# US 2025/0166148 A1 · Learning device, prediction device, learning method, program, and learning system

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

- Number: US 2025/0166148 A1
- Document ID: US20250166148A1
- Status: Published application
- Kind: A1
- Application number: 18/272,609
- Filed: 2022-01-18
- Published: 2025-05-22
- Earliest claimed: 2021-02-01
- Assignees: J-Oil Mills, Inc.
- Applicants: J-OIL MILLS, Inc.
- Inventors: Kenichi KAKIMOTO; Ryohei WATANABE; Ayato TAKASAKI; Masami INOUE
- Web page: https://patentgrep.com/patent/US20250166148A1

## CPC

- G06T 7/0002: {Inspection of images, e.g. flaw detection}
- A47J 37/12: Deep fat fryers, e.g. for frying fish or chips
- G01N 33/03: Edible oils or edible fats
- G06N 3/08: Learning methods
- G06N 20/00: Machine learning
- G06T 7/0004: {Industrial image inspection}
- G06V 10/70: using pattern recognition or machine learning (optical pattern recognition or electronic computations therefor G06V10/88)
- G06T 2207/10024: Color image
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T 2207/30128: Food products
- G06T 2207/30242: Counting objects in image
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A47J: KITCHEN EQUIPMENT; COFFEE MILLS; SPICE MILLS; APPARATUS FOR MAKING BEVERAGES
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

According to the present invention, AI for predicting the rate of deterioration is generated. A learning device comprises: an imaging section configured to acquire an image in which edible oil is captured; a state identification section configured to analyze the image to identify a state of the edible oil; and a learning section configured to cause a learning model to learn a correlation between the state and a rate of deterioration indicating an increased level of deterioration of the edible oil.

## Claims

### Claim 1

A learning device comprising:
an imaging section configured to acquire an image in which edible oil is captured;
a state identification section configured to analyze the image to identify a state of the edible oil; and
a learning section configured to cause a learning model to learn a correlation between the state and a rate of deterioration indicating an increased level of deterioration of the edible oil.

### Claim 2 (depends on 1)

The learning device according to claim 1, wherein
the state is a rate of formation of bubbles formed per predetermined time in the edible oil, the number of the bubbles, size of each of the bubbles, speed at which the bubbles disappear, or a combination thereof.

### Claim 3 (depends on 1)

The learning device according to claim 1, wherein
the rate of deterioration is a rate of increase in viscosity of the edible oil, an acid value of the edible oil, color of the edible oil, an Anisidine value of the edible oil, the quantity of polar compounds of the edible oil, a Carbonyl value of the edible oil, a smoke point of the edible oil, Tocopherol content of the edible oil, an iodine value of the edible oil, a refractive index of the edible oil, the quantity of volatile compounds of the edible oil, a composition of volatile compounds of the edible oil, flavor of the edible oil, the quantity of volatile compounds of a deep-fried food obtained by deep-fry cooking with the edible oil, a composition of volatile compounds of the deep-fried food, flavor of the deep-fried food, or a combination thereof.

### Claim 4 (depends on 1)

The learning device according to claim 1, wherein
the state is identified based on initial foam formed in edible oil having an acid value of less than 0.2.

### Claim 5 (depends on 1)

A prediction device comprising a prediction section configured to predict the rate of deterioration using a learned model that is the learning model made to learn by the learning device according to claim 1.

### Claim 6

A method of learning carried out by a learning device, comprising:
an imaging procedure in which the learning device acquires an image in which edible oil is captured;
a state identification procedure in which the learning device analyzes the image to identify a state of the edible oil; and
a learning procedure in which the learning device causes a learning model to learn a correlation between the state and a rate of deterioration indicating an increased level of deterioration of the edible oil.

### Claim 7 (depends on 6)

A computer readable media for causing a computer to execute the learning method according to claim 6.

### Claim 8 (depends on 1, 5)

A learning system comprising:
the learning device according to claim 1; and
the prediction device according to claim 5.
