# US 11,299,838 B2 · Washing machine and cloud server setting function based on object sensing using artificial intelligence, and method for setting function

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

- Number: US 11,299,838 B2
- Document ID: US11299838B2
- Status: Granted
- Kind: B2
- Application number: 16/354,691
- Filed: 2019-03-15
- Published: 2019-09-19
- Granted: 2022-04-12
- Earliest claimed: 2018-03-15
- Assignees: LG Electronics Inc.
- Applicants: LG Electronics Inc.
- Inventors: Sung Mok Hwang; Sang Yun Kim; Yun Sik Park
- Web page: https://patentgrep.com/patent/US11299838B2

## CPC

- D06F 33/47: Responding to irregular working conditions, e.g. malfunctioning of pumps (safety arrangements D06F37/42)
- D06F 34/18: Condition of the laundry, e.g. nature or weight
- G05B 13/027: {using neural networks only}
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- D06F 23/04: and rotating or oscillating about a vertical axis
- D06F 33/48: Preventing or reducing imbalance or noise
- D06F 34/04: Signal transfer or data transmission arrangements
- D06F 2103/02: Characteristics of laundry or load
- D06F 2103/04: Quantity, e.g. weight or variation of weight
- D06F 2103/24: Spin speed; Drum movements
- D06F 2103/26: Imbalance; Noise level
- D06F 2103/44: Current or voltage
- D06F 2105/46: Drum speed; Actuation of motors, e.g. starting or interrupting
- D06F: LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
- 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)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

A washing machine and at least one server that set functions of the washing machine based on object sensing using artificial intelligence, and a setting method thereof. The washing machine that sets functions based on object sensing produces information on setting of a wash course adequate for laundry on the basis of the height, image, and weight of the laundry, physical information or electrical information generated during a wash or receives the information from the at least one server and operates.

## Claims

### Claim 1

A washing machine configured to implement a plurality of functions based on object sensing, the washing machine comprising:
a washing function unit that includes a tub, a drum, and a motor and that is configured to perform physical and electrical functions for storing and washing of laundry;
a distance sensor configured to obtain a height of the laundry in the washing function unit based on a distance to the laundry, wherein the distance sensor is disposed at an upper portion or at a lateral portion of the washing function unit;
an image sensor configured to sense an image of the laundry, wherein the image sensor is disposed at the upper portion or at the lateral portion of the washing function unit;
at least one processor; and
at least one computer memory operably connectable to the at least one processor and storing instructions that, when executed, cause the at least one processor to perform operations comprising:
obtaining measurement information regarding at least one of (i) a weight of the laundry, (ii) physical information generated during the washing of the laundry, or (iii) electrical information generated during the washing of the laundry; and
controlling the washing function unit based on course setting information that is produced by a machine-learning network in accordance with (i) distance information obtained by the distance sensor, (ii) image information obtained by the image sensor, and (iii) the measurement information.

### Claim 2 (depends on 1)

The washing machine of claim 1, wherein the machine-learning network is configured to perform machine learning by using (i) at least one input factor that comprises the distance information, the image information, and the measurement information that was produced during at least one prior washing of laundry, and (ii) at least one output factor that comprises the course setting information that was produced during the at least one prior washing of laundry, and
wherein the machine-learning network is configured to:
determine whether the laundry satisfies at least one criterion based on the distance information, the image information, and the measurement information; and
based on the laundry satisfying the at least one criterion, produce the course setting information for the laundry.

### Claim 3 (depends on 1)

The washing machine of claim 1, wherein the machine-learning network comprises:
at least one input layer configured to set the distance information, the image information, and the measurement information as at least one input factor of at least one input node;
at least one output layer configured to set the course setting information as at least one output factor of at least one output node; and
at least one hidden layer configured to be arranged between the at least one input layer and the at least one output layer,
wherein the machine-learning network is configured to update at least one of a weight or a bias of nodes and edges in the at least one hidden layer during learning.

### Claim 4 (depends on 1)

The washing machine of claim 1, further comprising a communication unit,
wherein the machine-learning network is implemented in at least one server outside the washing machine, and
wherein the operations further comprise:
transmitting, through the communication unit to the at least one server, the distance information, the image information, and the measurement information produced during the washing of the laundry;
receiving, through the communication unit and from the at least one server, and based on the laundry satisfying at least one criterion, the course setting information for the laundry; and
controlling at least one operation of the washing function unit based on the received course setting information.

