Air conditioning system

Abstract

An air conditioner (2) is a device that can reduce the risk of a user developing heatstroke, and comprises: a receiving unit (211) that receives alert information relating to heatstroke; a temperature sensor (201) that detects the temperature of a space to be air-conditioned; a humidity sensor (202) that detects the humidity of the space; a calculating unit (23) that, when the alert information is received by the reception unit (211), calculates a heat index for the space on the basis of the temperature detected by the temperature sensor (201) and the humidity detected by the humidity sensor (202); and a control unit (20) that, if the calculated value of the heat index obtained by the calculating unit (23) is greater than a predetermined threshold value, controls the operation of the air conditioning of the space such that the heat index decreases.

Description

Air conditioners and air conditioning systems

[0001] The present disclosure relates to an air conditioner and an air conditioning system.

[0002] Generally, the WBGT (Wet-Bulb Globe Temperature [°C]), also known as the heat index, is measured by measuring three temperatures: the wet-bulb temperature, the black-bulb temperature, and the dry-bulb temperature. Then, when solar radiation is present, the WBGT is calculated as follows: WBGT = (0.7 × wet-bulb temperature) + (0.2 × black-bulb temperature) + (0.1 × dry-bulb temperature). When solar radiation is absent, the WBGT is calculated as follows: WBGT = (0.7 × wet-bulb temperature) + (0.3 × black-bulb temperature). However, Non-Patent Document 1 proposes a simple method for calculating the WBGT from two relatively easily available values: indoor temperature and indoor humidity, without obtaining these three or two temperatures. Another conventional heatstroke prevention device proposed is one that measures indoor temperature and humidity, calculates a heat index based on the measurements using a simple calculation table disclosed in Non-Patent Document 1, for example, and operates an air conditioner if the calculated value is equal to or greater than a threshold value (see, for example, Patent Document 1).

[0003] Japanese Patent Application Laid-Open No. 2019-39793

[0004] Japanese Society of Biometeorology, Heatstroke Prevention Research Committee, "Guidelines for Preventing Heatstroke in Daily Life," Ver. 4, published May 23, 2022, pp. 1-21

[0005] Conventional heatstroke prevention devices operate the air conditioner after the calculated heat index reaches or exceeds a threshold, so it takes time to change the indoor environment from a state where heatstroke may occur to a state where heatstroke can be prevented. In other words, conventional heatstroke prevention devices have the problem that heatstroke may occur during the time it takes to change the indoor environment from a state where heatstroke may occur to a state where heatstroke can be prevented.

[0006] The present disclosure has been made in consideration of the above, and aims to provide an air conditioner that can reduce the risk of a user developing heatstroke.

[0007] In order to solve the above-mentioned problems and achieve the objectives, the air conditioner of the present disclosure has a receiving unit that receives warning information related to heatstroke, a temperature sensor that detects the temperature of the space to be air-conditioned, a humidity sensor that detects the humidity of the space, a calculation unit that calculates a heat index for the space based on the temperature detected by the temperature sensor and the humidity detected by the humidity sensor when warning information is received by the receiving unit, and a control unit that controls the operation of the air conditioning for the space so that the heat index decreases when the calculated value of the heat index obtained by the calculation unit is greater than a predetermined threshold value.

[0008] The air conditioner according to the present disclosure has the effect of reducing the risk of a user developing heatstroke.

[0009] FIG. 1 is a diagram showing the configuration of an air conditioning system according to embodiment 1; Graph showing an example of a WBGT predicted value; FIG. 2 is a diagram showing an example of a simplified calculation table stored in a memory unit of an air conditioner according to embodiment 1; FIG. 3 is a diagram explaining the contents of a heat index (WBGT); a flowchart showing the procedure for the operation performed by the inference device included in the air conditioner according to embodiment 2; a flowchart showing the procedure for the first half of the procedure for determining whether to start operation of air conditioning control performed by the air conditioner according to embodiment 2; a flowchart showing the procedure for determining whether to stop operation of air conditioning control performed by the air conditioner according to embodiment 2; a diagram showing a processor in the case where at least some of the functions of the control unit, communication unit, time management unit and calculation unit included in the air conditioner according to embodiment 1 are realized by the processor; and a diagram showing a processing circuit in the case where at least some of the functions of the control unit, communication unit, time management unit and calculation unit included in the air conditioner according to embodiment 1 are realized by the processing circuit.

[0010] An air conditioner and an air conditioning system according to an embodiment will be described in detail below with reference to the drawings.

[0011] Embodiment 1. FIG. 1 is a diagram showing the configuration of an air conditioning system 1 according to Embodiment 1. The air conditioning system 1 includes an air conditioner 2, a cloud system server 3, and an internet site 4. The air conditioner 2 includes a control unit 20 and a communication unit 21 including a receiving unit 211 that receives warning information related to heatstroke. The warning information is heatstroke warning alert information or heatstroke prevention information. For example, the receiving unit 211 receives the warning information via the internet. Furthermore, for example, the receiving unit 211 continuously accesses a cloud system via the internet to receive warning information held by the cloud system. An example of a cloud system is the cloud system server 3.

[0012] The control unit 20 has a temperature sensor 201 that detects the temperature of a space to be air-conditioned, and a humidity sensor 202 that detects the humidity of the space. The space is the space in which the air conditioner 2 is installed. More specifically, the space is the interior space of the room in which the air conditioner 2 is installed. The temperature sensor 201 and the humidity sensor 202 are linked. The air conditioner 2 further has a time management unit 22, a calculation unit 23 that calculates a heat index for the space based on the temperature detected by the temperature sensor 201 and the humidity detected by the humidity sensor 202 when alert information is received by the receiving unit 211, and a memory unit 24. The memory unit 24 is realized, for example, by a semiconductor memory. When the heat index calculated by the calculation unit 23 is greater than a predetermined threshold, the control unit 20 controls the air conditioning operation for the space so that the heat index decreases.

[0013] The control unit 20 further includes an operation timer 204. The memory unit 24 stores a simplified calculation table 241 in which temperature and humidity correspond to a heat index. In the first embodiment, an indoor environment is assumed in which there is no solar radiation and no radiant heat source entering the room. The indoor environment is the environment inside the room in which the air conditioner 2 is installed. The data of the simplified calculation table 241 is stored in the memory unit 24 inside the air conditioner 2. For example, the calculation unit 23 calculates the heat index using the simplified calculation table 241 stored in the memory unit 24. The memory unit 24 further stores a heat index threshold value 243 at the start of operation, a heat index threshold value 244 at the end of operation, and a set time 245 for obtaining alert information.

