# US 2019/0313833 A1 · Multi-purpose smart rice cookers

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

- Number: US 2019/0313833 A1
- Document ID: US20190313833A1
- Status: Published application
- Kind: A1
- Application number: 15/770,731
- Filed: 2018-04-16
- Published: 2019-10-17
- Earliest claimed: 2018-04-16
- Assignees: Midea Group Co., Ltd.
- Applicants: Midea Group Co., Ltd.
- Inventors: Xiaochun Li; Linnan Zhu; Hua Zhou
- Web page: https://patentgrep.com/patent/US20190313833A1

## CPC

- A47J 27/0802: {Control mechanisms for pressure-cookers}
- A47J 36/321: {the electronic control being performed over a network, e.g. by means of a handheld device}
- A47J 27/21083: {with variable operating parameters, e.g. temperature or boiling period}
- G06N 3/045: Combinations of networks
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/09: Supervised learning
- G06T 7/0002: {Inspection of images, e.g. flaw detection}
- G06T 2207/30: Subject of image; Context of image processing
- A47J: KITCHEN EQUIPMENT; COFFEE MILLS; SPICE MILLS; APPARATUS FOR MAKING BEVERAGES
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL

## Abstract

A rice cooker assembly uses machine learning models to identify and classify different types of food stored. The rice cooker has a chamber including different compartments for storing different types of food. A camera is positioned to view an interior of the chamber. The camera captures images of the contents of the chamber. From the images, the machine learning model classifies the different types of food stored. The rice cooker determines a mixture of different types of food based on nutrition value and/or taste. The rice cooker creates the mixture and controls the cooking process accordingly. The one or more machine learning models may be resident in the rice cooker or it may be accessed via a network.

## Claims

### Claim 1

A rice cooker comprising:
a chamber configured to hold multiple types of food;
a camera; and
a processing system configured to:
cause the camera to capture one or more images of the multiple types of food;
provide the captured images as an input to one or more machine learning models, the one or more machine learning models configured to classify a type of the multiple types of food; and
determine a mixture of the multiple types of food based on the classification, the mixture including at least two types of the multiple types of food.

### Claim 2 (depends on 1)

The rice cooker of claim 1, wherein the first chamber includes multiple compartments, further comprising:
a second chamber configured to hold food and coupled to the first chamber, the camera positioned to view an interior of the second chamber;
wherein the processing system is further configured to:
cause the camera to capture the one or more images of contents of the second chamber; and
determine one of the multiple chambers for storing the food in the second chamber based on the classification.

### Claim 3 (depends on 1)

The rice cooker of claim 1, wherein the processing system is further configured to control a cooking process according to the mixture.

### Claim 4 (depends on 1)

The rice cooker of claim 1, wherein the chamber comprises multiple compartments and one or more gates positioned on a bottom support of the chamber, the gate configured to create one or more openings through the chamber.

### Claim 5 (depends on 4)

The rice cooker of claim 4, wherein the processing system is configured to cause the one or more gates to create a first opening through a first compartment and a second opening through a second compartment, a dimension of the first opening and a dimension of the second opening determined according to a first type of food and a second type of food.

### Claim 6 (depends on 5)

The rice cooker of claim 5, wherein the processing system is configured to determine that a dimension of the first opening is larger than the dimension of the second opening responsive to determining that a unit dimension of the first type of food is larger than a unit dimension of the second type of food.

### Claim 7 (depends on 4)

The rice cooker of claim 4, wherein the camera is configured to move from a portion of the chamber to another portion of the chamber.

### Claim 8 (depends on 1)

The rice cooker of claim 1, further comprising a conduit attached to the chamber, the conduit configured to distribute the contents of the chamber to another chamber for cooking.

### Claim 9 (depends on 1)

The rice cooker of claim 1, wherein the camera is positioned on a top lid of the chamber.

### Claim 10 (depends on 1)

The rice cooker of claim 1, wherein the camera is affixed to a camera holder separate from the chamber and the chamber is configured to rotate.

### Claim 11 (depends on 1)

The rice cooker of claim 1, further comprising a second chamber configured to be attached to the first chamber, the second chamber configured to store the multiple types of food for cooking.

### Claim 12 (depends on 1)

The rice cooker of claim 1, wherein the one or more machine learning models are physically located remote from rice cooker, the rice cooker accessing the one or more machine learning models via a network connection.

### Claim 13 (depends on 1)

The rice cooker of claim 1, wherein the one or more machine learning models are physically located in the rice cooker.

### Claim 14

A computer-implemented method for controlling a rice cooker, comprising:
capturing images of contents of a chamber over a period of time, the contents including multiple types of food;
providing the captured images as an input to one or more machine learning models, the one or more machine learning models configured to classify each of the multiple types of food; and
determining a mixture of the multiple types of food based on the classification, the mixture including at least two types of the multiple types of food.

### Claim 15 (depends on 14)

The computer-implemented method of claim 14, further comprising determining a compartment for storing a type of food and transferring the type of food from the chamber to the compartment.

### Claim 16 (depends on 14)

The computer-implemented method of claim 14, further comprising controlling a cooking process according to the mixture, and wherein controlling the cooking process comprises controlling a temperature-time curve for the rice cooker according to the mixture.

### Claim 17 (depends on 16)

The computer-implemented method of claim 16, wherein determining the mixture includes determining a ratio between a first type of food and a second type of food, and wherein the cooking process is further controlled according to the ratio.

### Claim 18 (depends on 14)

The computer-implemented method of claim 14, further comprising mixing the multiple types of food based on determined mixture.

### Claim 19 (depends on 18)

The computer-implemented method of claim 18, wherein the chamber includes a gate and wherein mixing the multiple types of food based on the mixture comprises controlling an opening of the gate.

### Claim 20 (depends on 19)

The computer-implemented method of claim 19, wherein controlling the opening of the gate comprises: responsive to determining that a first dimension of a first type of food greater than a second dimension of a second type of food, controlling the opening of the gate such that a first opening configured to distribute the first type of food is greater than a second opening configured to distribute the second type of food.

### Claim 21 (depends on 14)

The computer-implemented method of claim 14, further comprising:
responsive to determining that a level of one of the multiple types of food is below a threshold level, generating a signal including an alert to a user to refill the chamber.