### Claim 5 (depends on 1)

The washing machine of claim 1, wherein based on a determination that the laundry satisfies at least one criterion related to a weight of the laundry being less than a threshold weight and a volume of the laundry exceeding a threshold volume according to the distance information, the image information, and the measurement information:
controlling the washing function unit based on the course setting information comprises:
controlling the washing function unit according to a course setting for preventing water splash.

### Claim 6 (depends on 1)

The washing machine of claim 1, wherein based on a determination that the laundry satisfies at least one criterion related to the laundry being placed eccentrically in the washing function unit according to the distance information, the image information, and the measurement information:
controlling the washing function unit based on the course setting information comprises:
controlling the washing function unit according to a course setting for evenly distributing the laundry in the washing function unit.

### Claim 7 (depends on 1)

The washing machine of claim 1, wherein the course setting information is produced by the machine-learning network by extracting one or more features of the laundry from at least one of the distance information, the image information, or the measurement information using at least one of a convolution filter or a max-pooling filter.

### Claim 8

At least one server that is configured to set functions for at least one of a plurality of washing machines based on object sensing, the at least one server comprising:
a communication unit;
at least one processor; and
at least one computer memory operably connectable to the at least one processor and storing instructions that, based on being executed by the at least one processor, perform operations comprising:
receiving, through the communication unit and from a washing machine among the plurality of washing machines, (i) distance information related to a height of laundry in the washing machine, (ii) image information related to at least one image of the laundry in the washing machine, and (iii) measurement information related to at least one of a weight of the laundry, physical information generated during washing of the laundry, or electrical information generated during the washing of the laundry in the washing machine;
using a machine-learning network to process the distance information, the image information, and the measurement information to generate course setting information for the washing machine;
transmitting, through the communication unit and to the washing machine, the course setting information that was produced by the machine-learning network; and
monitoring, on the transmitted course setting information, delay in operations of the washing machine.

### Claim 9 (depends on 8)

The at least one server of claim 8, wherein the machine-learning network is configured to perform machine learning by using (i) at least one input factor that comprises the distance information, the image information, and the measurement information that was produced during at least one prior washing of laundry by at least one washing machine among the plurality of washing machines, and (ii) at least one output factor that comprises the course setting information that was produced during the at least one prior washing of laundry, and
wherein the machine-learning network is configured to:
determine whether the laundry satisfies at least one criterion based on the distance information, the image information, and the measurement information; and
based on the laundry satisfying the at least one criterion, produce the course setting information for the laundry.

### Claim 10 (depends on 8)

The at least one server of claim 8, wherein the machine-learning network of the at least one server comprises:
at least one input layer that is configured to set the distance information, the image information, and the measurement information as at least one input factor of at least one input node;
at least one output layer that is configured to set the course setting information as at least one output factor of at least one output node; and
at least one hidden layer that is configured to be arranged between the at least one input layer and the at least one output layer,
wherein the machine-learning network is configured to update at least one of a weight or a bias of nodes and edges in the at least one hidden layer during learning.

### Claim 11 (depends on 8)

The at least one server of claim 8, wherein using the machine-learning network to process the distance information, the image information, and the measurement information to generate the course setting information for the washing machine comprises:
based on a determination that the laundry in the washing machine satisfies at least one criterion related to a weight of the laundry being less than a threshold weight and a volume of the laundry exceeding a threshold volume according to the distance information, the image information, and the measurement information received from the washing machine:
producing the course setting information related to a course setting for preventing water splash in the washing machine.

### Claim 12 (depends on 8)

The at least one server of claim 8, wherein using the machine-learning network to process the distance information, the image information, and the measurement information to generate the course setting information for the washing machine comprises:
based on a determination that the laundry satisfies at least one criterion related to the laundry being placed eccentrically in the washing machine according to the distance information, the image information, and the measurement information received from the washing machine:
producing the course setting information related to a course setting for evenly distributing the laundry in the washing machine.

### Claim 13 (depends on 8)

The at least one server of claim 8, wherein the course setting information is produced by the machine-learning network by extracting one or more features of the laundry from at least one of the distance information, the image information, or the measurement information using at least one of a convolution filter or a max-pooling filter.