[0014] The air conditioner 2 can connect to an external internet site 4 via the communication unit 21, and can acquire data such as heatstroke prevention information from the internet site 4. The internet site 4 exists on a server external to the air conditioner 2. For example, the internet site 4 is a heatstroke prevention information site of the Ministry of the Environment, and by connecting to the Ministry of the Environment's heatstroke prevention information site, the air conditioner 2 can acquire information on "heatstroke warning alerts" and information on "electronic information provision service for predicted heat index (WBGT) values, etc."

[0015] Heatstroke prevention information may be prepared in the cloud system server 3, in which case the air conditioner 2 can connect to the cloud system server 3 and acquire the heatstroke prevention information from the cloud system server 3. Data indicating the designated time at which the air conditioner 2 connects to the cloud system server 3 and the internet site 4 to acquire the information is stored in the memory unit 24. The air conditioner 2 may be set to connect to the cloud system server 3 and the internet site 4 periodically, such as every 30 minutes.

[0016] The time management unit 22 manages the acquisition of indoor temperature and humidity, heat index estimates, data such as heatstroke prevention information, and time information required to start and stop operation of the air conditioner 2. The indoor space is the interior of the room in which the air conditioner 2 is installed.

[0017] Next, the operation of the air conditioner 2 according to the first embodiment will be described. The air conditioner 2 connects to the cloud system server 3 and the internet site 4 at each set time 245 for obtaining alert information stored in the memory unit 24 to obtain and store data such as heatstroke prevention information. For example, if a user of the air conditioner 2 registers the nearest area and conditions on the Ministry of the Environment's website, the air conditioner 2 can obtain data such as heatstroke prevention information under conditions similar to those of the indoor environment. As described above, the indoor environment is the environment inside the room in which the air conditioner 2 is installed.

[0018] The time when the heat index predicted value included in the heatstroke prevention information exceeds the heat index threshold value 243 at the start of operation stored in the memory unit 24, or the start time of the time period, is registered in the operation timer 204 as the operation start time of the air conditioner 2. The time when the heat index predicted value included in the heatstroke prevention information falls below the heat index threshold value 244 at the end of operation stored in the memory unit 24, or the end time of the time period, is registered in the operation timer 204 as the operation end time of the air conditioner 2.

[0019] 2 is a graph showing an example of a WBGT predicted value. In FIG. 2, a heat index threshold 243 at the start of operation, a heat index threshold 244 at the end of operation, a start timer time 204A, and a stop timer time 204B are shown. The start timer time 204A is the operation start time, and the stop timer time 204B is the operation end time. The heat index threshold 243 at the start of operation and the heat index threshold 244 at the end of operation may be different. The air conditioner 2 may be set to start operation a specified time earlier than the operation start time, or to end operation a specified time later than the operation end time.

[0020] The air conditioner 2 obtains a heat index estimate from the simplified calculation table 241 based on the indoor temperature and indoor humidity obtained from the temperature sensor 201 and humidity sensor 202. The air conditioner 2 compares the heat index predicted value and the heat index estimated value based on data such as heatstroke prevention information obtained from the cloud system server 3 or the internet site 4 at the same time, and treats the larger of the heat index predicted value and the heat index estimated value as the heat index for the target indoor environment. This is to reduce the risk of heatstroke as much as possible. If the heat index has already reached or exceeded the heat index threshold 243 at the start of operation of the air conditioner 2, the air conditioner 2 can start operation from that point on. An example of operation is cooling operation.

[0021] Fig. 3 is a diagram showing an example of a simplified calculation table 241 stored in the storage unit 24 of the air conditioner 2 according to embodiment 1. The source of Fig. 3 is a diagram (simple indoor WBGT estimation diagram) that simply estimates WBGT from the temperature and relative humidity for an indoor environment in the "Guidelines for Preventing Heatstroke in Daily Life Ver. 4" (2022) published by the Japanese Society of Biometeorology. Fig. 3 is a diagram obtained by modifying the simple indoor WBGT estimation diagram.

[0022] The simplified calculation table 241 is a table that makes it possible to calculate a heat index estimate based on the temperature and humidity acquired by the temperature sensor 201 and humidity sensor 202 of the air conditioner 2. Figure 3 shows, for example, that when the temperature is 35°C and the humidity is 60%, the estimated heat index is 30°C, and the risk level for the occurrence of heatstroke in that case is a high alert level. The above temperature is air temperature, and the above humidity is relative humidity. The example of the simplified calculation table 241 shown in Figure 3 is a simplified calculation table for indoor use, assuming no influence of solar radiation or radiant heat.

[0023] Figure 4 is a diagram explaining the contents of the heat index (WBGT). The source of Figure 4 is the "Guidelines for Preventing Heatstroke in Daily Life, Ver. 4" (2022) published by the Japanese Society of Biometeorology. Figure 4 was obtained by revising the contents of the "Guidelines for Preventing Heatstroke in Daily Life, Ver. 4." Figure 4 was also obtained by extracting information obtained from the Ministry of the Environment's heatstroke prevention information website.

[0024] Figure 5 is a flowchart showing the steps of the process for determining whether to start air conditioning control operation performed by the air conditioner 2 according to Embodiment 1. The air conditioner 2 is energized and started, but while in a standby state in which indoor air conditioning control has not yet started, the air conditioner 2 periodically executes the process shown in Figure 5 as a process for determining whether to start air conditioning control operation in order to prevent the occurrence of heatstroke.

[0025] The process shown in FIG. 5 will be described in detail below. The air conditioner 2 acquires the latest heat index forecast information from a specified homepage at a set time (S1). In step S1 of FIG. 5, the homepage is described as "HP." The heat index forecast information is a predicted WBGT value. The air conditioner 2 saves information indicating the time when the acquired predicted WBGT value exceeds the heat index threshold 243 at the start of operation, and sets the operation start time in the operation timer 204 (S2). In step S2 of FIG. 5, the heat index threshold 243 at the start of operation is described as "operation start threshold." The air conditioner 2 saves information indicating the time when the acquired predicted WBGT value falls below the heat index threshold 244 at the end of operation, and sets the operation stop time in the operation timer 204 (S3). In step S3 of FIG. 5, the heat index threshold 244 at the end of operation is described as "operation stop threshold."

