# US 2020/0393799 A1 · 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 2020/0393799 A1
- Document ID: US20200393799A1
- Status: Published application
- Kind: A1
- Application number: 16/817,465
- Filed: 2020-03-12
- Published: 2020-12-17
- Earliest claimed: 2019-06-14
- Assignees: Kabushiki Kaisha Toshiba
- Applicants: Kabushiki Kaisha Toshiba
- Inventors: Myungsook KO; Tatsuya INAGI; Masaaki TAKADA
- Web page: https://patentgrep.com/patent/US20200393799A1

## CPC

- G05B 13/0265: {the criterion being a learning criterion}
- G05B 13/041: {in which a variable is automatically adjusted to optimise the performance}
- G05B 13/042: {in which a parameter or coefficient is automatically adjusted to optimise the performance}
- 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 18/241: relating to the classification model, e.g. parametric or non-parametric approaches
- G06N 20/00: Machine learning
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

An information processing apparatus according to an embodiment of the present invention includes a group setting device configured to group a plurality of variables included in operation data into at least one type of groups, based on structure data representing a structural relation among the plurality of variables; a regularization term generator configured to generate at least one regularization term corresponding to the at least one type based on a coefficient for the variable included in the at least one type of groups, and a coefficient estimator configured to estimate, based on the operation data and an objective function including the at least one regularization term, values of a plurality of the coefficients for the plurality of variables.

## Claims

### Claim 1

An information processing apparatus comprising:
a group setting device configured to group a plurality of variables included in operation data into at least one type of groups, based on structure data representing a structural relation among the plurality of variables;
a regularization term generator configured to generate at least one regularization term corresponding to the at least one type based on a coefficient for the variable included in the at least one type of groups; and
a coefficient estimator configured to estimate, based on the operation data and an objective function including the least one regularization term, values of a plurality of the coefficients for the plurality of variables.

### Claim 2 (depends on 1)

The apparatus according to claim 1, further comprising:
a variable determiner configured to select a variable larger than zero or a threshold from the plurality of variables based on the estimated values of the coefficients; and
a variable structure generator configured to generate, based on the selected variable and the structure data, variable structure data representing a structural relation of the selected variable.

### Claim 3 (depends on 2)

The apparatus according to claim 2, wherein the variable structure generator sets the selected variable and a variable adjacent to the selected variable in the structure data to drawing variables and generate a structural relation between the drawing variables, the generated structural relation being the variable structure data.

### Claim 4 (depends on 2)

The apparatus according to claim 2, further comprising a display configured to display the variable structure data.

### Claim 5 (depends on 1)

The apparatus according to claim 1, wherein the at least one type indicates a group of a class relation integrating variables corresponding to instances of a class.

### Claim 6 (depends on 5)

The apparatus according to claim 5, wherein the regularization term generator generates a regularization term of Group Lasso for the group of the class relation.

### Claim 7 (depends on 1)

The apparatus according to claim 1, wherein the at least one type indicates a group of a hierarchical relation integrating variables corresponding to low-order nodes having a common high-order node in a tree structure.

### Claim 8 (depends on 7)

The apparatus according to claim 7, wherein the high-order node is a parent node of the plurality of low-order nodes.

### Claim 9 (depends on 7)

The apparatus according to claim 7, wherein the regularization term generator generates a regularization term of Overlapping Group Lasso for the group of the hierarchical relation.

### Claim 10 (depends on 1)

The apparatus according to claim 1, wherein the at least one type indicates a group of a reference relation integrating variables having the reference relation.

### Claim 11 (depends on 10)

The apparatus according to claim 10, wherein the regularization term generator generates a regularization term of Clustered Lasso for the group of the reference relation.

### Claim 12 (depends on 1)

The apparatus according to claim 1, further comprising a regularization-rule input device configured to receive a value of a regularization parameter included in the regularization term, wherein
the regularization term generator generates the regularization term using the input value of the regularization parameter.

### Claim 13 (depends on 12)

The apparatus according to claim 12 comprising
a display configured to display the variable structure data wherein
the regularization-rule input device receives a plurality of the values of the regularization parameter,
the variable structure generator generates the variable structure data for each of the plurality of values of the regularization parameter, and
the display comparably displays a plurality of sets of the plurality of values and a plurality of the variable structure data corresponding to the plurality of values.

### Claim 14 (depends on 2)

The apparatus according to claim 2, wherein
the operation data includes first operation data acquired in a first period and second operation data acquired in a second period later than the first period,
processing of the group setting device, the regularization term generator, the coefficient estimator, the variable determiner, and the variable structure generator is performed on each of the first operation data and the second operation data, and
the information processing apparatus further comprises a change determiner configured to determine whether the variable selected by the variable determiner for the first operation data coincide with the variable selected by the variable determiner for the second operation data and, when the variable selected for the first operation data does not coincide with the variable selected for the second operation data, output an alert.

### Claim 15 (depends on 1)

The apparatus according to claim 1, further comprising:
a model generator configured to construct, based on the coefficient estimated by the coefficient estimator and the variable for the coefficient, a model configured to detect occurrence of a predetermined event; and
a model determiner configured to calculate an output value of the model based on the model and the operation data and detect the occurrence of the predetermined event based on the output value.

### Claim 16

An information processing method performed by a computer including a processor and a memory comprising:
grouping a plurality of variables in operation data into at least one type of groups, based on structure data representing a structural relation among the plurality of variables;
generating at least one regularization term corresponding to the at least one group type based on a coefficient for the variable included in the at least one type of groups; and
estimating, based on the operation data and an objective function including the at least one regularization term, values of a plurality of the coefficients for the plurality of variables.

### Claim 17

A non-transitory computer readable medium having a computer program stored therein which causes a computer to perform processes comprising:
grouping a plurality of variables in operation data into at least one type of groups, based on structure data representing a structural relation among the plurality of variables;
generating at least one regularization term corresponding to the at least one group type based on a coefficient for the variable included in the at least one type of groups; and
estimating, based on the operation data and an objective function including the at least one regularization term, values of a plurality of the coefficients for the plurality of variables.
