US 12,223,523 B2
Methods, systems, and media for timing presentation of content
Chetan Pitambar Bhole, San Mateo, CA (US); Tanmay Khirwadkar, San Francisco, CA (US); Deepak Ramamurthi Sivaramapuram Chandrasekaran, San Jose, CA (US); and Sanjay Mangla, San Francisco, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Jan. 13, 2023, as Appl. No. 18/096,738.
Application 18/096,738 is a continuation of application No. 16/814,352, filed on Mar. 10, 2020, granted, now 11,556,953.
Prior Publication US 2023/0153855 A1, May 18, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06Q 30/00 (2023.01); G06Q 30/0207 (2023.01); H04N 21/234 (2011.01); G05B 19/418 (2006.01); G06N 20/00 (2019.01)
CPC G06Q 30/0239 (2013.01) [H04N 21/23424 (2013.01); G06N 20/00 (2019.01)] 21 Claims
OG exemplary drawing
 
1. A method for timing presentation of content, the method comprising:
identifying, using a server that includes a hardware processor and a communication interface, selectable content for a video sharing service that is to be presented to a user using a user device;
determining, using the hardware processor, a time window during which a feature associated with the selectable content is available to the user;
streaming, using the communication interface and through a communication network that connects the server to the user device, a first content item to the user device;
determining, using the hardware processor, a probability that the user will select the selectable content if the selectable content is presented at a first time point within the time window and during the streaming of the first content item using a trained model that generates, based on training samples for a same type of time window as the time window, an output of the probability that the user will select the selectable content if the selectable content is presented at the first time point within the time window and during the streaming of the first content item;
determining, using the hardware processor, whether to transmit, via the communication interface and through the communication network, the selectable content at the first time point based on at least on the probability determined using the trained model; and
in response to determining that the selectable content is not to be presented at the first time point based on at least the probability determined using the trained model, transmitting, via the communication interface and through the communication network, the selectable content to the user device for presentation on the user device at a second time point in connection with streaming, using the communication interface and through the communication network, a second content item to the user device, wherein the second time point is within the time window and after the first time point and during the streaming of the second content item.