Climate control navigation system, learning device, inference device and climate control navigation method

Abstract

An air conditioning navigation system (100) that performs navigation for a user with respect to a seat in an air conditioning state that conforms to a user's preference with respect to air conditioning, wherein the user uses a device that has an air conditioning target room in which an air conditioner (110) is installed, comprising: a mobile terminal (30) that transmits user characteristic information (321) indicating a characteristic related to a user's preference with respect to air conditioning;and a cloud server (20) that generates appropriate seat information (221) indicating a seat that matches a user's preference regarding air conditioning based on the user characteristic information (321) and air conditioning characteristic information (211) indicating an air conditioning characteristic of the air conditioning target room acquired by the mobile terminal (30), and transmits the appropriate seat information (221) to the mobile terminal (30);

Description

Area

[0001] The present disclosure relates to an air-conditioning navigation system that performs navigation with respect to a seat in an air-conditioning state consistent with a user's preference regarding air-conditioning, and to a learning device, an inference device, and an air-conditioning navigation method used in the air-conditioning navigation system. background

[0002] In recent years, there has been an increase in free-address offices, where employee seats are not fixed and employees freely choose their seats to work in. Furthermore, in facilities such as a library or restaurant, it is also common for a user to select a seat, which they will then occupy, and then use the facility.

[0003] In such an office, library, and restaurant, the indoor air conditioning environment is not uniform, and there may be a location where a user receives warm direct airflow or cold direct airflow—that is, a location where air conditioning is more effective—or a location far from an air conditioning outlet—that is, a location where air conditioning is less effective. It depends on the user whether the user wants a seat where air conditioning is more effective or a seat where air conditioning is less effective. For example, a user sensitive to cold often wants to sit in a seat where air conditioning is less effective during cooling operation, and a user sensitive to heat often wants to sit in a seat where air conditioning is more effective during cooling operation.

[0004] However, it is difficult for a user to determine which seat is a seat where the air conditioner is more effective and which seat is a seat where the air conditioner is less effective before the user sits.

[0005] Patent Literature 1 discloses an air conditioning navigation system that notifies a user using a free-seat office of information about a seat where an air conditioning environment desired by the user is provided. List of citationsPatent literature

[0006] Patent Literature 1: Japanese Patent Application Publication No. 2011 - 133 175 Brief description of the inventionProblem to be solved by the invention

[0007] However, the air conditioning navigation system disclosed in Patent Literature 1 has a problem that when a user uses multiple offices, air conditioning navigation is available only when the user's air conditioning preference information is registered in the air conditioning navigation system installed in each of the offices. That is, the air conditioning navigation system disclosed in Patent Literature 1 cannot obtain conformable seat information indicating a seat in an air conditioning environment that conforms to a user's air conditioning preference in multiple facilities unless air conditioning preference information is registered for each facility.

[0008] The present disclosure has been made in view of the foregoing, and an object thereof is to provide an air conditioning navigation system capable of obtaining appropriate seat information indicating a seat in an air conditioning environment that corresponds to a user's preference regarding air conditioning for a plurality of facilities without registering information regarding the air conditioning preference for each of the facilities. Means of solving the problem

[0009] To solve the above problem and achieve an object, an air conditioning navigation system according to the present disclosure performs navigation for a user with respect to a seat in an air conditioning state that conforms to a user's preference with respect to air conditioning, the user using a device having an air conditioning target room in which an air conditioner is installed, the air conditioning navigation system comprising: a user terminal for transmitting user characteristic information indicating a characteristic related to a user's preference with respect to air conditioning;and an information processing device for generating appropriate seat information indicating a seat that conforms to a user's preference regarding air conditioning based on the user characteristic information acquired by the user terminal and air conditioning characteristic information indicating an air conditioning characteristic of the air conditioning target room, and transmitting the appropriate seat information to the user terminal; Effects of the invention

[0010] An air conditioning navigation system according to the present disclosure achieves an effect that it is possible to obtain appropriate seat information indicating a seat in an air conditioning environment that corresponds to a user's preference regarding air conditioning for a plurality of facilities without registering information regarding the air conditioning preference for each of the facilities. Short description of the drawings Fig. 1 is a diagram illustrating a configuration of an air-conditioning navigation system according to a first embodiment. Fig. 2 is a flowchart illustrating a flow of operation of the air conditioning navigation system according to the first embodiment. Fig. 3 is a diagram illustrating an example of a user characteristic information input screen of the air-conditioning navigation system according to the first embodiment. Fig. 4 is a diagram illustrating an example of a navigation destination selection screen of the air-conditioning navigation system according to the first embodiment. Fig. 5 is a diagram illustrating an exemplary display of appropriate seat information of the air-conditioning navigation system according to the first embodiment. Fig. 6 is a flowchart illustrating a flow of an appropriate seat information output process by a processing unit of a cloud server of the air-conditioning navigation system according to the first embodiment. Fig. 7 is a diagram illustrating an exemplary configuration of a temperature preference point calculation table of the air conditioning navigation system according to the first embodiment. Fig. 8 is a diagram illustrating an exemplary configuration of a direct airflow permitting point calculation table of the air conditioning navigation system according to the first embodiment. Fig. 9 is a diagram illustrating an example of a floor map of the air-conditioning navigation system according to the first embodiment. Fig. 10 is a diagram illustrating an example of an indoor air conditioning disposition map of the air conditioning navigation system according to the first embodiment. Fig. 11 is a diagram illustrating an example of a direct airflow map of the air conditioning navigation system according to the first embodiment. Fig. 12 is a diagram illustrating an example of a temperature distribution map of the air-conditioning navigation system according to the first embodiment. Fig. 13 is a diagram illustrating an example of a temperature point map of the air-conditioning navigation system according to the first embodiment. Fig. 14 is a diagram illustrating an example of a direct airflow point map of the air conditioning navigation system according to the first embodiment. Fig. 15 is a diagram illustrating an example of the appropriate seat information of the air-conditioning navigation system according to the first embodiment. Fig. 16 is a diagram illustrating a configuration of the air conditioning navigation system according to a second embodiment. Fig. 17 is a flowchart illustrating an operation of the air conditioning navigation system according to the second embodiment. Fig. 18 is a flowchart illustrating a flow of an appropriate seat information output process by the processing unit of the cloud server of the air-conditioning navigation system according to the second embodiment. Fig. 19 is a diagram illustrating a configuration of the air-conditioning navigation system according to a third embodiment. Fig. 20 is a flowchart illustrating a flow of operation of the air conditioning navigation system according to the third embodiment. Fig. 21 is a diagram illustrating a configuration of the air conditioning navigation system according to a fourth embodiment. Fig. 22 is a flowchart illustrating a flow of an appropriate seat information output process by the processing unit of the cloud server of the air-conditioning navigation system according to the fourth embodiment. Fig. 23 is a diagram illustrating a configuration of a determination unit of the air conditioning navigation system according to the fourth embodiment. Fig. 24 is a diagram illustrating an exemplary configuration of a learning device included in the air-conditioning navigation system according to the fourth embodiment. Fig. 25 is a diagram for explaining a neural network used for generating a learned model by the learning device of the air-conditioning navigation system according to the fourth embodiment. Fig. 26 is a flowchart illustrating an example of an operation of the learning device of the air-conditioning navigation system according to the fourth embodiment. Fig. 27 is a diagram illustrating an exemplary configuration of an inference device of the air-conditioning navigation system according to the fourth embodiment. Fig. 28 is a flowchart illustrating an example of an operation of the inference device included in the air-conditioning navigation system according to the fourth embodiment. Fig. 29 is a diagram illustrating a configuration of the air-conditioning navigation system according to a fifth embodiment. Fig. 30 is a flowchart illustrating a flow of a user characteristic information correction process by a processing unit of a mobile terminal of the air-conditioning navigation system according to the fifth embodiment. Fig. 31 is a diagram illustrating an example of a hardware configuration of the cloud server of the air conditioning navigation system according to any one of the first to fifth embodiments. Description of the embodiments

