# US 2021/0065732 A1 · Noise manageable electronic apparatus and method for controlling the same

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

- Number: US 2021/0065732 A1
- Document ID: US20210065732A1
- Status: Published application
- Kind: A1
- Application number: 16/694,881
- Filed: 2019-11-25
- Published: 2021-03-04
- Earliest claimed: 2019-09-02
- Assignees: LG Electronics Inc.
- Applicants: LG Electronics Inc.
- Inventors: Yun Sik PARK
- Web page: https://patentgrep.com/patent/US20210065732A1

## CPC

- G10L 21/0232: Processing in the frequency domain
- G06N 3/0442: characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G10L 15/22: Procedures used during a speech recognition process, e.g. man-machine dialogue
- G10L 25/51: for comparison or discrimination
- G10L 25/84: for discriminating voice from noise
- H04L 12/282: {based on user interaction within the home (receiver circuitry for displaying additional information being controlled by a remote control apparatus H04N21/42204)}
- H04L 67/52: specially adapted for the location of the user terminal
- H04W 4/021: Services related to particular areas, e.g. point of interest [POI] services, venue services or geofences
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G10L 2015/223: {Execution procedure of a spoken command}
- H04L 67/125: involving control of end-device applications over a network
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)

## Abstract

According to the present disclosure, noises generated by electronic devices are measured in order to determine an electronic device which generates a noise by an electronic device located near a user in response to a noise management command generated by the user, and the operation of the electronic devices is controlled so that the measured noises are maintained as an appropriate noise, thereby maintaining the noises of the electronic devices at an appropriate level.

## Claims

### Claim 1

A method for noise management, the method comprising:
receiving a command from a user located within a defined space;
identifying a location of the user based on an input received from a camera that is configured to capture the user within the defined space;
obtaining, after the receiving of the command, first noise captured by a microphone of a voice reception device located adjacent to the location of the user;
identifying a first electronic device which has generated the first noise, from among a plurality of electronic devices within the defined space, by analyzing the first noise; and
controlling operation of the first electronic device to reduce the first noise.

### Claim 2 (depends on 1)

The method of claim 1, further comprising:
measuring (dB) levels of operation noises respective generated by the plurality of electronic devices as captured by h the microphone; and
identifying an operation noise having a highest level from among the operation noises generated by the plurality of electronic devices,
wherein an electronic device which generates the operation noise having the highest level is identified as the first electronic device.

### Claim 3 (depends on 2)

The method of claim 2, wherein the measuring the dB levels of the operation noises comprises measuring a level of at least one operation noise among a wind noise, a vibration noise, a suction noise, or an acoustic noise generated when the plurality of electronic devices operate.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
measuring (dB) levels of operation noises respectively generated by the plurality of electronic devices as captured by the microphone; and
identifying an electronic device, from among the plurality of electronic devices, that is located closest to the user as the first electronic device, when the measured dB levels of operation noises does not result in identification of an operation noise having a highest level.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
measuring a second noise obtained by the microphone after the controlling the operation of first electronic device; and
controlling operation of an electronic device having a highest power consumption, from among the plurality of electronic devices, when a difference between a magnitude of the first noise and a magnitude of the second noise is less than a threshold value.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
measuring (dB) levels of operation noises respectively generated by the plurality of electronic devices as captured by the microphone;
when the measured dB levels of operation noises does not result in identification of an operation noise having a highest level, the method further comprises:
controlling the operation of any one of the plurality of electronic devices;
measuring second levels of the operation noises respectively generated by the plurality of electronic devices except for the any one electronic device, except for the any one of the plurality of electronic devices, using the microphone;
identifying an operation noise level having a highest level among the second levels of operation noises based on the measuring the second levels; and
identifying an electronic device which generates the operation noise having a highest level as the first electronic device.

### Claim 7 (depends on 1)

The method of claim 1, wherein the method further comprises:
before the receiving the command from the user, receiving an input of a learning data set in which operation noises generated in each operation stage of the plurality of electronic devices are labeled when the plurality of electronic devices operate;
training, on the basis of the learning data set, a machine learning model for determining a stage of operation noises of the plurality of electronic devices generated during operation of the plurality of electronic devices; and
storing the machine learning model generated through the training as an operation noise determination program of the plurality of electronic devices.

### Claim 8 (depends on 1)

The method of claim 1, further comprising:
identifying the location of the user in response to the receiving the command;
activating the microphone to enable the microphone to capture the first noise,
wherein the defined space is a home, and
wherein the command is a noise management command.

