Air conditioning control system

Abstract

This air-conditioning control system (1) comprises an air-conditioner (100) having: a first discomfort index calculation unit for calculating an indoor first discomfort index by using information about an indoor temperature detected by an indoor temperature sensor and information about an indoor humidity detected by an indoor humidity sensor; and a control unit for controlling operation of the air-conditioner (100) on the basis of the indoor discomfort index. The air-conditioning control system (1) comprises a server (200) having a second discomfort index calculation unit for calculating a second discomfort index on the basis of: user information, which includes user characteristic information indicating characteristics of a user when the air-conditioner (100) is in use and discomfort index information constituted by a report of the user's sense of indoor warmth when the air-conditioner (100) is in use; and environmental information indicating the environment in which the air-conditioner (100) is used. The control unit controls the operation of the air-conditioner (100) on the basis of at least the first discomfort index.

Description

Air conditioning control system, learning device and inference device

[0001] The present disclosure relates to an air conditioning control system, a learning device, and an inference device that automatically control an indoor environment to make it comfortable for occupants.

[0002] Conventionally, in order to realize a comfortable thermal sensation for occupants in air conditioners, a comfort index called the predicted mean vote (PMV) that indicates how a person feels the thermal sensation has been proposed. As an air conditioner that controls based on the PMV index, Patent Document 1 describes an air conditioner that allows a user to input their current thermal sensation, allows the user to confirm the operation themselves, and controls heating and cooling by making accurate corrections as desired by the user based on the PMV value.

[0003] Japanese Patent Application Publication No. 7-55229

[0004] However, the air conditioner of Patent Document 1 requires the user to input their sense of temperature, and therefore has the problem that correction control of the heating and cooling control will not work if the user does not input information about their sense of temperature.

[0005] The present disclosure has been made in consideration of the above, and aims to provide an air conditioning control system that is capable of air conditioning control that makes the indoor environment comfortable without the user having to input a temperature sensation.

[0006] To solve the above-mentioned problems and achieve the object, the air conditioning control system according to the present disclosure is an air conditioning control system including an air conditioner and a server capable of communicating with the air conditioner. The air conditioning control system includes an air conditioner having an indoor temperature sensor that detects the temperature of an indoor area that is the air-conditioning target area of ​​the air conditioner, an indoor humidity sensor that detects the humidity of the indoor area, a first discomfort index calculation unit that calculates a first discomfort index for the indoor area using information on the indoor temperature detected by the indoor temperature sensor and information on the indoor humidity detected by the indoor humidity sensor, and a control unit that controls operation of the air conditioner based on the indoor discomfort index. The air conditioning control system also includes a server having a second discomfort index calculation unit that calculates a second discomfort index based on user information including user characteristic information that indicates the user's characteristics when using the air conditioner and discomfort index information that indicates the indoor temperature sensation felt by the user when using the air conditioner, and environmental information that is information that indicates the environment in which the air conditioner is used. The control unit controls operation of the air conditioner based on at least the first discomfort index.

[0007] The air conditioning control system according to the present disclosure has the advantage of being able to perform air conditioning control to make the indoor environment comfortable without the user having to input a temperature sensation.

[0008] 1 is a block diagram showing a system configuration of an air conditioning control system according to a first embodiment; FIG. 1 is a block diagram showing a configuration of an indoor unit of an air conditioner according to a first embodiment; FIG. 1 is a block diagram showing a configuration of an outdoor unit of an air conditioner according to a first embodiment; FIG. 1 is a block diagram showing a configuration of a remote controller of an air conditioner according to a first embodiment; FIG. 1 is a block diagram showing a configuration of a server according to a first embodiment;

[0009] An air conditioning control system, a learning device, and an inference device according to embodiments will be described in detail below with reference to the drawings.

[0010] Embodiment 1. Fig. 1 is a block diagram showing the system configuration of an air conditioning control system 1 according to embodiment 1. The air conditioning control system 1 according to embodiment 1 is a system that can automatically control air conditioning in order to achieve a comfortable thermal sensation for occupants. The air conditioning control system 1 according to embodiment 1 comprises an air conditioner 100, a server 200, and an external control terminal 300.

[0011] The air conditioner 100 has a function of automatically controlling air conditioning based on the discomfort index information so that the indoor environment, which is the area to be air-conditioned by the air conditioner 100, is comfortable for the occupants. The discomfort index information is information that indicates how a person feels thermal sensation, and PMV can be used.

[0012] The air conditioner 100 comprises an indoor unit 110 installed indoors, an outdoor unit 120 installed outdoors, and a remote controller 130. The indoor unit 110 is capable of communicating with the outdoor unit 120 via a communication line (not shown). The remote controller 130 is an operation device that a user operates to set control instructions and commands for the air conditioner 100 in order to control the air conditioner 100, and transmits the control instructions and commands operated by the user to the outdoor unit 120. Hereinafter, the remote controller may be referred to as a remote control.

[0013] The air conditioner 100, the server 200, and the external control terminal 300 are connected to each other so that they can communicate with each other via a network such as the Internet 400, which is a global information and communications network. In other words, the air conditioner 100, the server 200, and the external control terminal 300 are connected to the network and are able to send and receive information with each other. Note that the air conditioner 100, the server 200, and the external control terminal 300 may each communicate directly with other devices in the air conditioning control system 1 without using the Internet 400.

[0014] The air conditioner 100 forms a complete refrigeration cycle with an indoor unit 110 and an outdoor unit 120. The air conditioner 100 uses a refrigerant that circulates between the indoor unit 110 and the outdoor unit 120 through refrigerant pipes (not shown) to transfer heat between the air inside the room, which is the area to be air-conditioned, and the outside air, which is the air outside the room, thereby realizing air conditioning for the room.

[0015] Fig. 2 is a block diagram showing the configuration of the indoor unit 110 of the air conditioner 100 according to embodiment 1. As shown in Fig. 2, the indoor unit 110 includes an indoor unit sensor 111, an indoor unit storage unit 112, an indoor unit communication unit 113, and an indoor unit control unit 114. The above-described components of the indoor unit 110 can exchange information with each other.

[0016] The indoor unit sensor 111 is a detector that detects the state of the air conditioner 100 and the state of the environment in which the air conditioner 100 is used in order to control the air conditioner 100. Examples of the indoor unit sensor 111 include various sensors such as an indoor temperature sensor 1111 that detects the temperature inside the room and an indoor humidity sensor 1112 that detects the humidity inside the room.

