[go: up one dir, main page]

WO2021229769A1 - Système de climatisation et dispositif d'apprentissage - Google Patents

Système de climatisation et dispositif d'apprentissage Download PDF

Info

Publication number
WO2021229769A1
WO2021229769A1 PCT/JP2020/019342 JP2020019342W WO2021229769A1 WO 2021229769 A1 WO2021229769 A1 WO 2021229769A1 JP 2020019342 W JP2020019342 W JP 2020019342W WO 2021229769 A1 WO2021229769 A1 WO 2021229769A1
Authority
WO
WIPO (PCT)
Prior art keywords
time
temperature
data
set temperature
user
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2020/019342
Other languages
English (en)
Japanese (ja)
Inventor
貴則 京屋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mitsubishi Electric Corp
Original Assignee
Mitsubishi Electric Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Mitsubishi Electric Corp filed Critical Mitsubishi Electric Corp
Priority to PCT/JP2020/019342 priority Critical patent/WO2021229769A1/fr
Priority to JP2022522450A priority patent/JP7430784B2/ja
Publication of WO2021229769A1 publication Critical patent/WO2021229769A1/fr
Anticipated expiration legal-status Critical
Priority to JP2023190939A priority patent/JP7570488B2/ja
Ceased legal-status Critical Current

Links

Images

Classifications

    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F11/00—Control or safety arrangements
    • F24F11/62—Control or safety arrangements characterised by the type of control or by internal processing, e.g. using fuzzy logic, adaptive control or estimation of values
    • F24F11/63—Electronic processing
    • F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
    • F24—HEATING; RANGES; VENTILATING
    • F24F—AIR-CONDITIONING; AIR-HUMIDIFICATION; VENTILATION; USE OF AIR CURRENTS FOR SCREENING
    • F24F2120/00—Control inputs relating to users or occupants
    • F24F2120/20—Feedback from users

Definitions

  • This disclosure relates to an air conditioning system and a learning device.
  • a device for the purpose of comfortable temperature control in a wide space with an unspecified number of residents (users).
  • the air conditioner temperature control device described in Patent Document 1 statistically processes temperature change requests received from a plurality of request terminals, and a control request for each air conditioner based on each statistically processed request information and a current temperature. And, each air conditioner is controlled based on the set temperature.
  • the user may perform an operation to change the set temperature of the air conditioner, and after a certain period of time, the user may want to return the set temperature after the change operation to the set temperature before the change operation. .. In such a case, the user has to perform the operation of changing the set temperature of the air conditioner again, which is troublesome for the user.
  • the present disclosure is to provide an air conditioning system and a learning device capable of automatically changing the set temperature of the air conditioner to the temperature desired by the user.
  • the air conditioning system of the present disclosure is the body surface temperature of the air conditioner and the user who has performed the operation of changing the set temperature of the air conditioner from the first temperature to the second temperature at the first time. And, based on the body surface temperature of the user at the second time after the first time, the user performs an operation of returning the set temperature from the second temperature to the first temperature at the second time. It is provided with an inference device for inferring whether or not the temperature is present, and a control device for controlling the air conditioner based on the result of inference by the inference device.
  • the learning device of the present disclosure includes the body surface temperature at the first time of the user who performed the operation of changing the set temperature of the air conditioner from the first temperature to the second temperature at the first time, and the first time. Whether or not to perform an operation of returning the set temperature from the second temperature to the first temperature at the second time and the input data including the user's body surface temperature at the subsequent second time. Input data including the body surface temperature at the first time and the body surface temperature at the second time of the user by using the data acquisition unit for acquiring the learning data including the teacher data to be represented and the learning data. It is provided with a model generation unit for generating a trained model for inferring data indicating whether or not the user performs an operation of returning the set temperature from the second temperature to the first temperature at the second time from. ..
  • the body surface temperature at the first time of the user who performed the operation of changing the set temperature of the air conditioner from the first temperature to the second temperature at the first time and the second. Whether or not the user performs an operation of returning the set temperature from the second temperature to the first temperature at the second time based on the body surface temperature of the user at the second time after the first time. Infer. As a result, the set temperature of the air conditioner can be automatically changed to the temperature desired by the user.
  • FIG. 1 is a figure showing the set temperature change operation data DV1 of Embodiment 1.
  • B is a diagram showing the set temperature change operation data DV2 of the first embodiment.
  • C is a diagram showing the intermediate data DM1 of the first embodiment.
  • (D) is a diagram showing the set temperature change operation data DV3 of the first embodiment.
  • (E) is a diagram showing the intermediate data DM2 of the first embodiment. It is a figure which shows the example of the learning data of Embodiment 1.
  • FIG. It is a figure which shows the example of the learning data of Embodiment 1.
  • FIG. It is a figure which shows the example of the learning data of Embodiment 1.
  • FIG. It is a figure which shows the example of the learning data of Embodiment 1.
  • FIG. It is a figure which shows the structure of the power-off operation data of the air conditioner of Embodiment 1.
  • FIG. (A) is a figure showing the set temperature change operation data DV of Embodiment 1.
  • FIG. (B) is a figure showing the data DF at the time of power-off operation of the air conditioner of Embodiment 1.
  • FIG. (C) is a diagram showing the intermediate data DM of the first embodiment. It is a figure which shows the example of the learning data of Embodiment 1.
  • FIG. It is a figure which shows the example of the learning data of Embodiment 1.
  • FIG. It is a flowchart which shows the learning procedure by a learning apparatus 7. It is a figure which shows the structure of the inference apparatus 1. It is a figure which shows the set temperature change operation data DV of Embodiment 1.
  • FIG. It is a figure which shows the state data DK at the time of the prediction of Embodiment 1.
  • FIG. It is a figure which shows the example of the factor data X1 to X9 input to the inference apparatus 1 of Embodiment 1.
