# US 2026/0087496 A1 · Computer-readable recording medium having stored therein information processing program, information processing apparatus, and information processing system

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

- Number: US 2026/0087496 A1
- Document ID: US20260087496A1
- Status: Published application
- Kind: A1
- Application number: 19/329,672
- Filed: 2025-09-16
- Published: 2026-03-26
- Earliest claimed: 2024-09-26
- Assignees: Fujitsu Limited
- Applicants: Fujitsu Limited
- Inventors: Takuma YAMAMOTO
- Web page: https://patentgrep.com/patent/US20260087496A1

## CPC

- G06Q 20/4016: {involving fraud or risk level assessment in transaction processing}
- G07G 3/003: {Anti-theft control (theft alarms G08B13/00)}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 20/00: Machine learning
- G06Q 20/208: {Input by product or record sensing, e.g. weighing or scanner processing}
- G06V 10/762: using clustering, e.g. of similar faces in social networks
- G06V 10/764: using classification, e.g. of video objects
- G06V 20/52: Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69)
- G07G 1/0009: {Details of the software in the checkout register, electronic cash register [ECR] or point of sale terminal [POS]}
- G07G 1/0054: {with control of supplementary check-parameters, e.g. weight or number of articles}
- 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
- G07G: REGISTERING THE RECEIPT OF CASH, VALUABLES, OR TOKENS
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A computer-readable recording medium having stored therein an information processing program that causes a computer to perform a process including: classifying a plurality of items to be determined into one or more categories based on appearance images of the plurality of items, the appearance images being stored in a storage area in association with corresponding prices of the plurality of items; calculating, for each of the one or more categories into which the items are classified, a statistical value of prices of a plurality of items in the category, based on the plurality of prices stored in the storage area; changing a pattern for the classifying and performing the classifying and the calculating so that one or more of the statistical values satisfy a given condition; and outputting category information indicating a category of each of the plurality of items when the given condition is satisfied.

## Claims

### Claim 1

A non-transitory computer-readable recording medium having stored therein an information processing program that causes a computer to perform a process comprising:
classifying a plurality of items to be determined into one or more categories based on a plurality of appearance images of the plurality of items, the plurality of appearance images being stored in a storage area in association with corresponding prices of the plurality of items;
calculating, for each of the one or more categories into which the items are classified, a statistical value of prices of a plurality of items in the category, based on the plurality of prices stored in the storage area;
changing a pattern for the classifying and performing the classifying and the calculating so that one or more of the statistical values satisfy a given condition; and
outputting category information indicating a category of each of the plurality of items when the given condition is satisfied.

### Claim 2 (depends on 1)

The non-transitory computer-readable recording medium according to claim 1, wherein the process further comprises:
calculating a false alert rate of a machine learning model when the machine learning model is trained based on the one or more classified categories, the machine learning model outputting a category of the item to be determined based on a captured image of the item to be determined; and
changing the pattern for the classifying and performing the classifying and the calculating so that the one or more of the statistical values and the false alert rate satisfy the given condition.

### Claim 3 (depends on 2)

The non-transitory computer-readable recording medium according to claim 2, wherein
the changing the pattern for the classifying and the performing of the classifying and the calculating comprise a multi-objective optimization process that optimizes an objective function related to the one or more of the statistical values and an objective function related to the false alert rate.

### Claim 4 (depends on 1)

The non-transitory computer-readable recording medium according to claim 1, wherein
the classifying comprises:
obtaining an image feature of each of the plurality of appearance images stored in the storage area; and
clustering the plurality of appearance images based on a similarity of the image features.

### Claim 5 (depends on 1)

The non-transitory computer-readable recording medium according to any claim 1, wherein
the outputting of the category information comprises outputting, as training data for a machine learning model that outputs a category of the item to be determined based on a captured image of the item to be determined, each of the plurality of appearance images stored in the storage area and a category of each of the plurality of items indicated by the category information, and
the process further comprises executing a machine learning process of the machine learning model using the training data.

### Claim 6 (depends on 5)

The non-transitory computer-readable recording medium according to claim 5, wherein the process further comprises:
obtaining a category of an item registered in a self-checkout apparatus based on the category information;
determining whether or not a category obtained by inputting a captured image of the item to be determined into the trained machine learning model matches the category of the registered item; and
outputting an alert to the self-checkout apparatus when the category obtained by the inputting does not match the category of the registered item.