[0017] The indoor unit storage unit 112 is a storage unit that stores various control setting values ​​and control programs for controlling the air conditioner 100. The indoor unit storage unit 112 is a non-volatile storage unit, and is configured using a semiconductor storage medium such as a flash memory.

[0018] The indoor unit communication unit 113 communicates with devices external to the indoor unit 110. That is, the indoor unit communication unit 113 communicates with communication units of devices external to the indoor unit 110, such as a remote control communication unit 134 (described later) of the remote control 130, an outdoor unit communication unit 123 (described later) of the outdoor unit 120, and a server communication unit 210 (described later) of the server 200. The indoor unit communication unit 113 transmits information received from the communication units of devices external to the indoor unit 110 to the indoor unit control unit 114. The indoor unit communication unit 113 transmits information received from the indoor unit control unit 114 to the communication units of devices external to the indoor unit 110.

[0019] The communication method between the communication unit of the external device and the indoor unit communication unit 113 may be wired communication, or wireless communication using infrared communication, Wi-Fi (registered trademark) (Wireless Fidelity), Bluetooth (registered trademark), or the like.

[0020] The indoor unit control unit 114 is a control unit that controls the overall operation of the indoor unit 110, and controls the operation of the indoor unit 110 and the outdoor unit 120 to control the operation of the air conditioner 100. The indoor unit control unit 114, in conjunction with an outdoor unit control unit 126 of the outdoor unit 120 (described later), is capable of controlling the operation of the air conditioner 100 through automatic air conditioning control, which automatically controls air conditioning based on discomfort index information determined in the air conditioning control system 1 so that the indoor environment is comfortable according to the value of the discomfort index information, and normal air conditioning control, which controls air conditioning based on operating conditions set by the user via a remote control 130 or the like. The indoor unit control unit 114 controls the operation of the air conditioner 100 based on at least a first discomfort index (described later).

[0021] Fig. 3 is a block diagram showing the configuration of the outdoor unit 120 of the air conditioner 100 according to embodiment 1. As shown in Fig. 3, the outdoor unit 120 includes an outdoor unit sensor 121, an outdoor unit storage unit 122, an outdoor unit communication unit 123, an acquisition unit 124, an outdoor unit discomfort index calculation unit 125, and an outdoor unit control unit 126. The above-described components of the outdoor unit 120 can exchange information with each other.

[0022] The outdoor unit sensor 121 is a detector that detects the state of the air conditioner 100 and the state of the environment in which the air conditioner 100 is used in order to control the air conditioner 100. Examples of the outdoor unit sensor 121 include various sensors such as an outdoor temperature sensor (not shown) that detects the temperature of the outdoor air, which is the air outside the room, and an outdoor humidity sensor (not shown) that detects the humidity of the outdoor air, which is the air outside the room.

[0023] The outdoor unit storage unit 122 is a storage unit that stores various control setting values ​​and control programs for controlling the air conditioner 100. The outdoor unit storage unit 122 is a non-volatile storage unit that is configured with a semiconductor storage medium such as a flash memory. The outdoor unit storage unit 122 stores the air conditioner-calculated discomfort index information calculated by the outdoor unit discomfort index calculation unit 125 and the discomfort index information finally determined by the outdoor unit discomfort index calculation unit 125.

[0024] The outdoor unit communication unit 123 communicates with devices external to the outdoor unit 120. That is, the outdoor unit communication unit 123 communicates with communication units of devices external to the outdoor unit 120, such as a remote control communication unit 134 (described later) of the remote control 130, an indoor unit communication unit 113 of the indoor unit 110, and a server communication unit 210 (described later) of the server 200. The outdoor unit communication unit 123 transmits information received from the communication units of the devices external to the outdoor unit 120 to the outdoor unit control unit 126. The outdoor unit communication unit 123 transmits information received from the outdoor unit control unit 126 to the communication units of the devices external to the outdoor unit 120.

[0025] The communication method between the communication unit of the external device and the outdoor unit communication unit 123 may be wired communication, or may be wireless communication using infrared communication, Wi-Fi, Bluetooth, or the like.

[0026] The acquisition unit 124 acquires from the server 200 and stores server-calculated discomfort index information, which is discomfort index information calculated in the server 200. The server-calculated discomfort index information is second discomfort index information in the air conditioning control system 1. The acquisition unit 124 transmits the server-calculated discomfort index information acquired from the server 200 to the outdoor unit discomfort index calculation unit 125.

[0027] The outdoor unit discomfort index calculation unit 125 acquires information on the indoor temperature detected by the indoor temperature sensor 1111 and information on the indoor humidity detected by the indoor humidity sensor 1112 from the indoor unit 110, and calculates the indoor discomfort index, i.e., indoor discomfort index information, using the acquired indoor temperature information and indoor humidity information.

[0028] The outdoor unit discomfort index calculation unit 125 is a first discomfort index calculation unit in the air conditioning control system 1. The discomfort index calculated in the outdoor unit discomfort index calculation unit 125 is a conditioner-calculated discomfort index, and is the first discomfort index in the air conditioning control system 1. Information on the conditioner-calculated discomfort index is conditioner-calculated discomfort index information. Information on the first discomfort index is first discomfort index information.

[0029] The outdoor unit discomfort index calculation unit 125 calculates the discomfort index using, for example, the following formula (1). As a result, the outdoor unit discomfort index calculation unit 125 obtains discomfort index information, which is information on the discomfort index. The discomfort index calculated by the outdoor unit discomfort index calculation unit 125 is the conditioner-calculated discomfort index calculated by the air conditioner 100. In formula (1), T is the indoor temperature (°C), and H is the indoor humidity (%).

[0030] 0.81T+0.01H (0.99T-14.3)+46.3...(1)

[0031] The outdoor unit discomfort index calculation section 125 stores the calculated conditioning unit calculated discomfort index information and the finally determined discomfort index information in the outdoor unit storage section 122 .

[0032] The outdoor unit control unit 126 is a control unit that controls the overall operation of the outdoor unit 120, and controls the operation of the air conditioner 100 by controlling the operation of the outdoor unit 120. The outdoor unit control unit 126, in conjunction with the indoor unit control unit 114, is capable of controlling the operation of the air conditioner 100 by automatic air conditioning control, which automatically controls air conditioning based on discomfort index information determined in the air conditioning control system 1 so that the indoor environment is comfortable according to the value of the discomfort index information, and normal air conditioning control, which controls air conditioning based on operating conditions set by the user via the remote control 130 or the like. The outdoor unit control unit 126 controls the transmission of the finally determined discomfort index information to the indoor unit control unit 114 of the indoor unit 110. The outdoor unit control unit 126 controls the operation of the air conditioner 100 based on at least the first discomfort index.

