US 11,678,001 B2
Modulating a quality of media content
Greg Garner, Springdale, AR (US); and David Stern, Los Gatos, CA (US)
Assigned to ROKU, INC., San Jose, CA (US)
Filed by Roku, Inc., San Jose, CA (US)
Filed on Jun. 23, 2020, as Appl. No. 16/909,222.
Prior Publication US 2021/0400325 A1, Dec. 23, 2021
Int. Cl. H04N 21/2662 (2011.01); H04N 21/24 (2011.01); H04N 21/258 (2011.01); G06N 20/00 (2019.01); H04N 21/25 (2011.01)
CPC H04N 21/2662 (2013.01) [G06N 20/00 (2019.01); H04N 21/2402 (2013.01); H04N 21/251 (2013.01); H04N 21/25841 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
collecting, by at least one server, usage data information from a plurality of locations, wherein at least a location of the plurality of locations includes a plurality of media playback devices accessible by one or more users and coupled to a network device located at the location that is further coupled to the at least one server through a network;
determining, by the at least one server, a data cap for each of the plurality of locations including the location based on a notification received through the network from the network device located at the location that is coupled to the plurality of media playback devices at the location;
training a machine learning model using multiple usage data information and data caps including the usage data information and the data cap received from each of the plurality of locations to associate the usage data information with one of the one or more users based on how the one of the one or more users handles a remote control device to control the plurality of media playback devices;
predicting, using the machine learning model, based on the usage data information associated with the one of the one or more users, whether the location is going to exceed its associated data cap; and
determining whether to modulate a quality of media content transmitted to the location based on the prediction.