Air conditioning system, learning device and inferring device

Abstract

To support improvement of comfort of a user in a space to be cooled and dehumidified.SOLUTION: An air conditioning system includes: air-conditioning means capable of cooling and dehumidifying an object space; biological information acquisition means for acquiring biological information on a user in the object space; temperature information acquisition means for acquiring information on the room temperature in the object space; humidity information acquisition means for acquiring information on the humidity in the object space; learning means for learning a humidity threshold value X and a temperature threshold value T from the biological information and the information on the humidity; and control means for causing the air-conditioning means to perform cooling when the room temperature in the object space is the temperature threshold value T or higher and causing the air-conditioning means to perform dehumidification when the room temperature in the object space is lower than the temperature threshold value T and the humidity in the object space is the humidity threshold value X or higher.SELECTED DRAWING: Figure 4

Description

Technical Field

[0001] The present disclosure relates to an air conditioning system, a learning device, and an inference device.

Background Art

[0002] As a conventional technique, for example, Patent Document 1 discloses a technique for automatically switching between the cooling and dehumidifying functions of an air conditioner. In Patent Document 1, switching between cooling and dehumidifying is performed using a predetermined determination value.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] When the determination value for switching between cooling and dehumidifying is a predetermined value, the actual environment cannot be sufficiently considered, and some users may feel uncomfortable.

[0005] The present disclosure is for solving the above problems. An object of the present disclosure is to provide an air conditioning system, a learning device, and an inference device that can assist in improving the comfort of a user in a target space for cooling and dehumidifying.

Means for Solving the Problems

[0006] The air conditioning system according to the present disclosure includes an air conditioning means capable of cooling and dehumidifying a target space, a biological information acquisition means for acquiring biological information of a user in the target space, a temperature information acquisition means for acquiring information on the room temperature in the target space, a humidity information acquisition means for acquiring information on the humidity in the target space, a learning means for learning a humidity threshold value X from the biological information and the humidity information, and a control means for causing the air conditioning means to perform cooling when the room temperature in the target space is equal to or higher than a set value, and causing the air conditioning means to perform dehumidification when the room temperature in the target space is lower than the set value and the humidity in the target space is equal to or higher than the humidity threshold value X. Further, the air conditioning system according to the present disclosure includes an air conditioning means capable of cooling and dehumidifying a target space, a biological information acquisition means for acquiring biological information of a user in the target space, a temperature information acquisition means for acquiring information on the room temperature in the target space, a humidity information acquisition means for acquiring information on the humidity in the target space, a learning means for learning a temperature threshold value T from the biological information and the room temperature information, and a control means for causing the air conditioning means to perform cooling when the room temperature in the target space is equal to or higher than the temperature threshold value T, and causing the air conditioning means to perform dehumidification when the room temperature in the target space is lower than the temperature threshold value T and the humidity in the target space is equal to or higher than a set value. Further, the air conditioning system according to the present disclosure includes an air conditioning means capable of cooling and dehumidifying a target space, a biological information acquisition means for acquiring biological information of a user in the target space, a temperature information acquisition means for acquiring information on the room temperature in the target space, a humidity information acquisition means for acquiring information on the humidity in the target space, a learning means for learning a humidity threshold value X and a temperature threshold value T from the biological information, the humidity information and the room temperature information, and a control means for causing the air conditioning means to perform cooling when the room temperature in the target space is equal to or higher than the temperature threshold value T, and causing the air conditioning means to perform dehumidification when the room temperature in the target space is lower than the temperature threshold value T and the humidity in the target space is equal to or higher than the humidity threshold value X. In addition, the learning device according to the present disclosure is a learning device related to an air conditioning system that performs cooling when the room temperature in the target space is equal to or higher than a set value, and performs dehumidification when the room temperature in the target space is lower than the set value and the humidity in the target space is equal to or higher than a humidity threshold value X. The learning device includes a data acquisition unit that acquires learning data including information on the humidity in the target space, biometric information of the user in the target space, and information on the humidity set value input by the user of the air conditioning system, and a model generation unit that generates a learned model for inferring the humidity threshold value X from the humidity information and the biometric information using the learning data acquired by the data acquisition unit. In addition, the learning device according to the present disclosure is a learning device related to an air conditioning system that performs cooling when the room temperature in the target space is equal to or higher than a temperature threshold value T, and performs dehumidification when the room temperature in the target space is lower than the temperature threshold value T and the humidity is equal to or higher than a set value. The learning device includes a data acquisition unit that acquires learning data including information on the room temperature in the target space, biometric information of the user in the target space, and information on the room temperature set value input by the user of the air conditioning system, and a model generation unit that generates a learned model for inferring the temperature threshold value T from the room temperature information and the biometric information using the learning data acquired by the data acquisition unit. In addition, the learning device according to the present disclosure is a learning device related to an air conditioning system that performs cooling when the room temperature in the target space is equal to or higher than a temperature threshold value T, and performs dehumidification when the room temperature in the target space is lower than the temperature threshold value T and the humidity in the target space is equal to or higher than a humidity threshold value X. The learning device includes a data acquisition unit that acquires learning data including information on the humidity, room temperature in the target space, and biometric information of the user in the target space, and information on the humidity set value and temperature set value input by the user of the air conditioning system, and a model generation unit that generates a learned model for inferring the humidity threshold value X and the temperature threshold value T from the humidity information, the temperature information, and the biometric information using the learning data acquired by the data acquisition unit. In addition, the inference device according to the present disclosure is an inference device related to an air conditioning system that performs cooling when the room temperature in the target space is equal to or higher than a set value, and performs dehumidification when the room temperature in the target space is lower than the set value and the humidity in the target space is equal to or higher than a humidity threshold value X. The inference device includes a data acquisition unit that acquires information on the humidity in the target space and biometric information of a user in the target space, and an inference unit that uses a learned model for inferring the humidity threshold value X from the humidity information and the biometric information, and outputs the humidity threshold value X from the humidity information and the biometric information input from the data acquisition unit. In addition, the inference device according to the present disclosure is an inference device related to an air conditioning system that performs cooling when the room temperature in the target space is equal to or higher than a temperature threshold value T, and performs dehumidification when the room temperature in the target space is lower than the temperature threshold value T and the humidity in the target space is equal to or higher than a set value. The inference device includes a data acquisition unit that acquires information on the room temperature in the target space and biometric information of a user in the target space, and an inference unit that uses a learned model for inferring the temperature threshold value T from the room temperature information and the biometric information, and outputs the temperature threshold value T from the room temperature information and the biometric information input from the data acquisition unit. In addition, the inference device according to the present disclosure is an inference device related to an air conditioning system that performs cooling when the room temperature in the target space is equal to or higher than a temperature threshold value T, and performs dehumidification when the room temperature in the target space is lower than the temperature threshold value T and the humidity in the target space is equal to or higher than a humidity threshold value X. The inference device includes a data acquisition unit that acquires information on the humidity, room temperature in the target space, and biometric information of a user in the target space, and an inference unit that uses a learned model for inferring the humidity threshold value X and the temperature threshold value T from the humidity information, the room temperature information, and the biometric information, and outputs the humidity threshold value X and the temperature threshold value T from the humidity information, the room temperature information, and the biometric information input from the data acquisition unit.