[0026] The air conditioner 2 determines whether the current predicted WBGT value is greater than the heat index threshold 243 at the start of operation (S4). In step S4 of FIG. 5, the heat index threshold 243 at the start of operation is referred to as the "start heat index threshold." If the air conditioner 2 determines that the current predicted WBGT value is greater than the heat index threshold 243 at the start of operation (Yes in S4), it starts operation (S5). In step S5, the air conditioner 2 starts, for example, cooling operation. If the air conditioner 2 determines that the current predicted WBGT value is equal to or less than the heat index threshold 243 at the start of operation (No in S4), it saves the predicted WBGT value at the current time (S6). The air conditioner 2 acquires information indicating the indoor temperature and indoor humidity (S7). The air conditioner 2 acquires a heat index from the simplified calculation table 241 based on the indoor temperature and indoor humidity (S8). In step S8 of FIG. 5, the simplified calculation table 241 is referred to as the "simple index calculation table." The heat index obtained in step S8 is the WBGT estimated value at the current time.

[0027] The air conditioner 2 determines whether the estimated WBGT value at the current time is greater than the heat index threshold 243 at the start of operation (S9). In step S9 of FIG. 5, the heat index threshold 243 at the start of operation is described as the "start heat index threshold." If the air conditioner 2 determines that the estimated WBGT value at the current time is greater than the heat index threshold 243 at the start of operation (Yes in S9), the air conditioner 2 adds the difference between the estimated WBGT value and the predicted WBGT value to the total predicted WBGT values ​​for that day, and sets the resulting value as a new set of predicted WBGT values ​​(S10). This difference is (estimated WBGT value - predicted WBGT value). The air conditioner 2 saves information indicating the time when the new predicted WBGT value falls below the heat index threshold 244 at the end of operation, and sets the operation timer 204 to a time to stop operation (S11). In step S11 of FIG. 5, the heat index threshold 244 at the end of operation is described as the "operation stop threshold." The air conditioner 2 sets the current time in the operation timer 204 and starts operation (S12). In step S12, the air conditioner 2 starts, for example, cooling operation.

[0028] If the air conditioner 2 determines that the estimated WBGT value at the current time is equal to or less than the heat index threshold 243 at the start of operation (No in S9), it determines whether the time indicated by the operation timer 204 has passed the operation start time (S13). If the air conditioner 2 determines that the time indicated by the operation timer 204 has passed the operation start time (Yes in S13), it starts operation (S14). In step S14, the air conditioner 2 starts cooling operation, for example. If the air conditioner 2 determines that the time indicated by the operation timer 204 has not passed the operation start time (No in S13), it performs the operation of step S1.

[0029] Fig. 6 is a flowchart showing the procedure for the operation stop determination process of air conditioning control performed by the air conditioner 2 according to Embodiment 1. After starting operation by the process shown in Fig. 5, the air conditioner 2 periodically executes the process shown in Fig. 6 as determination process for stopping operation.

[0030] The process shown in Fig. 6 will be described in detail below. The air conditioner 2 acquires the latest heat index forecast information from a specified homepage at a set time (S21). In step S21 of Fig. 6, the homepage is written as "HP." The heat index forecast information is a predicted WBGT value. The air conditioner 2 saves information indicating the time when the acquired predicted WBGT value will fall below the heat index threshold 244 at the end of operation, and sets the operation stop time in the operation timer 204 (S22). In step S22 of Fig. 6, the heat index threshold 244 at the end of operation is written as "operation stop threshold."

[0031] The air conditioner 2 determines whether the current WBGT predicted value is smaller than the heat index threshold 244 at the end of operation (S23). In step S23 of Fig. 6, the heat index threshold 244 at the end of operation is described as the "stop heat index threshold." If the air conditioner 2 determines that the current WBGT predicted value is smaller than the heat index threshold 244 at the end of operation (Yes in S23), it stops operation (S24). In step S24, the air conditioner 2 stops cooling operation, for example.

[0032] If the air conditioner 2 determines that the current WBGT predicted value is equal to or greater than the heat index threshold 244 at the time of operation termination (No in S23), it determines whether the time indicated by the operation timer 204 has passed the operation stop time (S25). If the air conditioner 2 determines that the time indicated by the operation timer 204 has passed the operation stop time (Yes in S25), it stops operation (S26). In step S26, the air conditioner 2 stops cooling operation, for example. If the air conditioner 2 determines that the time indicated by the operation timer 204 has not passed the operation stop time (No in S25), it performs the operation of step S21.

[0033] As described above, the air conditioner 2 starts air conditioning control operation during a time period indicating a heat index predicted value indicating a high risk of heatstroke, thereby reliably reducing the risk of heatstroke among users and preventing the occurrence of heatstroke. The above operation is, for example, cooling operation. The air conditioner 2 acquires warning information, such as heatstroke prevention information, from the outside, and can predict the time or time period at which the heat index predicted value will exceed a predetermined threshold. By setting the operation timer 204 to a time before that time or time period as the operation start time of the air conditioner 2, the risk of heatstroke occurring between the start of operation of the air conditioner 2 and the establishment of a comfortable indoor environment can be reliably reduced and the occurrence of heatstroke can be prevented. Furthermore, the air conditioner 2 can predict that the heat index will reach a specific status level, such as "danger" or "high alert," on the same day or several hours later, and can start operation before that status level is reached. This reliably reduces the risk of heatstroke occurring between the start of operation of the air conditioner 2 and the establishment of a comfortable indoor environment, preventing the occurrence of heatstroke.

[0034] Furthermore, the air conditioner 2 also refers to the heat index estimated value that can be obtained from the simplified calculation table 241 based on the indoor temperature and indoor humidity, and if the heat index estimated value is greater than the heat index predicted value, the heat index estimated value is treated as the heat index, thereby further reducing the risk of heat stroke occurring.

[0035] Even when the air conditioner 2 is unable to obtain a predicted heat index value based on data such as heatstroke prevention information obtained from either or both of the cloud system server 3 and the internet site 4, it can determine the risk level of heatstroke from only the heat index estimated value that can be obtained from the simplified calculation table 241 based on the indoor temperature and indoor humidity. Therefore, the air conditioner 2 can prevent the occurrence of heatstroke.

