Artificial intelligence air conditioner and control method thereof

Patent metadata

Field	Value
Publication number	US-10871302-B2
Application number	US-201715845672-A
Country	US
Kind code	B2
Filing date	Dec 18, 2017
Priority date	Dec 19, 2016
Publication date	Dec 22, 2020
Grant date	Dec 22, 2020

Abstract

An artificial intelligence air conditioner may include a camera to obtain an image, an area recognition module for recognizing an area in which an occupant is located in an indoor space divided into a plurality of areas from the image obtained by the camera and distinguishing a living area with respect to the plurality of areas based on a result of recognizing a location of the occupant, and an airflow controller controlling airflow based on the distinguished living area, whereby airflow optimized for each living area of the indoor space may be controlled.

First claim

What is claimed is:

1. An air conditioner comprising:
a camera that obtains an image of an indoor space;
an area recognition device that determines, from the image obtained by the camera, a location of an occupant in the indoor space that is separated into a plurality of areas, and the area recognition device distinguishes a living area with respect to the plurality of areas based on a result of determining the location of the occupant; and
an airflow controller that controls airflow of the air conditioner based on the distinguished living area, and
wherein the area recognition device separates the plurality of areas into a residential living area, a movement living area, and a non-living area,
the airflow controller controls the airflow differently depending on the residential living area, the movement living area, and the non-living area, and controls airflow for cooling the residential living area first and before cooling the movement living area and the non-living area; and
wherein the area recognition device includes:
a human body recognizer that determines, from the image obtained from the camera, presence or absence of the occupant and the location of the occupant,
an area recognizer that distinguishes the living area with respect to the plurality of areas based on a result of determining the location of the occupant, and
a signal generator that provides an airflow control signal based on the distinguished living area, and

wherein a direction of airflow is controlled so that airflow is transmitted only toward the resident living area in an intensive cooling/heating mode,
wherein the direction of airflow is controlled so as to be transmitted only toward the living area in a direct heating and cooling mode,
wherein the direction of airflow is controlled such that an indirect cooling/heating operation is performed to transmit airflow only to the non-living area and the movement living area, except for the residential living area in an indirect cooling/heating mode,
wherein the area recognition device accumulates results of determining the location of the occupant to a histogram, and distinguishes the living area with respect to the plurality of areas based on the accumulated results of determining the location of the occupant,
wherein the histogram is generated in a matrix type in which detection frequency by distances and angles have a plurality of rows and columns.

2. The air conditioner of claim 1 , wherein the airflow controller controls a fan motor or a wind direction adjusting device based on the distinguished living area.

3. The air conditioner of claim 1 , wherein the area recognition device distinguishes the living area with respect to the plurality of areas using the result of determining the location of the occupant as input of data previously learned by machine learning.

4. The air conditioner of claim 1 , wherein the area recognition device includes an artificial neural network that is previously learned by machine learning, and
the area recognition device accumulates the result of determining the location of the occupant and provides the histogram that includes information on the plurality of areas, and the area recognition device distinguishes the living area by using the histogram as input data of the artificial neural network.

5. The air conditioner of claim 1 , further comprising:
a communication device that receives, from a server, data related to machine learning,
wherein the area recognition device is updated based on the data, received from the server, related to machine learning.

Assignees

• Lg Electronics Inc

Inventors

• Song Taeyup
• Song Jaeyong
• Han Dongwoo

Classifications

• G06V10/82

  using neural networks · CPC title

• G06V40/10

  Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands · CPC title

• G06V20/52

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title

• G05B13/027

  using neural networks only · CPC title

• F24F11/54

  using one central controller connected to several sub-controllers · CPC title