Advantages of the Invention

[0007] According to the air conditioning system, learning device, and inference device of the present disclosure, it is possible to assist in improving the comfort of the user in the target space for cooling and dehumidification.

Brief Description of the Drawings

[0008]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Mode for Carrying Out the Invention

[0009] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. The same reference numerals in each figure indicate the same or corresponding parts. In the present disclosure, duplicate descriptions will be appropriately simplified or omitted as necessary. Note that the present disclosure can include various modifications and combinations of the configurations disclosed by the following embodiments without departing from the spirit thereof.

[0010] Embodiment 1. FIG. 1 is a diagram showing the overall configuration of the air conditioning system 1 according to Embodiment 1. The air conditioning system 1 includes, for example, an air conditioner 2, a measuring device 3, a router 4, and a server 5. Note that the air conditioning system according to the present disclosure can also be realized, for example, by the air conditioner 2 alone. For example, the functions of the measuring device 3 and the server 5 may be mounted on the air conditioner 2.

[0011] The air conditioning system 1 is applied to, for example, a house 6 of a single-family house. Note that the air conditioning system according to the present disclosure is not limited to single-family houses and can be applied to various buildings such as apartment houses or office buildings. Hereinafter, in the embodiment, the air conditioning system 1 applied to a single-family house will be described as an example.

[0012] The air conditioner 2 is a facility for performing air conditioning on a target space inside the house 6. The air conditioner 2 is, for example, a heat pump type air conditioning facility that uses hydrofluorocarbon (HFC) or the like as a refrigerant. The air conditioner 2 is equipped with, for example, a vapor compression refrigeration cycle. The air conditioner 2 operates by obtaining electric power from a commercial power supply, a power generation facility, a power storage facility, or the like (not shown).

[0013] FIG. 2 is a diagram showing the configuration of the air conditioner 2 according to Embodiment 1. The air conditioner 2 performs air conditioning on the indoor space 71, which is the target space. Note that "air conditioning" means adjusting the temperature, humidity, cleanliness, air flow, etc. of the air in the target space, and specifically means operations such as heating, cooling, dehumidifying, humidifying, and air cleaning.

[0014] The air conditioner 2 includes, for example, an outdoor unit 11 provided outdoors, an indoor unit 13 provided indoors, and a remote controller 55 operated by a user. The outdoor unit 11 and the indoor unit 13 are connected via a refrigerant pipe 61 through which the refrigerant flows and a communication line 63 through which various signals are transferred. The air conditioner 2 cools the indoor space 71 by blowing cold air from the indoor unit 13 and heats the indoor space 71 by blowing warm air.

[0015] The outdoor unit 11 includes, for example, a compressor 21, a four-way valve 22, an outdoor heat exchanger 23, an expansion valve 24, an outdoor blower 26, and an outdoor unit control unit 51. The indoor unit 13 includes, for example, an indoor heat exchanger 25, an indoor blower 27, and an indoor unit control unit 53. The compressor 21, the four-way valve 22, the outdoor heat exchanger 23, the expansion valve 24, and the indoor heat exchanger 25 are annularly connected by a refrigerant pipe 61 to form a refrigeration cycle.

[0016] The compressor 21 compresses the refrigerant and circulates the compressed refrigerant through the refrigerant pipe 61. More specifically, the compressor 21 compresses a low-temperature and low-pressure refrigerant and discharges the high-temperature and high-pressure refrigerant to the four-way valve 22. The compressor 21 is provided with an inverter circuit capable of changing the operating capacity according to the drive frequency. The operating capacity is the amount of refrigerant discharged by the compressor 21 per unit time. The operating capacity of the compressor 21 is controlled by the outdoor unit control unit 51.

[0017] The four-way valve 22 is installed on the discharge side of the compressor 21. The four-way valve 22 switches the flow direction of the refrigerant in the refrigerant pipe 61 according to the type of operation of the air conditioner 2, specifically whether it is cooling, dehumidifying, or heating.

[0018] The outdoor heat exchanger 23 is a first heat exchanger that performs heat exchange between the refrigerant flowing through the refrigerant pipe 61 and the outdoor air. The outdoor blower 26 is provided beside the outdoor heat exchanger 23 and is a first blower that sends outdoor air to the outdoor heat exchanger 23. When the outdoor blower 26 starts the blowing operation, a negative pressure is generated inside the outdoor unit 11, and outdoor air is sucked in. The sucked air is supplied to the outdoor heat exchanger 23, undergoes heat exchange with the refrigerant flowing through the refrigerant pipe 61, and then is blown outdoors.

[0019] The expansion valve 24 is installed between the outdoor heat exchanger 23 and the indoor heat exchanger 25. The expansion valve 24 decompresses and expands the refrigerant flowing through the refrigerant pipe 61. The expansion valve 24 is, for example, an electronic expansion valve whose opening degree can be variably controlled. The opening degree of the expansion valve 24 is controlled by the outdoor unit control unit 51. By changing the opening degree of the expansion valve 24, the pressure of the refrigerant is adjusted.

[0020] The indoor heat exchanger 25 is a second heat exchanger that performs heat exchange between the refrigerant flowing through the refrigerant pipe 61 and the air in the indoor space 71. The indoor blower 27 is provided beside the indoor heat exchanger 25 and is a second blower that sends the air in the indoor space 71 to the indoor heat exchanger 25. When the indoor blower 27 starts its blowing operation, a negative pressure is generated inside the indoor unit 13, and the air in the indoor space 71 is sucked in. The sucked air is supplied to the indoor heat exchanger 25, undergoes heat exchange with the refrigerant flowing through the refrigerant pipe 61, and then is blown out into the indoor space 71.

[0021] The air that has undergone heat exchange in the indoor heat exchanger 25 is supplied to the indoor space 71 as conditioned air. Thereby, the indoor space 71 is air-conditioned. The greater the amount of heat exchange between the refrigerant and the air in the indoor heat exchanger 25, the higher the air-conditioning capacity of the air conditioner 2. The air-conditioning capacity is an index indicating the strength of air-conditioning by the air conditioner 2. The air-conditioning capacity during cooling is called the cooling capacity, and the air-conditioning capacity during heating is called the heating capacity.

[0022] In the present embodiment, the compressor 21, four-way valve 22, outdoor heat exchanger 23, expansion valve 24, and outdoor blower 26 that constitute the outdoor unit 11, and the indoor heat exchanger 25 and indoor blower 27 that constitute the indoor unit 13 are referred to as the "air-conditioning section". This air-conditioning section functions as an air-conditioning means for air-conditioning the indoor space 71.