[0036] The air conditioner 2 is not a device that starts operation immediately after determining that the heat index is within the dangerous level range and causes a sudden change in the indoor environment, so it can start operation with reduced power consumption.

[0037] Embodiment 2. In Embodiment 1, an indoor environment is assumed in which there is no solar radiation entering the room and no radiant heat source, and the air conditioner 2 calculates a heat index estimate using the simplified calculation table 241. The simplified calculation table 241 is a simplified calculation table that is intended for use in an indoor environment in which there is no solar radiation entering the room and no radiant heat source. Therefore, in Embodiment 1, the timing for starting operation of the air conditioner 2 may not be appropriate depending on the indoor environment. In Embodiment 2, the air conditioner 2A generates and utilizes a trained simplified calculation table 242 with improved accuracy so that it can be used in an indoor environment in which there is solar radiation entering the room and a radiant heat source. The trained simplified calculation table 242 is a table for calculating a heat index that takes into account solar radiation entering the room and radiant heat sources within the room.

[0038] FIG. 7 is a diagram illustrating the configuration of an air conditioning system 1A according to embodiment 2. The air conditioning system 1A includes an air conditioner 2A, a cloud system server 3, an internet site 4, and a mobile terminal device 5. FIG. 7 also illustrates a heat index meter with a black globe 6 and a wireless remote control 7. The air conditioner 2A includes a control unit 20A, a communication unit 21A, a time management unit 22, a calculation unit 23, a memory unit 24A, a learning device 25, an inference device 26, and a trained model memory unit 27. Each of the memory unit 24A and the trained model memory unit 27 is realized, for example, by a semiconductor memory. Because the configuration of the air conditioning system 1A is similar to that of the air conditioning system 1 according to embodiment 1, differences from embodiment 1 will be mainly described in embodiment 2.

[0039] The control unit 20A has a temperature sensor 201, a humidity sensor 202, a human presence sensor 203, an operation timer 204, a display panel 205, and a buzzer 206. A portion of the display panel 205 is configured as a liquid crystal display device. The communication unit 21A has a receiving unit 211 and a transmitting unit 212. The memory unit 24A stores a simplified calculation table 241, a learned simplified calculation table 242, a heat index threshold value at the start of operation 243, a heat index threshold value at the end of operation 244, a set time for obtaining alert information 245, and an autonomous driving enable / disable setting 246. The learning device 25 is a device related to the generation of the learned simplified calculation table 242 and has a first data acquisition unit 251 and a model generation unit 252. The inference device 26 has a second data acquisition unit 261 and an inference unit 262. The learned model memory unit 27 stores a learned model 271. Note that the trained model 271 is shown as the name of the concept after training has been performed, and the trained simple calculation table 242 is shown as the name of the output obtained from the trained model 271 in a more specific, referable state (table).

[0040] Fig. 8 is a diagram showing the configuration of the learning device 25 included in the air conditioner 2A according to embodiment 2. Fig. 8 also shows a learned model storage unit 27 and a learned model 271. The first data acquisition unit 251 acquires, as learning data, the data acquisition time, the indoor temperature, the indoor humidity, the heat index estimate calculated from the simplified calculation table 241 in a situation where learning is not being performed, weather information, and the actual heat index value (correct answer) indicated by the heat index meter with black ball 6. For example, the weather information includes information indicating the presence or absence of solar radiation.

[0041] 8 shows B1 input 1 and B2 input 2 as data acquired by the first data acquisition unit 251. B1 input 1 and B2 input 2 are associated with each other. In the second embodiment, B1 input 1 is the data acquisition time, indoor temperature, indoor humidity, heat index estimate, and weather information. B2 input 2 is the actual heat index value (correct answer) indicated by the heat index meter with black ball 6.

[0042] The model generation unit 252 learns a heat index inference value output with improved accuracy to suit each of a plurality of indoor environments, based on learning data created based on a combination of the B1 input 1 acquired by the first data acquisition unit 251 and the actual heat index measurement value (correct answer) indicated by the black ball heat index meter 6. In other words, the model generation unit 252 generates a trained model 271 that infers a heat index output with improved accuracy to suit each of a plurality of indoor environments, based on input data related to the data acquisition time and the actual heat index measurement value (correct answer) indicated by the black ball heat index meter 6.

[0043] The configuration of the learning device 25 will be further described. The first data acquisition unit 251 acquires learning input data, including information indicating the temperature detected by the temperature sensor 201, information indicating the humidity detected by the humidity sensor 202, and weather information, and learning data, including an actual heat index value associated with the learning input data and obtained from the black ball heat index meter 6 in the space to be air-conditioned. The space is a space in which the air conditioner 2A is installed. The model generation unit 252 regards the actual heat index value included in the learning data acquired by the first data acquisition unit 251 as the correct answer, and generates a learned simplified calculation table 242, based on the learning input data and the actual heat index value included in the learning data, that is associated with temperature and humidity and that outputs a heat index that reflects the degree of solar radiation on the space to be air-conditioned and the effect of radiant heat in the space.

[0044] The learning device 25 and the inference device 26 are used to learn a heat index inference value with improved accuracy suitable for each of a plurality of indoor environments. The learning device 25 and the inference device 26 are built into the air conditioner 2A as shown in Fig. 7. The learning device 25 and the inference device 26 may be separate devices provided outside the air conditioner 2A and connected via a network. The learning device 25 and the inference device 26 may also reside on the cloud system server 3.

[0045] Known algorithms such as supervised learning, unsupervised learning, or reinforcement learning can be used as the learning algorithm used by the model generation unit 252. As an example, a case where a neural network is applied to the learning algorithm used by the model generation unit 252 will be described.

[0046] The model generation unit 252 learns to output a heat index inference value with improved accuracy suitable for each of a plurality of indoor environments, for example, by so-called supervised learning according to a neural network model. Here, supervised learning refers to a method of providing the learning device 25 with a plurality of pieces of training data consisting of inputs and results (correct answers), learning the features of the training data, and inferring a result from the input.

[0047] FIG. 9 is a diagram illustrating an image of supervised learning in the second embodiment. FIG. 9 shows the relationship between input and output and the processing flow, and illustrates the implementation of learning using the learning algorithm used by the model generation unit 252 as a learning program. FIG. 10 is a diagram summarizing the task (objective), target, input, and output of supervised learning in the second embodiment. FIG. 11 is a diagram illustrating the characteristics of each processing phase of supervised learning in the second embodiment.

