Information processing apparatus, information processing method, nontransitory computer readable media storing program, and X-ray analysis apparatus
AssigneeRigaku Corporation
InventorsAkihiro Himeda, Takumi Ohta
Life of this patent
Estimating the term…
Abstract
According to an aspect of the present invention, provided is an information processing apparatus comprising a memory configured to store a program; and a processor configured to execute a program so as to output a parameter result in relation to a thin film by inputting a profile result in relation to an intensity of X-ray from the thin film to a neural network, wherein the neural network is a neural network that is allowed to machine-learn teacher data using profile data in relation to an intensity of X-ray from a thin film as input data and using parameter data in relation to the thin film as output data.
Claims10
An information processing apparatus comprising:
- an X-ray analysis apparatus including an X-ray source and a detector;
- and
- a processor,
- wherein the X-ray source irradiates a thin film with X-rays,
- wherein the detector detects a reflected intensity of X-rays from the thin film,
- wherein the processor is configured to execute a program so as to output a parameter result in relation to a thin film by inputting, to a neural network, a profile result in relation to a reflected intensity of X-rays from the thin film in a reflectance measurement using the X-ray analysis apparatus, the profile result being generated based on the detected reflected intensity of X-rays,
- wherein the neural network is a neural network that has been trained through machine learning based on teacher data using profile data in relation to a reflected intensity of X-ray from a thin film as input data and using parameter data in relation to the thin film as output data,
- wherein the parameter data and the parameter result are information in relation to at least one of film thickness, density, and roughness of a thin film, and
- wherein the parameter result is initial value information located within a parameter region enclosed by an ellipse formed around a correct solution parameter,
- wherein the processor is further configured to
- execute the program so as to obtain the correct solution parameter by optimizing the initial value information, and
- output the parameter result as an analysis result of a physical property of the thin film.
An information processing method executed by an information processing apparatus, comprising:
- outputting a parameter result by inputting, to a neural network, a profile result in relation to a reflected intensity of X-ray from a thin film in a reflectance measurement using an X-ray analysis apparatus including an X-ray source irradiating the thin film with X-rays and a detector detecting the reflected intensity of the X-rays from the thing film, the profile result being generated based on the detected reflected intensity of X-rays,
- wherein the neural network is a neural network that has been trained through machine learning based on teacher data using profile data in relation to a reflected intensity of X-ray from a thin film as input data and using parameter data in relation to the thin film as output data,
- wherein the parameter data and the parameter result are information in relation to at least one of film thickness, density, and roughness of a thin film,
- wherein the parameter result is initial value information located within a parameter region enclosed by an ellipse formed around a correct solution parameter;
- executing the program so as to obtain the correct solution parameter by optimizing the initial value information;
- and
- outputting the parameter result as an analysis result of a physical property of the thin film.
Dependencies are inferred from the claim text.