[0023] Note that the air-conditioning means according to the present disclosure may be any means that can at least perform cooling and dehumidification. The air-conditioning means according to the present disclosure may also be capable of performing heating, humidification, and air purification.

[0024] In the embodiment shown in FIG. 2, the indoor unit 13 includes a first temperature detection unit 41, a second temperature detection unit 44, a third temperature detection unit 45, a humidity detection unit 42, and an infrared detection unit 43. The first temperature detection unit 41 detects the temperature of the suction air of the indoor unit 13. The humidity detection unit 42 detects the humidity of the suction air of the indoor unit 13. The second temperature detection unit 44 and the third temperature detection unit 45 detect the temperature of the refrigerant flowing through the indoor heat exchanger 25. During cooling, the indoor heat exchanger 25 serves as an evaporator, the second temperature detection unit 44 detects the evaporator inlet temperature Tei, and the third temperature detection unit 45 detects the evaporator outlet temperature Teo. The infrared detection unit 43 detects the surface temperature of the floor of the indoor space 71 or a person in the indoor space 71, etc.

[0025] Also, as an example, although not shown in the figure, the air conditioner 2 includes various other detection units. Specifically, the air conditioner 2 includes a discharge-side pressure detection unit that detects the pressure of the refrigerant discharged from the compressor 21, a suction-side pressure detection unit that detects the pressure of the refrigerant sucked into the compressor 21, a discharge-side temperature detection unit that detects the temperature of the refrigerant discharged from the compressor 21, a suction-side temperature detection unit that detects the temperature of the refrigerant sucked into the compressor 21, an outdoor temperature detection unit that detects the temperature of the outside air, and the like.

[0026] Let the temperature measured by the discharge-side temperature detection unit of the compressor 21 be the discharge temperature Td. From the pressure measured by the discharge-side pressure detection unit of the compressor 21, the condensation temperature CT, which is the saturation temperature of the refrigerant, is obtained. The difference between the discharge temperature Td and the condensation temperature CT is defined as the discharge superheat degree SHd (=Td - CT) of the compressor 21. Also, let the temperature measured by the suction-side temperature detection unit of the compressor 21 be the suction temperature Ts. From the pressure measured by the suction-side pressure detection unit of the compressor 21, the evaporation temperature ET, which is the saturation temperature of the refrigerant, is obtained. The difference between the suction temperature Ts and the evaporation temperature ET is defined as the suction superheat degree SHs (=Ts - ET) of the compressor 21. Also, the difference between the evaporator outlet temperature Teo and the evaporation temperature ET is defined as the superheat degree SH (=Teo - ET) at the evaporator outlet. It may also be regarded that the evaporation temperature ET and the evaporator inlet temperature Tei are equal, and the superheat degree SH (=Teo - Tei) at the evaporator outlet is used.

[0027] The detection results by various detection units are sent to the indoor unit control unit 53. Also, the indoor unit control unit 53 sends the sent detection results to the outdoor unit control unit 51 via the communication line 63.

[0028] Figure 3 is a diagram showing the configuration of the indoor unit control unit 53 of Embodiment 1. The indoor unit control unit 53 controls the operation of the indoor unit 13. As shown in Figure 3, the indoor unit control unit 53 includes, for example, a control unit 101, a storage unit 102, and a communication unit 104. These units are connected via a bus 109.

[0029] The control unit 101 includes a CPU (Central Processing Unit), a ROM, and a RAM. The CPU is also referred to as a central processing unit, a processing unit, an arithmetic unit, a microprocessor, a microcomputer, or a DSP. In the control unit 101, the CPU reads the programs and data stored in the ROM and uses the RAM as a work area to overall control the outdoor unit control unit 51.

[0030] The storage unit 102 is a non-volatile or volatile semiconductor memory such as a flash memory, an EPROM, and an EEPROM, and serves as a so-called secondary storage device or auxiliary storage device. The storage unit 102 stores the programs and data used by the control unit 101 to perform various processes, and the data generated or acquired by the control unit 101 performing various processes.

[0031] The communication unit 104 is an interface for the indoor unit control unit 53 to communicate with the outdoor unit control unit 51 and the remote controller 55 via the communication line 63. The communication unit 104 receives the operation information received by the remote controller 55 from the user from the remote controller 55. Also, the communication unit 104 transmits the notification information for notifying the user to the remote controller 55. Also, the communication unit 104 transmits the operation command of the outdoor unit 11 to the outdoor unit control unit 51 and receives the information indicating the state of the outdoor unit 11 from the outdoor unit control unit 51.

[0032] The outdoor unit control unit 51 includes a CPU, a ROM, a RAM, a communication interface, and a rewritable semiconductor memory, similar to the indoor unit control unit 53. In the outdoor unit control unit 51, the CPU executes a control program stored in the ROM while using the RAM as a work memory. Thereby, the operation of the outdoor unit 11 is controlled.

[0033] In the present embodiment, the indoor unit control unit 53 is connected to the outdoor unit control unit 51 by a communication line 63 which is a wired, wireless, or other communication medium. The indoor unit control unit 53 cooperates with the outdoor unit control unit 51 by exchanging various signals via the communication line 63, and controls the entire air conditioner 2. The indoor unit control unit 53 and the outdoor unit control unit 51 function as control devices for controlling the air conditioner 2.

[0034] The indoor unit control unit 53 and the outdoor unit control unit 51 that function as control devices in the present embodiment are an example of control means for controlling the air conditioning means. The control means according to the present disclosure can selectively cause the air conditioning means to perform cooling and dehumidification. Note that the function of the control means according to the present disclosure may be realized by a control device such as the indoor unit control unit 53 and the outdoor unit control unit 51 provided in the air conditioner 2, or may be realized by an external device of the air conditioner 2. The function of the control means may be realized by an external device that comprehensively controls home appliances, such as a HEMS controller, for example, or may be realized by an external server 5 or the like connected to the air conditioner 2 via the router 4 and the network 200 or the like.

[0035] The outdoor unit control unit 51 and the indoor unit control unit 53 control the operation of the air conditioner 2 based on the detection results of the various detection units described above and the setting information of the air conditioner 2 set by the user. Specifically, the outdoor unit control unit 51 controls the drive frequency of the compressor 21, the switching of the four-way valve 22, the rotation speed of the outdoor blower 26, and the opening degree of the expansion valve 24. Also, the indoor unit control unit 53 controls the rotation speed of the indoor blower 27. Note that the outdoor unit control unit 51 may control the rotation speed of the indoor blower 27, or the indoor unit control unit 53 may control the drive frequency of the compressor 21, the switching of the four-way valve 22, the rotation speed of the outdoor blower 26, and the opening degree of the expansion valve 24. Thus, the outdoor unit control unit 51 and the indoor unit control unit 53, which function as the control device of the air conditioner 2, output operation commands to each device constituting the air conditioner 2 according to the operation commands given to the air conditioner 2.