[0048] A neural network consists 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. There may be only one intermediate layer, or two or more intermediate layers.

[0049] 12 is a diagram showing a neural network in embodiment 2. For example, in a three-layer neural network such as that shown in FIG. 12, when multiple inputs are input to the input layer (X1-X3), the input values ​​are multiplied by weights W1 (w11-w16), and the resulting values ​​are input to the intermediate layer (Y1-Y2), and the resulting values ​​are further multiplied by weights W2 (w21-w26), and the resulting values ​​are output from the output layer (Z1-Z3). The output result varies depending on the values ​​of weights W1 and W2.

[0050] The neural network in embodiment 2 learns to output a heat index inference value with improved accuracy to suit each of multiple indoor environments through so-called supervised learning, based on learning data including data acquired by the first data acquisition unit 251 and the heat index actual measurement value input (correct answer) indicated by the heat index meter with black ball 6.

[0051] That is, the neural network in embodiment 2 learns by adjusting the values ​​of weights W1 and W2 so that the data acquired by the first data acquisition unit 251 is input to the input layer and the result output from the output layer approaches the actual heat index value input (correct answer) indicated by the heat index meter 6 with black ball.

[0052] The model generation unit 252 generates and outputs a trained model 271 by performing the above-described learning.

[0053] The trained model storage unit 27 stores the trained model 271 output from the model generation unit 252.

[0054] Next, the learning process performed by the learning device 25 will be described with reference to Fig. 13. Fig. 13 is a flowchart showing the procedure of the learning process performed by the learning device 25 included in the air conditioner 2A according to Embodiment 2. Fig. 13 also shows the operation of the trained model storage unit 27.

[0055] In step S31, the first data acquisition unit 251 acquires B1 input 1 and B2 input 2 (correct answer). In Fig. 13, the operation of step S31 is indicated by the phrase "data acquisition." As long as the first data acquisition unit 251 can acquire B1 input 1 and B2 input 2 (correct answer) in association with each other, it may acquire B1 input 1 and B2 input 2 (correct answer) simultaneously, or it may acquire B1 input 1 and B2 input 2 (correct answer) at different times.

[0056] In step S32, the model generation unit 252 learns the C output by so-called supervised learning in accordance with the learning data including the B1 input 1 and the B2 input 2 (correct answer) acquired by the first data acquisition unit 251, and generates a trained model 271. The C output indicates a heat index (WBGT) inference value that takes into account solar radiation and indoor radiant heat, as shown in FIG.

[0057] In step S33, the trained model storage unit 27 stores the trained model 271 generated by the model generation unit 252.

[0058] Next, the inference device 26 will be described in detail. Fig. 14 is a diagram showing the configuration of the inference device 26 included in the air conditioner 2A according to embodiment 2. Fig. 14 shows the configuration of the inference device 26 related to the generation of the learned simplified calculation table 242. The inference device 26 has a second data acquisition unit 261 and an inference unit 262. Fig. 14 also shows a learned model storage unit 27 and a learned model 271.

[0059] The second data acquisition unit 261 acquires the B1 input 1.

[0060] The inference unit 262 infers the C output obtained by using the trained model 271. That is, the inference unit 262 can output the C output inferred from the B1 input 1 by inputting the B1 input 1 acquired by the second data acquisition unit 261 to the trained model 271.

[0061] The configuration of the inference device 26 will be further described. The second data acquisition unit 261 acquires inference input data including information indicating the temperature detected by the temperature sensor 201, information indicating the humidity detected by the humidity sensor 202, and weather information. The inference unit 262 infers a heat index using the inference input data acquired by the second data acquisition unit 261 and the learned simplified calculation table 242 generated by the learning device 25, and outputs an inferred value of the heat index.

[0062] The inference device 26 outputs C output using the learned model 271 learned by the model generation unit 252 of the learning device 25, but it may also acquire another learned model 271 from outside the air conditioner 2A and output C output based on the learned model 271 acquired from outside the air conditioner 2A.

[0063] Next, the processing performed by the inference device 26 when obtaining the C output will be described with reference to Fig. 15. Fig. 15 is a flowchart showing the procedure of the operation performed by the inference device 26 included in the air conditioner 2A according to the second embodiment.

[0064] In step S41, the second data acquisition unit 261 acquires B1 input 1. In Fig. 15, the operation of step S41 is indicated by the phrase "data acquisition."

[0065] In step S42, the inference unit 262 inputs B1 input 1 to the trained model 271 stored in the trained model storage unit 27, and obtains C output. In Figure 15, the operation of step S42 is indicated by the phrase "input data into trained model."

[0066] In step S43, the inference unit 262 outputs the C output obtained by the trained model 271 to the trained simplified calculation table 242. In Fig. 15, the operation of step S43 is indicated by the phrase "data output."

[0067] In step S44, the heat index inference value is output by referring to the learned simplified calculation table 242. In this way, the learned simplified calculation table 242 can output a heat index inference value with improved accuracy suitable for each of a plurality of indoor environments.

[0068] In the second embodiment, a case where supervised learning is applied to the learning algorithm used by the model generation unit 252 has been described, but this is not limiting. As for the learning algorithm, reinforcement learning, unsupervised learning, semi-supervised learning, or the like can also be applied in addition to supervised learning.

[0069] The model generation unit 252 may train the C output according to multiple pieces of training data collected under different conditions. The model generation unit 252 may use multiple pieces of training data acquired in the same region or under the same conditions, or may train the C output using multiple pieces of training data that exist independently in different regions. Furthermore, the trained model 271 may be updated by retraining after new training data has been added to the trained model 271 or by removing training data under unnecessary conditions.

[0070] Deep learning, which learns to extract features themselves, may also be used as the learning algorithm used in the model generation unit 252. Machine learning may also be performed according to other known methods, such as genetic programming, functional logic programming, or support vector machines.

[0071] Fig. 16 is a flowchart showing the steps of the first half of the process for determining whether to start air conditioning control operation performed by the air conditioner 2A according to Embodiment 2. Fig. 17 is a flowchart showing the steps of the second half of the process for determining whether to start air conditioning control operation performed by the air conditioner 2A according to Embodiment 2. The air conditioner 2A is energized and started, but while in a standby state in which it has not started air conditioning control for the room, it periodically executes the processes shown in Figs. 16 and 17 as processes for determining whether to start air conditioning control operation in order to prevent the occurrence of heatstroke.

