# US 2025/0164975 A1 · Information processing method, recording medium, and information processing apparatus

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

- Number: US 2025/0164975 A1
- Document ID: US20250164975A1
- Status: Published application
- Kind: A1
- Application number: 19/034,684
- Filed: 2025-01-23
- Published: 2025-05-22
- Earliest claimed: 2022-07-25
- Assignees: Tokyo Electron Limited
- Applicants: Tokyo Electron Limited
- Inventors: Masaki KITSUNEZUKA; Keiichi TAKAHASHI
- Web page: https://patentgrep.com/patent/US20250164975A1

## CPC

- G05B 19/4184: {characterised by fault tolerance, reliability of production system}
- G05B 23/02: Electric testing or monitoring
- G06N 3/02: Neural networks
- H10P 95/00: Generic processes or apparatus for manufacture or treatments not covered by the other groups of this subclass
- G05B 2219/45031: Manufacturing semiconductor wafers
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H10P: GENERIC PROCESSES OR APPARATUS FOR THE MANUFACTURE OR TREATMENT OF DEVICES COVERED BY CLASS H10

## Abstract

An information processing method includes, by an information processing apparatus: acquiring monitoring data which includes a plurality of items related to a state of each process performed by a target apparatus; generating a dimensional compression model for compressing the number of dimensions of the monitoring data; inputting the monitoring data into the dimensional compression model to convert the monitoring data into a low-dimensional representation; and outputting the monitoring data converted into the low-dimensional representation. In addition, the monitoring data may include a plurality of items classified into a plurality of categories, and the information processing apparatus may generate the dimensional compression model for each category, and may input the monitoring data into a dimensional compression model corresponding to each category to convert the monitoring data into a low-dimensional representation for each category.

## Claims

### Claim 1

An information processing method comprising, by an information processing apparatus:
acquiring monitoring data which includes a plurality of items related to a state of each process performed by a target apparatus;
generating a dimensional compression model for compressing the number of dimensions of the monitoring data;
inputting the monitoring data into the dimensional compression model to convert the monitoring data into a low-dimensional representation; and
outputting the monitoring data converted into the low-dimensional representation.

### Claim 2 (depends on 1)

The information processing method according to claim 1,
wherein the monitoring data includes a plurality of items classified into a plurality of categories, and
the information processing apparatus
generates the dimensional compression model for each category, and
inputs the monitoring data into a dimensional compression model corresponding to each category to convert the monitoring data into a low-dimensional representation for each category.

### Claim 3 (depends on 1)

The information processing method according to claim 1,
wherein the information processing apparatus
acquires the monitoring data about a plurality of the target apparatuses,
calculates a first distance of each monitoring data with respect to a monitoring data group of the plurality of target apparatuses,
calculates a second distance of each monitoring data with respect to a monitoring data group for each target apparatus, and
converts the monitoring data into a low-dimensional representation in which the first distance and the second distance are represented as dimensions.

### Claim 4 (depends on 3)

The information processing method according to claim 3,
wherein the information processing apparatus
calculates a first covariance matrix for the monitoring data group of the plurality of target apparatuses,
calculates a Mahalanobis distance of each monitoring data based on the first covariance matrix as the first distance,
calculates a second covariance matrix for the monitoring data group of each target apparatus, and
calculates a Mahalanobis distance of each monitoring data based on the second covariance matrix as the second distance.

### Claim 5 (depends on 3)

The information processing method according to claim 3,
wherein one or more monitoring data groups are selected based on the monitoring data converted into the low-dimensional representation,
a dimensional compression model for compressing the number of dimensions of the monitoring data included in the monitoring data group is generated for each selected monitoring data group,
the monitoring data is input into the dimensional compression model to convert the monitoring data into a low-dimensional representation, and
the monitoring data converted into the low-dimensional representation is output for each monitoring data group.