[0033] Fig. 4 is a block diagram showing the configuration of the remote controller 130 of the air conditioner 100 according to the first embodiment. As shown in Fig. 4, the remote controller 130 includes a remote controller operation unit 131, a remote controller display unit 132, a remote controller storage unit 133, a remote controller communication unit 134, and a remote controller control unit 135. The above-described components of the remote controller 130 can exchange information with each other.

[0034] The remote control operation unit 131 accepts setting operations related to air conditioning of the air conditioner 100 requested by the user. In other words, the remote control operation unit 131 is an interface for remotely controlling the operation of the air conditioner 100, and accepts operations from the user related to the operation of the air conditioner 100. When the remote control operation unit 131 accepts an operation from the user, it transmits information corresponding to the user operation to the remote control control unit 135 as operation information.

[0035] The remote control operation unit 131 is configured to allow the user to arbitrarily select various functions related to the air conditioning operation of the air conditioner 100, such as starting operation of the air conditioner 100, stopping operation of the air conditioner 100, selecting the operation mode of the air conditioner 100, changing the set temperature, changing the set humidity, setting the air volume, setting the air direction, and changing the settings of prohibited operations.

[0036] The remote control display unit 132 is a display unit that displays various information, and displays information and status necessary for air conditioning by the air conditioner 100, such as the set temperature and operating mode of the air conditioner 100, and switches and displays screens corresponding to operations on the remote control operation unit 131.

[0037] The remote control memory unit 133 stores various information necessary for air conditioning processing in the air conditioner 100, and temporarily or long-term stores information such as settings to be displayed on the remote control display unit 132 and image data related to the settings.

[0038] The remote control communication unit 134 is capable of two-way communication of information with the indoor unit communication unit 113 of the indoor unit 110. The communication method between the indoor unit communication unit 113 and the remote control communication unit 134 may be wired communication, or may be wireless communication using infrared communication, Wi-Fi, Bluetooth, or the like.

[0039] The remote control control unit 135 controls the overall operation of the remote control 130. The remote control control unit 135 controls the remote control 130 based on operation information transmitted from the remote control operation unit 131. In addition, the remote control control unit 135 transmits the operation information transmitted from the remote control operation unit 131 to the indoor unit communication unit 113 of the indoor unit 110.

[0040] The server 200 acquires user information, environmental information, and user setting information from the external control terminal 300, and stores and accumulates the information in the server storage unit 220. Then, the server 200 calculates a discomfort index based on the data accumulated in the server storage unit 220 using machine learning.

[0041] The user information includes the gender, age, and clothing of the user, and discomfort index information reported by the user when using the air conditioner 100. Therefore, in more detail, the user information includes user characteristic information indicating the user's characteristics, such as gender, age, and clothing, and discomfort index information reported by the user.

[0042] The discomfort index information reported by the user is information about the discomfort index of the indoor temperature sensation felt by the user when using the air conditioner 100. The discomfort index information reported by the user can be, for example, a PMV that quantifies the temperature sensation, such as hot, slightly warm, comfortable, slightly cool, or cool.

[0043] The environmental information is information that indicates the environment in which the air conditioner 100 is used, such as the weather, season, and time of day when the air conditioner 100 is used.

[0044] The user setting information is information about the operating conditions of the air conditioner 100 that are set by the user in order to control the operation of the air conditioner 100 .

[0045] 5 is a block diagram showing the configuration of the server 200 according to the first embodiment. The server 200 includes a server communication unit 210, a server storage unit 220, a server discomfort index calculation unit 230, and a server control unit 240. The components of the server 20 can exchange information with each other.

[0046] The server communication unit 210 is capable of communicating with the indoor unit communication unit 113 of the indoor unit 110 and the outdoor unit communication unit 123 of the outdoor unit 120. The indoor unit communication unit 113 and the outdoor unit communication unit 123 are capable of communicating with the server communication unit 210, for example, via the Internet 400. The server communication unit 210 receives information transmitted from the indoor unit communication unit 113 or the outdoor unit communication unit 123 via the Internet 400. The server communication unit 210 transmits the received information to the server control unit 240. In addition, the server communication unit 210 transmits information transmitted from the server control unit 240 to the indoor unit communication unit 113 or the outdoor unit communication unit 123.

[0047] The server communication unit 210 is capable of communicating with a later-described device communication unit 340 of the external control terminal 300. The device communication unit 340 of the external control terminal 300 and the server communication unit 210 are capable of communicating via, for example, the Internet 400. The server communication unit 210 transmits information transmitted from the server control unit 240 to the device communication unit 340 of the external control terminal 300 via the Internet 400.

[0048] The server storage unit 220 stores various types of information used for controlling the server 200. The server storage unit 220 also has a storage unit 221 that stores and accumulates information acquired from the external control terminal 300, such as environmental information, user information, and user setting information, as well as server-calculated discomfort index information. The storage unit 221 accumulates user information and environmental information transmitted from multiple external control terminals 300, grouped by similar information. This makes it possible to improve the calculation accuracy of the server-calculated discomfort index information when calculating server-calculated discomfort index information using machine learning, which will be described later, from multiple pieces of information with similar characteristics.

[0049] The server discomfort index calculation unit 230 includes a machine learning device 270 having a learning device 250 and an inference device 260, and calculates the discomfort index of the room by machine learning, i.e., calculates the discomfort index information of the room. The learning device 250 and the inference device 260 will be described in detail later.

[0050] The server discomfort index calculation unit 230 is a second discomfort index calculation unit in the air conditioning control system 1. The discomfort index calculated in the server discomfort index calculation unit 230 is a server-calculated discomfort index, and is a second discomfort index in the air conditioning control system 1. Information on the server-calculated discomfort index is server-calculated discomfort index information. Information on the second discomfort index is second discomfort index information.

[0051] The server control unit 240 controls the overall processing of the server 200. The server control unit 240 receives environmental information from the external control terminal 300 via the server communication unit 210, and stores the received environmental information in the server storage unit 220. In this way, the environmental information is acquired in the server 200. The server control unit 240 also receives user information from the external control terminal 300 via the server communication unit 210, and stores the received user information in the server storage unit 220. In this way, the user information is acquired in the server 200.

