US 11,782,915 B2
Searchable index
Jeremiah Harmsen, Zurich (CH); Tushar Deepak Chandra, Los Altos, CA (US); and Marcus Fontoura, Bellevue, WA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Nov. 30, 2020, as Appl. No. 17/107,790.
Application 17/107,790 is a continuation of application No. 16/366,260, filed on Mar. 27, 2019, granted, now 10,853,360.
Application 16/366,260 is a continuation of application No. 14/268,049, filed on May 2, 2014, granted, now 10,255,319, issued on Apr. 9, 2019.
Prior Publication US 2021/0149890 A1, May 20, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 16/24 (2019.01); G06F 16/245 (2019.01); G06N 20/00 (2019.01); G06F 16/22 (2019.01); G06N 5/025 (2023.01); G06F 16/31 (2019.01)
CPC G06F 16/245 (2019.01) [G06F 16/2228 (2019.01); G06F 16/319 (2019.01); G06N 5/025 (2013.01); G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
before receiving a subsequent model input that is associated with at least one or more features:
generating, using a machine learning model, data indicating a predicted model output for a model input that is associated with the one or more features, wherein the predicted model output is generated by the predictive model based at least on the one or more features; and
storing, in a record entry of a database for an index, data that associates the one or more features with the data indicating the predicted model output generated by the predictive model;
receiving the subsequent model input that is associated with at least the one or more features;
in response to receiving the subsequent model input:
accessing the record entry of the database for the index to identify the predicted model output that was previously generated by the predictive model based at least on the one or more features associated with the subsequent model input; and
providing data corresponding to the predicted model output in response to the subsequent model input.