  • FIG. It is a flowchart which shows the inference procedure by the inference apparatus 1. It is a figure which shows the input data of Embodiment 2 and teacher data (prediction data). It is a figure which shows the example of the learning data of Embodiment 2. It is a figure which shows the example of the learning data of Embodiment 2. It is a figure which shows the example of the learning data of Embodiment 2. It is a figure which shows the example of the learning data of Embodiment 2. It is a figure which shows the example of the learning data of Embodiment 2. It is a figure which shows the input data of Embodiment 3 and teacher data (prediction data).
  • FIG. 1 It is a figure which shows the structure of the set temperature change operation data of Embodiment 3. It is a figure which shows the structure of the intermediate data of Embodiment 3.
  • A is a figure showing the set temperature change operation data DV1 of the third embodiment.
  • B is a diagram showing the set temperature change operation data DV2 of the third embodiment.
  • C is a diagram showing the intermediate data DM1 of the third embodiment.
  • D is a diagram showing the set temperature change operation data DV3 of the third embodiment.
  • E is a diagram showing the intermediate data DM2 of the third embodiment. It is a figure which shows the example of the learning data of Embodiment 3. It is a figure which shows the example of the learning data of Embodiment 3.
  • (A) is a figure showing the set temperature change operation data DV1 of Embodiment 4.
  • (B) is a diagram showing the set temperature change operation data DV2 of the fourth embodiment.
  • (C) is a diagram showing the intermediate data DM1 of the fourth embodiment.
  • (D) is a diagram showing the set temperature change operation data DV3 of the fourth embodiment.
  • (E) is a diagram showing the intermediate data DM2 of the fourth embodiment. It is a figure which shows the example of the learning data of Embodiment 4. It is a figure which shows the example of the learning data of Embodiment 4. It is a figure which shows the example of the learning data of Embodiment 4. It is a figure which shows the example of the learning data of Embodiment 4. It is a figure which shows the example of the learning data of Embodiment 4.
  • (C) is a diagram showing the intermediate data DM1 of the fifth embodiment.
  • (D) is a diagram showing the set temperature change operation data DV3 of the fifth embodiment.
  • (E) is a diagram showing the intermediate data DM2 of the fifth embodiment.
  • FIG. 1 is a diagram showing a configuration of an air conditioning system according to an embodiment.
  • the air conditioning system 10 includes an air conditioning device 2, a room temperature sensor 3, a body surface temperature sensor 4, a biometric authentication sensor 5, an input device 9, a communication device 8, a control device 6, a learning device 7, and the like.
  • the trained model storage device 75 and the inference device 1 are provided.
  • the air conditioner 2 sucks in the air in the room in which it is installed and adjusts the temperature and humidity of the air in the room.
  • the input device 9 receives the input of the set temperature from the user.
  • the input device 9 is configured by, for example, a remote controller.
  • the body surface temperature sensor 4 measures the temperature of the body surface of a person existing in the room in which the air conditioner 2 is installed.
  • the body surface temperature sensor 4 is configured by, for example, an infrared monitor.
  • the biometric authentication sensor 5 identifies the person who operated the input device 9.
  • the room temperature sensor 3 measures the temperature of the room in which the air conditioner 2 is installed.
  • the communication device 8 communicates with an external device.
  • the communication device 8 can acquire the outside air temperature (air temperature) through the Internet.
  • the learning device 7 has the body surface temperature at the first time of the user who performed the operation of changing the set temperature of the air conditioner 2 from the first temperature to the second temperature at the first time, and after the first time. From the input data including the body surface temperature at the second time, the data indicating whether or not the user performs the operation of returning the set temperature from the second temperature to the first temperature at the second time is inferred. Generate a trained model for.
  • the trained model storage device 75 stores the trained model generated by the learning device 7.
  • the inference device 1 is the body surface temperature at the first time of the user who performed the operation of changing the set temperature of the air conditioner 2 from the first temperature to the second temperature at the first time, and after the first time. Based on the temperature of the user's body surface at the second time, it is inferred whether or not the user performs an operation of returning the set temperature from the second temperature to the first temperature at the second time.
  • FIG. 2 is a diagram showing the configuration of the learning device 7.
  • the learning device 7 includes a learning data generation unit 76, a data acquisition unit 71, and a model generation unit 72.
  • the learning data generation unit 76 generates learning data based on the operation of changing the set temperature of the air conditioner 2.
  • the data acquisition unit 71 has the body surface temperature at the first time of the user who has performed the operation of changing the set temperature of the air conditioner from the first temperature to the second temperature at the first time, and after the first time. Indicates whether or not the input data including the user's body surface temperature at the second time and the operation of returning the set temperature from the second temperature to the first temperature at the second time are performed. Acquire training data including teacher data.
  • the model generation unit 72 uses the training data to allow the user to use the second time from the input data including the body surface temperature at the first time of the user and the body surface temperature at the second time. Generates a trained model for inferring data indicating whether or not to perform an operation of returning the set temperature from the temperature of the first temperature to the first temperature.
  • the data acquisition unit 71 acquires learning data consisting of input data and teacher data.
  • the learning data is data in which factor data X1 to X9 and teacher data Z are associated with each other.
  • FIG. 3 is a diagram showing the input data of the first embodiment and the teacher data (prediction data).
  • the input data includes factor data X1 to X9.
  • the factor data X1 is the user S who has performed the operation of changing the set temperature.
  • the factor data X2 is the time t0 (first time) when the set temperature is changed.
  • the factor data X3 is the temperature at time t0.
  • the factor data X4 is the body surface temperature of the user at time t0.
  • the factor data X5 is a set temperature (Tb) (first temperature) before the change operation at time t0.
  • the factor data X6 is a set temperature (Ta) (second temperature) after the change operation at time t0.
  • the factor data X7 is the time t1 (second time) after the time t0.
  • the factor data X8 is the air temperature at time t1.
  • the factor data X9 is the body surface temperature of the user at time t1.
  • the teacher data (correct answer data) Z is data indicating whether or not the user S performs an operation of returning the set
  • the model generation unit 72 uses the learning data to change the user from the second temperature (Ta) to the first temperature (Tb) at the second time (t1) from the input data including the factor data X1 to X9. Generate a trained model to infer data indicating whether or not to perform the operation to return the set temperature.