[0011] Hereinafter, an air conditioning navigation system, a learning device, an inference device, and an air conditioning navigation method according to each embodiment will be described in detail with reference to the drawings. First embodiment

[0012] Fig. 1 is a diagram illustrating a configuration of an air-conditioning navigation system according to a first embodiment. An air-conditioning navigation system 100 includes a device-side air-conditioning device 10, a cloud server 20, and a mobile terminal 30.

[0013] The facility-side air conditioning device 10 includes a plurality of air conditioners 110 and an air conditioning control unit 120 that controls the air conditioners 110. The air conditioners 110 and the air conditioning control unit 120 are connected to the cloud server 20. The connection between the cloud server 20 and the air conditioners 110 and the air conditioning control unit 120 is implemented using, for example, the Internet.

[0014] Each air conditioner 110 transmits temperature distribution information 111 to the cloud server 20. The temperature distribution information 111 is a temperature value of each area when an air conditioning target room is divided. Regarding the temperature distribution information 111, examples of an acquisition method thereof include a method in which acquisition is performed by a thermal imaging sensor attached to the air conditioner 110 and a method in which acquisition is performed by arranging a plurality of temperature sensors in the room and using communication, but there is no limitation on an acquisition method and a data format.

[0015] The air conditioning system 110 transmits setting information 119 to the air conditioning control unit 120. The setting information 119 includes room temperature setting, airflow direction setting, and airflow speed setting.

[0016] The air conditioning control unit 120 transmits air conditioning control information 121 to the cloud server 20. The air conditioning control information 121 is information indicating the operating states of the respective devices constituting the facility-side air conditioning device 10 and the influence of their operations on the air conditioning target space. The air conditioning control information 121 includes the room temperature setting of the air conditioner 110 and / or the airflow direction setting of the air conditioner 110 and / or the airflow speed setting of the air conditioner 110.

[0017] The cloud server 20, which is an information processing device, is a server communicatively connected to the facility-side air conditioning device 10 and the mobile terminal 30. The cloud server 20 includes a storage unit 210 that stores information and a processing unit 220 that performs a calculation process using the information stored in the storage unit 210.

[0018] The storage unit 210 of the cloud server 20 stores air conditioning characteristic information 211. The air conditioning characteristic information 211 includes room structure information 212, the temperature distribution information 111, and the air conditioning control information 121. The room structure information 212 includes the floor plan of the air conditioning target room and the installation positions of the air conditioners 110 in the air conditioning target room.

[0019] The cloud server 20 receives an appropriate seat reference request 311 and user characteristic information 321 from the mobile terminal 30, performs a calculation in the processing unit 220 using the received information items and the air conditioning characteristic information 211 stored in the storage unit 210, and outputs appropriate seat information 221. Additionally, the cloud server 20 transmits the appropriate seat information 221 to the mobile terminal 30.

[0020] The mobile terminal 30 is a user terminal operated by a user. The mobile terminal 30 includes an input unit 310, a storage unit 320, a display unit 330, and a processing unit 350. The mobile terminal 30 can communicate with the cloud server 20. The connection between the mobile terminal 30 and the cloud server 20 is implemented, for example, using the Internet. The mobile terminal 30 is configured, for example, by a smartphone and an application installed on the smartphone, but may have a configuration different from the example. Here, the configuration in which the user terminal is the mobile terminal 30 is taken as an example, but the user terminal does not necessarily have portability. For example, the user terminal may be a desktop computer terminal.

[0021] The mobile terminal 30 stores user characteristic information 321 indicating a characteristic related to a user's preference regarding air conditioning. The user characteristic information 321 includes at least one of the user's age, the user's gender, a user's temperature preference, a user's direct airflow preference, and a user's physical condition. The user's temperature preference is information indicating whether the user is sensitive to heat or cold. The user's direct airflow preference is information indicating a preference regarding direct airflow.

[0022] The input unit 310 of the mobile terminal 30 receives an input operation from the user. At least one of the information items constituting the user characteristic information 321 stored in the storage unit 320 is input by the user via the input unit 310. The user of the mobile terminal 30 can transmit the appropriate seat reference request 311 and the user characteristic information 321 to the cloud server 20 by operating the input unit 310.

[0023] The mobile terminal 30 displays the appropriate seat information 221 received from the cloud server 20 on the display unit 330.

[0024] Next, an operation of the air conditioning navigation system 100 according to the first embodiment will be described. Fig. 2 is a flowchart illustrating a flow of operation of the climate control navigation system according to the first embodiment. Before executing the Fig. 2, in response to an operation by a manager of the air conditioners 110, the room structure information 212, such as the floor plan of the air conditioning target room, is stored in the storage unit 210 of the cloud server 20. Each time the control state of each air conditioner 110 changes, the air conditioning controller 120 transmits the air conditioning control information 121 to the cloud server 20 to store the air conditioning control information 121 in the storage unit 210 of the cloud server 20. The air conditioners 110 each periodically acquire the temperature distribution information 111 of the air conditioning target room through the thermal imaging sensor and periodically transmit the temperature distribution information 111 to the cloud server 20 to store the temperature distribution information 111 in the storage unit 210 of the cloud server 20.

[0025] In step S1, the mobile terminal 30 receives an input operation of the user characteristic information 321 at the input unit 310 and stores the user characteristic information 321 in the storage unit 320. Fig. 3 is a diagram illustrating an example of a user characteristic information input screen of the air conditioning navigation system according to the first embodiment. A user characteristic information input screen 400 includes an age input field 401, a gender input field 402, a room cooling temperature preference input field 403, a room heating temperature preference input field 404, and a direct airflow tolerance input field 405. By pressing a set button 406 after inputting information into each input field, the user characteristic information 321 is stored in the storage unit 320. In addition, the user can cancel the input of the user characteristic information 321 by pressing a cancel button 407.