### Claim 6 (depends on 1)

The information processing method according to claim 1,
wherein the information processing apparatus
acquires monitoring data about a plurality of the target apparatuses,
converts the monitoring data about the plurality of target apparatuses into a low-dimensional representation,
selects one or more monitoring data groups based on the monitoring data converted into the low-dimensional representation,
converts the monitoring data into a low-dimensional representation for each selected monitoring data group, and
outputs the monitoring data for each monitoring data group converted into the low-dimensional representation.

### Claim 7 (depends on 1)

The information processing method according to claim 1,
wherein the information processing apparatus
acquires first label information related to a class classification assigned to the monitoring data,
selects a predetermined number of dimensions based on the first label information about the monitoring data converted into the low-dimensional representation by the dimensional compression model, and
outputs the monitoring data in the selected dimensions.

### Claim 8 (depends on 1)

The information processing method according to claim 1,
wherein the information processing apparatus
acquires first label information related to a class classification assigned to the monitoring data,
determines a reference for scale conversion based on the monitoring data classified into a predetermined class in the first label information,
performs scale conversion of the monitoring data of the predetermined class and a class other than the predetermined class based on the determined reference, and
generates the dimensional compression model based on the scale-converted monitoring data.

### Claim 9 (depends on 1)

The information processing method according to claim 1,
wherein the information processing apparatus
acquires first label information related to a class classification assigned to the monitoring data,
generates a self-encoder based on the monitoring data classified into a predetermined class in the first label information,
calculates a difference between an input and an output of the self-encoder when monitoring data of the predetermined class and a class other than the predetermined class is input into the self-encoder, and
generates the dimensional compression model for compressing the number of dimensions of the calculated difference.

### Claim 10 (depends on 1)

The information processing method according to claim 1,
wherein the information processing apparatus
assigns second label information to the monitoring data of the low-dimensional representation that has been output as data, and
generates a prediction model for predicting the second label information about an input of the monitoring data, based on the monitoring data to which the second label information is assigned.

### Claim 11 (depends on 10)

The information processing method according to claim 10,
wherein the information processing apparatus
calculates a degree of importance of a plurality of items included in the monitoring data based on the generated prediction model,
selects a predetermined number of items for the monitoring data based on the degree of importance, and
outputs the monitoring data for the selected item.

### Claim 12 (depends on 1)

The information processing method according to claim 1,
wherein the information processing apparatus
acquires time series data from the target apparatus,
divides the process performed by the target apparatus into a plurality of periods, and calculates statistical values in each period of the acquired time series data,
receives a selection of the period based on the calculated statistical values, and
stores the statistical values of the periods during which the selection is received, as the monitoring data.

### Claim 13 (depends on 10)

The information processing method according to claim 10,
wherein the process performed by the target apparatus includes any one of a substrate processing process, a substrate transfer process, a wafer-less dry cleaning process, a seasoning process, a plasma health check process, or a sensor automatic check process.

### Claim 14 (depends on 1)

The information processing method according to claim 1,
wherein the information processing apparatus outputs the monitoring data converted into the low-dimensional representation using a histogram, a box and whisker plot, a violin chart, a scattering diagram, a density contour diagram, or a heat map.

### Claim 15

An information processing method comprising, by an information processing apparatus:
acquiring monitoring data which includes a plurality of items related to a state of each process performed by an analysis target apparatus;
acquiring analysis information which includes monitoring data related to an analyzed apparatus or a dimensional compression model generated based on the monitoring data;
inputting the monitoring data of the acquired analysis target apparatus into the dimensional compression model generated based on the acquired monitoring data included in the analysis information or a dimensional compression model included in the analysis information, to convert the monitoring data into a low-dimensional representation; and
outputting the monitoring data converted into the low-dimensional representation.

### Claim 16 (depends on 15)

The information processing method according to claim 15,
wherein a presence or absence of the analysis information is determined,
a dimensional compression model for compressing the number of dimensions of the monitoring data is generated when it is determined that there is no analysis information,
the monitoring data is input into the dimensional compression model to convert the monitoring data into a low-dimensional representation; and
the monitoring data converted into the low-dimensional representation is output.