  • the model generation unit 72 generates a trained model by so-called supervised learning according to, for example, a neural network model.
  • Supervised learning is a method of learning a feature in the learning data by giving a set of data of factors and results (labels) to the learning device 7 and inferring the result from the input.
  • a neural network is composed of an input layer consisting of a plurality of neurons, an intermediate layer (hidden layer) consisting of a plurality of neurons, and an output layer consisting of a plurality of neurons.
  • the intermediate layer may be one layer or two or more layers.
  • FIG. 4 is a diagram showing the configuration of the neural network.
  • FIG. 4 shows a three-layer neural network.
  • a configuration having three inputs and three outputs is shown.
  • the value is multiplied by the weight W1 (w11-w16) and input to the intermediate layer (Y1-Y2), and the result is further weighted W2 (w21-). It is output from the output layer (Z1-Z3) by multiplying it by w26).
  • This output result depends on the values of the weights W1 and W2.
  • the data input to the input layer is X1 to X9
  • the data output from the output layer is Z.
  • the neural network is an operation of returning the set temperature by so-called supervised learning according to the learning data created based on the combination of the factor data X1 to X9 acquired by the data acquisition unit 71 and the prediction data Z (supervised data). Learn the presence or absence of. That is, the neural network learns by inputting factor data X1 to X9 into the input layer and adjusting the weight so that the result output from the output layer approaches the prediction data Z (correct answer).
  • the model generation unit 72 generates a trained model by executing the above learning, and outputs the trained model to the trained model storage device 75.
  • the trained model storage device 75 stores the trained model output from the model generation unit 72.
  • the learning data generation unit 76 generates the set temperature change operation data.
  • FIG. 5 is a diagram showing the structure of the set temperature change operation data of the first embodiment.
  • the set temperature change operation data includes the user S, the time, the air temperature, the body surface temperature of the user S, the set temperature before the change operation, and the set temperature after the change operation.
  • the user S represents a person who has performed the set temperature change operation.
  • the time represents the time when the set temperature change operation is performed by the user S.
  • the air temperature represents the air temperature at the time when the set temperature change operation is performed by the user S.
  • the body surface temperature of the user S represents the body surface temperature of the person who performed the set temperature change operation.
  • the set temperature before the change operation represents the set temperature before the set temperature change operation by the user S.
  • the set temperature after the change operation represents the set temperature after the set temperature change operation by the user S.
  • the learning data generation unit 76 creates one or more intermediate data related to the set temperature change operation data after the set temperature change operation data is created.
  • the midway data represents the state of the room until the set temperature change operation is performed, and the state of the person who performed the set temperature change operation.
  • FIG. 6 is a diagram showing the structure of the intermediate data of the first embodiment.
  • the mid-career data includes the user S, the time, the air temperature, and the body surface temperature of the user S.
  • the user S represents a person who has performed the set temperature change operation.
  • the time represents a time tx before the time when the set temperature change operation is performed by the user S.
  • the air temperature represents the air temperature at time tx.
  • the body surface temperature of the user S represents the body surface temperature of the user S at time tx.
  • FIG. 7A is a diagram showing the set temperature change operation data DV1 of the first embodiment. This data is created when "Mr. A” executes the operation of changing the set temperature at "8:45". The temperature at “8:45” is “22 ° C”. The body surface temperature of "Mr. A” at “8:45” is “37 ° C.”. The change in the set temperature is from “28 ° C” to "25 ° C”.
  • FIG. 7B is a diagram showing the set temperature change operation data DV2 of the first embodiment. This data is created when "Mr. A” executes the operation of changing the set temperature at "9:15". The temperature at “9:15” is “25 ° C”. The body surface temperature of "Mr. A” at “9:15” is “36 ° C.”. The change in the set temperature is from “25 ° C” to "28 ° C”.
  • FIG. 7C is a diagram showing the intermediate data DM1 of the first embodiment.
  • the midway data DM1 is created after the set temperature change operation data DV2 is created, and is the state of the room until the set temperature change operation is performed in the set temperature change operation data DV2, and the state of the person who performed the set temperature change operation. Represents.
  • FIG. 7D is a diagram showing the set temperature change operation data DV3 of the first embodiment. This data is created when "Mr. A” executes the operation of changing the set temperature at "12:25". The temperature at “12:25” is “29 ° C”. The body surface temperature of "Mr. A” at “12:25” is “37 ° C.”. The change in the set temperature is from “28 ° C” to "26 ° C”.
  • FIG. 7 (e) is a diagram showing the intermediate data DM2 of the first embodiment.
  • the midway data DM2 is created after the set temperature change operation data DV3 is created, and is the state of the room until the set temperature change operation is performed in the set temperature change operation data DV3, and the state of the person who performed the set temperature change operation. Represents.
  • the learning data generation unit 76 generates learning data based on the set temperature change operation data and the intermediate data.
  • the learning data of FIG. 8 is created from the set temperature change operation data DV1 of FIG. 7A and the set temperature change operation data DV2 of FIG. 7B. That is, X1 to X6 are created from the set temperature change operation data DV1. X7 to X9 are created from the time (9:15) of the set temperature change operation data DV2, the air temperature (25 ° C), and the body surface temperature (36 ° C) of the user S. Z is created from the set temperature (28 ° C.) before the change operation of the set temperature change operation data DV1 and the set temperature (28 ° C.) after the change operation of the set temperature change operation data DV2. Since the set temperature has been returned to the original value, Z is set to "there is a set temperature return operation".
  • the learning data of FIG. 9 is created from the set temperature change operation data DV1 of FIG. 7 (a) and the intermediate data DM1 of FIG. 7 (c). That is, X1 to X6 are created from the set temperature change operation data DV1. X7 to X9 are created from the time (9:00), the air temperature (24 ° C), and the body surface temperature (36.5 ° C) of the user S in the midway data DM1. Since the midway data is the data at the time when the set temperature has not been changed, Z is set to "no return operation of the set temperature".
