US 12,200,310 B2
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 Dec. 12, 2023, as Appl. No. 18/536,627.
Application 18/536,627 is a continuation of application No. 17/882,184, filed on Aug. 5, 2022, granted, now 11,895,372.
Prior Publication US 2024/0137621 A1, Apr. 25, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 21/482 (2011.01); H04N 21/466 (2011.01)
CPC H04N 21/4826 (2013.01) [H04N 21/4668 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computer-implemented method for creating dynamic banners, the method comprising:
generating, by at least one computer processor and 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, wherein the first subset of content assets includes content reflecting interests of a user;
generating, based on the trained machine learning model, a second call to the content recommendation system for a second subset of content assets for the target banner template, wherein the second subset of content assets includes content related to the interests of the user and differs from the first subset of content assets, wherein the trained machine learning model is trained to weight content asset subset generation based on the target banner template, including at least the second subset of content assets being selected by the user at a frequency above a threshold value;
generating, based on the trained machine learning model, a third call to the content recommendation system for a third subset of content assets for the target banner template, wherein the third subset of content assets includes content selections unrelated to the interests of the user and absent from either the first subset or the second subset of content assets;
upon receiving the first subset of content assets, the second subset of content assets, and the third subset of content assets, selecting, based on an affinity of the user for selection of the content assets, a collective set of the content assets drawn from each of the first subset of content assets, the second subset of content assets, and the third subset of content assets;
randomly selecting at least a content asset from the collective set of the content assets;
receiving, at a media device, the content asset;
stitching the content asset into the target banner template to form a composite banner; and
rendering the composite banner on a display of the media device.