US 12,259,947 B2
Generating a selectable suggestion using a provisional machine learning model when use of a default suggestion model is inconsequential
Keun Soo Yim, San Jose, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Appl. No. 17/252,218
Filed by Google LLC, Mountain View, CA (US)
PCT Filed May 29, 2020, PCT No. PCT/US2020/035290
§ 371(c)(1), (2) Date Dec. 14, 2020,
PCT Pub. No. WO2021/242257, PCT Pub. Date Dec. 2, 2021.
Prior Publication US 2022/0147775 A1, May 12, 2022
Int. Cl. G06F 18/21 (2023.01); G06N 20/20 (2019.01); H04L 51/02 (2022.01); H04L 51/046 (2022.01)
CPC G06F 18/2178 (2023.01) [G06N 20/20 (2019.01); H04L 51/02 (2013.01); H04L 51/046 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method implemented by one or more processors, the method comprising:
receiving a request to generate suggestion data using application content, wherein the application content is generated by an application that is accessible via a computing device;
processing, at the computing device and in response to receiving the request, the application content using a first suggestion model to generate the suggestion data,
wherein the first suggestion model is stored at the computing device;
determining, based on processing the application content, whether the suggestion data is insufficient for rendering at an interface of the computing device; and
when the suggestion data is determined to be insufficient for rendering at the interface of the computing device:
causing the application content to be processed, at a remote computing device and using a second suggestion model stored at the remote computing device, in furtherance of generating additional suggestion data,
wherein the first suggestion model is assigned as a default suggestion model with respect to generating selectable suggestions associated with the application,
determining that the additional suggestion data is sufficient for rendering at the interface of the computing device, and
causing the computing device to render one or more selectable suggestions that are based on the additional suggestion data;
providing feedback data that characterizes an interaction between a user and the one or more selectable suggestions that are based on the additional suggestion data;
subsequent to providing feedback data that characterizes the interaction between the user and the one or more selectable suggestions that are based on the additional suggestion data:
receiving, at the computing device and based on providing the feedback data, the second suggestion model,
wherein receiving the second suggestion model at the computing device causes the second suggestion model to be stored at the computing device and used, at the computing device, as the default suggestion model instead of the first suggestion model.