  • the learning data of FIG. 10 is created from the set temperature change operation data DV2 of FIG. 7 (b) and the set temperature change operation data DV3 of FIG. 7 (d). That is, X1 to X6 are created from the set temperature change operation data DV2. X7 to X9 are created from the time (12:25) of the set temperature change operation data DV3, the air temperature (29 ° C), and the body surface temperature (37 ° C) of the user S. Z is created from the set temperature (25 ° C.) before the change operation of the set temperature change operation data DV2 and the set temperature (26 ° C.) after the change operation of the set temperature change operation data DV3. Since the set temperature has not been returned to the original value, Z is set to "No return operation for the set temperature".
  • the learning data of FIG. 11 is created from the set temperature change operation data DV2 of FIG. 7 (b) and the intermediate data DM2 of FIG. 7 (e). That is, X1 to X6 are created from the set temperature change operation data DV2. X7 to X9 are created from the time (11:00), the air temperature (28 ° C), and the body surface temperature (36 ° C) of the user S in the midway data DM2. Since the midway data is the data at the time when the set temperature has not been changed, Z is set to "no return operation of the set temperature".
  • the learning data generation unit 76 further generates data at the time of power-off operation of the air conditioner.
  • FIG. 12 is a diagram showing the structure of data at the time of power-off operation of the air conditioner according to the first embodiment. This data represents the state of the room when the power of the air conditioner is turned off and the state of the person who turned off the power of the air conditioner.
  • This data includes the user S, the time, the air temperature, and the body surface temperature of the user S.
  • the user S represents a person who has turned off the power of the air conditioner.
  • the time represents the time ty when the power of the air conditioner is turned off.
  • the air temperature represents the air temperature at time ty.
  • the body surface temperature of the user S represents the body surface temperature of the user S at time ty.
  • FIG. 13A is a diagram showing the set temperature change operation data DV of the first embodiment. This data is created when "Mr. B" executes the operation of changing the set temperature at "8:45". The temperature at “8:45” is “24 ° C”. The body surface temperature of "Mr. B” at “8:45” is “37 ° C.”. The change in the set temperature is from “28 ° C” to "24 ° C”.
  • FIG. 13B is a diagram showing the data DF at the time of power-off operation of the air conditioner of the first embodiment.
  • FIG. 13C is a diagram showing the intermediate data DM of the first embodiment.
  • the midway data DM is created after the data DF at the time of power-off operation of the air conditioner is created, and the indoor state until the power-off operation of the air conditioner in the data DF at the time of power-off operation of the air conditioner is performed. And the state of the person who turned off the power of the air conditioner.
  • the learning data generation unit 76 generates learning data based on the power-off operation data of the air conditioner and the set temperature change operation data.
  • the learning data of FIG. 14 is created from the set temperature change operation data DV of FIG. 13 (a) and the power-off operation data DF of the air conditioner of FIG. 13 (b). That is, X1 to X6 are created from the set temperature change operation data DV. X7 to X9 are created from the time (22:30), the air temperature (21 ° C.), and the body surface temperature (35 ° C.) of the user S when the power of the air conditioner is turned off. Z is created from the set temperature (25 ° C.) before the change operation and the set temperature (28 ° C.) after the change operation of the set temperature change operation data DV2. Since the data at the time of power-off operation of the air conditioner is the data at the time when the set temperature has not been changed, Z is set to "no change".
  • the learning data of FIG. 15 is created from the set temperature change operation data DV of FIG. 13 (a) and the intermediate data DM of FIG. 13 (c). That is, X1 to X6 are created from the set temperature change operation data DV. X7 to X9 are created from the time (12:00) of the midway data DM, the air temperature (27 ° C), and the body surface temperature (37 ° C) of the user S. Since the midway data is the data at the time when the set temperature has not been changed, Z is set to "no change".
  • the data acquisition unit 71 acquires the learning data of FIGS. 8 to 11, 14, and 15, and the data equivalent to these.
  • the model generation unit 72 generates a trained model using the training data of FIGS. 8 to 11, 14 and 15, and data equivalent thereto.
  • FIG. 16 is a flowchart showing a learning procedure by the learning device 7.
  • the data acquisition unit 71 acquires learning data including factor data X1 to X9 and teacher data Z. It is assumed that the factor data X1 to X9 and the teacher data (correct answer) Z are acquired at the same time, but it is sufficient if the factor data X1 to X9 and the teacher data (correct answer) Z can be input in association with each other. Data (correct answer) Z data may be acquired at different timings.
  • the model generation unit 72 is a trained model by so-called supervised learning according to the learning data created based on the combination of the factor data X1 to X9 acquired by the data acquisition unit 71 and the teacher data Z. To generate.
  • step S103 the trained model storage device 75 stores the trained model generated by the model generation unit 72.
  • FIG. 17 is a diagram showing the configuration of the inference device 1.
  • the inference device 1 includes an inference data generation unit 77, a data acquisition unit 73, and an inference unit 74.
  • the inference data generation unit 77 generates inference data based on the operation of changing the set temperature of the air conditioner 2.
  • the inference data generation unit 77 generates factor data from the inference data.
  • the data acquisition unit 73 acquires the body surface temperature of the user at the first time and the body surface temperature at the second time, which are factor data.
  • the reasoning unit 74 returns the temperature set by the user from the second temperature to the first temperature at the second time from the body surface temperature at the first time of the user and the body surface temperature at the second time. At the second time from the body surface temperature at the first time and the body surface temperature at the second time acquired by the data acquisition unit 73 using the model for inferring whether or not to perform the operation. It is inferred whether or not the user performs an operation of returning the set temperature from the second temperature to the first temperature.
  • the data acquisition unit 73 acquires factor data X1 to X9.
  • the inference unit 74 outputs the prediction data Z using the trained model stored in the trained model storage device 75 and the factor data X1 to X9 acquired by the data acquisition unit 73.