[0026] In step S2, the mobile terminal 30 receives an operation for selecting a navigation destination and an operation for requesting the acquisition of the appropriate seat information 221 at the input unit 310. Fig. 4 is a diagram illustrating an example of a navigation destination selection screen of the air-conditioned navigation system according to the first embodiment. A navigation destination selection screen 410 includes an input-from-map button 411, an address search button 412, a facility name search button 413, an address input field 414, and a facility name input field 415. In addition, the navigation destination selection screen 410 includes a physical condition input field 416, a basic information setting button 417, a seat number input field 418, and an appropriate seat display button 419. The user's physical condition is information included in the user characteristic information 321, but it is information that changes daily.Therefore, the physical condition input field is provided on the navigation destination selection screen 410 so that the physical condition can be set along with the selection of the navigation destination. Note that the physical condition input field 416 may be provided on the user characteristic information input screen 400 shown in FIG. Fig. 3. The user characteristic information 321 includes the physical condition of the user to be specified on the navigation destination selection screen 410 shown in Fig. 4, in addition to the user's age, user's gender, user's temperature preference and user's direct airflow preference, which are based on the Fig. 3 shown user characteristic information input screen 400.

[0027] By pressing the input-from-map button 411, the user can select the navigation destination facility from the map. In addition, after entering an address of the navigation destination facility into the address input field 414 by pressing the address search button 412, a facility present at the address entered into the address input field 414 can be selected as the navigation destination facility. Furthermore, after entering a facility name into the facility name input field 415 by pressing the facility name search button 413, a facility whose name was entered into the facility name input field 415 can be selected as the navigation destination facility.

[0028] In step S3, the mobile terminal 30 transmits the user characteristic information 321 and an identifier 322 of the navigation target device together with the appropriate seat acquisition request 311 to the cloud server 20. By pressing the appropriate seat display button 419 while the navigation target device is selected, the user characteristic information 321 and the identifier 322 of the navigation target device together with the appropriate seat acquisition request 311 are transmitted to the cloud server 20.

[0029] In step S4, the cloud server 20 reads the air conditioning characteristic information 211 of the facility indicated by the identifier 322 of the navigation destination facility from the storage unit 210, and generates the appropriate seat information 221 indicating a seat that conforms to the user's preference regarding air conditioning based on the air conditioning characteristic information 211 of the navigation destination facility and the received user characteristic information 321.

[0030] In step S5, the cloud server 20 transmits the appropriate seat information 221 to the mobile terminal 30 in response to the appropriate seat acquisition request 311.

[0031] In step S6, the mobile terminal 30 displays the appropriate seat information 221 received from the cloud server 20 on the display unit 330. Fig. 5 is a diagram illustrating an exemplary display of the appropriate seat information of the air-conditioned navigation system according to the first embodiment. The appropriate seat information 221 includes a facility map 421 and an appropriate seat list 422. The facility map 421 is a sketch of the navigation destination facility and represents a layout of tables and seats. The appropriate seat list 422 displays a list of information about seats in the navigation destination facility that match the user's preference regarding air conditioning. In addition, the mobile terminal 30 can display on the display unit 330 information used to output the appropriate seat information 221, such as the information shown in Fig. 11 shown direct air flow map 453 and the one in Fig. Temperature distribution map 454 shown in Figure 12.

[0032] Fig. 6 is a flowchart illustrating a flow of an appropriate seat information output process by the processing unit of the cloud server of the climate control navigation system according to the first embodiment. In step S201, the processing unit 220 calculates a temperature preference point. Fig. 7 is a diagram illustrating an exemplary configuration of a temperature preference point calculation table of the air-conditioning navigation system according to the first embodiment. The processing unit 220 calculates a temperature preference point based on a temperature preference point calculation table 430 and the received user characteristic information 321. The temperature preference point calculation table 430 includes a correction value table 431 in which answers to respective questions of age, gender, preference for room cooling temperature / cooled room temperature, preference for room heating temperature / heated room temperature, and physical condition are associated with temperature preference correction values, and a conversion table 432 in which total values ​​of temperature preference correction values ​​based on the answers to the respective questions are associated with temperature preference points.In the correction value table 431, temperature preference correction values ​​during cooling operation and temperature preference correction values ​​during heating operation are defined separately. The temperature preference point can be calculated by obtaining temperature preference correction values ​​based on the answers to the respective questions with reference to the correction value table 431, summing the values, and converting the total of the temperature preference correction values ​​into the temperature preference point with reference to the conversion table 432.

[0033] Next, in step S202, the processing unit 220 calculates a direct airflow permission point. Fig. 8 is a diagram illustrating an exemplary configuration of a direct airflow permissive point calculation table of the air conditioning navigation system according to the first embodiment. The processing unit 220 calculates the direct airflow permissive point based on a direct airflow permissive point calculation table 440 and the received user characteristic information 321. The direct airflow permissive point calculation table 440 is a table in which the degree of sensitivity to airflow from an air conditioner is associated with the direct airflow permissive point.

[0034] In step S203, the processing unit 220 obtains the air conditioning characteristic information 211 of the navigation destination device from the storage unit 210. The air conditioning characteristic information 211 includes, for example, a floor map 451, an indoor air conditioning disposition map 452, the direct airflow map 453, and the temperature distribution map 454.

[0035] Fig. 9 is a diagram illustrating an example of the floor map of the air conditioning navigation system according to the first embodiment. On the floor map 451, the position of each table in the room is linked to the number of seats at the corresponding table.

[0036] Fig. 10 is a diagram illustrating an example of the indoor air conditioning disposition map of the air conditioning navigation system according to the first embodiment. On the indoor air conditioning disposition map 452, the position of each air conditioner 110 in the room is linked to information indicating the characteristics of the corresponding air conditioner 110. The information indicating the characteristics of the air conditioner 110 includes the number of outlets and a direction correction angle.

[0037] Fig. 11 is a diagram illustrating an example of the direct airflow map of the air conditioning navigation system according to the first embodiment. On the direct airflow map 453, positions in the room are linked to direct airflow points at the corresponding positions. The direct airflow point is a numerical value indicating the intensity of the direct airflow of a respective air conditioner 110. The larger the numerical value of the point, the more intense the direct airflow from the corresponding air conditioner 110.

[0038] Fig. 12 is a diagram illustrating an example of the temperature distribution map of the air-conditioning navigation system according to the first embodiment. On the temperature distribution map 454, positions in the room are linked to temperature points at the corresponding positions. The temperature point is a numerical value indicating the temperature at the position, where the temperature is expressed as one of the temperature zones. The larger the numerical value of the point, the higher the temperature of the zone.

[0039] In step S204, the processing unit 220 overlays the floor map 451 and the temperature distribution map 454 to generate a temperature point map 455 indicating a temperature point for each seat. Fig. 13 is a diagram illustrating an example of the temperature point map of the air-conditioning navigation system according to the first embodiment. The temperature point map 455 indicates temperature points at positions where respective seats are located in the room.