[0052] The external control terminal 300 has a function of remotely setting and controlling the operating conditions of the air conditioner 100 via the server 200, and remotely controlling the operation of the air conditioner 100. The external control terminal 300 also has a function of receiving various types of information from the user, such as user information, user setting information, and environmental information, and transmitting the information to the server 200.

[0053] 6 is a block diagram showing the functional configuration of the external control terminal 300 according to the first embodiment. The external control terminal 300 includes a terminal operation unit 310, a terminal display unit 320, a terminal storage unit 330, a terminal communication unit 340, and a terminal control unit 350. Information can be exchanged between the above-described components of the external control terminal 300.

[0054] The terminal operation unit 310 is an operation reception unit that receives user operations, i.e., operations from the user. The terminal operation unit 310 receives various operations from the user. When the terminal operation unit 310 receives an operation from the user, it transmits operation information corresponding to the operation to the terminal control unit 350. The terminal operation unit 310 is composed of input devices such as a keyboard, a mouse, and a touch panel display with a touch panel function, and operations on the external control terminal 300 are performed by the user.

[0055] The terminal display unit 320 is a display unit that displays various types of information inside the external control terminal 300. The terminal display unit 320 also displays various types of information acquired from the air conditioner 100 and the server 200, and presents the various types of information to the user.

[0056] The terminal storage unit 330 is a storage unit that stores various types of information inside the external control terminal 300. The terminal storage unit 330 stores various types of information such as user information, user setting information, and environmental information.

[0057] The terminal communication unit 340 is connected to the Internet 400 and communicates with the server 200. The terminal communication unit 340 transmits various pieces of information transmitted from the server 200 to the terminal control unit 350. The terminal communication unit 340 transmits various pieces of information transmitted from the terminal control unit 350 to the server 200.

[0058] The terminal control unit 350 controls the overall processing of the external control terminal 300. The terminal control unit 350 also controls the transmission of various information, such as user information, user setting information, and environmental information, to the server 200 based on operations from the user.

[0059] Furthermore, based on an operation from the user, the terminal control unit 350 controls the display of various information acquired from the server 200 on the terminal display unit 320. In other words, the terminal control unit 350 functions as a display control unit that controls the display of information on the terminal display unit 320.

[0060] Next, a description will be given of the air conditioning control operation of the air conditioning control system 1. Fig. 7 is a flowchart showing the procedure of the air conditioning control operation of the air conditioning control system 1 according to the first embodiment.

[0061] First, in step S110, indoor temperature and humidity information is acquired in the air conditioner 100. Specifically, the indoor temperature sensor 1111 of the indoor unit 110 of the air conditioner 100 detects the indoor temperature as the indoor temperature and humidity information. Furthermore, the indoor humidity sensor 1112 of the indoor unit 110 of the air conditioner 100 detects the indoor humidity as the indoor temperature and humidity information. Then, the process proceeds to step S120.

[0062] In step S120, the outdoor unit discomfort index calculation unit 125 of the outdoor unit 120 of the air conditioner 100 calculates a discomfort index. Specifically, the outdoor unit discomfort index calculation unit 125 acquires information on the indoor temperature detected by the indoor temperature sensor 1111 and information on the indoor humidity detected by the indoor humidity sensor 1112, and calculates the discomfort index using the acquired indoor temperature information and indoor humidity information according to the above-mentioned formula (1). The discomfort index calculated by the outdoor unit discomfort index calculation unit 125 in step S120 is the conditioner-calculated discomfort index calculated by the air conditioner 100. Then, the process proceeds to step S130.

[0063] In step S130, it is determined whether or not there is server-calculated discomfort index information, which is information on the discomfort index calculated by the server 200. Specifically, the outdoor unit discomfort index calculation unit 125 determines whether or not there is server-calculated discomfort index information.

[0064] When the acquisition unit 124 of the outdoor unit 120 receives the server-calculated discomfort index information from the server 200 via the outdoor unit communication unit 123, it stores the received server-calculated discomfort index information. The server-calculated discomfort index information is always updated to the latest information. The acquisition unit 124 may store the discomfort index information acquired from the server 200 in the outdoor unit storage unit 122.

[0065] The outdoor unit discomfort index calculation unit 125 determines that server-calculated discomfort index information exists when server-calculated discomfort index information acquired and stored by the acquisition unit 124 within a predetermined time range is stored in the acquisition unit 124. The outdoor unit discomfort index calculation unit 125 determines that server-calculated discomfort index information does not exist when server-calculated discomfort index information acquired and stored by the acquisition unit 124 within a predetermined time range is not stored in the acquisition unit 124.

[0066] If it is determined that server-calculated discomfort index information exists, the answer is Yes in step S130, and the process proceeds to step S140. If it is determined that server-calculated discomfort index information does not exist, the answer is No in step S130, and the process proceeds to step S160.

[0067] In step S140, the server-calculated discomfort index information is acquired in the outdoor unit discomfort index calculation unit 125. Specifically, the outdoor unit discomfort index calculation unit 125 acquires the server-calculated discomfort index information from the acquisition unit 124. Thereafter, the process proceeds to step S150.

[0068] In step S150, the discomfort index is corrected. Specifically, the outdoor unit discomfort index calculation unit 125 corrects the discomfort index based on the server-calculated discomfort index information acquired from the acquisition unit 124 and the conditioner-calculated discomfort index information, which is information on the conditioner-calculated discomfort index calculated in step S120. Details of the discomfort index correction process will be described later. Then, the process proceeds to step S160.

[0069] In step S160, discomfort index information is determined. Specifically, the outdoor unit discomfort index calculation unit 125 determines a discomfort index, thereby determining discomfort index information, which is information about the discomfort index. If it is determined in step S130 that server-calculated discomfort index information exists, the outdoor unit discomfort index calculation unit 125 determines the discomfort index corrected in step S150 as the discomfort index. If it is determined in step S130 that server-calculated discomfort index information does not exist, the outdoor unit discomfort index calculation unit 125 determines the harmonics-calculated discomfort index calculated by the outdoor unit discomfort index calculation unit 125 in step S120 as the discomfort index. As a result, the outdoor unit discomfort index calculation unit 125 determines the determined discomfort index information as the discomfort index information. Then, the process proceeds to step S170.