  • the factor data X1 to X9 are data input to the input unit of the model.
  • the prediction data Z is data output from the output unit of the model. That is, by inputting the factor data X1 to X9 acquired by the data acquisition unit 73 into this trained model, it is possible to output the data Z indicating the presence or absence of the set temperature return operation inferred from the factor data X1 to X9. can.
  • the factor data X1 to X9 are the same as those shown in FIG.
  • the inference data generation unit 77 generates the set temperature change operation data when the set temperature change operation is performed.
  • the inference data generation unit 77 represents the state of the room at the time of predicting whether or not the set temperature return operation is performed (prediction time point) and the state of the person who has performed the set temperature change operation. To generate.
  • FIG. 18 is a diagram showing the set temperature change operation data DV of the first embodiment. This data is created when "Mr. A” executes the operation of changing the set temperature at "8:50". The temperature at “8:50” is “23 ° C”. The body surface temperature of "Mr. A” at “8:50” is “36.5 ° C.”. The change in the set temperature is from “27 ° C” to "26 ° C”.
  • FIG. 19 is a diagram showing the state data DK at the time of prediction according to the first embodiment.
  • “Mr. A” is the target person who executed the operation to change the set temperature
  • the predicted time is “9:00”
  • the temperature at the predicted time is “26 ° C”
  • “A” at the predicted time It shows that the body surface temperature of "san” is "36 ° C”.
  • FIG. 20 is a diagram showing an example of factor data X1 to X9 input to the inference device 1 of the first embodiment.
  • the factor data X1 to X9 in FIG. 20 are created from the set temperature change operation data DV in FIG. 18 and the state data DK at the time of prediction in FIG. That is, X1 to X6 are created from the set temperature change operation data DV. X7 to X9 are created from the time (9:00) of the state data DK at the time of prediction, the air temperature (25 ° C), and the body surface temperature (36 ° C) of the target person “Mr. A” at “9:00”.
  • the data acquisition unit 73 acquires the factor data X1 to X9 shown in FIG. By inputting the factor data X1 to X9 of FIG. 20 into the trained neural network, the inference unit 74 obtains data Z indicating the presence or absence of the set temperature return operation.
  • FIG. 21 is a flowchart showing an inference procedure by the inference device 1.
  • the inference data generation unit 77 generates inference data including the set temperature change operation data and the state data at the time of prediction.
  • the inference data generation unit 77 generates factor data X1 to X9 from the set temperature change operation data and the state data at the time of prediction.
  • the data acquisition unit 73 acquires factor data X to X9.
  • step S202 the inference unit 74 inputs factor data X1 to X9 into the trained model stored in the trained model storage device 75, and obtains data Z indicating the presence or absence of the set temperature return operation.
  • step S203 the inference unit 74 outputs the data Z indicating the presence / absence of the return operation of the set temperature to the control device 6.
  • step S204 the control device 6 controls the air conditioner 2 by using the data indicating the presence / absence of the return operation of the temperature change. That is, when there is a return operation of the set temperature, the control device 6 controls the air conditioner 2 with the set temperature (X5) before the change operation as the target temperature.
  • the changed value is maintained when the set temperature change operation is a permanent request by a certain user specified by a fixed daily work place or the like. If the set temperature change operation is a temporary request, the air conditioning system will automatically change to the original set temperature after an appropriate time. As a result, for example, the troublesome operation of lowering the temperature setting for 30 minutes immediately after coming to work in the summer and returning it to the original set value is automated, so that the comfort is improved.
  • the data acquisition unit 71 has the body surface temperature at the first time of the user who has performed the operation of changing the set temperature of the air conditioner from the first temperature to the second temperature at the first time, and after the first time.
  • the learning data including the input data including the body surface temperature of the user at the second time and the teacher data representing the set temperature of the air conditioner desired by the user at the second time is acquired.
  • the model generation unit 72 uses the learning data and is desired by the user at the second time from the input data including the body surface temperature at the first time of the user and the body surface temperature at the second time. Generate a trained model for inferring data representing the set temperature of the air conditioner.
  • the data acquisition unit 71 acquires learning data including input data and teacher data.
  • the learning data is data in which factor data X1 to X9 and teacher data Z are associated with each other.
  • FIG. 22 is a diagram showing the input data of the second embodiment and the teacher data (prediction data).
  • the input data includes factor data X1 to X9.
  • the factor data X1 is the user S who has performed the operation of changing the set temperature.
  • the factor data X2 is the time t0 (first time) when the set temperature is changed.
  • the factor data X3 is the temperature at time t0.
  • the factor data X4 is the body surface temperature of the user at time t0.
  • the factor data X5 is a set temperature (Tb) (first temperature) before the change operation at time t0.
  • the factor data X6 is a set temperature (Ta) (second temperature) after the change operation at time t0.
  • the factor data X7 is the time t1 (second time) after the time t0.
  • the factor data X8 is the air temperature at time t1.
  • the factor data X9 is the body surface temperature of the user at time t1.
  • the teacher data (correct answer data) Z is data representing the set temperature desired by the user S at time t1.
  • the model generation unit 72 uses the training data to infer a trained model representing the set temperature desired by the user at the second time (t1) from the input data including the factor data X1 to X9. Generate.
  • the model generation unit 72 generates a trained model by so-called supervised learning according to, for example, a neural network model.
  • the data input to the input layer is X1 to X9
  • the data output from the output layer is Z.
  • the trained model storage device 75 stores the trained model output from the model generation unit 72.
  • the learning data generation unit 76 generates learning data based on the set temperature change operation data and the intermediate data.
  • the learning data of FIG. 23 is created from the set temperature change operation data DV1 of FIG. 7A and the set temperature change operation data DV2 of FIG. 7B. That is, X1 to X6 are created from the set temperature change operation data DV1. X7 to X9 are created from the time (9:15) of the set temperature change operation data DV2, the air temperature (25 ° C), and the body surface temperature (36 ° C) of the user S. Z (desired set temperature) is created from the set temperature (28 ° C.) after the change operation in the set temperature change operation data DV2.
