# US 2024/0177064 A1 · Information processing apparatus, storage medium, and optimal solution search method

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2024/0177064 A1
- Document ID: US20240177064A1
- Status: Published application
- Kind: A1
- Application number: 18/521,112
- Filed: 2023-11-28
- Published: 2024-05-30
- Earliest claimed: 2022-11-29
- Assignees: Tokyo Electron Limited
- Applicants: Tokyo Electron Limited
- Inventors: Satoshi ITOH; Hitoshi YONEMICHI
- Web page: https://patentgrep.com/patent/US20240177064A1

## CPC

- G06N 20/00: Machine learning
- G03F 7/706841: {Machine learning}
- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G06N 5/04: Inference or reasoning models
- G06F 2119/18: Manufacturability analysis or optimisation for manufacturability
- H10P 72/0612: {Production flow monitoring, e.g. for increasing throughput}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G03F: PHOTOMECHANICAL PRODUCTION OF TEXTURED OR PATTERNED SURFACES, e.g. FOR PRINTING, FOR PROCESSING OF SEMICONDUCTOR DEVICES; MATERIALS THEREFOR; ORIGINALS THEREFOR; APPARATUS SPECIALLY ADAPTED THEREFOR; (phototypographic composing devices B41B; photosensitive materials or processes for photographic purposes G03C; electrophotography, sensitive layers or processes therefor G03G)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- H10P: GENERIC PROCESSES OR APPARATUS FOR THE MANUFACTURE OR TREATMENT OF DEVICES COVERED BY CLASS H10

## Abstract

An information processing apparatus includes: a learning trainer configured to train a machine learning model to train a relationship between a process condition and a processing result of a substrate processing apparatus that has executed a processing based on the process condition; an inferrer configured to infer a plurality of processing results depending on a plurality of process conditions using the trained machine learning model; a graph creator configured to plot the plurality of processing results inferred with the machine learning model on a graph with an achievement level for a plurality of target values of the plurality of processing results as a plurality of axes; and an information display configured to display, on the graph, information used by an operator to select an optimal solution for the process condition, based on the plot of the plurality of inferred processing results.

## Claims

### Claim 1

An information processing apparatus comprising:
a learning trainer configured to train a machine learning model to learn a relationship between a process condition and a processing result of a substrate processing apparatus that has executed a processing based on the process condition;
an inferrer configured to infer a plurality of processing results depending on a plurality of process conditions using the trained machine learning model;
a graph creator configured to plot the plurality of processing results inferred with the machine learning model on a graph with an achievement level for a plurality of target values of the plurality of processing results as a plurality of axes; and
an information display configured to display, on the graph, information used by an operator to select an optimal solution for the process condition, based on the plot of the plurality of inferred processing results.

### Claim 2 (depends on 1)

The information processing apparatus of claim 1, wherein the information display displays, on the graph, a limit of the substrate processing apparatus in terms of the achievement level for the plurality of target values of the plurality of processing results predicted based on the plot.

### Claim 3 (depends on 2)

The information processing apparatus of claim 2, wherein the information display displays, on the graph, information on the optimal solution which is selected based on the plot displayed on the graph and the limit of the substrate processing apparatus in terms of the achievement level for the plurality of target values of the plurality of processing results.

### Claim 4 (depends on 3)

The information processing apparatus of claim 3, wherein the learning trainer retrains the machine learning model to relearn a relationship between the process condition of the optimal solution and the processing result of the substrate processing apparatus when a distance in the graph between the processing result of the substrate processing apparatus that has executed the processing based on the process condition of the optimal solution and the processing result depending on the process condition of the optimal solution inferred with the trained machine learning model is not within a threshold, and
wherein the graph creator updates the plot of the graph with the plurality of processing results inferred with the retrained machine learning model.

### Claim 5 (depends on 3)

The information processing apparatus of claim 3, wherein the graph creator plots the plurality of processing results inferred with the machine learning model on the graph with values calculated from a plurality of measured values of a substrate processed by the substrate processing apparatus based on the process condition as axes.

### Claim 6 (depends on 3)

The information processing apparatus of claim 3, wherein the graph creator plots the plurality of processing results inferred with the machine learning model on the graph with an in-plane uniformity and an inter-plane uniformity of a substrate processed by the substrate processing apparatus based on the process condition as axes.

### Claim 7 (depends on 3)

The information processing apparatus of claim 3, wherein the substrate processing apparatus is of a batch type or single wafer type.

### Claim 8 (depends on 2)

The information processing apparatus of claim 2, wherein the learning trainer retrains the machine learning model to relearn a relationship between the process condition of the optimal solution and the processing result of the substrate processing apparatus when a distance in the graph between the processing result of the substrate processing apparatus that has executed the processing based on the process condition of the optimal solution and the processing result depending on the process condition of the optimal solution inferred with the trained machine learning model is not within a threshold, and
wherein the graph creator updates the plot of the graph with the plurality of processing results inferred with the retrained machine learning model.

### Claim 9 (depends on 2)

The information processing apparatus of claim 2, wherein the graph creator plots the plurality of processing results inferred with the machine learning model on the graph with values calculated from a plurality of measured values of a substrate processed by the substrate processing apparatus based on the process condition as axes.

### Claim 10 (depends on 2)

The information processing apparatus of claim 2, wherein the graph creator plots the plurality of processing results inferred with the machine learning model on the graph with an in-plane uniformity and an inter-plane uniformity of a substrate processed by the substrate processing apparatus based on the process condition as axes.

### Claim 11 (depends on 2)

The information processing apparatus of claim 2, wherein the substrate processing apparatus is of a batch type or single wafer type.

### Claim 12

A non-transitory computer-readable storage medium storing a program that causes an information processing apparatus to execute a process comprising:
training a machine learning model to learn a relationship between a process condition and a processing result of a substrate processing apparatus that has executed a processing based on the process condition;
inferring a plurality of processing results depending on a plurality of process conditions using the trained machine learning model;
plotting the plurality of processing results inferred with the machine learning model on a graph with an achievement level for a plurality of target values of the plurality of processing results as a plurality of axes; and
displaying, on the graph, information used by an operator to select an optimal solution for the process condition, based on the plot of the plurality of inferred processing results.

### Claim 13

An optimal solution search method executed by an information processing apparatus, the optimal solution search method comprising
training a machine learning model to learn a relationship between a process condition and a processing result of a substrate processing apparatus that has executed a processing based on the process condition;
inferring a plurality of processing results depending on a plurality of process conditions using the trained machine learning model;
plotting the plurality of processing results inferred with the machine learning model on a graph with an achievement level for a plurality of target values of the plurality of processing results as a plurality of axes; and
displaying, on the graph, information used by an operator to select an optimal solution for the process condition, based on the plot of the plurality of inferred processing results.