[0036] The remote controller 55 is installed in the indoor space 71. The remote controller 55 transmits and receives various signals to and from the indoor unit control unit 53. The user of the air conditioner 2 inputs an operation command to the air conditioner 2 by operating the remote controller 55. Examples of the operation command include a switching command between operation and stop, a switching command of the operation mode such as automatic, cooling, dehumidification, heating, etc., a switching command of the target temperature, a switching command of the target humidity, a switching command of the air volume, a switching command of the air direction, and a switching command of the timer. The air conditioner 2 operates according to the input operation command.

[0037] Here, the "cooling" and "dehumidification" operations performed by the air conditioner 2 will be described. When the outdoor unit control unit 51 receives a "cooling" or "dehumidification" operation command, it switches the flow path of the four-way valve 22 so that the refrigerant discharged from the compressor 21 flows into the outdoor heat exchanger 23, opens the expansion valve 24, and drives the compressor 21 and the outdoor blower 26. Also, when the indoor unit control unit 53 receives a "cooling" or "dehumidification" operation command, it drives the indoor blower 27.

[0038] When the compressor 21 is driven, the refrigerant discharged from the compressor 21 passes through the four-way valve 22 and flows into the outdoor heat exchanger 23. The refrigerant flowing into the outdoor heat exchanger 23 exchanges heat with the outdoor air, condenses and liquefies, and then flows into the expansion valve 24. The refrigerant flowing into the expansion valve 24 is depressurized by the expansion valve 24 and then flows into the indoor heat exchanger 25. The refrigerant flowing into the indoor heat exchanger 25 exchanges heat with the air sucked from the indoor space 71, evaporates, passes through the four-way valve 22, and is sucked into the compressor 21 again. By flowing the refrigerant in this way, the air sucked from the indoor space 71 is cooled by the indoor heat exchanger 25. The amount of heat exchange between the refrigerant and the indoor air in the indoor heat exchanger 25 is called the cooling capacity. Among the cooling capacity, the part that lowers the temperature of the air is called the sensible heat capacity, and the part that removes the moisture in the air, that is, the part of dehumidification, is called the latent heat capacity.

[0039] The dehumidification operation modes of the air conditioner 2 include, for example, "weak cooling and dehumidification", "partial cooling and dehumidification", and "reheat dehumidification". The operation mode of "weak cooling and dehumidification" is the first dehumidification mode in which the cooling capacity is lower than that in "cooling" and the dehumidification capacity is higher. When receiving an operation command of "weak cooling and dehumidification", the control unit 101 circulates the refrigerant in the same direction as in "cooling". Then, the control unit 101 reduces the rotation speed of the indoor blower 27 compared to the case of "cooling". In "weak cooling and dehumidification", the control unit 101 reduces the air volume sent to the indoor heat exchanger 25 by the indoor blower 27 compared to "cooling".

[0040] Generally, the larger the air volume of the indoor blower 27, the higher the evaporation temperature of the refrigerant in the indoor heat exchanger 25, and the more efficient the refrigeration cycle. Therefore, when the air conditioner 2 performs "cooling", it leads to energy saving by operating with an air volume large enough not to cause noise. On the contrary, in "weak cooling and dehumidification", the control unit 101 reduces the air volume of the indoor blower 27 compared to "cooling" to lower the evaporation temperature of the refrigerant. As a result, the sensible heat capacity of the indoor heat exchanger 25 decreases and the latent heat capacity increases. Therefore, the sensible heat ratio decreases. As a result, in "weak cooling and dehumidification" compared to "cooling", the room temperature Ti is less likely to decrease and the indoor humidity RHi is more likely to decrease.

[0041] The operation mode of "partial cooling and dehumidification" is the second dehumidification mode in which the evaporation temperature of the refrigerant is made lower than the dew point temperature of the air on the inlet side of the indoor heat exchanger 25 and the superheat degree of the refrigerant is increased on the outlet side of the indoor heat exchanger 25. When receiving an operation command of "partial cooling and dehumidification", the control unit 101 circulates the refrigerant in the same direction as in "cooling". Then, the control unit 101 controls the opening degree of the expansion valve 24 so that the evaporation temperature of the refrigerant at the inlet where the refrigerant flows into the indoor heat exchanger 25 is lower than the dew point temperature of the air.

[0042] In "cooling" and "weak cooling and dehumidification", the control unit 101 controls the opening degree of the expansion valve 24 so that the refrigerant becomes a saturated gas at the outlet of the refrigerant in the indoor heat exchanger 25, that is, the superheat degree near the outlet of the refrigerant in the indoor heat exchanger 25 becomes close to zero. The control unit 101 reduces the opening degree of the expansion valve 24 more in "partial cooling and dehumidification" than in "cooling" and "weak cooling and dehumidification". As a result, the evaporation temperature of the refrigerant near the inlet of the indoor heat exchanger 25 decreases, and most of the refrigerant evaporates near the inlet of the indoor heat exchanger 25, so the superheat degree near the outlet of the indoor heat exchanger 25 increases. As a result, it becomes possible to dehumidify the air at a low temperature on the inlet side of the indoor heat exchanger 25, and the air is not over-cooled on the outlet side. "Partial cooling and dehumidification" makes it less likely for the room temperature Ti to decrease and more likely for the indoor humidity RHi to decrease than "weak cooling and dehumidification".

[0043] The operation mode of "reheat dehumidification" is the third dehumidification mode in which the humidity is reduced while suppressing the decrease in the temperature of the indoor space 71. When receiving an operation command of "reheat dehumidification", the control unit 101 circulates the refrigerant in the same direction as in "cooling". Then, the upstream part of the indoor heat exchanger 25 is made to function as a condenser for condensing the refrigerant to warm the air supplied by the indoor blower 27. On the other hand, the downstream part of the indoor heat exchanger 25 is made to function as an evaporator for evaporating the refrigerant to reduce the humidity of the air supplied by the indoor blower 27. In order to reduce the humidity while warming the air, "reheat dehumidification" makes it less likely for the room temperature Ti to decrease and more likely for the indoor humidity RHi to decrease than other dehumidification modes.

[0044] Next, the operation of "heating" performed by the air conditioner 2 will be described. When the outdoor unit control unit 51 receives a "heating" operation command, it switches the flow path of the four-way valve 22 so that the refrigerant discharged from the compressor 21 flows into the indoor heat exchanger 25, opens the expansion valve 24, and drives the compressor 21 and the outdoor blower 26. Also, when the indoor unit control unit 53 receives a "heating" operation command, it drives the indoor blower 27.