  • the learning data of FIG. 25 is created from the set temperature change operation data DV2 of FIG. 7 (b) and the set temperature change operation data DV3 of FIG. 7 (d). That is, X1 to X6 are created from the set temperature change operation data DV2. X7 to X9 are created from the time (12:25) of the set temperature change operation data DV3, the air temperature (29 ° C), and the body surface temperature (37 ° C) of the user S. Z (desired set temperature) is created from the set temperature (26 ° C.) after the change operation in the set temperature change operation data DV2.
  • the inference device 1 has the body surface temperature at the first time of the user who performed the operation of changing the set temperature of the air conditioner from the first temperature to the second temperature at the first time, and the body surface temperature after the first time. Based on the body surface temperature of the user at the second time, the set temperature of the air conditioner desired by the user at the second time is inferred.
  • the control device 6 controls the air conditioner 2 based on the result of inference by the inference device 1. When it is inferred that the group performs an operation of returning the set temperature from the second temperature to the first temperature at the second time, the control device 6 returns the set temperature of the air conditioner 2 to the first set temperature. ..
  • the data acquisition unit 73 acquires factor data X1 to X9.
  • the inference unit 74 outputs the prediction data Z using the trained model stored in the trained model storage device 75 and the factor data X1 to X9 acquired by the data acquisition unit 73.
  • the factor data X1 to X9 are data input to the input unit of the model.
  • the prediction data Z is data output from the output unit of the model. That is, by inputting the factor data X1 to X9 acquired by the data acquisition unit 73 into this trained model, the setting of the air conditioner 2 desired by the user at the second time inferred from the factor data X1 to X9 is set. Data Z representing the temperature can be output.
  • the factor data X1 to X9 are the same as those shown in FIG.
  • Embodiment 3. ⁇ Learning phase>
  • the data acquisition unit 71 is the position at the first time of the user who performed the operation of changing the set temperature of the air conditioner from the first temperature to the second temperature at the first time, and the second after the first time.
  • Input data including the position of the user at the time of 2 and teacher data indicating whether or not the user performs an operation of returning the set temperature from the second temperature to the first temperature at the second time.
  • Acquire the training data including.
  • Location data can be acquired using known technologies such as BLE (Bluetooth Low Energy) or image analysis for people, and BIM (Building Information Modeling) or floor maps for equipment such as own seats.
  • BLE Bluetooth Low Energy
  • BIM Building Information Modeling
  • the model generation unit 72 uses the training data to allow the user to take the second temperature to the second from the input data including the position at the first time of the user and the position at the second time. Generate a trained model for inferring data indicating whether or not to perform an operation of returning the set temperature to the temperature of 1.
  • the data acquisition unit 71 acquires learning data including input data and teacher data.
  • the learning data is data in which factor data X1 to X9 and teacher data Z are associated with each other.
  • FIG. 27 is a diagram showing the input data of the third embodiment and the teacher data (prediction data).
  • the input data includes factor data X1 to X9.
  • the factor data X1 is the user S who has performed the operation of changing the set temperature.
  • the factor data X2 is the time t0 (first time) when the set temperature is changed.
  • the factor data X3 is the temperature at time t0.
  • the factor data X4 is the position of the user at time t0.
  • the factor data X5 is a set temperature (Tb) (first temperature) before the change operation at time t0.
  • the factor data X6 is a set temperature (Ta) (second temperature) after the change operation at time t0.
  • the factor data X7 is the time t1 (second time) after the time t0.
  • the factor data X8 is the air temperature at time t1.
  • the factor data X9 is the position of the user at time t1.
  • the teacher data (correct answer data) Z is data indicating whether or not the user S performs an operation of returning the set temperature from Ta to
  • the model generation unit 72 uses the learning data to change the user from the second temperature (Ta) to the first temperature (Tb) at the second time (t1) from the input data including the factor data X1 to X9. Generate a trained model to infer data indicating whether or not to perform the operation to return the set temperature.
  • the model generation unit 72 generates a trained model by so-called supervised learning according to, for example, a neural network model.
  • the data input to the input layer is X1 to X9
  • the data output from the output layer is Z.
  • the learning data generation unit 76 generates the set temperature change operation data.
  • FIG. 28 is a diagram showing the structure of the set temperature change operation data of the third embodiment.
  • the set temperature change operation data includes the user S, the time, the temperature, the position of the user S, the set temperature before the change operation, and the set temperature after the change operation.
  • the user S represents a person who has performed the set temperature change operation.
  • the time represents the time when the set temperature change operation is performed by the user S.
  • the air temperature represents the air temperature at the time when the set temperature change operation is performed by the user S.
  • the position of the user S represents the position of the person who performed the set temperature change operation.
  • the set temperature before the change operation represents the set temperature before the set temperature change operation by the user S.
  • the set temperature after the change operation represents the set temperature after the set temperature change operation by the user S.
  • the learning data generation unit 76 creates the intermediate data related to the set temperature change operation data after the set temperature change operation data is created.
  • the midway data represents the state of the room until the set temperature change operation is performed, and the state of the person who performed the set temperature change operation.
  • FIG. 29 is a diagram showing the structure of the intermediate data of the third embodiment.
  • the midway data includes the user S, the time, the temperature, and the position of the user S.
  • the user S represents a person who has performed the set temperature change operation.
  • the time represents a time tx before the time when the set temperature change operation is performed by the user S.
  • the air temperature represents the air temperature at time tx.
  • the position of the user S represents the position of the user S at time tx.
  • FIG. 30A is a diagram showing the set temperature change operation data DV1 of the third embodiment. This data is created when "Mr. A” executes the operation of changing the set temperature at "8:45". The temperature at “8:45” is “22 ° C”. The position of "Mr. A” at “8:45” is “own seat”. The change in the set temperature is from “28 ° C” to "25 ° C”.
