US 12,443,681 B2
Processing execution system, processing execution method, and program
Chikara Hashimoto, Tokyo (JP)
Assigned to RAKUTEN GROUP, INC., Tokyo (JP)
Appl. No. 18/548,337
Filed by RAKUTEN GROUP, INC., Tokyo (JP)
PCT Filed Feb. 2, 2022, PCT No. PCT/JP2022/003988
§ 371(c)(1), (2) Date Aug. 30, 2023,
PCT Pub. No. WO2023/079769, PCT Pub. Date May 11, 2023.
Claims priority of application No. PCT/JP2021/040852 (WO), filed on Nov. 5, 2021.
Prior Publication US 2024/0143701 A1, May 2, 2024
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 7/00 (2006.01); G06F 16/00 (2019.01); G06F 16/2455 (2019.01); G06F 18/2415 (2023.01); G06F 40/30 (2020.01)
CPC G06F 18/2415 (2023.01) [G06F 16/2455 (2019.01); G06F 40/30 (2020.01)] 16 Claims
OG exemplary drawing
 
1. A processing execution system, comprising at least one processor configured to:
input first data into a first machine learning model and acquire first classification information as an output of the first machine learning model;
input second data into the first machine learning model and acquire second classification information related to a classification of the second data as an output of the first machine learning model;
wherein the first machine learning model has learned a relationship between the first data and the first classification information, which indicates an attribute of the first data;
estimate, based on a predetermined estimation method, a validity relating to a combination of the second data and the second classification information;
execute predetermined processing based on an estimation result for the validity;
wherein the predetermined estimation method comprises a method using a second model which has learned a relationship between a combination of third data and third classification information indicating an attribute of the third data and a validity of the combination,
wherein the at least one processor is configured to estimate the validity based on the second model;
wherein the first model is configured to learn a relationship between the first data and the first classification information,
wherein the first data and the first classification information have been acquired based on a first database including candidates for the first data and candidates for the first classification information, and
wherein the second model is configured to learn a relationship between the third data and the third classification information,
wherein the third data and the third classification information have been acquired based on a second database including candidates for the third data and candidates for the third classification information, the second database having been obtained from a point of view different from a point of view of the first database.