Method of smart rice cookers capable of mixed grain cooking and abnormal conditions detection

Patent metadata

Field	Value
Publication number	US-11406121-B2
Application number	US-201815760841-A
Country	US
Kind code	B2
Filing date	Mar 8, 2018
Priority date	Mar 8, 2018
Publication date	Aug 9, 2022
Grant date	Aug 9, 2022

Abstract

A rice cooker assembly uses machine learning models to identify and classify content in grain mixtures thereby to provide better automation of the cooking process. As one example, a rice cooker has a chamber storing grains. 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 determines whether the contents of the chamber includes one type or multiple types of grain or whether the contents of the chamber includes any inedible objects. The machine learning model further classifies the one or more types of grains and inedible objects if any. The cooking process may be controlled accordingly. The machine learning model may be resident in the rice cooker or it may be accessed via a network.

First claim

What is claimed is:

1. A computer-implemented method for controlling a rice cooker, comprising:
capturing, using a camera positioned within the rice cooker, an image of an interior of a chamber of the rice cooker, the chamber containing food content including at least one food component;
providing the captured image as a first input to a first machine learning model, in a control system of the rice cooker, the first machine learning model configured to determine whether the food content includes only a first food component or multiple food components including the first food component and one or more objects different from the first food component;
responsive to determining by the first machine learning model that the food content includes multiple food components including the first food component and one or more objects different from the first food component, applying the captured image as a second input to a second machine learning model in the control system of the rice cooker that is distinct from the first machine learning model, wherein the second machine learning model is configured to determine each of the one or more objects and the first food component of the food content, and wherein the second machine learning model is configured to identify at least one of the one or more objects mixed within the first food component in the rice cooker as an inedible object; and
controlling the rice cooker by controlling a cooking process of the rice cooker according to the determined first food component and the determined one or more objects different from the first food component.

2. The computer-implemented method of claim 1 , further comprising:
responsive to determining, by the first machine learning model, that the food content includes multiple food components including the first food component and the one or more objects different from the first food component, controlling a cooking process according to the determined first food component and the determined one or more objects different from the first food component.

3. The computer-implemented method of claim 1 , further comprising:
responsive to determining, by the second machine learning model, that at least one of the one or more objects mixed within the first food component as the inedible object, emptying contents of the chamber.

4. The computer-implemented method of claim 2 , wherein controlling the cooking process comprises controlling a temperature-time curve for the rice cooker according to the determined first food component and the one or more objects.

5. The computer-implemented method of claim 2 , wherein the rice cooker has different cooking modes, and controlling the cooking process comprises selecting a cooking mode according to the determined first food component and the one or more objects.

6. The computer-implemented method of claim 2 , wherein the cooking process has different phases, and controlling the cooking process comprises transitioning between different phases according to the determined first food component and the one or more objects.

7. The computer-implemented method of claim 2 , further comprising:
determining a ratio between the first food component and the one or more objects, wherein the cooking process is controlled further according to the ratio.

8. The computer-implemented method of claim 2 , further comprising:
receiving a user input about content in the chamber or the cooking process, wherein the cooking process is controlled further according to the user input.

9. The computer-implemented method of claim 2 , further comprising:
accessing a user's profile for information about content in the chamber or the cooking process, wherein the cooking process is controlled further according to the information from the user's profile.

10. The computer-implemented method of claim 2 , further comprising:
accessing historical data for the rice cooker, wherein the cooking process is controlled further according to the historical data.

11. The method of claim 1 , wherein the chamber is separate from the rice cooker.

12. The method of claim 1 , wherein the rice cooker includes the chamber.

13. The method of claim 1 , wherein the camera is located on a side wall of the chamber.

Assignees

• Midea Group Co Ltd

Inventors

• Wang Dongyan
• Zhu Linnan
• Li Xiaochun
• Zhou Junyang

Classifications

• A23L5/13 Primary

  using water or steam · CPC title

• G06V20/00

  Scenes; Scene-specific elements (control of digital cameras H04N23/60) · CPC title

• G06V10/776

  Validation; Performance evaluation · CPC title

• A47J36/32 Primary

  Time-controlled igniting mechanisms or alarm devices · CPC title

• H04N23/60

  Control of cameras or camera modules · CPC title