US 11,842,292 B1
Predicting results for a video posted to a social media influencer channel
Richard Ray Butler, Van Nuys, CA (US); Estelle Evonne Cramer, Mailbu, CA (US); Tyler Folkman, Lehi, UT (US); Jacob Bradshaw Maughan, Spanish Fork, UT (US); Alexander Charles McFadyen, London (GB); and Theodore Sheffield, Encino, CA (US)
Assigned to BEN GROUP, INC., Sherman Oaks, CA (US)
Filed by BEN GROUP, INC., Sherman Oaks, CA (US)
Filed on Oct. 19, 2022, as Appl. No. 17/968,821.
Application 17/968,821 is a continuation of application No. 16/697,734, filed on Nov. 27, 2019, granted, now 11,507,866.
Claims priority of provisional application 62/840,958, filed on Apr. 30, 2019.
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 3/08 (2023.01); G06N 5/046 (2023.01); G06N 20/20 (2019.01); G06Q 50/00 (2012.01); G06F 16/78 (2019.01)
CPC G06N 5/046 (2013.01) [G06F 16/78 (2019.01); G06N 3/08 (2013.01); G06N 20/20 (2019.01); G06Q 50/01 (2013.01)] 22 Claims
OG exemplary drawing
 
12. A server computer, comprising:
a processor;
a communication interface in communication with the processor;
a data storage for storing results;
a memory in communication with the processor for storing instructions, which when executed by the processor, cause the server:
to maintain a database of results data for media clips posted on an influencer channel, wherein an influencer channel includes (1) unstructured data in the form of media clips, (2) structured data that describes the influencer channel and provides information about the media clips;
to provide to a first machine learning model a first set of channel data, comprising (1) a media clip, and (2) a first selection of the structured data;
to extract a first set of features from the media clip and from the first selection of structured data; and
to predict, based on the first set of extracted features, a value for a first target variable.