US 12,236,322 B2
Training and/or utilizing a model for predicting measures reflecting both quality and popularity of content
Spurthi Amba Hombaiah, San Jose, CA (US); Vladimir Ofitserov, Foster City, CA (US); Mike Bendersky, Sunnyvale, CA (US); and Marc Alexander Najork, Palo Alto, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by GOOGLE LLC, Mountain View, CA (US)
Filed on Dec. 5, 2022, as Appl. No. 18/074,774.
Application 18/074,774 is a continuation of application No. 16/946,779, filed on Jul. 6, 2020, granted, now 11,551,150.
Prior Publication US 2023/0094198 A1, Mar. 30, 2023
Int. Cl. G06N 20/00 (2019.01); G06F 16/9038 (2019.01); G06N 5/04 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 16/9038 (2019.01); G06N 5/04 (2013.01)] 19 Claims
OG exemplary drawing
 
10. A method implemented by one or more processors, the method comprising:
for each of a plurality of user accounts:
identifying a plurality of corresponding values for defined features, wherein the corresponding values are specific to the user account;
processing the corresponding values, using a trained model, to generate a corresponding predicted measure for the user account; and
assigning, in one or more non-transitory computer readable media, an association of the corresponding predicted measure to the user account;
subsequent to assigning the associations of the corresponding predicted measures to the user accounts:
determining, using the corresponding predicted measures, to, for at least a given query, render a given content item, generated by a given user account, that is responsive to the one or more queries,
wherein determining to render the given content item is based on the corresponding predicted measure, for the given user account, satisfying a threshold; and
in response to determining to render the given content item:
causing rendering of the given content item responsive to the given query;
determining, using the corresponding predicted measures, to, for an additional given query, render an additional given content item, generated by the given user account, that is responsive to the additional given query,
wherein determining to render the additional given content item is based on the corresponding predicted measure, for the given user account, satisfying a threshold; and
in response to determining to render the additional given content item:
causing rendering of the additional given content item responsive to the additional given query.