[0045] When the compressor 21 is driven, the refrigerant discharged from the compressor 21 passes through the four-way valve 22 and flows into the indoor heat exchanger 25. The refrigerant that has flowed into the indoor heat exchanger 25 exchanges heat with the air sucked from the indoor space 71, condenses and liquefies, and then flows into the expansion valve 24. The refrigerant that has flowed into the expansion valve 24 is depressurized by the expansion valve 24 and then flows into the outdoor heat exchanger 23. The refrigerant that has flowed into the outdoor heat exchanger 23 exchanges heat with the outdoor air, evaporates, passes through the four-way valve 22, and is sucked into the compressor 21 again. By flowing the refrigerant in this way, the air sucked from the indoor space 71 is heated by the indoor heat exchanger 25. The amount of heat exchange between the refrigerant and the indoor air in the indoor heat exchanger 25 is called the heating capacity.

[0046] The air conditioner 2 of the present embodiment can operate in the "automatic mode". During the operation in the "automatic mode", the air conditioner 2 automatically switches between "cooling" and "dehumidifying". FIG. 4 is a diagram showing the temperature and humidity ranges of cooling and dehumidifying performed by the air conditioner 2 of Embodiment 1. In FIG. 4, the horizontal axis represents the room temperature, which is the temperature in the target space, and the vertical axis represents the humidity in the target space, showing the ranges in which cooling and dehumidifying are performed. In the present disclosure, what is simply referred to as "humidity" basically means "relative humidity".

[0047] As shown in FIG. 4, when the room temperature is equal to or higher than a predetermined value, the air conditioner 2 performs cooling, and when the room temperature is lower than the predetermined value and the humidity is equal to or higher than the predetermined value, the air conditioner 2 performs dehumidification. Here, the predetermined value of the room temperature may be the set temperature Tset which is a set value set in advance or input by the user, or may be the temperature threshold T determined by automatic control. The predetermined value of the humidity may be the set humidity Xset which is a set value set in advance or input by the user, or may be the humidity threshold X determined by automatic control. What to use as the predetermined value of the room temperature and the predetermined value of the humidity can be selected by the user. Also, whether the currently performed operation is cooling or dehumidification is displayed to the user by the remote controller 55 or the smartphone application. Further, the user may be notified at the time of switching between the cooling and dehumidification operations.

[0048] As described above, the air conditioning system 1 of the present embodiment includes the measuring device 3. As shown in FIG. 1, the measuring device 3 includes a temperature sensor 31, a humidity sensor 32, and a biological sensor 33. The temperature sensor 31 functions as temperature information acquisition means for acquiring information on the room temperature in the target space. The humidity sensor 32 functions as humidity information acquisition means for acquiring information on the humidity in the target space. The biological sensor 33 functions as biological information acquisition means for acquiring biological information of the user in the target space. Examples of the biological information acquired by the biological sensor 33 include information such as pulse wave, pulse rate, heart rate, respiration, blood pressure, deep body temperature, skin temperature, sweating, expression, and posture, and images including the same.

[0049] The human body maintains a constant body temperature by the balance between heat generation by metabolism and heat dissipation to the surrounding environment. The less heat dissipation there is relative to heat generation, the higher the body temperature rises and the hotter one feels, and the more heat dissipation there is, the lower the body temperature drops and the colder one feels. Heat dissipation includes heat dissipation due to the temperature difference between the skin and the air, and heat dissipation due to water evaporation by sweating and respiration. When the air temperature is high, the amount of sweating increases to increase heat dissipation by water evaporation. It is considered that in this case, when the humidity is high, sweat is less likely to evaporate, causing discomfort.

[0050] The autonomic nervous system consists of the sympathetic nervous system and the parasympathetic nervous system. The skin blood vessels and sweat glands involved in body temperature regulation as described above are mainly controlled by the sympathetic nervous system. Also, when the sympathetic nervous system is excited, the heart rate increases. By performing frequency analysis on the fluctuations in the heart rate interval to obtain the power spectral density and using LF (Low Frequency), which is the integrated value of the low-frequency band, and HF (High Frequency), which is the integrated value of the high-frequency band, the activities of the sympathetic and parasympathetic nerves can be captured. HF reflects respiratory fluctuations and serves as an indicator of parasympathetic nerve activity. LF reflects blood pressure fluctuations and is affected by both the sympathetic and parasympathetic nerves. Therefore, LF / HF is also used as an indicator of sympathetic nerve activity.

[0051] Thus, it is considered that changes in the room temperature and humidity within the target space cause changes in various types of biological information as well as secondary information obtained from biological information such as HF, LF, and LF / HF.

[0052] As described above, when the room temperature is equal to or higher than a predetermined value, the air conditioner 2 performs cooling, and when the room temperature is lower than the predetermined value and the humidity is equal to or higher than the predetermined value, it performs dehumidification. As the predetermined value for the room temperature, the set temperature Tset or the temperature threshold T is used. As the predetermined value for the humidity, the set humidity Xset or the humidity threshold X is used. In this embodiment, the learning device learns the humidity threshold X from the biological information and the humidity information. Thereby, considering the actual environment, the humidity threshold X can be optimized. Also, the learning device learns the temperature threshold T from the biological information and the room temperature information. Thereby, considering the actual environment, the temperature threshold T can be optimized. Note that, as input data for learning the humidity threshold X and the temperature threshold T, environmental information other than the room temperature and humidity may be further used.

[0053] As an example, the server 5 functions as a learning device according to the present disclosure. Note that the learning device is not limited to the server 5. For example, computer devices installed in the house 6 or the like may function as the learning device, or devices mounted on the air conditioner 2 may function as the learning device. The learning device is an example of the learning means according to the present disclosure and can be realized by any device.

[0054] In the present embodiment, the air conditioner 2 operates based on the humidity threshold value X or the temperature threshold value T automatically obtained by learning. For example, when the room temperature is equal to or higher than the set value, the indoor unit control unit 53 and the outdoor unit control unit 51 cause the air conditioning unit to perform cooling, and when the room temperature is lower than the set value and the humidity is equal to or higher than the humidity threshold value X, the air conditioning unit is caused to perform dehumidification. By switching between cooling and dehumidification based on the humidity threshold value X considering the actual environment, it is possible to support the improvement of the comfort of the user in the target space. For example, when the room temperature is equal to or higher than the temperature threshold value T, the indoor unit control unit 53 and the outdoor unit control unit 51 cause the air conditioning unit to perform cooling, and when the room temperature is lower than the temperature threshold value T and the humidity is at the set value, the air conditioning unit is caused to perform dehumidification. By switching between cooling and dehumidification based on the temperature threshold value T considering the actual environment, it is possible to support the improvement of the comfort of the user in the target space.

[0055] Furthermore, the humidity threshold value X and the temperature threshold value T may be learned from the biological information, the humidity information, and the room temperature information. Then, for example, when the room temperature is equal to or higher than the temperature threshold value T, the indoor unit control unit 53 and the outdoor unit control unit 51 may cause the air conditioning unit to perform cooling, and when the room temperature is lower than the temperature threshold value T and the humidity is equal to or higher than the humidity threshold value X, the air conditioning unit may be caused to perform dehumidification. By switching between cooling and dehumidification based on the humidity threshold value X and the temperature threshold value T considering the actual environment, it is possible to more effectively support the improvement of the comfort of the user in the target space.