[0070] In step S170, the air conditioner 100 is controlled. Specifically, the indoor unit control unit 114 of the indoor unit 110 and the outdoor unit control unit 126 of the outdoor unit 120 of the air conditioner 100 control the air conditioning of the air conditioner 100 based on the discomfort index information determined in step S160. The indoor unit control unit 114 of the indoor unit 110 and the outdoor unit control unit 126 of the outdoor unit 120 control the air conditioning of the air conditioner 100 so that the discomfort index indicated in the discomfort index information determined in step S160 satisfies the target discomfort index information. In other words, the indoor unit control unit 114 of the indoor unit 110 and the outdoor unit control unit 126 of the outdoor unit 120 automatically control the air conditioning based on the discomfort index information so that the indoor environment is comfortable for occupants.

[0071] The target discomfort index information is information on a discomfort index at which the user feels the indoor environment is comfortable, i.e., information on a discomfort index set so that the indoor environment is comfortable for the occupants. The target discomfort index information may be information on a range of discomfort indexes or may be a single discomfort index value. The target discomfort index information is determined in advance and stored in the outdoor unit storage unit 122. The target discomfort index information can be changed from the remote control 130 or the external control terminal 300.

[0072] Next, a description will be given of the calculation of discomfort index information in the server 200. Fig. 8 is a flowchart showing the procedure for determining discomfort index information in the server 200 of the air conditioning control system 1 according to the first embodiment.

[0073] First, in step S210, environmental information is acquired in the server 200. Specifically, the server control unit 240 of the server 200 receives the environmental information from the external control terminal 300 via the server communication unit 210, and stores the received environmental information in the server storage unit 220. In this way, the environmental information is acquired in the server 200. Then, the process proceeds to step S220.

[0074] In step S220, user information is acquired. Specifically, the server control unit 240 receives the user information from the external control terminal 300 via the server communication unit 210, and stores the received user information in the server storage unit 220 of the server 200. In this way, the user information is acquired in the server 200. That is, in step S220, user characteristic information indicating user characteristics such as age and clothing, and discomfort index information declared by the user are acquired as the user information. Thereafter, the process proceeds to step S230.

[0075] In step S230, it is determined whether or not there is learning information related to the discomfort index. Specifically, the server discomfort index calculation unit 230 determines whether or not there is learning information related to the discomfort index in the server discomfort index calculation unit 230. The learning information related to the discomfort index is the trained model 283, which will be described later. If it is determined that there is learning information related to the discomfort index, the answer is Yes in step S230, and the process proceeds to step S240. If it is determined that there is no learning information related to the discomfort index, the answer is No in step S230, and the process proceeds to step S270.

[0076] In step S240, the discomfort index is calculated by applying the learning information related to the discomfort index. Specifically, the server discomfort index calculation unit 230 calculates the server-calculated discomfort index using machine learning, using the environmental information acquired in step S210, the user information acquired in step S220, and a trained model 283 (described later). The discomfort index calculated in step S240 is the server-calculated discomfort index. Then, the process proceeds to step S250.

[0077] In step S250, the discomfort index information is presented to the outdoor unit 120. Specifically, the server discomfort index calculation unit 230 transmits the server-calculated discomfort index information of the server-calculated discomfort index calculated in step S240 to the acquisition unit 124 of the outdoor unit 120.

[0078] When the acquisition unit 124 receives the server-calculated discomfort index information from the server discomfort index calculation unit 230, the acquisition unit 124 stores the server-calculated discomfort index information. Then, the process proceeds to step S260.

[0079] In step S260, the learning information related to the discomfort index is updated. Specifically, the learning device 250 (described later) learns the learning information related to the discomfort index using the environmental information acquired in step S210, the user information acquired in step S220, and the server-calculated discomfort index calculated in step S240, and updates the trained model 283.

[0080] In step S270, learning information related to the discomfort index is created. Specifically, the learning device 250, which will be described later, learns the discomfort index and creates the learning information related to the discomfort index. Then, the process proceeds to step S240. When proceeding from step S230 to step S270 and step S240, the server discomfort index calculation unit 230 does not create learning information related to the discomfort index until the learning information related to the discomfort index is created.

[0081] Next, the correction process of the discomfort index information in the above-mentioned step S150 will be described. Fig. 9 is a flowchart showing the procedure for correcting the discomfort index information in the air conditioning control system 1 according to embodiment 1. The process shown below is the process performed in the above-mentioned step S150.

[0082] First, in step S310, discomfort index information that has a large difference from the target discomfort index information is determined between the harmony-machine-calculated discomfort index information and the server-calculated discomfort index information. Specifically, the outdoor unit discomfort index calculation unit 125 compares the harmony-machine-calculated discomfort index information, which is information on the harmony-machine-calculated discomfort index calculated in step S120, with the server-calculated discomfort index information acquired in step S140, and determines discomfort index information that has a large difference from the target discomfort index information. In other words, the outdoor unit discomfort index calculation unit 125 compares the discomfort index indicated in the harmony-machine-calculated discomfort index with the discomfort index indicated in the server-calculated discomfort index information, and determines discomfort index information that has a large difference from the discomfort index indicated in the target discomfort index information. Then, the process proceeds to step S320.

[0083] In step S320, discomfort index information is determined. Specifically, the outdoor unit discomfort index calculation unit 125 determines the discomfort index information determined in step S310 as discomfort index information having a large difference from the target discomfort index information between the harmony-machine-calculated discomfort index information and the server-calculated discomfort index information as discomfort index information for the correction process.

[0084] Thereafter, the air conditioner 100 performs air conditioning control based on the discomfort index information in the correction process determined in step S320.

[0085] However, if the discomfort index information declared by the user in the user information indicates that the user does not find the indoor environment uncomfortable, the current air conditioning control is maintained in the air conditioner 100. If the user does not find the indoor environment uncomfortable, there is no need to change the air conditioning control of the air conditioner 100.

[0086] Next, the calculation of the discomfort index using machine learning by the server discomfort index calculation unit 230 in step S240 described above will be described. The server discomfort index calculation unit 230 calculates the discomfort index, i.e., calculates discomfort index information, using a machine learning device 270 including a learning device 250 and an inference device 260. The configurations of the learning device 250 and the inference device 260 will be described below.

[0087] 10 is a diagram showing the configuration of a learning device 250 according to the first embodiment. The learning device 250 includes a data acquisition unit 251, a model generation unit 252, and a trained model storage unit 253. The data acquisition unit 251 is a first data acquisition unit in the air conditioning control system 1. The trained model storage unit 253 may be located outside the learning device 250, or may be provided in the server storage unit 220 of the server 200.