[0072] The processing shown in FIGS. 16 and 17 will be described in detail below. The air conditioner 2A acquires the latest heat index forecast information from a specified homepage at a set time (S51). In step S51 of FIG. 16, the homepage is described as "HP." The heat index forecast information is a predicted WBGT value. The air conditioner 2A saves information indicating the time when the acquired predicted WBGT value exceeds the heat index threshold 243 at the start of operation, and sets the operation start time in the operation timer 204 (S52). In step S52 of FIG. 16, the heat index threshold 243 at the start of operation is described as "operation start threshold." The air conditioner 2A saves information indicating the time when the acquired predicted WBGT value falls below the heat index threshold 244 at the end of operation, and sets the operation stop time in the operation timer 204 (S53). In step S53 of FIG. 16, the heat index threshold 244 at the end of operation is described as "operation stop threshold."

[0073] The air conditioner 2A determines whether or not a learned simplified calculation table 242 exists (S54). In step S54 of FIG. 16, the learned simplified calculation table 242 is described as a "learned heat index simplified calculation table." If the air conditioner 2A determines that the learned simplified calculation table 242 exists (Yes in S54), it acquires information indicating the indoor temperature and indoor humidity (S55). The air conditioner 2A acquires a heat index from the learned simplified calculation table 242 based on the indoor temperature and indoor humidity (S56). In step S56 of FIG. 16, the learned simplified calculation table 242 is described as a "learned heat index simplified calculation table." The heat index acquired in step S56 is the heat index inference value at the current time.

[0074] The air conditioner 2A determines whether the learned heat index inference value at the current time is greater than the heat index threshold value 243 at the start of operation (S57). In step S57 of FIG. 16, the heat index threshold value 243 at the start of operation is described as the "start heat index threshold." If the air conditioner 2A determines that the learned heat index inference value at the current time is equal to or less than the heat index threshold value 243 at the start of operation (No in S57), it performs the operation of step S51. If the air conditioner 2A determines that the learned heat index inference value at the current time is greater than the heat index threshold value 243 at the start of operation (Yes in S57), it adds the difference between the WBGT inference value and the WBGT predicted value to the total WBGT predicted values ​​for that day, and sets the result as a new group of WBGT predicted values ​​(S58). The difference between the WBGT inference value and the WBGT predicted value is (WBGT inference value - WBGT predicted value).

[0075] The air conditioner 2A saves information indicating the time when the new WBGT predicted value will fall below the heat index threshold 244 at the time of operation termination, and sets the operation stop time in the operation timer 204 (S59). In step S59 of FIG. 16, the heat index threshold 244 at the time of operation termination is written as "operation stop threshold." The air conditioner 2A sets the current time in the operation timer 204 and starts operation (S60). In step S60, the air conditioner 2A starts, for example, cooling operation.

[0076] If the air conditioner 2A determines that a learned heat index simple calculation table does not exist (No in S54), it determines whether the current WBGT predicted value is greater than the heat index threshold 243 at the start of operation (S61). In step S61 of FIG. 17, the heat index threshold 243 at the start of operation is described as the "start heat index threshold." If the air conditioner 2A determines that the current WBGT predicted value is greater than the heat index threshold 243 at the start of operation (Yes in S61), it starts operation (S62). In step S62, the air conditioner 2A starts, for example, cooling operation.

[0077] If the air conditioner 2A determines that the current predicted WBGT value is equal to or less than the heat index threshold 243 at the start of operation (No in S61), it saves the predicted WBGT value at the current time (S63). The air conditioner 2A acquires information indicating the indoor temperature and indoor humidity (S64). The air conditioner 2A acquires a heat index from the simplified calculation table 241 based on the indoor temperature and indoor humidity (S65). In step S65 of FIG. 17, the simplified calculation table 241 is described as a "simple index calculation table." The heat index acquired in step S65 is the estimated WBGT value at the current time.

[0078] The air conditioner 2A determines whether the estimated WBGT value at the current time is greater than the heat index threshold 243 at the start of operation (S66). In step S66 of FIG. 17, the heat index threshold 243 at the start of operation is described as the "start heat index threshold." If the air conditioner 2A determines that the estimated WBGT value at the current time is greater than the heat index threshold 243 at the start of operation (Yes in S66), it adds the difference between the estimated WBGT value and the predicted WBGT value to all the predicted WBGT values ​​for that day, and sets the result as a new group of predicted WBGT values ​​(S67). The difference between the estimated WBGT value and the predicted WBGT value is (estimated WBGT value - predicted WBGT value).

[0079] The air conditioner 2A saves information indicating the time when the new WBGT predicted value will fall below the heat index threshold 244 at the time of operation termination, and sets the operation stop time in the operation timer 204 (S68). In step S68 of FIG. 17, the heat index threshold 244 at the time of operation termination is entered as "operation stop threshold." The air conditioner 2A sets the current time in the operation timer 204 and starts operation (S69). In step S69, the air conditioner 2A starts, for example, cooling operation.

[0080] If the air conditioner 2A determines that the estimated WBGT value at the current time is equal to or less than the heat index threshold 243 at the start of operation (No in S66), it determines whether the time indicated by the operation timer 204 has passed the operation start time (S70). If the air conditioner 2A determines that the time indicated by the operation timer 204 has passed the operation start time (Yes in S70), it starts operation (S71). In step S71, the air conditioner 2A starts cooling operation, for example. If the air conditioner 2A determines that the time indicated by the operation timer 204 has not passed the operation start time (No in S70), it performs the operation of step S51.

[0081] Fig. 18 is a flowchart showing the procedure for the operation stop determination process of air conditioning control performed by the air conditioner 2A according to Embodiment 2. After starting operation through the processes shown in Fig. 16 and Fig. 17, the air conditioner 2A periodically executes the process shown in Fig. 18 as determination process for stopping operation.

[0082] The processing shown in Figure 18 will be described in detail below. The air conditioner 2A acquires the latest heat index forecast information from the specified homepage at the set time (S81). In step S81 of Figure 18, the homepage is written as "HP." The heat index forecast information is a WBGT predicted value. The air conditioner 2A saves information indicating the time when the acquired WBGT predicted value will fall below the heat index threshold 244 at the end of operation, and sets the operation stop time in the operation timer 204 (S82). In step S82 of Figure 18, the heat index threshold 244 at the end of operation is written as "operation stop threshold."