[0056] As described above, the air conditioning system 1 of the present embodiment learns the humidity threshold value X or the temperature threshold value T in consideration of the actual environment, and performs cooling and dehumidification according to the learning result. Thereby, it is possible to support the improvement of the comfort of the user in the target space.

[0057] FIG. 5 is a diagram showing an example of the control flow of the air conditioning system 1 according to Embodiment 1. Taking the case where LF / HF is used as a stress index based on the room temperature and humidity in the target space as an example, the control flow of the air conditioning system 1 will be described with reference to FIG. 5.

[0058] First, biological information and temperature / humidity information are acquired (step S101). The biological information and temperature / humidity information are acquired by the measuring device 3 and transmitted to the server 5 that functions as a learning device via the router 4 and a network or the like. When LF / HF is used as a stress index, for example, information on pulse waves and heartbeats is acquired as biological information.

[0059] The server 5 calculates, for example, LF / HF, which is a stress index, from the acquired biological information, learns the room temperature and humidity states in which the user's stress increases from the data group of room temperature, humidity, and stress index (step S102), and outputs information on the temperature threshold T and humidity threshold X obtained as a result of the learning (step S103).

[0060] The air conditioner 2 operates based on the humidity threshold X and temperature threshold T as a result of the learning. When the room temperature is equal to or higher than the temperature threshold T (YES in step S104), the air conditioner 2 performs cooling (step S105). When the room temperature is lower than the temperature threshold T and the humidity is equal to or higher than the humidity threshold X (NO in step S106), the air conditioner 2 performs dehumidification (step S107).

[0061] In the learning phase from step S101 to step S103 in FIG. 5, known algorithms such as supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning can be used. FIG. 6 is a configuration diagram of a learning device 200a related to the air conditioning system 1 according to Embodiment 1. The learning device 200a includes a data acquisition unit 201a, a model generation unit 202a, and a learned model storage unit 203a.

[0062] The data acquisition unit 201a acquires, as learning data, information on the humidity in the target space of the air conditioning system 1, biometric information of the user in the target space, and information on the set humidity Xset input by the user. The set humidity Xset input by the user is used as correct answer data. The data acquisition unit 201a may also acquire, as learning data, information on the room temperature in the target space of the air conditioning system 1, biometric information of the user in the target space, and information on the set temperature Tset input by the user. The set temperature Tset input by the user is used as correct answer data.

[0063] The model generation unit 202a learns the humidity threshold X based on the learning data created based on the combination of the biometric information and humidity information output from the data acquisition unit 201a and the set humidity Xset. The model generation unit 202a may also learn the temperature threshold T based on the learning data created based on the combination of the biometric information and temperature information output from the data acquisition unit 201a and the set temperature Tset. That is, a learned model for inferring the optimal temperature threshold T or humidity threshold X from the biometric information and temperature and humidity information in the target space is generated. Here, the learning data is data that associates the biometric information and temperature and humidity information with the set humidity Xset or set temperature Tset, which is the correct answer data, with each other.

[0064] Note that the learning device 200a and the inference device 300a described later are used to learn the temperature threshold T or humidity threshold X of the air conditioning system 1. However, for example, they may be connected to the air conditioner 2 via a network and be a device separate from this air conditioner 2. Also, the learning device 200a and the inference device 300a may be built into the air conditioner 2. Furthermore, the learning device 200a and the inference device 300a may exist on a cloud server.

[0065] As the learning algorithm used by the model generation unit 202a, known algorithms such as supervised learning, unsupervised learning, semi-supervised learning, and reinforcement learning can be used. As an example, the case of applying a neural network will be described.

[0066] The model generation unit 202a learns the temperature threshold T or the humidity threshold X, for example, by so-called supervised learning according to a neural network model. Here, supervised learning refers to a method of giving a learning device a set of input and result (label) data, learning the characteristics of the learning data, and inferring the result from the input.

[0067] A neural network is composed of an input layer consisting of a plurality of neurons, an intermediate layer (hidden layer) consisting of a plurality of neurons, and an output layer consisting of a plurality of neurons. The intermediate layer may be one layer or two or more layers.

[0068] FIG. 7 is a diagram showing an example of a neural network. For example, in the case of a three-layer neural network as shown in FIG. 7, when a plurality of inputs are input to the input layer (X1-X3), the values are multiplied by weights W1 (w11-w16) and input to the intermediate layer (Y1-Y2), and the result is further multiplied by weights W2 (w21-w26) and output from the output layer (Z1-Z3). This output result varies depending on the values of weights W1 and W2.

[0069] In the present application, the neural network learns the temperature threshold T or the humidity threshold X by so-called supervised learning according to the learning data acquired by the data acquisition unit 201a. That is, the neural network learns by adjusting the weights W1 and W2 so that the result output from the output layer when biological information and temperature / humidity information are input to the input layer approaches the set humidity Xset or the set temperature Tset.

[0070] The model generation unit 202a generates and outputs a learned model by executing the above learning. The learned model storage unit 203a stores the learned model output from the model generation unit 202a.

[0071] FIG. 8 is a flowchart regarding the learning process of the learning device 200a. The process by which the learning device 200a learns will be described with reference to FIG. 8.

[0072] First, the data acquisition unit 201a acquires humidity information, biological information, and the information of the set humidity Xset input by the user as learning data (step S201). Although it is assumed that the humidity information, biological information, and the information of the set humidity Xset input by the user are acquired simultaneously, it is sufficient that the humidity information, biological information, and the information of the set humidity Xset input by the user can be input in association with each other, and each data may be acquired at different timings. As described above, the data acquisition unit 201a may acquire room temperature information, biological information, and the information of the set temperature Tset input by the user as learning data.

[0073] The model generation unit 202a learns the temperature threshold T or the humidity threshold X by so-called supervised learning according to the learning data acquired by the data acquisition unit 201a, and generates a learned model (step S202). The learned model storage unit 203a stores the learned model generated by the model generation unit 202a (step S203).

[0074] FIG. 9 is a configuration diagram of the inference device 300a related to the air conditioning system 1 of the first embodiment. The inference device 300a includes a data acquisition unit 301a and an inference unit 302a. The data acquisition unit 301a acquires biological information and humidity or temperature information. The inference unit 302a infers the humidity threshold X or the temperature threshold T obtained by using the learned model. That is, by inputting the information acquired by the data acquisition unit 301a into this learned model, the inferred humidity threshold X or temperature threshold T can be output.

[0075] In this embodiment, it has been described that the humidity threshold X or the temperature threshold T is output using the learned model learned by the model generation unit 202a of the air conditioning system 1 and stored in the learned model storage unit 203a. However, a learned model may be acquired from another external air conditioning device or the like, and the humidity threshold X or the temperature threshold T may be output based on this learned model.

