# US 2023/0055892 A1 · Data processing apparatus, data processing method, and storage medium storing program

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

- Number: US 2023/0055892 A1
- Document ID: US20230055892A1
- Status: Published application
- Kind: A1
- Application number: 17/682,125
- Filed: 2022-02-28
- Published: 2023-02-23
- Earliest claimed: 2021-08-19
- Assignees: Kabushiki Kaisha Toshiba
- Applicants: Kabushiki Kaisha Toshiba
- Inventors: Wataru WATANABE; Takayuki ITOH; Jumpei ANDO; Keisuke KAWAUCHI; Toshiyuki ONO
- Web page: https://patentgrep.com/patent/US20230055892A1

## CPC

- G05B 19/41875: {characterised by quality surveillance of production}
- G05B 23/0221: {Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods}
- G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks}
- G05B 23/0272: {Presentation of monitored results, e.g. selection of status reports to be displayed; Filtering information to the user}
- G06F 18/23: Clustering techniques
- G05B 2219/32201: Build statistical model of past normal proces, compare with actual process
- G05B 2219/32221: Correlation between defect and measured parameters to find origin of defect
- G05B 2219/32222: Fault, defect detection of origin of fault, defect of product
- Y02P 90/30: Computing systems specially adapted for manufacturing
- 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)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

A data processing apparatus includes a processor. The processor generates visualization data for displaying estimation results of manufacturing conditions based on estimation results and relationship data. The relationship data includes first relationship data as a relationship between first manufacturing conditions recorded during an analysis, and second relationship data as a relationship between second manufacturing conditions corresponding. The processor divides the estimation results of the manufacturing conditions into a first group based on the first relationship data, and into a second group based on the second relationship data. The processor generates the visualization data based on a change in manufacturing condition relationship between the first group and the second group.

## Claims

### Claim 1

A data processing apparatus comprising a processor including hardware and configured to generate visualization data for displaying estimation results of manufacturing conditions of a plurality of cause candidates for a specific status of a product to be analyzed, based on the estimation results and relationship data representing a relationship between the manufacturing conditions of the plurality of cause candidates, the relationship data including first relationship data as a relationship between a plurality of first manufacturing conditions as a plurality of manufacturing conditions of the product recorded during the analysis, and second relationship data as a relationship between a plurality of second manufacturing conditions corresponding to the first manufacturing conditions and different from the first manufacturing conditions,
wherein the processor divides the estimation results of the manufacturing conditions of the plurality of cause candidates into a first group based on the first relationship data, and into a second group based on the second relationship data, and
generates the visualization data based on a change in manufacturing condition relationship between the first group and the second group.

### Claim 2 (depends on 1)

The apparatus according to claim 1, wherein the processor divides the cause candidate manufacturing conditions belonging to the first group into large groups each including
a representative cause candidate manufacturing condition,
a first small group as a group of manufacturing conditions that have not changed a strength of the relationship with the second group including the representative cause candidate manufacturing condition,
a second small group as a group of manufacturing conditions that have increased the strength of the relationship with the second group including the representative cause candidate manufacturing condition,
a third small group as a group of manufacturing conditions that have decreased the strength of the relationship with the second group including the representative cause candidate manufacturing condition, and
generates the visualization data for each of the representative cause candidate manufacturing condition, the first small group, the second small group, and the third small group.

### Claim 3 (depends on 2)

The apparatus according to claim 2, wherein the processor generates the visualization data such that the display of the cause candidate manufacturing conditions belonging to the first small group, the cause candidate manufacturing conditions belonging to the second small group, and the cause candidate manufacturing conditions belonging to the third small group are omitted with respect to the display of the representative cause candidate manufacturing condition.

### Claim 4 (depends on 2)

The apparatus according to claim 2, wherein the processor generates the visualization data such that the cause candidate manufacturing conditions belonging to the second small group or the cause candidate manufacturing conditions belonging to the third small group are emphasized or made inconspicuous with respect to the display of the cause candidate manufacturing conditions belonging to the first small group.

### Claim 5 (depends on 2)

The apparatus according to claim 2, wherein the processor determines the representative cause candidate manufacturing condition based on one of a predetermined manufacturing condition, a manufacturing condition used in estimation of the cause candidate manufacturing condition and having a high index value, a first manufacturing condition in an order of manufacturing steps of the product, a first manufacturing condition in an order in a dictionary, and a manufacturing condition by which the number of conditions is maximum or minimum.

### Claim 6 (depends on 2)

The apparatus according to claim 2, wherein the processor determines the representative cause candidate manufacturing condition such that the number of cause candidate manufacturing conditions having changed a relationship strength between the first group and the second group decreases.

### Claim 7 (depends on 1)

The apparatus according to claim 1, wherein the processor generates the visualization data such that a drawing showing a relationship between the manufacturing conditions is included.

### Claim 8 (depends on 1)

The apparatus according to claim 1, wherein the processor displays, on a display, estimation results of manufacturing conditions of a plurality of cause candidates for a specific status of the product, based on the visualization data.

### Claim 9 (depends on 1)

The apparatus according to claim 1, wherein the processor further generates status data indicating a degree to which the product is in a specific status, from individual data indicating individual measurement values of the product.

### Claim 10 (depends on 1)

The apparatus according to claim 1, wherein the first relationship data and the second relationship data are index values representing a strength of a relationship between the manufacturing conditions.

### Claim 11 (depends on 1)

The apparatus according to claim 1, wherein
the first relationship data is data representing a first group to which the manufacturing condition belongs, and
the second relationship data is data representing a second group to which the manufacturing condition belongs.

### Claim 12 (depends on 1)

The apparatus according to claim 1, wherein the processor further calculates the first relationship data and the second relationship data based on manufacturing data as data of the manufacturing condition.

### Claim 13 (depends on 12)

The apparatus according to claim 12, wherein the processor generates the first relationship data and the second relationship data by dividing the manufacturing condition into a plurality of clusters based on the manufacturing data.

### Claim 14

A data processing method comprising:
dividing estimation results of manufacturing conditions of a plurality of cause candidates for a specific status of a product to be analyzed into a first group based on first relationship data as a relationship between a plurality of first manufacturing conditions as a plurality of manufacturing conditions of the product recorded during the analysis;
dividing the estimation results of the manufacturing conditions of the plurality of cause candidates into a second group based on second relationship data as a relationship between a plurality of second manufacturing conditions corresponding to the first manufacturing conditions and different from the first manufacturing conditions; and
generating visualization data for displaying the estimation results based on a change in manufacturing condition relationship between the first group and the second group.

### Claim 15

A non-transitory storage medium storing a computer-readable data processing program for causing a computer to execute:
dividing estimation results of manufacturing conditions of a plurality of cause candidates for a specific status of a product to be analyzed into a first group based on first relationship data as a relationship between a plurality of first manufacturing conditions as a plurality of manufacturing conditions of the product recorded during the analysis;
dividing the estimation results of the manufacturing conditions of the plurality of cause candidates into a second group based on second relationship data as a relationship between a plurality of second manufacturing conditions corresponding to the first manufacturing conditions and different from the first manufacturing conditions; and
generating visualization data for displaying the estimation results based on a change in manufacturing condition relationship between the first group and the second group.
