# US 12,223,236 B2 · Information processing apparatus, information processing method, and non-transitory computer readable medium

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

- Number: US 12,223,236 B2
- Document ID: US12223236B2
- Status: Granted
- Kind: B2
- Application number: 17/193,546
- Filed: 2021-03-05
- Published: 2022-03-03
- Granted: 2025-02-11
- Earliest claimed: 2020-08-31
- Assignees: Kaisha Toshiba; Kioxia Corporation
- Applicants: Kabushiki Kaisha Toshiba; Kioxia Corporation
- Inventors: Daiki Kiribuchi; Satoru Yokota; Soh Koike; Tadayoshi Uechi
- Web page: https://patentgrep.com/patent/US12223236B2

## CPC

- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202)
- G06Q 50/04: Manufacturing
- G06F 2111/08: Probabilistic or stochastic CAD
- G06F 2111/10: Numerical modelling
- Y02P 90/30: Computing systems specially adapted for manufacturing
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- Y02P: CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS

## Abstract

An information processing apparatus according to an embodiment of the present invention includes an estimator and a recommender. The estimator is configured to, based on a data set including a set value set for a parameter and an evaluation value or an evaluation value variation where the set value is set for the parameter, estimate a relationship between the set value and the evaluation value variation. The evaluation value variation indicates a variation of respective evaluation values where a plurality of values included within a neighborhood range that is based on the set value are set for the parameter. The recommender is configured to, based on the estimated relationship, determine a recommended set value.

## Claims

### Claim 1

An information processing apparatus comprising:
a processing circuitry configured to acquire data based on a data set including
a plurality of first pairs each including both a set value and an evaluation value, the set value being a value set for a parameter of a system in operation or a product to be manufactured and the evaluation value being a value obtained by evaluating a result of testing the system or the product where the set value is set for the parameter, or
a plurality of second pairs each including both the set value and an evaluation value variation obtained in a case where the set value is set for the parameter in the system or the product wherein the evaluation value variation indicates a variation of respective evaluation values obtained in a case where a plurality of values included within a neighborhood range of the set value are set for the parameter in the system or the product, the neighborhood range including a first range of values larger than or equal to the set value and a second range of values smaller than the set value;
estimate a first relationship expression expressing a relationship between the set value and the evaluation value variation or estimate a second relationship expression expressing a relationship between the set value and the evaluation value and a third relationship expression expressing a relationship between the evaluation value and the evaluation value variation; and
determine, based on the first relationship expression or a pair of the second relationship expression and the third relationship expression, a recommended set value which is a set value recommended to a user for the parameter in the system or the product;
an output circuitry configured to output the recommended set value visibly to the user,
wherein the processing circuitry further iterates processes until a termination condition is satisfied, the processes include acquiring an evaluation value by evaluating a result of testing the system or the product for which the recommended set value to the user is set to the parameter, updating the data set using the recommended set value and the acquired evaluation value, and estimating the first relationship equation or estimating the second relationship expression and the third relationship expression using the updated data set, and determining a recommended set value which is a set value recommended to the user, and
when the termination condition is satisfied, the processing circuitry selects an optimum set value to be set for the system or the product from among a plurality of set values that have been set for the parameter of the system or the product so far, based on the evaluation value variation corresponding to each of the plurality of set values, wherein the selected optimum set value is set to the system or the product.

### Claim 2 (depends on 1)

The information processing apparatus according to claim 1, wherein:
the processing circuitry calculates a mean and a variance of a probability distribution of the first relationship expression; and
the processing circuitry determines the recommended set value based on an acquisition function including the calculated mean and variance.

### Claim 3 (depends on 2)

The information processing apparatus according to claim 2, wherein the processing circuitry determines a set value that maximizes or minimizes a value of the acquisition function that is based on the calculated mean and variance, as the recommended set value.

### Claim 4 (depends on 1)

The information processing apparatus according to claim 1, wherein the optimum set value is the set value for which the evaluation value variation is minimized or the set value for which a predicted value of the evaluation value variation is smallest.

### Claim 5 (depends on 1)

The information processing apparatus according to claim 1, wherein the processing circuitry determines a difference between maximum and minimum evaluation values of evaluation values for values within a neighborhood range for the recommended set value, as the evaluation value variation for the recommended set value.

### Claim 6 (depends on 1)

The information processing apparatus according to claim 1, wherein:
the processing circuitry further estimates a fourth relationship expression expressing a relationship between the set value and a worst evaluation value of the respective evaluation values obtained in a case where the plurality of values included within the neighborhood range of the set value are set for the parameter; and
the processing circuitry determines the recommended set value based further on the fourth relationship expression.