  • FIG. 30B is a diagram showing the set temperature change operation data DV2 of the third embodiment. This data is created when "Mr. A” executes the operation of changing the set temperature at "9:15". The temperature at “9:15” is “25 ° C”. The position of "Mr. A” at “9:15” is the “reception seat”. The change in the set temperature is from “25 ° C” to "28 ° C”.
  • FIG. 30C is a diagram showing the intermediate data DM1 of the third embodiment.
  • the midway data DM1 is created after the set temperature change operation data DV2 is created, and is the state of the room until the set temperature change operation is performed in the set temperature change operation data DV2, and the state of the person who performed the set temperature change operation. Represents.
  • FIG. 30D is a diagram showing the set temperature change operation data DV3 of the third embodiment. This data is created when "Mr. A” executes the operation of changing the set temperature at "12:25". The temperature at “12:25” is “29 ° C”. The position of "Mr. A” at “12:25” is “own seat”. The change in the set temperature is from “28 ° C” to "26 ° C”.
  • FIG. 30E is a diagram showing the intermediate data DM2 of the third embodiment.
  • the midway data DM2 is created after the set temperature change operation data DV3 is created, and is the state of the room until the set temperature change operation is performed in the set temperature change operation data DV3, and the state of the person who performed the set temperature change operation. Represents.
  • the learning data generation unit 76 generates learning data based on the set temperature change operation data and the intermediate data.
  • the learning data of FIG. 31 is created from the set temperature change operation data DV1 of FIG. 30 (a) and the set temperature change operation data DV2 of FIG. 30 (b). That is, X1 to X6 are created from the set temperature change operation data DV1. X7 to X9 are created from the time (9:15) of the set temperature change operation data DV2, the air temperature (25 ° C.), and the position of the user S (reception seat). Z is created from the set temperature (28 ° C.) before the change operation of the set temperature change operation data DV1 and the set temperature (28 ° C.) after the change operation of the set temperature change operation data DV2. Since the operation for returning the set temperature has been performed, Z is set to "there is an operation for returning the set temperature".
  • the learning data of FIG. 32 is created from the set temperature change operation data DV1 of FIG. 30 (a) and the intermediate data DM1 of FIG. 30 (c). That is, X1 to X6 are created from the set temperature change operation data DV1. X7 to X9 are created from the time (9:00), the temperature (24 ° C.), and the position (own seat) of the user S in the midway data DM1. Since the midway data is the data at the time when the set temperature has not been changed, Z is set to "no return operation of the set temperature".
  • the learning data of FIG. 33 is created from the set temperature change operation data DV2 of FIG. 30 (b) and the set temperature change operation data DV3 of FIG. 30 (d). That is, X1 to X6 are created from the set temperature change operation data DV2. X7 to X9 are created from the time (12:25) of the set temperature change operation data DV3, the temperature (29 ° C.), and the position of the user S (own seat). Z is created from the set temperature (25 ° C.) before the change operation of the set temperature change operation data DV2 and the set temperature (26 ° C.) after the change operation of the set temperature change operation data DV3. Since the operation for returning the set temperature has not been performed, Z is set to "no operation for returning the set temperature".
  • the learning data of FIG. 34 is created from the set temperature change operation data DV2 of FIG. 30 (b) and the intermediate data DM2 of FIG. 30 (e). That is, X1 to X6 are created from the set temperature change operation data DV2. X7 to X9 are created from the time (11:00), the temperature (28 ° C.), and the position (reception seat) of the user S in the midway data DM2. Since the midway data is the data at the time when the set temperature has not been changed, Z is set to "no return operation of the set temperature".
  • the data acquisition unit 71 acquires the learning data of FIGS. 31 to 34 and data equivalent thereto.
  • the model generation unit 72 generates a trained model using the training data of FIGS. 31 to 34 and data equivalent thereto.
  • the inference device 1 is the position at the first time of the user who performed the operation of changing the set temperature of the air conditioner from the first temperature to the second temperature at the first time, and the second after the first time. Based on the position of the user at the time of, it is inferred whether or not the user performs an operation of returning the set temperature from the second temperature to the first temperature at the second time.
  • the control device 6 controls the air conditioner 2 based on the result of inference by the inference device. When it is inferred that the user performs an operation of returning the set temperature from the second temperature to the first temperature at the second time, the control device 6 sets the set temperature of the air conditioner 2 to the first set temperature. return.
  • the inference data generation unit 77 generates inference data based on the operation of changing the set temperature of the air conditioner 2.
  • the inference data generation unit 77 generates factor data from the inference data.
  • the data acquisition unit 73 acquires the position of the user at the first time and the position at the second time, which are factor data.
  • the reasoning unit 74 performs an operation of returning the set temperature from the second temperature to the first temperature at the second time from the position at the first time of the user and the position at the second time. From the position at the first time and the position at the second time acquired by the data acquisition unit 73 using the model for inferring whether or not the user is from the second temperature at the second time. It is inferred whether or not to carry out the operation of returning the set temperature to the first temperature.
  • the data acquisition unit 73 acquires factor data X1 to X9.
  • the inference unit 74 outputs the prediction data Z using the trained model stored in the trained model storage device 75 and the factor data X1 to X9 acquired by the data acquisition unit 73.
  • the factor data X1 to X9 are data input to the input unit of the model.
  • the prediction data Z is data output from the output unit of the model. That is, by inputting the factor data X1 to X9 acquired by the data acquisition unit 73 into this trained model, it is possible to output the data Z indicating the presence or absence of the set temperature return operation inferred from the factor data X1 to X9. can.
  • the factor data X1 to X9 are the same as those shown in FIG. 27.
  • the inference data generation unit 77 generates the set temperature change operation data when the set temperature change operation is performed.
  • the inference data generation unit 77 represents the state of the room at the time of predicting whether or not the set temperature return operation is performed (prediction time point) and the state of the person who has performed the set temperature change operation. To generate.