[0083] The air conditioner 2A determines whether the current WBGT predicted value is smaller than the heat index threshold 244 at the end of operation (S83). In step S83 of FIG. 18, the heat index threshold 244 at the end of operation is described as the "stop heat index threshold." If the air conditioner 2A determines that the current WBGT predicted value is smaller than the heat index threshold 244 at the end of operation (Yes in S83), it stops operation (S84). In step S84, the air conditioner 2A stops cooling operation, for example.

[0084] If the air conditioner 2A determines that the current WBGT predicted value is equal to or greater than the heat index threshold 244 at the time of operation termination (No in S83), it determines whether the time indicated by the operation timer 204 has passed the operation stop time (S85). If the air conditioner 2A determines that the time indicated by the operation timer 204 has passed the operation stop time (Yes in S85), it stops operation (S86). In step S86, the air conditioner 2A stops cooling operation, for example. If the air conditioner 2A determines that the time indicated by the operation timer 204 has not passed the operation stop time (No in S85), it performs the operation of step S81.

[0085] As described above, the air conditioner 2A according to embodiment 2 has a learning device 25 and an inference device 26, and calculates a heat index inference value using a learned simplified calculation table 242 that has been designed to improve accuracy by taking into account the effects of solar radiation on the room and radiant heat sources within the room, and is therefore able to calculate a heat index inference value suitable for each of a plurality of indoor environments.

[0086] When calculating the heat index based on the simplified calculation table 241 in a situation where learning has not been performed and the heat index is assumed to be used in an indoor environment where there is no solar radiation and no radiant heat source, the calculated heat index tends to be low. In many indoor environments, there is solar radiation and the influence of radiant heat indoors due to walls, etc. The air conditioner 2A can further reduce the risk of heatstroke by calculating and using a heat index inference value with improved accuracy that takes into account the influence of solar radiation and radiant heat indoors based on the trained model 271. In other words, the air conditioner 2A can reduce the risk of heatstroke in the room in which the air conditioner 2A is installed by taking into account the influence of solar radiation on the room and radiant heat inside the room.

[0087] Embodiment 3 In the above-described Embodiments 1 and 2, the data obtained by the temperature sensor 201 and the humidity sensor 202 and the data in the simplified calculation table 241 are stored in the storage unit 24 or the storage unit 24A. In Embodiment 3, the data obtained by the temperature sensor 201 and the humidity sensor 202 and the data in the simplified calculation table 241 are uploaded to the cloud system server 3. If the air conditioner according to Embodiment 3 is, for example, the air conditioner 2A shown in FIG. 7 , the transmission unit 212 uploads information indicating the temperature and humidity of the space in which the air conditioner 2A is installed to the cloud system server 3. Furthermore, the transmission unit 212 uploads the data obtained by the temperature sensor 201 and the humidity sensor 202 and the data in the simplified calculation table 241 to the cloud system server 3. The heat index is calculated by the cloud system server 3 based on the simplified calculation table 241.

[0088] As described above, in the third embodiment, data storage and heat index calculation are performed by the cloud system server 3. Therefore, even if an older model air conditioner that does not have the resources to store data and calculate the heat index is used, the effects obtained by the first embodiment can be obtained.

[0089] Embodiment 4. In the configuration of Embodiment 1, Embodiment 2, or Embodiment 3 described above, an air conditioner according to Embodiment 4 notifies a user of the operating status and heatstroke prevention information in real time when the operation, such as the start and end of operation, is changed. The heatstroke prevention information may include an alert, etc. If the air conditioner according to Embodiment 4 is, for example, air conditioner 2A shown in FIG. 7 , the air conditioner according to Embodiment 4 performs some or all of the following: displaying the operating status and heatstroke prevention information on the display panel 205; activating the buzzer 206; notifying the cloud system server 3 of the operating status and heatstroke prevention information using the transmission unit 212 included in the communication unit 21A; and notifying a mobile terminal device 5, such as a smartphone, of the operating status and heatstroke prevention information using the transmission unit 212. In other words, the air conditioner according to Embodiment 4 has an alarm unit that notifies a user of the operating status and heatstroke prevention information of the air conditioner when the air conditioner starts or ends automatic operation control. The display panel 205 and the buzzer 206 are examples of an alarm unit. The transmission unit 212 notifies one or both of the cloud system server 3 and the mobile terminal device 5 of the driving status and heatstroke prevention information, and therefore the transmission unit 212 is also an example of a notification unit.

[0090] As described above, in embodiment 4, heatstroke prevention information, etc. is notified to the user, and according to embodiment 4, the user can be encouraged to take actions to prevent the onset of heatstroke, thereby further reducing the risk of heatstroke occurring.

[0091] Embodiment 5. An air conditioner according to Embodiment 5 has a function that allows a user to manually set whether the air conditioner is to operate automatically, in the configuration of each of the above-described embodiments 1 to 4. If the air conditioner according to Embodiment 5 is, for example, the air conditioner 2A shown in FIG. 7 , the air conditioner according to Embodiment 5 has a function that allows a user to manually set whether the air conditioner according to Embodiment 5 is to automatically start or stop operation, and the automatic operation setting 246 set by the user is stored in the memory unit 24A. If the air conditioner according to Embodiment 5 is, for example, an air conditioner that is capable of determining the presence or absence of a person using a human presence sensor 203, like the air conditioner 2A shown in FIG. 7 , the air conditioner according to Embodiment 5 may automatically start or stop operation only if it determines that a person is present. One way to enable a user to manually set whether the air conditioner is to operate automatically is to send a setting command to the air conditioner 2A via an external device such as a wireless remote control 7.

[0092] As described above, the air conditioner according to the fifth embodiment has a function that allows the user to manually set whether or not to operate the air conditioner automatically. Therefore, according to the fifth embodiment, it is possible to reduce unnecessary power consumption caused by the air conditioner operating automatically in a space where no one is present for a long period of time.