### Claim 7 (depends on 4)

The information processing apparatus according to claim 4, wherein the output circuitry outputs the optimum set value.

### Claim 8 (depends on 7)

The information processing apparatus according to claim 7, wherein the output circuit outputs information including
values within a neighborhood range of the optimum set value and
a variation of evaluation values for the values.

### Claim 9 (depends on 7)

The information processing apparatus according to claim 7, wherein the output circuit outputs information indicating at least one of a minimum value and a maximum value among evaluation values obtained for values within a neighborhood range of the set value regarded as optimum.

### Claim 10

An information processing method comprising:
providing a data set including
a plurality of first pairs each including both a set value and an evaluation value, the set value being a value set for a parameter of a system in operation or a product to be manufactured and the evaluation value being a value obtained by evaluating a result of testing the system or the product where the set value is set for the parameter or
a plurality of second pairs each including both the set value and an evaluation value variation obtained in a case where the set value is set for the parameter in the system or the product wherein the evaluation value variation indicates a variation of respective evaluation values obtained in a case where a plurality of values included within a neighborhood range of the set value are set for the parameter in the system or the product, the neighborhood range including a first range of values larger than or equal to the set value and a second range of values smaller than the set value;
estimating a first relationship expression expressing a relationship between the set value and the evaluation value variation based on the data set, or estimate a second relationship expression expressing a relationship between the set value and the evaluation value and a third relationship expression expressing a relationship between the evaluation value and the evaluation value variation;
determining, based on the first relationship expression or a pair of the second relationship expression and the third relationship expression, a recommended set value which is a set value recommended to a user for the parameter in the system or the product; and
outputting the recommended set value visibly to the user,
the method further comprising
iterating processes until a termination condition is satisfied, the processes including
acquiring an evaluation value by evaluating a result of testing the system or the product for which the recommended set value to the user is set to the parameter,
updating the data set using the recommended set value and the acquired evaluation value, and
estimating the first relationship equation or estimating the second relationship expression and the third relationship expression using the updated data set, and
determining a recommended set value which is a set value recommended to the user, and
selecting, when the termination condition is satisfied, an optimum set value to be set for the system or the product from among a plurality of set values that have been set for the parameter of the system or the product so far, based on the evaluation value variation corresponding to each of the plurality of set values, wherein the selected optimum set value is set to the system or the product.

### Claim 11

A non-transitory computer readable medium storing a program that causes a computer to perform a method comprising:
reading, from a memory, a data set including
a plurality of first pairs each including both a set value and an evaluation value, the set value being a value set for a parameter of a system in operation or a product to be manufactured and the evaluation value being a value obtained by evaluating a result of testing the system or the product where the set value is set for the parameter or
a plurality of second pairs each including both the set value and an evaluation value variation obtained in a case where the set value is set for the parameter in the system or the product wherein the evaluation value variation indicates a variation of respective evaluation values obtained in a case where a plurality of values included within a neighborhood range of the set value are set for the parameter in the system or the product, the neighborhood range including a first range of values larger than or equal to the set value and a second range of values smaller than the set value;
estimating a first relationship expression expressing a relationship between the set value and the evaluation value variation based on the data set, or estimate a second relationship expression expressing a relationship between the set value and the evaluation value and a third relationship expression expressing a relationship between the evaluation value and the evaluation value variation;
determining, based on the first relationship expression or a pair of the second relationship expression and the third relationship expression, a recommended set value which is a set value recommended to a user for the parameter in the system or the product; and
outputting the recommended set value visibly to the user,
the method further comprising
iterating processes until a termination condition is satisfied, the processes including
acquiring an evaluation value by evaluating a result of testing the system or the product for which the recommended set value to the user is set to the parameter,
updating the data set using the recommended set value and the acquired evaluation value, and
estimating the first relationship equation or estimating the second relationship expression and the third relationship expression using the updated data set, and
determining a recommended set value which is a set value recommended to the user, and
selecting, when the termination condition is satisfied, an optimum set value to be set for the system or the product from among a plurality of set values that have been set for the parameter of the system or the product so far, based on the evaluation value variation corresponding to each of the plurality of set values, wherein the selected optimum set value is set to the system or the product.

### Claim 12 (depends on 1)

The information processing apparatus according to claim 1, wherein the termination condition is a condition based on a number of times the set value has been set to the parameter of the system or the product or an elapsed time.