[0076] FIG. 10 is a flowchart regarding the inference process of the inference device 300a. Using FIG. 10, the process for obtaining the humidity threshold value X or the temperature threshold value T using the inference device 300a will be described.

[0077] First, the data acquisition unit 301a acquires biological information and temperature / humidity information (step S301). Next, the inference unit 302a acquires the learned model from the learned model storage unit 203a, inputs the biological information and temperature / humidity information into the acquired learned model, and obtains the humidity threshold value X or the temperature threshold value T (step S302). The inference unit outputs the humidity threshold value X or the temperature threshold value T obtained by the learned model to the air conditioner 2 (step S303).

[0078] The air conditioner 2 performs control to automatically switch between cooling and dehumidification using the output humidity threshold value X or temperature threshold value T. In step S304, the air conditioner 2 operates in the same manner as steps S104 to S107 of FIG. 5 described above. By switching between cooling and dehumidification based on the humidity threshold value X or temperature threshold value T considering the actual environment, it is possible to support the improvement of the comfort of the user in the target space.

[0079] The model generation unit 202a may learn the humidity threshold value X or the temperature threshold value T according to the learning data created for a plurality of air conditioners 2. Note that the model generation unit 202a may acquire learning data from a plurality of air conditioners 2 used in the same area, or may use the learning data collected from a plurality of air conditioners 2 operating independently in different areas to learn the temperature threshold value T or the humidity threshold value X. It is also possible to add or remove the air conditioner 2 for collecting the learning data as a target midway. Furthermore, the learning device 200a that has learned the humidity threshold value X or the temperature threshold value T for a certain air conditioner 2 may be applied to another air conditioner 2 different from this, and the humidity threshold value X or the temperature threshold value T for the other air conditioner 2 may be relearned and updated.

[0080] As described above, as the learning algorithm, not only supervised learning but also known algorithms such as unsupervised learning, semi-supervised learning, and reinforcement learning can be used. Further, as the learning algorithm, deep learning that learns the extraction of the feature amount itself can also be used, and machine learning may be executed according to other known methods such as genetic programming, inductive logic programming, and support vector machines.

[0081] As an example, the case where reinforcement learning is applied as the learning algorithm will be described with reference to the drawings. FIG. 11 is a configuration diagram of a learning device 200b related to the air conditioning system 1 of the first embodiment. The learning device 200b includes a data acquisition unit 201b and a model generation unit 202b.

[0082] The data acquisition unit 201b acquires, as learning data, information on the humidity in the target space of the air conditioning system 1 and biometric information of the user in the target space. Further, information on the set humidity Xset input by the user in a state where the humidity information and the biometric information are obtained is acquired as learning data. The data acquisition unit 201a may acquire, as learning data, information on the room temperature in the target space of the air conditioning system 1 and biometric information of the user in the target space, and information on the set temperature Tset input by the user in a state where the room temperature information and the biometric information are obtained.

[0083] The model generation unit 202b learns a humidity threshold X or a temperature threshold T based on the learning data acquired by the data acquisition unit 201a. That is, a learned model that infers an optimal temperature threshold T or humidity threshold X from the biometric information and the temperature and humidity information in the target space is generated.

[0084] In reinforcement learning, an agent (acting entity) in a certain environment observes the current state (parameters of the environment) and determines the action to be taken. The action of the agent causes the environment to change dynamically, and the agent is given a reward according to the change in the environment. The agent repeats this process and learns the action policy that can obtain the most rewards through a series of actions. As typical methods of reinforcement learning, Q-learning and TD-learning are known. For example, in the case of Q-learning, the general update formula for the action value function Q(s,a) is represented by Equation (1) below.

[0085]

Equation

[0086] In Equation (1), s t represents the state of the environment at time t, and a t represents the action at time t. Due to the action a t , the state changes to s t+1 . r t+1 represents the reward obtained due to the change in that state, γ represents the discount rate, and α represents the learning coefficient. Note that γ is in the range of 0 < γ ≤ 1, and α is in the range of 0 < α ≤ 1. The set humidity Xset and set temperature Tset input by the user become the action a t , the humidity information, temperature information in the target space, and the biological information of the user in the target space become the state s t , and the best action a t in the state s at time t is learned. t

[0087] The update formula represented by Equation (1) increases the action value Q if the action value Q of the action a with the highest Q value at time t + 1 is greater than the action value Q of the action a executed at time t, and decreases the action value Q in the opposite case. In other words, the action value function Q(s,a) is updated so that the action value Q of the action a at time t approaches the best action value at time t + 1. Thereby, the best action value in a certain environment is sequentially propagated to the action value in the previous environment.

[0088] When generating a learned model by reinforcement learning as described above, the model generation unit 202b includes a reward calculation unit 204 and a function update unit 205.

[0089] The reward calculation unit 204 calculates a reward based on the learning data acquired by the data acquisition unit 201a. The reward calculation unit 204 calculates, for example, a reward r based on a stress index. For example, when the stress index decreases, the reward r is increased (for example, a reward of "1" is given), while when the stress index increases, the reward r is decreased (for example, a reward of "-1" is given).

[0090] The function update unit 205 updates a function for determining the humidity threshold X or the temperature threshold T according to the reward calculated by the reward calculation unit 204, and outputs it to the learned model storage unit 203b. For example, in the case of Q-learning, the action value function Q(s t ,a t ) is used as a function for calculating the humidity threshold X or the temperature threshold T.

[0091] In reinforcement learning, the above learning is repeatedly executed. The learned model storage unit 203b stores the action value function Q(s t ,a t ) updated by the function update unit 205, that is, stores the learned model.

[0092] FIG. 12 is a flowchart related to the learning process of the learning device 200b. The process by which the learning device 200b learns will be described with reference to FIG. 12.

[0093] First, the data acquisition unit 201b acquires information on humidity and biological information, and information on the set humidity Xset input by the user, as learning data (step S401). As described above, the data acquisition unit 201b may acquire information on room temperature and biological information, and information on the set temperature Tset input by the user, as learning data.

[0094] The model generation unit 202b calculates a reward based on the humidity threshold X or the temperature threshold T, the temperature and humidity information, and the biological information (step S402). Specifically, the reward calculation unit 204 acquires the learning data acquired by the data acquisition unit 201a, and determines whether to increase the reward (step S403) or decrease the reward (step S404) based on a predetermined stress index.

[0095] When the reward calculation unit 204 determines to increase the reward, it increases the reward in step S403. On the other hand, when the reward calculation unit 204 determines to decrease the reward, it decreases the reward in step S404.

[0096] The function update unit 205 updates the action value function Q(s t , a t ) represented by the number 1 stored in the learned model storage unit 203b based on the reward calculated by the reward calculation unit 204 (step S405).

[0097] The learning device 200b repeatedly executes the processes from step S401 to step S405 above, and stores the generated action value function Q(s t , a t ) as a learned model.

