# US 2026/0289038 A1 · Information processing method 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 2026/0289038 A1
- Document ID: US20260289038A1
- Status: Published application
- Kind: A1
- Application number: 19/323,382
- Filed: 2025-09-09
- Published: 2026-09-24
- Earliest claimed: 2025-03-21
- Assignees: Kioxia Corporation
- Applicants: Kioxia Corporation
- Inventors: Tetsuro WATANABE
- Web page: https://patentgrep.com/patent/US20260289038A1

## CPC

- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- G06F 2111/06: Multi-objective optimisation, e.g. Pareto optimisation using simulated annealing [SA], ant colony algorithms or genetic algorithms [GA]
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

According to one embodiment, there is provided an information processing method causing an information processing apparatus to execute: generating multiple pieces of model information corresponding to multiple objective variables; generating acquisition function information using the multiple pieces of model information; and generating, based on the acquisition function information, explanatory variable information indicating an explanatory variable for optimization of the multiple objective variables, wherein generating the acquisition function information comprises: obtaining, for each of the multiple objective variables, an importance level of optimizing the objective variable; obtaining, for each of the multiple objective variables, a statistic of evaluations using the model information and an evaluation set for each range of values of the objective variable; and generating the acquisition function information by using the multiple importance levels of optimizing the objective variables and the multiple statistics of the evaluations.

## Claims

### Claim 1

An information processing method causing an information processing apparatus to execute:
generating multiple pieces of model information corresponding to multiple objective variables;
generating acquisition function information using the multiple pieces of model information; and
generating, based on the acquisition function information, explanatory variable information indicating an explanatory variable for optimization of the multiple objective variables,
wherein generating the acquisition function information comprises:
obtaining, for each of the multiple objective variables, an importance level of optimizing the objective variable;
obtaining, for each of the multiple objective variables, a statistic of evaluations using the model information and an evaluation set for each range of values of the objective variable; and
generating the acquisition function information by using the multiple importance levels of optimizing the objective variables and the multiple statistics of the evaluations.

### Claim 2 (depends on 1)

The information processing method according to claim 1, wherein
obtaining the importance level of optimizing the objective variable includes:
performing a pairwise comparison on importance of optimizing the objective variables; and
obtaining the importance level of optimizing the objective variable according to a result of the pairwise comparison, and
obtaining the statistic of the evaluations includes
obtaining, for each of the multiple objective variables, the statistic of the evaluations by using a probability distribution of the objective variable according to the model information and a criterion evaluation value for each range of the values of the objective variable.

### Claim 3 (depends on 2)

The information processing method according to claim 2, wherein
obtaining the statistic of the evaluations includes
obtaining, for each of the multiple objective variables, the probability distribution of the objective variable according to the model information.

### Claim 4 (depends on 2)

The information processing method according to claim 2, wherein
obtaining the importance level of optimizing the objective variable further includes
confirming a consistency index of the multiple importance levels obtained for the multiple objective variables, and
obtaining the statistic of the evaluations includes
obtaining, when the consistency index complies with a predetermined condition, the statistic of the evaluations for each of the multiple objective variables by using the model information and the evaluation set for each range of the values of the objective variable.

### Claim 5 (depends on 1)

The information processing method according to claim 1, wherein
generating the multiple pieces of model information corresponding to the multiple objective variables includes
generating the multiple pieces of model information each including a model that predicts a corresponding objective variable from the explanatory variable.

### Claim 6 (depends on 1)

The information processing method according to claim 1, wherein
generating the multiple pieces of model information corresponding to the multiple objective variables includes
generating model information capable of expressing a probability distribution of each corresponding objective variable.

### Claim 7 (depends on 1)

The information processing method according to claim 1, wherein
obtaining the statistic of the evaluations includes
performing, for each of the multiple objective variables, a product-sum operation of an integral value for each range of the values of the objective variable and a criterion evaluation value for each range of the values of the objective variable with respect to a probability distribution of the objective variable according to the model information, and obtaining the statistic of the evaluations.

### Claim 8 (depends on 1)

The information processing method according to claim 1, wherein
generating the acquisition function information includes
generating, for each of the multiple explanatory variable information serving as candidates for optimization of the multiple objective variables, the acquisition function information using the multiple importance levels of optimizing the objective variables and the multiple statistics of the evaluations.

### Claim 9 (depends on 1)

The information processing method according to claim 1, wherein
generating the acquisition function information includes
performing, for each of the multiple explanatory variable information serving as candidates for optimization of the multiple objective variables, a product-sum operation of the importance level of optimizing the objective variable and the statistic of the evaluations, and generating the acquisition function information.

