US 12,443,892 B2
Information processing device, information processing method, and computer program product for estimating parameter of model for specified time parameter
Masaaki Takada, Abiko (JP); and Gen Li, Ota (JP)
Assigned to KABUSHIKI KAISHA TOSHIBA, Tokyo (JP)
Filed by KABUSHIKI KAISHA TOSHIBA, Tokyo (JP)
Filed on Feb. 23, 2022, as Appl. No. 17/652,123.
Claims priority of application No. 2021-091198 (JP), filed on May 31, 2021.
Prior Publication US 2022/0391777 A1, Dec. 8, 2022
Int. Cl. G06N 3/04 (2023.01); G06F 18/20 (2023.01); G06F 18/2134 (2023.01); G06N 3/045 (2023.01); G06N 20/20 (2019.01)
CPC G06N 20/20 (2019.01) [G06F 18/21345 (2023.01); G06F 18/285 (2023.01); G06N 3/045 (2023.01)] 13 Claims
OG exemplary drawing
 
1. An information processing device comprising:
one or more processors configured to:
receive input of a plurality of pieces of input data obtained during K time periods, K being an integer equal to or greater than two, the plurality of pieces of input data including one or more explanatory variables and one or more objective variables, the one or more explanatory variables and the one or more objective variables being variables related to a manufacturing process performed by a manufacturing plant that includes a semiconductor factory and a chemical plant;
create K first models, each of the K first models being a model that receives input of the one or more explanatory variables and outputs the one or more objective variables, each of the K first models being created for a corresponding period among the K time periods, by machine learning using a plurality of pieces of input data obtained during the corresponding period;
create a second model that receives input of a first time parameter and outputs a parameter of a third model that receives input of the one or more explanatory variables and outputs the one or more objective variables, the second model being created by machine learning using a plurality of parameters of the created K first models; and
estimate the parameter of the third model by inputting a specified second time parameter to the created second model.