### Claim 17 (depends on 16)

The information processing method according to claim 16,
wherein the monitoring data and the dimensional compression model generated based on the monitoring data are stored as the analysis information.

### Claim 18 (depends on 17)

The information processing method according to claim 17,
wherein the monitoring data includes a plurality of items classified into a plurality of categories,
the dimensional compression model is generated for each category, and
the monitoring data is input into a dimensional compression model corresponding to each category to convert the monitoring data into a low-dimensional representation for each category.

### Claim 19 (depends on 15)

The information processing method according to claim 15,
wherein the analysis information includes statistics of the monitoring data related to the analyzed apparatus,
the statistics of the monitoring data of the analysis target apparatus are calculated, and
a state of the analysis target apparatus is determined based on a comparison between the statistics of the analyzed apparatus and the statistics of the analysis target apparatus.

### Claim 20 (depends on 19)

The information processing method according to claim 19,
wherein statistics related to a plurality of the apparatuses are calculated based on the monitoring data of the plurality of apparatuses, and
statistics related to each apparatus are calculated based on the monitoring data of each apparatus.

### Claim 21 (depends on 19)

The information processing method according to claim 19,
wherein the apparatus includes a plurality of sensors for acquiring the monitoring data,
statistics related to the plurality of sensors are calculated based on the monitoring data of the plurality of sensors, and
statistics related to each sensor are calculated based on the monitoring data of each sensor.

### Claim 22 (depends on 21)

The information processing method according to claim 21,
wherein a distance of each monitoring data with respect to a monitoring data group of the plurality of sensors is calculated, and
statistics related to the calculated distance are calculated.

### Claim 23 (depends on 15)

The information processing method according to claim 15,
wherein the monitoring data of the analysis target apparatus converted into the low-dimensional representation and the monitoring data of the analyzed apparatus converted into the low-dimensional representation are output together.

### Claim 24

A non-transitory recording medium in which a computer program is recorded, the computer program for causing a computer to perform a process comprising:
acquiring monitoring data which includes a plurality of items related to a state of each process performed by a target apparatus;
generating a dimensional compression model for compressing the number of dimensions of the monitoring data;
inputting the monitoring data into the dimensional compression model to convert the monitoring data into a low-dimensional representation; and
outputting the monitoring data converted into the low-dimensional representation.

### Claim 25

A non-transitory recording medium in which a computer program is recorded, the computer program for causing a computer to perform a process comprising:
acquiring monitoring data which includes a plurality of items related to a state of each process performed by an analysis target apparatus;
acquiring analysis information which includes monitoring data related to an analyzed apparatus or a dimensional compression model generated based on the monitoring data;
inputting the monitoring data of the acquired analysis target apparatus into the dimensional compression model generated based on the acquired monitoring data included in the analysis information or a dimensional compression model included in the analysis information, to convert the monitoring data into a low-dimensional representation; and
outputting the monitoring data converted into the low-dimensional representation.

### Claim 26

An information processing apparatus comprising:
an acquirer configured to acquire monitoring data which includes a plurality of items related to a state of each process performed by a target apparatus;
a generator configured to generate a dimensional compression model for compressing the number of dimensions of the monitoring data;
a converter configured to input the monitoring data into the dimensional compression model to convert the monitoring data into a low-dimensional representation; and
an outputter configured to output the monitoring data converted into the low-dimensional representation.

### Claim 27

An information processing apparatus comprising:
a monitoring data acquirer configured to acquire monitoring data which includes a plurality of items related to a state of each process performed by an analysis target apparatus;
an analysis information acquirer configured to acquire analysis information which includes monitoring data related to an analyzed apparatus or a dimensional compression model generated based on the monitoring data;
a converter configured to input the monitoring data of the acquired analysis target apparatus into the dimensional compression model generated based on the acquired monitoring data included in the analysis information or a dimensional compression model included in the analysis information, to convert the monitoring data into a low-dimensional representation; and
an outputter configured to output the monitoring data converted into the low-dimensional representation.