### Claim 7

An information processing apparatus comprising:
a memory; and
a processor coupled to the memory, the processor being configured to execute a process comprising:
classifying a plurality of items to be determined into one or more categories based on a plurality of appearance images of the plurality of items, of the plurality appearance images being stored in a storage area in association with corresponding prices of the plurality of items;
calculating, for each of the one or more categories into which the items are classified, a statistical value of prices of a plurality of items in the category, based on the plurality of prices stored in the storage area;
changing a pattern for the classifying and performing the classifying and the calculating so that one or more of the statistical values satisfy a given condition; and
outputting category information indicating a category of each of the plurality of items when the given condition is satisfied.

### Claim 8 (depends on 7)

The information processing apparatus according to claim 7, wherein
the process further comprising:
calculating a false alert rate of a machine learning model when the machine learning model is trained based on the one or more classified categories, the machine learning model outputting a category of the item to be determined based on a captured image of the item to be determined; and
changing the pattern for the classifying and performing the classifying and the calculating so that the one or more of the statistical values and the false alert rate satisfy the given condition.

### Claim 9 (depends on 8)

The information processing apparatus according to claim 8, wherein
the changing of the pattern for the classifying and the performing of the classifying and the calculating comprise a multi-objective optimization process that optimizes an objective function related to the one or more of the statistical values and an objective function related to the false alert rate.

### Claim 10 (depends on 7)

The information processing apparatus according to claim 7, wherein
the classifying comprises:
obtaining an image feature of each of the plurality of appearance images stored in the storage area; and
clustering the plurality of appearance images based on a similarity of the image features.

### Claim 11 (depends on 7)

The information processing apparatus according to claim 7, wherein
the outputting of the category information comprises outputting, as training data for a machine learning model that outputs a category of the item to be determined based on a captured image of the item to be determined, each of the plurality of appearance images stored in the storage area and a category of each of the plurality of items indicated by the category information; and
the process further comprises executing a machine learning process of the machine learning model using the training data.

### Claim 12 (depends on 11)

The information processing apparatus according to claim 11, wherein
the process further comprises:
obtaining a category of an item registered in a self-checkout apparatus based on the category information;
determining whether or not a category obtained by inputting a captured image of the item to be determined into the trained machine learning model matches the category of the registered item; and
outputting an alert to the self-checkout apparatus when the category obtained by the inputting does not match the category of the registered item.

### Claim 13

An information processing system comprising:
a self-checkout apparatus;
a fraud detection apparatus configured to perform fraud detection in the self-checkout apparatus using an image recognition model; and
a processor, the processor configured to execute a process comprising:
classifying a plurality of items to be determined into one or more categories based on a plurality of appearance images of the plurality of items, the plurality of appearance images being stored in a storage area in association with corresponding prices of the plurality of items;
calculating, for each of the one or more categories into which the items are classified, a statistical value of prices of a plurality of items in the category, based on the plurality of prices stored in the storage area;
changing a pattern for the classifying and performing the classifying and the calculating so that one or more of the statistical values satisfy a given condition; and
outputting category information indicating a category of each of the plurality of items when the given condition is satisfied, and
the fraud detection apparatus is configured to perform the fraud detection by the image recognition model trained using the category information.

### Claim 14 (depends on 13)

The information processing system according to claim 13, wherein
the process further comprises:
calculating a false alert rate of a machine learning model when the machine learning model is trained based on the one or more classified categories, the machine learning model outputting a category of the item to be determined based on a captured image of the item to be determined; and
changing the pattern for the classifying and performing the classifying and the calculating so that the one or more of the statistical values and the false alert rate satisfy the given condition.

### Claim 15 (depends on 14)

The information processing system according to claim 14, wherein
the changing of the pattern for the classifying and the performing of the classifying and the calculating comprises a multi-objective optimization process that optimizes an objective function related to the one or more of the statistical values and an objective function related to the false alert rate.

### Claim 16 (depends on 13)

The information processing system according to claim 13, wherein
the classifying comprises:
obtaining an image feature of each of the plurality of appearance images stored in the storage area; and
clustering the plurality of appearance images based on a similarity of the image features.

### Claim 17 (depends on 13)

The information processing system according to claim 13, wherein
the outputting of the category information comprises outputting, as training data for a machine learning model that outputs a category of the item to be determined based on a captured image of the item to be determined, each of the plurality of appearance images stored in the storage area and a category of each of the plurality of items indicated by the category information.

### Claim 18 (depends on 17)

The information processing system according to claim 17, wherein
the fraud detection apparatus is configured to perform a process comprising:
obtaining a category of an item registered in the self-checkout apparatus based on the category information;
determining whether or not a category obtained by inputting a captured image of the item to be determined into the trained machine learning model matches the category of the registered item; and
outputting an alert to the self-checkout device when the category obtained by the inputting does not match the category of the registered item.