### Claim 9

A computer program product comprising a non-transitory machine readable medium having a computer readable program stored therein, wherein the computer readable program, when executed by a computing device, causes the computing device to:
receive a command from a user located within a defined space;
identify a location of the user based on an input received from a camera that is configured to capture the user within the defined space;
obtain, after the receiving of the command, first noise captured by a microphone of a voice reception device located adjacent to the location of the user;
identify a first electronic device which has generated the first noise, from among a plurality of electronic devices within the defined space, by analyzing the first noise; and
control operation of the first electronic device to reduce the noise.

### Claim 10 (depends on 9)

The computer program product of claim 9, wherein the computer readable program, when executed by the computing device, further causes the computing device to:
measure (dB) levels of operation noises respectively generated by the plurality of electronic devices as captured by the microphone; and
extract an operation noise having a highest level from among the operation noises generated by the plurality of electronic devices,
wherein an electronic device which generates the operation noise having the highest level is identified as the first electronic device.

### Claim 11 (depends on 10)

The computer program product of claim 10, wherein the measure the dB levels of the operation noises comprises measure a level of at least one operation noise among a wind noise, a vibration noise, a suction noise, or an acoustic noise generated when the plurality of electronic devices operate.

### Claim 12 (depends on 9)

The computer program product of claim 9, wherein the computer readable program, when executed by the computing device, further causes the computing device to:
measure (dB) levels of operation noises respectively generated by the plurality of electronic devices as captured by the microphone; and
identify an electronic device, from among the plurality of electronic devices, that is located closest to the user as the first electronic device, when the measured dB levels of operation noises does not result in identification of an operation noise having a highest level.

### Claim 13 (depends on 12)

The computer program product of claim 12, wherein the computer readable program, when executed by the computing device, further causes the computing device to:
measure a second noise obtained by the microphone after the control the operation of the first electronic device; and
control operation of an electronic device having a highest power consumption, from among the plurality of electronic devices, when a difference between a magnitude of the first noise and a magnitude of the second noise is less than a threshold value.

### Claim 14 (depends on 9)

The computer program product of claim 9, wherein the computer readable program, when executed by the computing device, further causes the computing device to:
measure (dB) levels of operation noises respectively generated by the plurality of electronic devices as captured by the microphone;
when the measured dB levels of operation noises does not result in identification of an operation noise having a highest level, the computer readable program, when executed by the computing device, further causes the computing device to:
control the operation of any one of the plurality of electronic devices;
measure second levels of the operation noises respectively generated by the plurality of electronic devices, except for the any one of the plurality of electronic devices, using the microphone;
identify an operation noise level having a highest level among the second levels of operation noises based on the measuring the second levels; and
identify an electronic device which generates the operation noise having a highest level as the first electronic device.

### Claim 15 (depends on 9)

The computer program product of claim 9, wherein the computer readable program, when executed by the computing device, further causes the computing device to:
before the receive the command from the user, receive an input of a learning data set in which operation noises generated in each operation stage of the plurality of electronic devices are labeled when the plurality of electronic devices operate;
train, on the basis of the learning data set, a machine learning model for determining a stage of operation noises of the plurality of electronic devices generated during operation of the plurality of electronic devices; and
store the machine learning model generated through the training as an operation noise determination program of the plurality of electronic devices.

### Claim 16

A noise management electronic device, comprising:
a receiver configured to receive a command from a user located within a defined space;
a location determiner configured to identify a location of the user based on an input received from a camera that is configured to capture the user within the defined space;
a collector configured to obtain first noise captured by a microphone of a voice reception device located adjacent to the location of the user;
a noise source determiner configured to identify a first electronic device which has generated the first noise, from among a plurality of electronic devices within the defined space, by analyzing the first noise;
an operation controller configured to control operation of the first electronic device to reduce the first noise;
a memory in which information about operation noises of the plurality of electronic devices generated during operation of the plurality of electronic devices is stored; and
a controller configured to control the memory and the operation controller.

### Claim 17 (depends on 16)

The electronic device of claim 16, wherein the noise source determiner comprises:
a level measurer configured to measure (dB) levels of operation noises respectively generated by the plurality of electronic devices as captured by the microphone; and
a noise extractor configured to extract an operation noise having a highest level among the operation noises generated by the plurality of electronic devices,
wherein an electronic device which generates the operation noise having the highest level is identified as the first electronic device.

### Claim 18 (depends on 17)

The electronic device of claim 17, wherein the level measurer measures the level of at least one operation noise among a wind noise, a vibration noise, a suction noise, or an acoustic noise generated when the plurality of electronic devices operate.

### Claim 19 (depends on 16)

The electronic device of claim 16, wherein the memory trains a machine learning model for determining a stage of operation noises of the plurality of electronic devices generated during operation of the plurality of electronic devices on a basis of a learning data set in which operation noises generated in each operation stage of the plurality of electronic devices are labeled when the plurality of electronic devices operate, and stores the machine learning model generated through the training as an operation noise determination program of the plurality of electronic devices.