[0040] In step S205, the processing unit 220 overlays the floor map 451 on the direct airflow map 453 to generate a direct airflow point map 456 indicating a direct airflow for each seat. Fig. 14 is a diagram illustrating an example of the direct airflow point map of the air conditioning navigation system according to the first embodiment. The direct airflow point map 456 indicates direct airflow points at positions where respective seats are arranged in the room.

[0041] In step S206, the processing unit 220 extracts a seat having a temperature preference point that matches the temperature preference point on the temperature point map 455 and having a direct airflow permissive point that is equal to or lower than the direct airflow permissive point on the direct airflow point map 456, and generates the appropriate seat information 221. Fig. 15 is a diagram illustrating an example of the appropriate seat information of the air-conditioning navigation system according to the first embodiment.

[0042] In the air conditioning navigation system 100 according to the first embodiment, for example, for a user who is a 30-year-old woman, is in a normal physical condition, is sensitive to heat, and wishes to avoid the air flow from the air conditioner, visiting a restaurant in the summer season when the cooling operation is performed, the temperature preference point is determined by the Fig. 7 is calculated to be “4”. In addition, the direct air flow permissive point is calculated based on the temperature preference point calculation table 430 shown in Fig. 8 shown direct air flow acceptance point calculation table 440 to "0". If the user wishes to use a table with four seats in a restaurant for which the Fig. 9 shown floor map 451, which in Fig. 10 shown interior air conditioning disposition card 452, which in Fig. 11 shown direct air flow map 453 and the one in Fig. 12, the appropriate seats are specified as air conditioning characteristic information 211, G11, G14, G15, G17, G21, J11, J24, M11, M20, M21, P11, P12, P18, P20, and Q4. As shown in Fig. 5, the display unit 330 of the mobile terminal 30 displays the appropriate seat information 221, which includes a layout of seats in the restaurant and a list of seats that match the user's temperature preference.

[0043] The air-conditioning navigation system 100 according to the first embodiment can obtain the appropriate seat information 221 indicating a seat in an air-conditioning environment that corresponds to a user's air-conditioning preference in multiple facilities, without registering the user characteristic information 321, which is information regarding the user's air-conditioning preference for each of the facilities. The air-conditioning navigation system 100 according to the first embodiment displays the appropriate seat information 221 on the mobile terminal 30, and thereby the user can easily recognize where a seat matches the user's temperature preference, even in a facility used by the user for the first time. Second embodiment

[0044] Fig. 16 is a diagram illustrating a configuration of the air-conditioning navigation system according to a second embodiment. The air-conditioning navigation system 100 according to the second embodiment differs from the air-conditioning navigation system 100 according to the first embodiment in that the storage unit 210 of the cloud server 20 stores past temperature distribution information 213 and past air-conditioning control information 214.

[0045] In the past temperature distribution information 213, values ​​of the temperature distribution information 111 are traced back to the past and stored at predetermined intervals for a specific period of time. For example, hourly values ​​of the temperature distribution information 111 are stored for one year.

[0046] In the past climate control information 214, values ​​of the climate control information 121 are traced back to the past and stored at predetermined intervals for a specific period of time. For example, hourly values ​​of the climate control information 121 are stored for one year.

[0047] Fig. Fig. 17 is a flowchart illustrating an operation of the climate control navigation system according to the second embodiment. Before executing the Fig. In the operation illustrated in Figure 17, the room structure information 212, such as the floor plan of the air conditioning target room, is stored in the storage unit 210 of the cloud server 20. Each time the control state of each air conditioner 110 changes, the air conditioning controller 120 transmits the air conditioning control information 121 to the cloud server 20 to store the air conditioning control information 121 in the storage unit 210 of the cloud server 20. The air conditioners 110 each periodically acquire the temperature distribution information 111 of the air conditioning target room through the thermal imaging sensor and periodically transmit the temperature distribution information 111 to the cloud server 20 to store the temperature distribution information 111 in the storage unit 210 of the cloud server 20.When the air conditioning control information 121 is received from the air conditioning control device 120, the cloud server 20 stores the already stored air conditioning control information 121 as the past air conditioning control information 214 in the storage unit 210 and then stores the received air conditioning control information 121 in the storage unit 210. In addition, the cloud server 20 stores the already stored temperature distribution information 111 as the past temperature distribution information 213 in the storage unit 210 and then stores the received temperature distribution information 111 in the storage unit 210 when the temperature distribution information 111 is received from a respective air conditioner 110.

[0048] The process of step S11 is similar to the process of step S1 of the air conditioning navigation system 100 according to the first embodiment.

[0049] In step S12, the mobile terminal 30 receives an operation for selecting a navigation destination, an operation for selecting a date and time for use, and an operation for requesting the acquisition of the appropriate seat information 221 at the input unit 310.

[0050] In step S13, the mobile terminal 30 transmits the user characteristic information 321, the date and time of use, and the identifier 322 of the navigation destination device together with the appropriate seat acquisition request 311 to the cloud server 20.

[0051] In step S14, the cloud server 20 generates the appropriate seat information 221 on the date and time for use based on the air conditioning characteristic information 211 of the navigation target device and the received user characteristic information 321.

[0052] The processes in steps S15 and S16 are similar to the processes in steps S5 and S6 of the air conditioning navigation system 100 according to the first embodiment.

[0053] Fig. 18 is a flowchart illustrating a flow of an appropriate seating information output process by the processing unit of the cloud server of the air-conditioning navigation system according to the second embodiment. In the air-conditioning navigation system 100 according to the second embodiment, an air-conditioning state at a future time is predicted using the past temperature distribution information 213 and the past air-conditioning control information 214, and used to calculate the appropriate seating information 221.

[0054] The processes in steps S211 and S212 are similar to the processes in steps S201 and S202 of the air conditioning navigation system 100 according to the first embodiment.

[0055] In step S213, the processing unit 220 acquires the room structure information 212, the past temperature distribution information 213, and the past air conditioning control information 214 of the target facility from the storage unit 210, and extracts from the acquired pieces of information data predicted to correspond to an air conditioning state on the date and time specified by the user. For example, there is a method in which, when the time specified by the user is 11:00 a.m. on August 6th, and the current time is 3:00 p.m. on August 5th, the temperature distribution information 111 and the air conditioning control information 121 recorded at 11:00 a.m. on August 5th, which is the same time as the user-specified time, are simply applied as prediction data. However, there is no limitation on the prediction method.

[0056] The processes in steps S214, S215, and S216 are similar to the processes in steps S204, S205, and S206 of the air-conditioning navigation system 100 according to the first embodiment.

[0057] In the above description, the processing unit 220 calculates the air conditioning characteristic information 211 at the future time based on the past temperature distribution information 213 and the past air conditioning control information 214. However, if schedules of the air conditioners 110 are stored in the storage unit 210 of the cloud server 20, the processing unit 220 may calculate the air conditioning characteristic information 211 at the future time based on the control schedules stored in the storage unit 210. The processing unit 220 may calculate the air conditioning characteristic information 211 at the future time based on the control schedules stored in the storage unit 210 in addition to the past temperature distribution information 213 and the past air conditioning control information 214.