### Claim 10 (depends on 1)

The information processing method according to claim 1, wherein
generating the explanatory variable information indicating the explanatory variable for optimization of the multiple objective variables includes
obtaining, based on the acquisition function information, an explanatory variable information that maximizes an acquisition function among multiple pieces of the explanatory variable information that indicate explanatory variables serving as candidates for optimization of the multiple objective variables, and generating the explanatory variable information that indicates the explanatory variable optimizing the multiple objective variables.

### Claim 11 (depends on 1)

The information processing method according to claim 1, wherein
the explanatory variable includes a manufacturing condition in design of a semiconductor process, and
the multiple objective variables include multiple process parameters.

### Claim 12 (depends on 1)

The information processing method according to claim 1, wherein
the explanatory variable includes an operation terminal condition of a semiconductor device, and
the multiple objective variables include multiple design parameters in design of the semiconductor device.

### Claim 13 (depends on 11)

The information processing method according to claim 11, wherein
the manufacturing condition includes at least one condition selected from power supply power of a semiconductor manufacturing apparatus, a power supply frequency of the semiconductor manufacturing apparatus, a power supply pulse period of the semiconductor manufacturing apparatus, a processing gas flow rate of the semiconductor manufacturing apparatus, a processing gas in-plane supply rate of the semiconductor manufacturing apparatus, an auxiliary gas flow rate of the semiconductor manufacturing apparatus, a processing chamber pressure of the semiconductor manufacturing apparatus, a processing time of the semiconductor manufacturing apparatus, a substrate heating temperature of the semiconductor manufacturing apparatus, and a chiller temperature of the semiconductor manufacturing apparatus, and
the multiple process parameters include multiple parameters each indicating a characteristic of a processed cross-sectional shape, multiple parameters each indicating a characteristic of a processed planar shape, or both the multiple parameters.

### Claim 14 (depends on 12)

The information processing method according to claim 12, wherein
the operation terminal condition includes an applied voltage or an applied current to an operation terminal, and
the multiple design parameters include parameters selected from a gate voltage/a drain current characteristic, a drain voltage/a drain current characteristic, a substrate voltage/a threshold voltage characteristic, a gate length/a threshold voltage characteristic, a gate width/a threshold current characteristic, a temperature/a threshold current characteristic, a substrate voltage/an on-current characteristic, a gate length/an on-current characteristic, a gate width/an on-current characteristic, a temperature/an on-current characteristic, a gate voltage/a gate capacitance characteristic, a drain voltage/a gate capacitance characteristic, and a substrate voltage/a substrate capacitance characteristic.

### Claim 15 (depends on 13)

The information processing method according to claim 13, wherein
the multiple process parameters include parameters selected from parameters related to an upper occlusion rate of a cross-sectional shape, a bowing degree of the cross-sectional shape, a twisting degree of the cross-sectional shape, a bending degree of the cross-sectional shape, a tilting degree of the cross-sectional shape, a bottom occlusion rate of the cross-sectional shape, a residual film thickness of a hard mask, a distortion degree of a planar shape, an etching rate.

### Claim 16

An information processing apparatus comprising:
an importance level calculation unit that obtains an importance level of optimizing an objective variable for each of the multiple objective variables;
a model generation unit that generates multiple pieces of model information corresponding to the multiple objective variables;
a range evaluation unit that obtains, for each of the multiple objective variables, a statistic of evaluations using the model information and an evaluation set for each range of values of the objective variable;
a comprehensive evaluation unit that generates acquisition function information using multiple importance levels of optimizing the objective variables and multiple statistics of the evaluations; and
a multi-objective optimization unit that generates, based on the acquisition function information, explanatory variable information indicating an explanatory variable that optimizes the multiple objective variables.

### Claim 17 (depends on 16)

The information processing apparatus according to claim 16, further comprising
a pairwise comparison unit that performs a pairwise comparison with respect to importance of optimizing the objective variables,
wherein the importance level calculation unit obtains the importance level of optimizing the objective variable according to a result of the pairwise comparison, and
the range evaluation unit obtains, for each of the multiple objective variables, the statistic of the evaluations by using a probability distribution of the objective variable according to the model information and a criterion evaluation value for each range of the values of the objective variable.

### Claim 18 (depends on 17)

The information processing apparatus according to claim 17, wherein
the range evaluation unit obtains, for each of the multiple objective variables, a probability distribution of the objective variable according to the model information.

### Claim 19 (depends on 17)

The information processing apparatus according to claim 17, wherein
the importance level calculation unit further confirms a consistency index of the multiple importance levels obtained for the multiple objective variables, and
the range evaluation unit obtains, when the consistency index complies with a predetermined condition, the statistic of the evaluations for each of the multiple objective variables by using the model information and the evaluation set for each range of the values of the objective variable.

### Claim 20 (depends on 16)

The information processing apparatus according to claim 16, wherein
the model generation unit generates the multiple pieces of model information each including a model that predicts a corresponding objective variable from the explanatory variable.