[0098] In the example shown in FIG. 11, the learned model is stored in the learned model storage unit 203b provided outside the learning device 200b. However, the learned model storage unit 203b may be provided inside the learning device 200b.

Explanation of Signs

[0099] 1 Air conditioning system, 2 Air conditioner, 3 Measuring device, 4 Router, 5 Server, 6 House, 11 Outdoor unit, 13 Indoor unit, 21 Compressor, 22 Four-way valve, 23 Outdoor heat exchanger, 24 Expansion valve, 25 Indoor heat exchanger, 26 Outdoor blower, 27 Indoor blower, 31 Temperature sensor, 32 Humidity sensor, 33 Biosensor, 41 First temperature detection unit, 42 Humidity detection unit, 43 Infrared detection unit, 44 Second temperature detection unit, 45 Third temperature detection unit, 51 Outdoor unit control unit, 53 Indoor unit control unit, 55 Remote controller, 61 Refrigerant pipe, 63 Communication line, 71 Indoor space, 101 Control unit, 102 Memory unit, 104 Communication unit, 109 Bus, 200a Learning device, 200b Learning device, 201a Data acquisition unit, 201b Data acquisition unit, 202a Model generation unit, 202b Model generation unit, 203a Learned model memory unit, 203b Learned model memory unit, 204 Reward calculation unit, 205 Function update unit, 300a Inference device, 301a Data acquisition unit, 302a Inference unit

Claims

1. Air conditioning means capable of cooling and dehumidifying a target space, biometric information acquisition means for acquiring biometric information of a user in the target space, temperature information acquisition means for acquiring information on the room temperature in the target space, humidity information acquisition means for acquiring information on the humidity in the target space, learning means for learning a humidity threshold value X from the biometric information and the humidity information, control means for causing the air conditioning means to perform cooling when the room temperature in the target space is equal to or higher than a set value, and for causing the air conditioning means to perform dehumidification when the room temperature in the target space is lower than the set value and the humidity in the target space is equal to or higher than the humidity threshold value X, An air conditioning system comprising the above.

2. Air conditioning means capable of cooling and dehumidifying a target space, biometric information acquisition means for acquiring biometric information of a user in the target space, temperature information acquisition means for acquiring information on the room temperature in the target space, humidity information acquisition means for acquiring information on the humidity in the target space, learning means for learning a temperature threshold value T from the biometric information and the room temperature information, control means for causing the air conditioning means to perform cooling when the room temperature in the target space is equal to or higher than the temperature threshold value T, and for causing the air conditioning means to perform dehumidification when the room temperature in the target space is lower than the temperature threshold value T and the humidity in the target space is equal to or higher than a set value, An air conditioning system comprising the above.

3. Air conditioning means capable of cooling and dehumidifying a target space, biometric information acquisition means for acquiring biometric information of a user in the target space, temperature information acquisition means for acquiring information on the room temperature in the target space, humidity information acquisition means for acquiring information on the humidity in the target space, learning means for learning a humidity threshold value X and a temperature threshold value T from the biometric information, the humidity information and the room temperature information, control means for causing the air conditioning means to perform cooling when the room temperature in the target space is equal to or higher than the temperature threshold value T, and for causing the air conditioning means to perform dehumidification when the room temperature in the target space is lower than the temperature threshold value T and the humidity in the target space is equal to or higher than the humidity threshold value X, An air conditioning system comprising the above.

4. A learning device for an air conditioning system that performs cooling when the room temperature in a target space is equal to or higher than a set value, and performs dehumidification when the room temperature in the target space is lower than the set value and the humidity in the target space is equal to or higher than a humidity threshold value X, A data acquisition unit that acquires learning data including information on the humidity in the target space, biometric information of the user in the target space, and information on the humidity set value input by the user of the air conditioning system; A model generation unit that generates a learned model for inferring the humidity threshold value X from the humidity information and the biometric information using the learning data acquired by the data acquisition unit; A learning device comprising the above.

5. A learning device for an air conditioning system that performs cooling when the room temperature in the target space is equal to or higher than the temperature threshold value T, and performs dehumidification when the room temperature in the target space is lower than the temperature threshold value T and the humidity is equal to or higher than the set value, A data acquisition unit that acquires learning data including information on the room temperature in the target space, biometric information of the user in the target space, and information on the room temperature set value input by the user of the air conditioning system; A model generation unit that generates a learned model for inferring the temperature threshold value T from the room temperature information and the biometric information using the learning data acquired by the data acquisition unit; A learning device comprising the above.

6. A learning device for an air conditioning system that performs cooling when the room temperature in the target space is equal to or higher than the temperature threshold value T, and performs dehumidification when the room temperature in the target space is lower than the temperature threshold value T and the humidity in the target space is equal to or higher than the humidity threshold value X, A data acquisition unit that acquires learning data including information on the humidity, room temperature in the target space, biometric information of the user in the target space, and information on the humidity set value and temperature set value input by the user of the air conditioning system; A model generation unit that generates a learned model for inferring the humidity threshold value X and the temperature threshold value T from the humidity information, temperature information, and biometric information using the learning data acquired by the data acquisition unit; A learning device comprising the above.

7. An inference device for an air conditioning system that performs cooling when the room temperature in the target space is equal to or higher than the set value, and performs dehumidification when the room temperature in the target space is lower than the set value and the humidity in the target space is equal to or higher than the humidity threshold value X, A data acquisition unit that acquires information on the humidity in the target space and biometric information of the user in the target space; An inference unit that outputs the humidity threshold value X from the humidity information and the biometric information input from the data acquisition unit using a learned model for inferring the humidity threshold value X from the humidity information and the biometric information; An inference device comprising the above.

8. An inference device related to an air conditioning system that performs cooling when the room temperature in a target space is equal to or higher than a temperature threshold T, and performs dehumidification when the room temperature in the target space is lower than the temperature threshold T and the humidity in the target space is equal to or higher than a set value, a data acquisition unit that acquires information on the room temperature in the target space and biometric information of a user in the target space; an inference unit that outputs the temperature threshold T from the room temperature information and the biometric information input from the data acquisition unit, using a learned model for inferring the temperature threshold T from the room temperature information and the biometric information; An inference device comprising the above.

9. An inference device related to an air conditioning system that performs cooling when the room temperature in a target space is equal to or higher than a temperature threshold T, and performs dehumidification when the room temperature in the target space is lower than the temperature threshold T and the humidity in the target space is equal to or higher than a humidity threshold X, a data acquisition unit that acquires information on the humidity, room temperature, and biometric information of a user in the target space; an inference unit that outputs the humidity threshold X and the temperature threshold T from the humidity information, room temperature information, and biometric information input from the data acquisition unit, using a learned model for inferring the humidity threshold X and the temperature threshold T from the humidity information, room temperature information, and biometric information; An inference device comprising the above.

Images