
Assigned to CLIPr Co., Kirkland, WA (US)
Filed by CLIPr Co., Kirkland, WA (US)
Filed on May 11, 2021, as Appl. No. 17/317,643.
Prior Publication US 2022/0366283 A1, Nov. 17, 2022
Int. Cl. G06N 3/091 (2023.01); G06V 20/40 (2022.01); G10L 15/08 (2006.01); G10L 15/25 (2013.01); G10L 17/00 (2013.01); G10L 17/04 (2013.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01); G06T 11/20 (2006.01); G10L 15/18 (2013.01); G10L 15/22 (2006.01); G10L 25/57 (2013.01)
CPC G06N 7/01 (2023.01) [G06N 20/00 (2019.01); G06T 11/206 (2013.01); G06V 20/41 (2022.01); G06V 20/46 (2022.01); G10L 15/1815 (2013.01); G10L 15/22 (2013.01); G10L 25/57 (2013.01); G06V 20/44 (2022.01); G10L 2015/088 (2013.01)] 16 Claims
OG exemplary drawing
 
9. A method of determining an outcome probability of an event based on one or more videos, the method comprising:
receiving, by a video input module, the one or more videos representative of at least one event;
creating, by a building block creation module, a building block model;
extracting, by a video analysis module, an audio content, a video content or a combination thereof from the one or more videos;
analyzing, by the video analysis module, extracted audio content and extracted video content to generate an analysis result;
analyzing, by an engagement analysis module, an engagement between at least one speaker and at least one participant associated with the event captured in the one or more videos based on the analysis result;
generating, by an outcome probability calculation module, a data lake comprising a keyword library based on the analysis result and an analyzed engagement;
computing, by the outcome probability calculation module, the outcome probability of the event using the building block model and a probability input received from at least one user;
enabling, by a building block enhancement module, the building block model to learn from the data lake and the computed outcome probability, and to generate an enhanced building block model; and
representing, by an outcome representation module, the outcome probability in a pre-defined format.