US 12,335,218 B2
Machine-learning notification service
Imran Akbar, Allen, TX (US); Gaurav Chakravorty, Fremont, CA (US); Ravi Mandliya, Issaquah, WA (US); and Risa Pesavento, Sunnyvale, CA (US)
Assigned to DISCORD INC., San Francisco, CA (US)
Filed by DISCORD INC., San Francisco, CA (US)
Filed on Sep. 26, 2022, as Appl. No. 17/935,432.
Claims priority of provisional application 63/397,705, filed on Aug. 12, 2022.
Claims priority of provisional application 63/408,023, filed on Sep. 19, 2022.
Prior Publication US 2024/0056410 A1, Feb. 15, 2024
Int. Cl. H04L 51/224 (2022.01); G06F 9/54 (2006.01); G06Q 50/00 (2012.01)
CPC H04L 51/224 (2022.05) [G06F 9/542 (2013.01); G06Q 50/01 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method including:
running a smart notification generator periodically that reviews what past notifications have been sent in a server that supports near real-time communications;
sending, by the smart notification generator to a smart notification service with a machine-learning model, first notification data based on the review;
determining to immediately send a push notification to respective user accounts based on the first notification data;
sending, by a first smart channel module at a first time, a subset of the first notification data to an asynchronous channel that stores notification data at a data store and queued for a later dispatch; and
training the machine-learning model based on characteristics of a user interaction with the immediately sent notification.