[0058] The climate control navigation system 100 according to the second embodiment allows the user to select a future date and time and obtain an appropriate seat. Therefore, if the user cannot obtain a seat that matches the user's climate control preference at the selected time, the user can take action such as changing the device to be used. Third embodiment

[0059] Fig. 19 is a diagram illustrating a configuration of the air-conditioning navigation system according to a third embodiment. Differences from the air-conditioning navigation system 100 according to the second embodiment are that the mobile terminal 30 receives an input operation for inputting an after-use impression 340 at the input unit 310, transmits the after-use impression 340 to the cloud server 20, and includes the processing unit 350 that analyzes the after-use impression 340 and performs a process for correcting a value of the user characteristic information 321. The air-conditioning navigation system 100 according to the third embodiment differs from the air-conditioning navigation system 100 according to the second embodiment in that the storage unit 210 of the cloud server 20 stores an air-conditioning request 230, which is a request for air conditioning.

[0060] The post-use impression 340 is the user's impression after using the facility based on the appropriate seating information 221. The post-use impression 340 includes dissatisfaction with room temperature and / or dissatisfaction with direct airflow. The air conditioning request 230 is data obtained by collecting the post-use impression 340 from users using the air conditioning navigation system 100.

[0061] Fig. 20 is a flowchart illustrating an operation sequence of the climate-controlled navigation system according to the third embodiment. The processes in steps S21 to S26 are similar to the processes in steps S1 to S6 of the climate-controlled navigation system 100 according to the first embodiment. In step S27, the mobile terminal 30 receives an input operation of the impression-after-use 340 at the input unit 310.

[0062] In step S28, the mobile terminal 30 analyzes the impression-after-use 340 in the processing unit 350 and corrects the user characteristic information 321 so that an appropriate seat that matches a user's desire can be presented next time and subsequent times. For example, there is a method for correcting the user characteristic information 321 in which, when an impression that it was cold is input in the summer season during which the cooling operation is performed, in the air conditioning navigation system 100 using the Fig. 7, the value "1" is subtracted from a temperature preference correction value for cooling operation for the preference regarding the room cooling temperature. However, there is no limitation on a method for correcting the user characteristic information 321.

[0063] In step S29, the mobile terminal 30 transmits the identifier 322 of the navigation destination device, an occupied seat, and the impression after use 340 to the cloud server 20.

[0064] In step S30, the cloud server 20 updates the air conditioning request 230 to reflect the post-use impression 340 received from the mobile terminal 30. For example, there is a method in which the air conditioning target room is divided into five areas, and with respect to impressions of users belonging to the areas, impressions of the last 20 people are summed by the moving average, thereby updating the air conditioning request 230, but there is no limitation on a method for updating the air conditioning request 230.

[0065] In step S31, the cloud server 20 notifies the air conditioning manager of the content of the air conditioning request update 230 using means such as email.

[0066] Since the air conditioning navigation system 100 according to the third embodiment corrects the user characteristic information 321 based on the impression after use 340 input by the user, a seat that better matches the user's preference regarding air conditioning can be recommended to the user. Fourth embodiment

[0067] Fig. 21 is a diagram illustrating a configuration of the air-conditioning navigation system according to a fourth embodiment. The air-conditioning navigation system 100 according to the fourth embodiment differs from the air-conditioning navigation system 100 according to the second embodiment in that a learned model 240 for estimating and correcting the air-conditioning characteristic information 211 is stored in the storage unit 210 of the cloud server 20, and the processing unit 220 includes a determination unit 52.

[0068] In the air-conditioning navigation systems 100 according to the first to third embodiments, an appropriate seating position is selected using the air-conditioning systems 110, the air-conditioning characteristic information 211 received from the air-conditioning control unit 120, and the air-conditioning characteristic information 211 set by the air-conditioning manager, but the air-conditioning navigation system 100 according to the fourth embodiment selects an appropriate seating position using machine learning.

[0069] In the air conditioning navigation system 100 according to the fourth embodiment, with the floor plan of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and an outside temperature as inputs, the determination unit 52 estimates or corrects the air conditioning characteristic information 211 using the learned model 240 and outputs the appropriate seating information 221.

[0070] Fig. 22 is a flowchart illustrating a flow of an appropriate seating information output process by the processing unit of the cloud server of the climate-controlled navigation system according to the fourth embodiment. In the fourth embodiment, the processing unit 220 estimates or corrects the climate characteristic information 211 using the learned model 240 and uses a result of the estimation or correction to calculate the appropriate seating information 221.

[0071] The processes in steps S221 and S222 are similar to the processes in steps S201 and S202 of the air conditioning navigation system 100 according to the first embodiment. In step S223, the processing unit 220 obtains the air conditioning characteristic information 211 of the target facility and the learned model 240 from the storage unit 210, and, with the layout of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature as inputs, estimates or corrects the air conditioning characteristic information 211 using the learned model 240, which derives a direct airflow at each position in the room and a temperature distribution in the room.

[0072] For example, there is a procedure in which the Fig. 9 shown floor map 451 of the target facility and the Fig. 10, a direct air flow at each position in the room and a temperature distribution in the room are estimated using the learned model 240 shown in Fig. 11 shown direct air flow map 453 and the one in Fig. 12 can be automatically generated and used for subsequent calculations. However, there is no limitation on an estimation method and a correction method. A learning operation of the learned model 240 and an inference operation using the learned model 240 by the determination unit 52 are described below.

[0073] The processes in steps S224, S225, and S226 are similar to the processes in steps S204, S205, and S206 of the air-conditioning navigation system 100 according to the first embodiment.

[0074] Fig. Figure 23 is a diagram illustrating a configuration of the determination unit of the climate control navigation system according to the fourth embodiment. The determination unit 52 includes a learning device 60 and an inference device 61.

[0075] Fig. Fig. 24 is a diagram illustrating an exemplary configuration of the learning device included in the climate control navigation system according to the fourth embodiment. The learning device 60 includes a data acquisition unit 601 and a model generation unit 602. Note that a Fig. 24 shown storage unit for learned model 250 is part of the Fig. 21, which stores the learned model 240.

[0076] The data acquisition unit 601 acquires learning data including the floor plan of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature. That is, the learning data includes the floor plan of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature.

[0077] Using the learning data output from the data acquisition unit 601, the model generation unit 602 learns a relationship between the layout of the air conditioning target space, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature on the one hand, and on the other hand, the intensity of the direct airflow from each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each area when the air conditioning target space is divided.That is, the model generation unit 602 generates, from the floor plan of the air conditioning target space, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature, the learned model 240 for deriving the intensity of the direct air flow from each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each area when the air conditioning target space is divided.

[0078] Here, the learning data is data in which the floor plan of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature are associated with the intensity of the direct airflow from each of the air conditioners 110 at each position in the air conditioning target room, and the temperature distribution which is a temperature value of each area when the air conditioning target room is divided.

