Information processing device, recording medium, and process condition search method

Patent metadata

Field	Value
Publication number	US-12253838-B2
Application number	US-202217584712-A
Country	US
Kind code	B2
Filing date	Jan 26, 2022
Priority date	Feb 4, 2021
Publication date	Mar 18, 2025
Grant date	Mar 18, 2025

Abstract

An information processing device includes: a machine learning model selection part configured to select a machine learning model appropriate for a data set used for learning of the machine learning model; a calculation part configured to perform an optimization calculation by using the selected machine learning model to calculate process conditions that can achieve a target process result, predicted values of a process result corresponding to each of the process conditions, and reliability of the predicted values; a process condition selection part configured to select, among the process conditions that can achieve the target process result, one or more process conditions according to the predicted values of the process result and the reliability of the predicted values; and a display controller configured to display the selected process conditions, the predicted values of the process result corresponding to each of the selected process conditions, and the reliability of the predicted values.

First claim

What is claimed is:

1. A system comprising:
an analysis server, which creates a machine learning model of a semiconductor manufacturing device executing a process according to a process condition and searches for a process condition that can achieve a target process result by using the machine learning model, the analysis server comprising:
a machine learning model selector configured to select a machine learning model among a plurality of machine learning models created by using a plurality of regression methods;
a calculator configured to perform an optimization calculation by using the selected machine learning model to calculate a plurality of process conditions that can achieve the target process result, predicted values of a process result corresponding to each of the plurality of process conditions, and reliability of the predicted values;
a process condition selector configured to select, among the plurality of the process conditions that can achieve the target process result, one or more process conditions according to the predicted values of the process result and the reliability of the predicted values; and
a display controller configured to display the selected process conditions, the predicted values of the process result corresponding to each of the selected process conditions, and the reliability of the predicted values,
wherein the process condition selector is further configured to select the one or more process conditions among the plurality of process conditions that can achieve the target process result, based on priorities assigned to a plurality of target values included in the target process result, priorities assigned to a plurality of adjustment targets, which is included in the process conditions and to be adjusted in order to achieve the target process result, and achievement levels of the predicted values with respect to the target values of the process result; and

a device controller configured to:
control the semiconductor manufacturing device to execute the process according to each of the selected process conditions.

2. The system of claim 1 , the analysis server further comprising a determination part configured to determine whether to continue or terminate a process condition search based on a comparison result between actually measured values of a process result obtained by executing the process by the semiconductor manufacturing device according to each of the selected process conditions and target values of the process result.

3. The system of claim 2 , the analysis server further comprising a feedback part configured to feed back the selected process conditions and the actually measured values of the process result obtained by executing the process by the semiconductor manufacturing device according to each of the selected process conditions to the machine learning model selector.

4. The system of claim 1 , wherein the display controller is further configured to display an input field for inputting the priorities assigned to the target values, an input field for inputting the priorities assigned to the plurality of adjustment targets, and the machine learning model to be used, and to display a screen for receiving a change in the machine learning model to be used.

5. The system of claim 1 , the analysis server further comprising a feedback part configured to feed back the selected process conditions and actually measured values of the process result obtained by executing the process by the semiconductor manufacturing device according to each of the selected process conditions to the machine learning model selector.

6. At least one non-transitory computer-readable storage medium storing a first program that causes an analysis server, which creates a machine learning model of a semiconductor manufacturing device executing a process according to a process condition and searches for a process condition that can achieve a target process result by using the machine learning model, to execute:
selecting a machine learning model among a plurality of machine learning models created by using a plurality of regression methods;
performing an optimization calculation by using the selected machine learning model to calculate a plurality of process conditions that can achieve the target process result, predicted values of a process result corresponding to each of the plurality of process conditions, and reliability of the predicted values;
selecting, among the plurality of the process conditions that can achieve the target process result, one or more process conditions according to the predicted values of the process result and the reliability of the predicted values; and
displaying the selected process conditions, the predicted values of the process result corresponding to each of the selected process conditions, and the reliability of the predicted values,
wherein the selecting the one or more process conditions includes selecting the one or more process conditions among the plurality of process conditions that can achieve the target process result, based on priorities assigned to a plurality of target values included in the target process result, priorities assigned to a plurality of adjustment targets, which is included in the process conditions and to be adjusted in order to achieve the target process result, and achievement levels of the predicted values with respect to the target values of the process result,
and a second program that causes a device controller to execute:
controlling the semiconductor manufacturing device to execute the process according to each of the selected process conditions.

7. A process condition search method for an analysis server, which creates a machine learning model of a semiconductor manufacturing device executing a process according to a process condition and searches for a process condition that can achieve a target process result by using the machine learning model, the process condition search method comprising:
selecting a machine learning model among a plurality of machine learning models created by using a plurality of regression methods;
performing an optimization calculation by using the selected machine learning model to calculate a plurality of process conditions that can achieve the target process result, predicted values of a process result corresponding to each of the plurality of process conditions, and reliability of the predicted values;
selecting, among the plurality of the process conditions that can achieve the target process result, one or more process conditions according to the predicted values of the process result and the reliability of the predicted values;
displaying the selected process conditions, the predicted values of the process result corresponding to each of the selected process conditions, and the reliability of the predicted values,
wherein the selecting the one or more process conditions includes selecting the one or more process conditions among the plurality of process conditions that can achieve the target process result, based on priorities assigned to a plurality of target values included in the target process result, priorities assigned to a plurality of adjustment targets, which is included in the process conditions and to be adjusted in order to achieve the target process result, and achievement levels of the predicted values with respect to the target values of the process result; and,
causing the semiconductor manufacturing device to execute the process according to the selected process conditions.

Assignees

• Tokyo Electron Ltd

Inventors

• Noda Yuto
• Yamazaki Shota
• Takenaga Yuichi
• Fukumoto Toshiyuki

Classifications

• H10P72/0604

  Process monitoring, e.g. flow or thickness monitoring · CPC title

• G05B13/0265 Primary

  the criterion being a learning criterion · CPC title

• G05B23/0235

  based on a comparison with predetermined threshold or range, e.g. "classical methods", carried out during normal operation; threshold adaptation or choice; when or how to compare with the threshold · CPC title

• G05B23/0262

  Confirmation of fault detection, e.g. extra checks to confirm that a failure has indeed occurred · CPC title

• G06F2119/02

  Reliability analysis or reliability optimisation; Failure analysis, e.g. worst case scenario performance, failure mode and effects analysis [FMEA] · CPC title