The apparatus for generating a learned model, the apparatus for checking the learned model, the method for generating a learned model, the program for using the learned model, the method for checking the learned model, and the program for checking the learned model.

Abstract

This invention improves the reliability of electronic component inspection. The learned model generation device 3 generates a learned model 35 represented by the sum of the following two models: a first model f(Rdc4,Rdc2) that uses the first measured value Rdc4 of the DC resistance of the DUT using the 4-terminal method and the second measured value Rdc2 of the DC resistance of the DUT using the 2-terminal method as explanatory variables and the value of the resistance component caused by the measurement system using the 2-terminal method as the target variable; and a second model g(Ls) that uses the fourth measured value Ls of the inductance of the DUT using the 2-terminal method as explanatory variables and the value of the resistance component caused by the DUT as the target variable. The learned model generation device 3 generates a second model by performing machine learning on the fourth measurement Ls of the DUT where the difference between the first measurement Rdc4 and the second measurement Rdc2 is less than the threshold value Rdth, and generates a first model by performing machine learning on the first measurement Rdc4 and the second measurement Rdc2 of the DUT where the difference is greater than the threshold value Rdth.

Images