[0079] Although the learning device 60 is used to learn the relationship between the layout of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature on the one hand, and the intensity of the direct airflow from each of the air conditioners 110 at each position in the air conditioning target room, and the temperature distribution, which is a temperature value of each area when the air conditioning target room is divided, on the other hand, the learning device 60 may be configured to operate as a device connected to the cloud server 20 via a network and separate from the cloud server 20.

[0080] A learning algorithm used by the model generation unit 602 may be a known algorithm, such as supervised learning, unsupervised learning, or reinforcement learning. As an example, a case where a neural network is used will be described.

[0081] For example, the model generation unit 602 learns, according to a neural network model, the relationship between the layout of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature, on the one hand, and the intensity of the direct airflow from each of the air conditioners 110 at each position in the air conditioning target room and the temperature distribution, which is a temperature value of each region obtained by dividing the air conditioning target room, on the other hand, through so-called supervised learning according to a neural network model. Here, supervised learning is a method in which data sets, each including an input and a label, which is a result, are input to the learning device 60, and thereby characteristics included in the learning data are learned and results are derived from inputs.

[0082] A neural network comprises an input layer 71 containing multiple neurons, an intermediate layer 72 containing multiple neurons, and an output layer 73 containing multiple neurons. The intermediate layer 72, which is a hidden layer, may be one layer or two or more layers.

[0083] Fig. Fig. 25 is a diagram for explaining a neural network used to generate a learned model by the learning device of the air-conditioning navigation system according to the fourth embodiment. For example, as for a three-layer neural network as shown in Fig. 25, when multiple inputs are input to the neurons X1, X2, and X3 of the input layer 71, values ​​thereof are multiplied by weights w11, w12, w13, w14, w15, and w16 and input to the neurons Y1 and Y2 of the intermediate layer 72, and further results thereof are multiplied by weights w21, w22, w23, w24, w25, and w26 and output from the neurons Z1, Z2, and Z3 of the output layer 73. The output results vary depending on the values ​​of the weights w11, w12, w13, w14, w15, and w16 and the weights w21, w22, w23, w24, w25, and w26.

[0084] The neural network used in the model generation unit 602 of the learning device 60 according to the fourth embodiment performs so-called supervised learning in accordance with the learning data acquired by the data acquisition unit 601 and generated based on a combination of the layout of the air conditioning target space, the installation positions of the air conditioners 110, the operating states of the air conditioners 110 and the outside temperature, and the intensity of the direct airflow from each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each region obtained by dividing the air conditioning target space.According to the supervised learning, the neural network learns the intensity of the direct airflow from each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each area obtained by dividing the air conditioning target space, according to the layout of the air conditioning target space, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature.

[0085] That is, the neural network performs learning by adjusting the weights w11, w12, w13, w14, w15, and w16 and the weights w21, w22, w23, w24, w25, and w26 so that results output from the output layer 73 after the layout of the air conditioning target space, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature are input to the input layer 71 approximate the intensity of the direct airflow from each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each region obtained by dividing the air conditioning target space.

[0086] The model generation unit 602 generates the learned model 240 by performing learning as described above and outputs the learned model 240.

[0087] The learned model storage unit 250 stores the learned model 240 output from the model generation unit 602.

[0088] Next, with reference to Fig. 26 describes an operation in which the learning device 60 generates the learned model 240. Fig. 26 is a flowchart illustrating an example of an operation of the learning device of the air-conditioning navigation system according to the fourth embodiment.

[0089] In step S111, the learning device 60 acquires learning data. Specifically, the data acquisition unit 601 acquires the learning data including the floor plan of the air-conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature, as well as the intensity of the direct airflow from each of the air conditioners 110 at each position in the air-conditioning target room, and the temperature distribution, which is a temperature value of each region obtained by dividing the air-conditioning target room. It should be noted that although the floor plan of the air-conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature, and, on the other hand, the intensity of the direct airflow from each of the air conditioners 110 at each position in the air-conditioning target room, and the temperature distribution, which is a temperature value of each region,obtained by dividing the air conditioning target space, it is sufficient as long as the floor plan of the air conditioning target space, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature, and on the other hand, the intensity of the direct air flow from each of the air conditioners 110 at a respective position in the air conditioning target space and the temperature distribution, which is a temperature value of each area obtained by dividing the air conditioning target space, can be obtained in conjunction with each other. It is sufficient that the floor plan of the air conditioning target space, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature, and the intensity of the direct air flow from each of the air conditioners 110 at a respective position in the air conditioning target space and the temperature distribution,which is a temperature value of each area obtained by dividing the air conditioning target space at different times.

[0090] In step S112, the learning device 60 performs a learning process. Specifically, the model generation unit 602 performs so-called supervised learning according to the learning data acquired by the data acquisition unit 601, which includes the floor plan of the air conditioning target space, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, the outside temperature and the intensity of the direct airflow from each of the air conditioners 110 at each position in the air conditioning target space, and the temperature distribution, which is a temperature value of each region obtained by dividing the air conditioning target space.According to the supervised learning, the model generation unit 602 learns the intensity of the direct air flow of each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each area obtained by dividing the air conditioning target space, according to the layout of the air conditioning target space, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature, and generates the learned model 240.

[0091] In step S113, the learning device 60 stores the learned model 240 in the learned model storage unit 250. Specifically, the model generation unit 602 outputs the learned model 240 generated in step S112, and the learned model storage unit 250 stores the learned model 240.

[0092] Note that in the present embodiment, the case where supervised learning is applied to the learning algorithm used by the model generation unit 602 of the learning device 60 has been described, but this is not limited to this. It is also possible to use reinforcement learning, unsupervised learning, semi-supervised learning, or the like as the learning algorithm other than supervised learning.

[0093] As the learning algorithm used in the model generation unit 602, deep learning that learns the extraction of feature quantities by itself can also be used, and machine learning can be performed according to another known method, for example, genetic programming, functional logic programming, or a support vector machine.

[0094] Fig. Fig. 27 is a diagram illustrating an exemplary configuration of the inference device of the air-conditioning navigation system according to the fourth embodiment. The inference device 61 includes a data acquisition unit 611 and an inference unit 612. Note that the Fig. 27 shown storage unit for learned model 250 is the same as that shown in Fig. 24 shown storage unit for learned model 250.

[0095] The data acquisition unit 611 acquires the floor plan of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature. The floor plan of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature acquired by the data acquisition unit 611 are similar to the floor plan of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature acquired by the data acquisition unit 601 of the learning device 60.

[0096] Using the learned model 240 stored in the learned model storage unit 250, the inference unit 612 derives the intensity of the direct air flow of each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each area obtained by dividing the air conditioning target space, according to the layout of the air conditioning target space, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature.That is, the inference unit 612 inputs the floor plan of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature acquired from the data acquisition unit 611 into the learned model 240, and causes the learned model 240 to derive the intensity of the direct air flow of each of the air conditioners 110 at each position in the air conditioning target room and the temperature distribution, which is a temperature value of each area obtained by dividing the air conditioning target room, according to the floor plan of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature.Then, the inference unit 612 obtains, as an inference result, the intensity of the direct air flow of each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each area obtained by dividing the air conditioning target space, which are derived from the floor plan of the air conditioning target space, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature.