[0088] The learning device 250 learns the discomfort index, i.e., learns discomfort index information, based on learning data. The learning device 250 learns the discomfort index information based on learning data for a plurality of users that is input to the learning device 250. This allows the learning device 250 to learn discomfort index information taking into account the learning data for a plurality of users.

[0089] The data acquiring unit 251 acquires, as learning data, input information 281 and discomfort index information 282 of a state corresponding to the input information 281. The input information 281 includes environmental information and user information. The discomfort index information 282 is discomfort index information corresponding to the state indicated by the input information 281. Here, the learning data is data in which the input information 281 and the discomfort index information 282 are associated with each other. The data acquiring unit 251 acquires the learning data from the server control unit 240 of the server 200. The learning data may also be input to the data acquiring unit 251 from a device external to the server 200. The data acquiring unit 251 generates the learning data by associating the input information 281 with the discomfort index information 282.

[0090] The model generation unit 252 learns discomfort index information based on learning data created based on a combination of input information 281 and discomfort index information 282 sent from the data acquisition unit 251. The model generation unit 252 has a function of a learning unit that generates a trained model 283 for inferring appropriate discomfort index information corresponding to a combination of environmental information and user information from the input information 281 and discomfort index information 282.

[0091] Next, a processing procedure of the learning process by the learning device 250 will be described with reference to Fig. 11. Fig. 11 is a flowchart showing a processing procedure of the learning process by the learning device 250 according to the first embodiment.

[0092] In step S410, the data acquiring unit 251 acquires learning data. Specifically, the data acquiring unit 251 acquires input information 281 and discomfort index information 282 as learning data. Note that the data acquiring unit 251 may acquire the input information 281 and the discomfort index information 282 at the same timing, or may acquire them at different timings. In other words, the data acquiring unit 251 may acquire the input information 281 and the discomfort index information 282 at any timing as long as the input information 281 and the discomfort index information 282 can be associated with each other.

[0093] In step S420, the model generation unit 252 executes a learning process in accordance with the learning data, which is a combination of the input information 281 and the discomfort index information 282 acquired by the data acquisition unit 251. The model generation unit 252 generates a learned model 283, for example, by so-called supervised learning in accordance with the learning data.

[0094] In step S430, the trained model storage unit 253 stores the trained model 283. That is, the model generation unit 252 stores the generated trained model 283 in the trained model storage unit 253.

[0095] The learning algorithm used by the model generation unit 252 may be a known algorithm such as supervised learning, unsupervised learning, reinforcement learning, etc. As an example, a case will be described in which the model generation unit 252 executes supervised learning using a neural network.

[0096] The model generation unit 252 learns discomfort index information by so-called supervised learning, for example, in accordance with a neural network model. Here, supervised learning refers to a technique in which a learning device is provided with pairs of input and result (label) data, and the learning device learns features of the learning data and infers a result from the input.

[0097] A neural network is composed of an input layer consisting of multiple neurons, an intermediate layer (hidden layer) consisting of multiple neurons, and an output layer consisting of multiple neurons. The intermediate layer may be one layer, or two or more layers.

[0098] 12 is a diagram showing the configuration of a neural network used by the learning device 250 according to the first embodiment. For example, in the case of a three-layer neural network as shown in FIG. 12, when a plurality of pieces of data are input to input layers X1 to X3, the values ​​are multiplied by weights w11 to w16 and input to intermediate layers Y1 to Y2, and the results are further multiplied by weights w21 to w26 and output from output layers Z1 to Z3. This output result varies depending on the values ​​of weights w11 to w16 and weights w21 to w26.

[0099] In the first embodiment, the neural network learns discomfort index information by so-called supervised learning in accordance with learning data (data set) created based on a combination of input information 281 acquired by the data acquisition unit 251 and discomfort index information 282.

[0100] That is, the neural network learns by inputting input information 281 to input layers X1 to X3 and adjusting weights w11 to w16 and w21 to w26 so that the results output from output layers Z1 to Z3 approach discomfort index information 282.

[0101] The model generation unit 252 generates and outputs a trained model 283 by performing the above-described learning.

[0102] The trained model storage unit 253 stores the trained model 283 output from the model generation unit 252.

[0103] 13 is a diagram showing the configuration of an inference device 260 according to the first embodiment. The inference device 260 includes a data acquisition unit 261 and an inference unit 262. The data acquisition unit 261 is a second data acquisition unit in the air conditioning control system 1. The inference unit 262 is connected to the learned model storage unit 253.

[0104] Environmental information in the input information 281 is input from the server control unit 240 of the server 200 to the data acquisition unit 261. User information in the input information 281 is input from the server control unit 240 to the data acquisition unit 261. The inference unit 262 uses the trained model 283 obtained by the learning device 250 to output server-calculated discomfort index information, which is information on the server-calculated discomfort index, as discomfort index information.

[0105] The data acquisition unit 261 acquires environmental information and user information as inference data. The inference data is input to the data acquisition unit 261 from the server control unit 240.

[0106] The inference unit 262 outputs discomfort index information using the obtained trained model 283. The inference unit 262 reads out the trained model 283 from the trained model storage unit 253. The inference unit 262 inputs the input information 281 to the trained model 283. As a result, the inference unit 262 infers discomfort index information. That is, the inference unit 262 can output discomfort index information inferred from the input information 281 by inputting the input information 281 for inferring discomfort index information, acquired by the data acquisition unit 261, into the trained model 283 for inferring discomfort index information.

[0107] Next, the procedure of the inference process performed by the inference device 260 will be described with reference to Fig. 14. Fig. 14 is a flowchart showing the procedure of the inference process performed by the inference device 260 according to the first embodiment.

[0108] In step S510, the data acquisition unit 261 acquires data for inference, that is, the data acquisition unit 261 acquires environmental information and user information as data for inference.

[0109] In step S520, the inference unit 262 inputs the environmental information and user information, which are the inference data acquired by the data acquisition unit 261, into the learned model 283 stored in the learned model storage unit 253, and obtains discomfort index information corresponding to the input information as the inference result obtained by the learned model 283.

[0110] In step S530, the inference result obtained by the trained model 283 is output to the outdoor unit 120. Specifically, the inference unit 262 transmits the inference result obtained by the trained model 283 to the server control unit 240. The server control unit 240 transmits the inference result to the outdoor unit control unit 126 of the outdoor unit 120.

