US 12,452,472 B2
Systems and methods for predicting television viewership patterns for advanced consumer segments
Diana Saafi, Silver Spring, MD (US)
Assigned to DISCOVERY COMMUNICATIONS, LLC, Silver Spring, MD (US)
Filed by DISCOVERY COMMUNICATIONS, LLC, Silver Spring, MD (US)
Filed on Apr. 5, 2024, as Appl. No. 18/628,055.
Application 18/628,055 is a continuation of application No. 17/540,932, filed on Dec. 2, 2021, granted, now 11,979,623.
Claims priority of provisional application 63/120,468, filed on Dec. 2, 2020.
Prior Publication US 2024/0251118 A1, Jul. 25, 2024
Int. Cl. H04N 21/258 (2011.01); H04N 21/25 (2011.01); H04N 21/81 (2011.01)
CPC H04N 21/25883 (2013.01) [H04N 21/252 (2013.01); H04N 21/25891 (2013.01); H04N 21/812 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method for training a machine-learning model to predict television viewership, the computer-implemented method comprising:
receiving, by one or more processors, one or more historical viewership training profiles;
transforming, by the one or more processors, the one or more historical viewership training profiles to generate one or more multi-dimensional arrays;
training, by the one or more processors, a model based on the one or more multi-dimensional arrays to predict a viewership level forecast for each of one or more training profiles, wherein the training the model is based on one or more expected television viewership levels;
applying, by the one or more processors, the trained model to a second plurality of runtime television viewership profiles to generate a set of predicted runtime viewership characteristics for each of the second plurality of runtime television viewership profiles; and
storing, by the one or more processors, the set of predicted runtime viewership characteristics in one or more data stores.