[0097] In the present embodiment, it has been described that the learned model 240 generated by the learning device 60 in the cloud server 20 constituting the air conditioning navigation system 100 is used to output the direct airflow intensity of each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each region obtained by dividing the air conditioning target space. However, a learned model 240 generated from outside the air conditioning navigation system 100 may be acquired, and the direct airflow intensity of each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each region obtained by dividing the air conditioning target space, can be output using this learned model 240.

[0098] Fig. 28 is a flowchart illustrating an example of the operation of the inference device included in the air-conditioning navigation system according to the fourth embodiment. In step S121, the inference device 61 acquires data to be used for inferring the air-conditioning characteristic information 211. Specifically, the data acquisition unit 611 acquires the floor plan of the air-conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature.

[0099] In step S122, the inference device 61 inputs the data obtained in step S121 into the learned model 240 stored in the learned model storage unit 250 and obtains an inference result.That is, the inference unit 612 inputs the floor plan of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature acquired from the data acquisition unit 611 into the learned model 240 stored in the learned model storage unit 250, and obtains, according to the floor plan of the air conditioning target room, the installation positions of the air conditioners 110, the operating states of the air conditioners 110, and the outside temperature, the intensity of the direct airflow of each of the air conditioners 110 at each position in the air conditioning target room and the temperature distribution, which is a temperature value of each area obtained by dividing the air conditioning target room, which are output from the learned model 240 as a result of the input.

[0100] In step S123, the inference device 61 outputs an inference result.

[0101] In the air conditioning navigation system 100 according to the fourth embodiment, using the air conditioning characteristic information 211 obtained by deriving the intensity of the direct air flow of each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each region obtained by dividing the air conditioning target space, using machine learning, an appropriate seat position is selected, so that it is possible to guide the user to a seat adapted to the user's temperature preference.

[0102] In the above description, the configuration in which the intensity of the direct airflow of each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each region obtained by dividing the air conditioning target space, are derived using machine learning was given as an example. However, a configuration in which each of the intensity of the direct airflow of each of the air conditioners 110 at each position in the air conditioning target space and the temperature distribution, which is a temperature value of each region obtained by dividing the air conditioning target space, are derived using machine learning may be used. Fifth embodiment

[0103] Fig. 29 is a diagram illustrating a configuration of the air-conditioned navigation system according to a fifth embodiment. The air-conditioned navigation system 100 according to the fifth embodiment differs from the air-conditioned navigation system 100 according to the third embodiment in that a learned model 241 for correcting the user characteristic information 321 is stored in the storage unit 210 of the cloud server 20, the appropriate seat information 221 is stored in the storage unit 320 of the mobile terminal 30, and the processing unit 350 of the mobile terminal 30 includes a determination unit 62. The determination unit 62 is similar to the determination unit 52 of the air-conditioned navigation system 100 according to the fourth embodiment and includes the learning device 60 and the inference device 61.

[0104] Fig. 30 is a flowchart illustrating a flow of a user characteristic information correction process by the processing unit of the mobile terminal of the air-conditioned navigation system according to the fifth embodiment. The air-conditioned navigation system 100 according to the fifth embodiment corrects the user characteristic information 321 using the learned model 241. In the air-conditioned navigation system 100 according to the fifth embodiment, the learning data is data in which the impression after use 340 is associated with a correction value of the user characteristic information 321. In the learning device 60 of the air-conditioned navigation system 100 according to the fifth embodiment, the model generation unit 602 learns a relationship between the impression after use 340 and the correction value of the user characteristic information 321 using the learning data output from the data acquisition unit 601.That is, the model generation unit 602 generates the learned model 241 to derive the correction value of the user characteristic information 321 from the after-use impression 340. In the inference device 61 of the air-conditioned navigation system 100 according to the fifth embodiment, the inference unit 612 derives the correction value of the user characteristic information 321 corresponding to the after-use impression 340 using the learned model 241 stored in the learned model storage unit 250.

[0105] In step S301, the processing unit 350 of the mobile terminal 30 obtains from the cloud server 20 the air conditioning characteristic information 211 of the facility that is the subject of the after-use impression 340.

[0106] In step S302, the processing unit 350 of the mobile terminal 30 obtains the learned model 241 from the cloud server 20 based on the air conditioning characteristic information 211 and the appropriate seating information 221 stored in the storage unit 320. In step S303, the processing unit 350 of the mobile terminal 30 calculates the correction value of the user characteristic information 321 using the impression after use 340 and the learned model 241. In step S304, the processing unit 350 of the mobile terminal 30 applies the correction value to the user characteristic information 321 and stores the corrected user characteristic information 321 in the storage unit 320.

[0107] Since the air conditioning navigation system 100 according to the fifth embodiment corrects the user characteristic information 321 using the correction value using machine learning, it is possible to guide the user to a seat adapted to the user's temperature preference.

[0108] Next, hardware configurations of the cloud server 20 and the mobile terminal 30 constituting the air conditioning navigation system 100 will be described. Fig. 31 is a diagram illustrating an example of a hardware configuration of the cloud server of the air conditioning navigation system according to any one of the first to fifth embodiments. As shown in Fig.As shown in Figure 31, the cloud server 20 is a computer system including a processor 101, a data memory 102, a storage device 103, and an interface circuit 104. The processor 101, the data memory 102, the storage device 103, and the interface circuit 104 can transmit and receive data to and from each other via a bus 105.

[0109] The processor 101 performs a function of the processing unit 220 by reading and executing an operating system (OS) and a processing program stored in the storage device 103. Part or all of the processing unit 220 may also be configured by hardware represented by an application-specific integrated circuit (ASIC) and a field-programmable gate array (FPGA). That is, a processing circuit that realizes part or all of the processing unit 220 may be dedicated hardware.

[0110] In addition, the processor 101 can also read an operating system (OS) and a processing program from one or more storage media such as a magnetic disk, a Universal Serial Bus (USB) memory, an optical disk, a compact disc, and a digital versatile disc (DVD) via an interface (not shown), store the operating system (OS) and the processing program in the storage device 103, and execute the operating system (OS) and the processing program.

[0111] The cloud server 20 may be implemented by multiple servers that are interconnected. When the cloud server 20 comprises multiple servers, with respect to a process executed by the cloud server 20, the multiple servers each execute the process and can thus be virtually considered as one server.

[0112] Similarly, the mobile terminal 30 is a computer system including the processor 101, the data memory 102, the storage device 103, and the interface circuit 104. The storage unit 320 is implemented by the data memory 102 and the storage device 103. The processor 101 performs a function of the processing unit 350 by reading and executing the operating system (OS) and the processing program stored in the storage device 103. Note that part or all of the processing unit 350 may also be configured by hardware represented by ASIC and FPGA. That is, a processing circuit that realizes part or all of the processing unit 350 may be dedicated hardware.