[0093] 19 is a diagram showing a processor 91 in a case where at least some of the functions of the control unit 20, communication unit 21, time management unit 22, and calculation unit 23 of the air conditioner 2 according to Embodiment 1 are realized by the processor 91. In other words, at least some of the functions of the control unit 20, communication unit 21, time management unit 22, and calculation unit 23 may be realized by the processor 91 that executes a program stored in memory 92. The processor 91 is a CPU (Central Processing Unit), a processing system, an arithmetic system, a microprocessor, or a DSP (Digital Signal Processor). FIG. 19 also shows the memory 92.

[0094] When at least some of the functions of the control unit 20, the communication unit 21, the time management unit 22, and the calculation unit 23 are realized by the processor 91, the functions are realized by the processor 91 and software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in the memory 92. The processor 91 realizes at least some of the functions of the control unit 20, the communication unit 21, the time management unit 22, and the calculation unit 23 by reading and executing the program stored in the memory 92.

[0095] When at least some of the functions of the control unit 20, the communication unit 21, the time management unit 22, and the calculation unit 23 are realized by the processor 91, the air conditioner 2 has a memory 92 for storing a program that results in the execution of at least some of the steps executed by the control unit 20, the communication unit 21, the time management unit 22, and the calculation unit 23. It can also be said that the program stored in the memory 92 causes a computer to execute at least some of the procedures or methods executed by the control unit 20, the communication unit 21, the time management unit 22, and the calculation unit 23.

[0096] The memory 92 may be, for example, a non-volatile or volatile semiconductor memory such as a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, an EPROM (Erasable Programmable Read Only Memory), an EEPROM (registered trademark) (Electrically Erasable Programmable Read-Only Memory), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD (Digital Versatile Disk).

[0097] 20 is a diagram showing a processing circuit 93 in a case where at least some of the functions of the control unit 20, the communication unit 21, the time management unit 22, and the calculation unit 23 included in the air conditioner 2 according to Embodiment 1 are realized by the processing circuit 93. In other words, at least some of the functions of the control unit 20, the communication unit 21, the time management unit 22, and the calculation unit 23 may be realized by the processing circuit 93.

[0098] The processing circuitry 93 is dedicated hardware, and may be, for example, a single circuit, a composite circuit, a programmed processor, a parallel programmed processor, an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a combination thereof.

[0099] Some of the functions of the control unit 20, communication unit 21, time management unit 22, and calculation unit 23 of the air conditioner 2 may be realized by dedicated hardware separate from the hardware that realizes the remaining functions.

[0100] Some of the functions of the control unit 20, the communication unit 21, the time management unit 22, and the calculation unit 23 may be realized by software or firmware, and the remaining functions may be realized by dedicated hardware. In this way, the functions of the control unit 20, the communication unit 21, the time management unit 22, and the calculation unit 23 can be realized by hardware, software, firmware, or a combination thereof.

[0101] At least some of the functions of the control unit 20A, communication unit 21A, time management unit 22, calculation unit 23, learning device 25, and inference device 26 of the air conditioner 2A according to embodiment 2 may be realized by a processor that executes a program stored in memory. The memory is the same as memory 92. The processor is the same as processor 91. At least some of the functions of the control unit 20A, communication unit 21A, time management unit 22, calculation unit 23, learning device 25, and inference device 26 may be realized by a processing circuit. The processing circuit is the same as processing circuit 93.

[0102] 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, or part of the configuration may be omitted or modified within the scope of the gist of the invention.

[0103] 1, 1A Air conditioning system, 2, 2A Air conditioner, 3 Cloud system server, 4 Internet site, 5 Mobile terminal device, 6 Heat index meter with black ball, 7 Wireless remote control, 20, 20A Control unit, 21, 21A Communication unit, 22 Time management unit, 23 Calculation unit, 24, 24A Storage unit, 25 Learning device, 26 Inference device, 27 Trained model storage unit, 91 Processor, 92 Memory, 93 Processing circuit, 201 Temperature sensor, 202 Humidity sensor, 203 Human presence sensor, 204 Operation timer, 205 Display panel, 206 Buzzer, 211 Receiving unit, 212 Transmitting unit, 241 Simplified calculation table, 242 Trained simplified calculation table, 243 Heat index threshold at start of operation, 244 Heat index threshold at end of operation, 245 Set time for obtaining warning information, 246 Setting whether autonomous driving is possible, 251 first data acquisition unit, 252 model generation unit, 261 second data acquisition unit, 262 inference unit, 271 trained model.

Claims

1. A temperature sensor for detecting the temperature of a space to be air-conditioned, A humidity sensor for detecting the humidity of the aforementioned space, A storage unit that stores a simplified calculation table that associates temperature, humidity, and heat index, A data acquisition unit acquires learning data including learning input data that includes information indicating temperature detected by the temperature sensor, information indicating humidity detected by the humidity sensor, and weather information, and learning data that includes measured heat index values ​​obtained from a heat index meter with a black globe in the space, which are associated with the learning input data. An air conditioning system comprising: a model generation unit that uses the measured heat index values ​​included in the training data acquired by the data acquisition unit as the correct answer, and generates a trained simplified calculation table based on the training input data and the measured heat index values ​​included in the training data.

2. The air conditioning system according to Claim 1, wherein the heat index in the learned simplified calculation table is associated with temperature and humidity and reflects the degree of solar radiation to the space and the effect of radiant heat in the space.

3. A temperature sensor for detecting the temperature of a space to be air-conditioned, A humidity sensor for detecting the humidity of the aforementioned space, A memory unit that stores a learned simplified calculation table that associates temperature, humidity, and heat index, A data acquisition unit that acquires inference input data including information indicating temperature detected by the temperature sensor, information indicating humidity detected by the humidity sensor, and weather information, An inference unit that uses the inference input data acquired by the data acquisition unit and the learned simplified calculation table to infer the heat index and output the inferred value of the heat index, An air conditioning system comprising: a control unit that controls the operation of the air conditioning system for the space such that the heat index decreases when the inferred value of the heat index obtained by the inference unit is greater than a predetermined threshold.

4. Further comprising a transmission unit that uploads information indicating the temperature and humidity of the space to a cloud system, The aforementioned heat index is calculated by the cloud system based on a simplified calculation table. The air conditioning system according to claim 3.

5. A function that allows the user to manually set whether or not to enable automatic operation of the air conditioner. The air conditioning system according to claim 4.

6. The system further includes a notification unit that informs the user of the operating status of the air conditioner and information on preventing heatstroke when the air conditioner starts or stops automatic operation control. The air conditioning system according to claim 5.