US 11,895,372 B1
Rendering a dynamic endemic banner on streaming platforms using content recommendation systems and content modeling for user exploration and awareness
Mehul Sanghavi, San Jose, CA (US); Rohit Mahto, San Jose, CA (US); Kelly Lee, Fullerton, CA (US); and Madhulika Taneja, San Jose, CA (US)
Assigned to ROKU, INC., San Jose, CA (US)
Filed by ROKU, INC., San Jose, CA (US)
Filed on Aug. 5, 2022, as Appl. No. 17/882,184.
Int. Cl. H04N 21/482 (2011.01); H04N 21/466 (2011.01)
CPC H04N 21/4826 (2013.01) [H04N 21/4668 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A computer implemented method for creating dynamic banners, the method comprising:
generating, based on a trained machine learning model, a first call to a content recommendation system for a first subset of content assets for a target banner template;
generating, based on the trained machine learning model and at least a second subset of content assets, a second call to the content recommendation system for recommended content assets for the target banner template, wherein the second subset of content assets differ from the first subset of content assets;
selecting, based on the trained machine learning model, a content asset from the first subset of content assets or the at least the second subset of content assets, wherein the selecting of the content asset from the at least the second subset of content assets is based on the trained machine learning model being trained to weight content asset subset generation based on the at least the second subset of content assets being selected when a composite banner is historically selected by users at a frequency above a threshold value;
receiving, at a media device, the content asset;
stitching the content asset into the target banner template to form the composite banner; and
rendering the composite banner on a display of the media device.