| CPC G06Q 10/04 (2013.01) [G06N 5/022 (2013.01); G06Q 10/06395 (2013.01); G16C 60/00 (2019.02)] | 12 Claims |

|
1. An information processing apparatus that predicts a quality of a product obtained by a process including one or more pieces of processing, through each piece of processing an object to be processed becoming a processed object, the apparatus comprising:
at least one processor configured to
acquire, in at least one piece of processing of the process, at least one piece of chemical information of the object to be processed before the processing as well as at least one piece of chemical information of the processed object after the processing, acquire a calculation value of a difference between numerical values that are obtained from the at least one piece of chemical information of the object to be processed before the processing and the at least one piece of chemical information of the processed object after the processing, and
set the difference as an explanatory variable, set the quality of the product as an objective variable, and predict the quality of the product based on the calculation value by using a trained model obtained by performing machine learning based on a known data set of the explanatory variable and the objective variable,
wherein the trained model is trained based on a quality of the product produced by a flow processing device that has at least one processing unit corresponding to each of the at least one piece of processing and a difference for learning that is a first difference between numerical values that are obtained from the at least one piece of chemical information obtained from the object to be processed before the processing performed in each of the at least one processing unit and at least one piece of chemical information obtained from the processed object after the process performed in each of the at least one processing unit, and
the prediction of the quality of the product is used for searching for a processing condition of the flow processing device.
|