[0113] The configurations described in the above embodiments are merely examples of the content and can be combined with other known technologies, and part of the configurations may be omitted or modified without departing from the gist thereof. List of reference symbols 10 facility-side air conditioning system; 20 cloud servers; 30 mobile devices; 52, 62 unit of determination; 60 learning device; 61 inference device; 71 input layer; 72 intermediate layer; 73 Output layer; 100 climate control navigation system; 101 processor; 102 data storage; 103 storage device; 104 interface circuit; 105 buses; 110 air conditioning; 111 Temperature distribution information; 119 Setting information; 120 air conditioning control unit; 121 Climate control information; 210, 320 storage unit; 211 Climate control characteristic information; 212 spatial structure information; 213 past temperature distribution information; 214 past climate control information; 220, 350 processing unit; 221 Appropriate Seat Information; 230 air conditioning request; 240, 241 learned model; 250 memory units for learned models; 310 input unit; 311 Adequate Seat Reference Requirement; 321 User characteristics information; 322 identifiers; 330 display unit; 340 impression-after-use; 400 User characteristic information input screen; 401 Age input field; 402 Gender input field; 403 Room cooling temperature preference input field; 404 Room heating temperature preference input field; 405 Tolerance input field for direct air flow; 406 setting button, 407 Cancel key; 410 Navigation destination selection screen; 411 Input from card key; 412 Address search button; 413 Facility name search key; 414 Address input field; 415 Facility name input field; 416 Physical condition input field; 417 Basic information setting button; 418 Number of seats input field; 419 Appropriate Seat Indicator Button; 421 Facility card; 422 Appropriate Seating List; 430 Temperature preference point calculation table; 431 Correction value table; 432 Conversion table; 440 Permissibility point calculation table for direct air flow; 451 floor map; 452 Interior air conditioning dispatch card; 453 Direct airflow map; 454 Temperature distribution map; 455 temperature point map; 456 direct airflow point card; 601, 611 data reference unit; 602 Model generation unit; 612 Inference unit.

Claims

[1] An air conditioning navigation system that performs navigation for a user with respect to a seat in an air conditioning state consistent with a user's preference regarding air conditioning, wherein the user uses a device having an air conditioning target room in which an air conditioner is installed, the air conditioning navigation system comprising: a user terminal for transmitting user characteristic information indicating a characteristic relating to a user's preference regarding air conditioning; and an information processing device for generating appropriate seat information indicating a seat that conforms to a user's preference regarding air conditioning based on the user characteristic information acquired by the user terminal and air conditioning characteristic information indicating an air conditioning characteristic of the air conditioning target room, and transmitting the appropriate seat information to the user terminal. [2] The air-conditioning navigation system according to claim 1, wherein the user terminal comprises an input unit that receives an input operation by the user, and wherein the user terminal transmits the user characteristic information to the information processing device in response to an operation for inputting the user characteristic information at the input unit. [3] The air-conditioning navigation system according to claim 2, wherein the user terminal corrects the user characteristic information based on an impression-after-use, which is an impression of the user using the facility, based on the appropriate seating information inputted at the input unit. [4] Air conditioning navigation system according to claim 3, wherein the user terminal transmits the impression-after-use to the information processing device, and the information processing device notifies a manager of the air conditioning system of the after-use impression. [5] The air-conditioning navigation system according to claim 3 or 4, wherein the user terminal derives a correction value of the user characteristic information from the impression-after-use using a learned model to derive a correction value of the user characteristic information from the impression-after-use. [6] The air conditioning navigation system according to any one of claims 1 to 5, wherein the air conditioning characteristic information includes at least one of a floor plan of the air conditioning target room, an installation position of the air conditioner in the air conditioning target room, an operating state of the air conditioner, and a temperature distribution which is a temperature value of each area obtained by dividing the air conditioning target room. [7] The air conditioning navigation system according to claim 6, wherein the information processing device derives from a floor plan of the air conditioning target room, an installation position of an air conditioner in the air conditioning target room, an operating state of the air conditioner and an outside temperature, an intensity of a direct airflow from the air conditioner at each position in the air conditioning target room, and the temperature distribution by using a learned model for deriving at least one of the direct airflow and the temperature distribution from a floor plan of the air conditioning target room, an installation position of the air conditioner in the air conditioning target room, an operating state of the air conditioner and an outside temperature. [8] The air conditioning navigation system according to any one of claims 1 to 6, wherein the user characteristic information includes an age of the user and / or a gender of the user and / or a temperature preference of the user and / or a physical condition of the user and / or a direct airflow preference of the user. [9] The air conditioning navigation system according to any one of claims 1 to 8, wherein the information processing device calculates the air conditioning characteristic information at a future time based on a control schedule of the air conditioner and / or past control information of the air conditioner and / or a past temperature distribution in the air conditioning target room, and generates the appropriate seat information at the future time using the air conditioning characteristic information at the future time. [10] Learning device, comprising: a data acquisition unit for acquiring learning data including a floor plan of an air conditioning target room, an installation position of an air conditioner in the air conditioning target room, an operating state of the air conditioner, and an outside temperature and an intensity of direct airflow from the air conditioner at each position in the air conditioning target room, and a temperature distribution that is a temperature value of each area obtained by dividing the air conditioning target room; and a model generation unit for generating a learned model for deriving at least one of the direct air flow and the temperature distribution from a floor plan of an air conditioning target room, an installation position of the air conditioner in the air conditioning target room, an operating state of the air conditioner, and an outside temperature using the learning data. [11] Inference device, comprising: a data acquisition unit for acquiring a floor plan of an air conditioning target room, an installation position of an air conditioner in the air conditioning target room, an operating state of the air conditioner, and an outside temperature; and an inference unit for deriving, using a learned model, from a floor plan of the air conditioning target room, an installation position of the air conditioner in the air conditioning target room, an operating state of the air conditioner and an outside temperature, an intensity of a direct airflow from the air conditioner at each position in the air conditioning target room, and a temperature distribution that is a temperature value of each area obtained by dividing the air conditioning target room, at least one of the direct airflow and the temperature distribution from a floor plan of the air conditioning target room, an installation position of the air conditioner in the air conditioning target room, an operating state of the air conditioner and an outside temperature. [12] An air conditioning navigation method for performing navigation for a user with respect to a seat in an air conditioning state consistent with a user's preference with respect to air conditioning, wherein the user uses a device having an air conditioning target room in which an air conditioner is installed, the air conditioning navigation method comprising: a step, performed by a user terminal, of outputting user characteristic information indicating a characteristic related to a user's preference regarding air conditioning; a step, performed by an information processing device receiving the user characteristic information, of generating appropriate seat information indicating a seat that conforms to a user's preference regarding air conditioning based on the user characteristic information acquired by the user terminal and air conditioning characteristic information indicating an air conditioning characteristic of the air conditioning target room; a step performed by the information processing device of transmitting the appropriate seat information to the user terminal; and a step performed by the user terminal to display the appropriate seating information.

Images