[0111] The inference result obtained by the trained model 283 is discomfort index information corresponding to the inference data acquired by the data acquisition unit 261.

[0112] In step S540, the outdoor unit 120 corrects the discomfort index in step S150 described above using the inference result to determine discomfort index information, and controls the air conditioner 100 based on the determined discomfort index information.

[0113] In this way, the inference unit 262 can easily infer discomfort index information by using the trained model 283. This allows the air conditioner 100 to perform air conditioning control by utilizing the discomfort index information calculated by the air conditioner 100 and the server 200.

[0114] Although the learning device 250 and the inference device 260 are used to learn discomfort index information, the learning device 250 and the inference device 260 may be devices separate from the server 200, connected to the server 200 via a network such as the Internet. At least one of the learning device 250 and the inference device 260 may be connected to the server 200 via a network, for example. At least one of the learning device 250 and the inference device 260 may be devices separate from the server 200. At least one of the learning device 250 and the inference device 260 may exist on a cloud server. At least one of the learning device 250 and the inference device 260 may be built into the server 200. At least one of the learning device 250 and the inference device 260 may be built into the external control terminal 300.

[0115] Furthermore, in the first embodiment, it has been described that the discomfort index information is output using the trained model 283 trained by the model generating unit 252 of the server 200, but it is also possible to acquire a trained model from an external device such as another server 200 and output the discomfort index information based on this trained model.

[0116] In addition, in the first embodiment, a case where supervised learning is applied to the learning algorithm used by the model generation unit 252 has been described, but the present invention is not limited to this. As for the learning algorithm, reinforcement learning, unsupervised learning, semi-supervised learning, or the like can also be applied in addition to supervised learning.

[0117] The model generation unit 252 may also learn discomfort index information according to learning data created for multiple external control terminals 300. The model generation unit 252 may acquire learning data from multiple external control terminals 300 used in the same area, or may learn discomfort index information using learning data collected from multiple external control terminals 300 operating independently in different areas. It is also possible to add or remove external control terminals 300 that collect learning data from the targets midway. Furthermore, a learning device that has learned discomfort index information for a certain external control terminal 300 may be applied to another external control terminal 300, and the discomfort index information for the other external control terminal 300 may be re-learned and updated.

[0118] In addition, the learning algorithm used in the model generation unit 252 can be deep learning, which learns to extract the features themselves, or machine learning can be performed according to other known methods, such as support vector machines.

[0119] According to the air conditioning control system 1 of the above-described first embodiment, an air conditioning control system is provided that includes an air conditioner and a server capable of communicating with the air conditioner, and the air conditioner has an indoor temperature sensor that detects the temperature of the room, which is the air conditioning target area of ​​the air conditioner, an indoor humidity sensor that detects the humidity of the room, a first discomfort index calculation unit that calculates a first discomfort index of the room using information on the indoor temperature detected by the indoor temperature sensor and information on the indoor humidity detected by the indoor humidity sensor, and a control unit that controls the operation of the air conditioner based on the indoor discomfort index, and a server that has a second discomfort index calculation unit that calculates a second discomfort index based on user information including user characteristic information that indicates the characteristics of the user when using the air conditioner and discomfort index information that reports the indoor temperature sensation felt by the user when using the air conditioner, and environmental information that is information that indicates the usage environment of the air conditioner, and the control unit controls the operation of the air conditioner based on at least the first discomfort index.

[0120] Furthermore, in the air conditioning control system 1 according to the first embodiment, a learning device is realized that includes: user information including user characteristic information indicating the characteristics of the user when using the air conditioner and discomfort index information reporting the indoor temperature sensation felt by the user when using the air conditioner; environmental information that is information indicating the usage environment of the air conditioner; and discomfort index information of a state corresponding to the environmental information and the user information; and a model generation unit that uses the learning data to generate a trained model for inferring discomfort index information corresponding to the combination of the environmental information and the user information.

[0121] Furthermore, in the air conditioning control system 1 according to the first embodiment, an inference device is realized which includes a second data acquisition unit that acquires user information including user characteristic information indicating the characteristics of the user when using the air conditioner and discomfort index information reporting the indoor temperature sensation felt by the user when using the air conditioner, and environmental information that is information indicating the usage environment of the air conditioner, and an inference unit that outputs discomfort index information from the environmental information and the user information using a trained model for inferring discomfort index information corresponding to the combination of the environmental information and the user information.

[0122] The air conditioning control system 1 according to the first embodiment described above is configured to calculate the discomfort index in both the air conditioner 100 and the server 200 to obtain discomfort index information, and therefore can calculate the discomfort index and obtain discomfort index information without input of information from the user such as user information. This allows the air conditioning control system 1 to perform heating and cooling control in the air conditioner 100 without input of information from the user such as user information.

[0123] That is, in the air conditioning control system 1, the outdoor unit discomfort index calculation unit 125 of the outdoor unit 120 of the air conditioner 100 can calculate a discomfort index using information about the indoor temperature detected by the indoor temperature sensor 1111 and information about the indoor humidity detected by the indoor humidity sensor 1112. That is, the air conditioning control system 1 calculates the conditioner-calculated discomfort index as a discomfort index in the air conditioner 100 using only information obtained by the air conditioner 100, without using information from the user. In this way, the air conditioning control system 1 can obtain discomfort index information by the air conditioner 100 alone, without using information from the user, and can automatically control the air conditioning of the air conditioner 100 based on the discomfort index information so that the indoor environment is comfortable according to the value of the discomfort index information.

[0124] As a result, the air conditioning control system 1 eliminates the inconvenience of users having to frequently input information such as user information in order to obtain a comfortable indoor environment for the user, thereby reducing the burden on the user and improving user comfort.

[0125] Furthermore, the air conditioning control system 1 is configured so that the server 200 also calculates discomfort index information based on environmental information and user information, making it possible to implement air conditioning control that is more comfortable for the user. Furthermore, the server 200 is configured to calculate discomfort index information using machine learning, making it possible to calculate discomfort index information with higher accuracy, making it possible to implement air conditioning control that is more comfortable for the user.

[0126] Next, the hardware configuration of each of the control units 80 according to the first embodiment will be described. The control unit 80 according to the first embodiment corresponds to the indoor unit control unit 114 of the indoor unit 110 of the air conditioner 100, the outdoor unit control unit 126 of the outdoor unit 120 of the air conditioner 100, the remote control control unit 135 of the remote control 130, the server control unit 240 of the server 200, and the terminal control unit 350 of the external control terminal 300 according to the first embodiment. Each function of the control unit 80 according to the first embodiment is realized by a processing circuit. The processing circuit may be dedicated hardware, or may be a processing unit that executes a program stored in a storage device.

