A method for determining an optical constant of a material includes: acquiring ellipsometric parameters; obtaining a optical constant of the material corresponding to the ellipsometric parameters by a machine learning model; the machine learning model including a mapping relationship between the ellipsometric parameters and the material optical constant of the material corresponding to the ellipsometric parameters. The method uses the machine learning model to implement an automatic fitting of ellipsometric parameters. In the method, the optical constant of the material is calculated by a machine learning model, which no longer depends on the experiences of the experimenters, thereby reducing requirements for the operator, accelerating the fitting of the data curve when calculating the optical constants of the material and improving the operation efficiency.