[0127] When the processing circuit is dedicated hardware, the processing circuit may be a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an application specific integrated circuit, a field programmable gate array, or a combination thereof. Figure 15 is a diagram showing a configuration in which the functions of the control unit 80 according to the first embodiment are realized by hardware. The processing circuit 81 incorporates a logic circuit 81a that realizes the functions of the control unit 80.

[0128] When the processing circuit 81 is a processing device, the functions of the control unit 80 are realized by software, firmware, or a combination of software and firmware.

[0129] FIG. 16 is a diagram illustrating a configuration in which the functions of the control unit 80 according to the first embodiment are implemented by software. The processing circuit 81 includes a processor 811 that executes a program 81b, a random access memory 812 that the processor 811 uses as a work area, and a storage device 813 that stores the program 81b. The processor 811 deploys the program 81b stored in the storage device 813 on the random access memory 812 and executes it, thereby realizing the functions of the control unit 80. The software or firmware is written in a programming language and stored in the storage device 813. The processor 811 may be, but is not limited to, a central processing unit. The storage device 813 may be a semiconductor memory such as a random access memory (RAM), a read-only memory (ROM), a flash memory, an erasable programmable read-only memory (EPROM), or an electrically erasable programmable read-only memory (EEPROM). The semiconductor memory may be either a non-volatile memory or a volatile memory. In addition to semiconductor memory, a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disc) can be used as the storage device 813. The processor 811 may output data such as calculation results to the storage device 813 for storage, or may store the data in an auxiliary storage device (not shown) via the random access memory 812. By integrating the processor 811, the random access memory 812, and the storage device 813 on a single chip, the functions of the control unit 80 can be realized by a microcomputer.

[0130] The processing circuitry 81 reads and executes the program 81b stored in the storage device 813 to realize the functions of the control unit 80. The program 81b can also be said to cause the computer to execute the procedures and methods for realizing the functions of the control unit 80.

[0131] The processing circuit 81 may be configured so that some of the functions of the control unit 80 are realized by dedicated hardware, and some of the functions of the control unit 80 are realized by software or firmware.

[0132] In this way, the processing circuitry 81 can realize each of the above-described functions by hardware, software, firmware, or a combination of these.

[0133] The configurations shown in the above embodiments are merely examples, and may be combined with other known technologies, or different embodiments may be combined with each other. It is also possible to omit or modify parts of the configurations as long as they do not deviate from the gist of the invention.

[0134] 1 Air conditioning control system, 80 Control unit, 81 Processing circuit, 81a Logic circuit, 81b Program, 100 Air conditioner, 110 Indoor unit, 111 Indoor unit sensor, 112 Indoor unit memory unit, 113 Indoor unit communication unit, 114 Indoor unit control unit, 120 Outdoor unit, 121 Outdoor unit sensor, 122 Outdoor unit memory unit, 123 Outdoor unit communication unit, 124 Acquisition unit, 125 Outdoor unit discomfort index calculation unit, 126 Outdoor unit control unit, 130 Remote controller, 131 Remote controller operation unit, 132 Remote controller display unit, 133 Remote controller memory unit, 134 Remote controller communication unit, 135 Remote controller control unit, 200 Server, 210 Server communication unit, 220 Server memory unit, 221 Accumulation unit, 230 Server discomfort index calculation unit, 240 Server control unit, 250 Learning device, 251, 261 Data acquisition unit, 252 Model generation unit, 253 Learned model storage unit, 260 Inference device, 262 Inference unit, 270 Machine learning device, 281 Input information, 282 Discomfort index information, 283 Learned model, 300 External control terminal, 310 Terminal operation unit, 320 Terminal display unit, 330 Terminal storage unit, 340 Terminal communication unit, 350 Terminal control unit, 400 Internet, 811 Processor, 812 Random access memory, 813 Storage device, 1111 Indoor temperature sensor, 1112 Indoor humidity sensor.

Claims

1. An air conditioning control system comprising an air conditioner and a server capable of communicating with the air conditioner, an indoor temperature sensor for detecting a temperature inside a room which is an area to be air-conditioned by the air conditioner; an indoor humidity sensor for detecting the indoor humidity; a first discomfort index calculation unit that calculates a first discomfort index in the room using information on the indoor temperature detected by the indoor temperature sensor and information on the indoor humidity detected by the indoor humidity sensor; A control unit that controls the operation of the air conditioner based on the indoor discomfort index; An air conditioner having a server having a second discomfort index calculation unit that calculates a second discomfort index based on user information including user characteristic information indicating characteristics of a user when using the air conditioner and discomfort index information reporting a sense of indoor temperature felt by the user when using the air conditioner, and environmental information that is information indicating an environment in which the air conditioner is used; Equipped with The control unit is Controlling operation of the air conditioner based on at least the first discomfort index; controlling the operation of the air conditioner based on a discomfort index that has a large difference from target discomfort index information, which is information on the discomfort index at which the user feels comfortable in the indoor environment, of the first discomfort index and the second discomfort index; Air conditioning control system.

2. The control unit controls the operation of the air conditioner based on the first discomfort index and the second discomfort index. The air conditioning control system according to claim 1 .

3. The user characteristic information includes the gender, age, and clothing of the user when using the air conditioner.

3. An air conditioning control system according to claim 1 or 2.

4. The environmental information includes the weather, season, and time when the air conditioner is used. The air conditioning control system according to claim 1 .

5. The server accumulates the user information and the environmental information transmitted from a plurality of external control terminals that remotely operate settings and control of the operating conditions of the air conditioner via the server, for each group of similar information. The air conditioning control system according to claim 1 .

6. The server, a first data acquisition unit that acquires learning data including the user information, the environmental information, and the discomfort index information of a state corresponding to the environmental information and the user information; a model generation unit that generates a trained model for inferring the discomfort index information corresponding to a combination of the environmental information and the user information, using the learning data; A learning device having The air conditioning control system according to claim 1 .

7. The server, a second data acquisition unit that acquires the user information and the environmental information; an inference unit that outputs the discomfort index information from the environmental information and the user information by using a trained model for inferring the discomfort index information corresponding to a combination of the environmental information and the user information; a reasoning device comprising: The air conditioning control system according to claim 1 .