  • FIG. 35 is a diagram showing the set temperature change operation data DV of the third embodiment. This data is created when "Mr. A” executes the operation of changing the set temperature at "8:50". The temperature at “8:50” is “23 ° C”. The position of "Mr. A” at “8:50” is “own seat”. The change in the set temperature is from “27 ° C” to "26 ° C”.
  • FIG. 36 is a diagram showing the state data DK at the time of prediction according to the third embodiment.
  • “Mr. A” is the target person who executed the operation to change the set temperature
  • the predicted time is “9:00”
  • the temperature at the predicted time is "25 ° C”
  • “A” at the predicted time Indicates that the position of "san” is "own seat”.
  • FIG. 37 is a diagram showing an example of factor data X1 to X9 input to the inference device 1 of the third embodiment.
  • the factor data X1 to X9 in FIG. 37 are created from the set temperature change operation data DV in FIG. 35 and the state data DK at the time of prediction in FIG. That is, X1 to X6 are created from the set temperature change operation data DV. X7 to X9 are created from the time (9:00) of the state data DK at the time of prediction, the temperature (25 ° C.), and the position (own seat) of the target person "Mr. A" at "9:00".
  • the data acquisition unit 73 acquires the factor data X1 to X9 shown in FIG. 37.
  • the inference unit 74 obtains data Z indicating the presence / absence of the set temperature return operation.
  • Embodiment 4. ⁇ Learning phase>
  • the data acquisition unit 71 performs the activity at the first time of the group that performed the operation of changing the set temperature of the air conditioner from the first temperature to the second temperature at the first time, and the second after the first time. Learning including input data including the activity of the group at the time of time and teacher data indicating whether or not the user performs an operation of returning the set temperature from the second temperature to the first temperature at the second time. Get the data for.
  • Group and activity data can be acquired using known technology such as a scheduler.
  • the model generation unit 72 uses the training data to allow the user to first from the second temperature at the second time from the input data including the activity at the first time and the activity at the second time of the group. Generates a trained model for inferring data indicating whether or not to perform an operation to return the set temperature to the temperature of.
  • the data acquisition unit 71 acquires learning data including input data and teacher data.
  • the learning data is data in which factor data X1 to X9 and teacher data Z are associated with each other.
  • FIG. 38 is a diagram showing the input data of the fourth embodiment and the teacher data (prediction data).
  • the input data includes factor data X1 to X9.
  • the factor data X1 is the group L after performing the operation of changing the set temperature.
  • the factor data X2 is the time t0 (first time) when the set temperature is changed.
  • the factor data X3 is the temperature at time t0.
  • the factor data X4 is the activity of the group L at time t0.
  • the factor data X5 is a set temperature (Tb) (first temperature) before the change operation at time t0.
  • the factor data X6 is a set temperature (Ta) (second temperature) after the change operation at time t0.
  • the factor data X7 is the time t1 (second time) after the time t0.
  • the factor data X8 is the air temperature at time t1.
  • the factor data X9 is the activity of the group L at time t1.
  • the teacher data (correct answer data) Z is data indicating whether or not the user S performs an operation of returning the set temperature from Ta
  • the model generation unit 72 uses the learning data to change the user from the second temperature (Ta) to the first temperature (Tb) at the second time (t1) from the input data including the factor data X1 to X9. Generate a trained model to infer data indicating whether or not to perform the operation to return the set temperature.
  • the model generation unit 72 generates a trained model by so-called supervised learning according to, for example, a neural network model.
  • the data input to the input layer is X1 to X9
  • the data output from the output layer is Z.
  • the learning data generation unit 76 generates the set temperature change operation data.
  • FIG. 39 is a diagram showing the structure of the set temperature change operation data of the fourth embodiment.
  • the set temperature change operation data includes the group L, the time, the temperature, the activity of the group L, the set temperature before the change operation, and the set temperature after the change operation.
  • the group L represents a group in which the set temperature change operation is performed.
  • the time represents the time when the set temperature change operation by the group L is performed.
  • the air temperature represents the air temperature at the time when the set temperature change operation by the group L is performed.
  • the activity of the group L represents the activity of the group that performed the set temperature change operation.
  • the set temperature before the change operation represents the set temperature before the change operation by the group L.
  • the set temperature after the change operation represents the set temperature after the set temperature change operation by the group L.
  • the learning data generation unit 76 creates the intermediate data related to the set temperature change operation data after the set temperature change operation data is created.
  • the midway data shows the state of the room until the set temperature change operation is performed and the state of the group in which the set temperature change operation is performed.
  • FIG. 40 is a diagram showing the structure of the intermediate data of the fourth embodiment.
  • Midway data includes group L, time, temperature, and group L activity.
  • the group L represents a group in which the set temperature change operation is performed.
  • the time represents a time tx before the time when the set temperature change operation by the group L is performed.
  • the air temperature represents the air temperature at time tx.
  • the activity of group L represents the activity of group L at time tx.
  • FIG. 41A is a diagram showing the set temperature change operation data DV1 of the fourth embodiment. This data is created when the "1st year 2nd group" executes the operation of changing the set temperature at "8:45".
  • the temperature at "8:45” is "22 ° C”.
  • the activity of "1st year 2nd group” at “8:45” is "Physical education”.
  • the change in the set temperature is from “28 ° C” to "25 ° C”.
  • FIG. 40B is a diagram showing the set temperature change operation data DV2 of the fourth embodiment. This data is created when the "1st year 2nd group" executes the operation of changing the set temperature at "9:15".
  • the temperature at "9:15” is “25 ° C”.
  • the activity of "1st year 2nd group” at “9:15” is "music”.
  • the change in the set temperature is from “25 ° C” to "28 ° C”.
  • FIG. 41 (c) is a diagram showing the intermediate data DM1 of the fourth embodiment.
  • the intermediate data DM1 is created after the set temperature change operation data DV2 is created, and represents the state until the set temperature change operation is performed in the set temperature change operation data DV2, and the state of the group in which the set temperature change operation is performed. ..
  • FIG. 41 (d) is a diagram showing the set temperature change operation data DV3 of the fourth embodiment. This data is created when “Group L” executes the operation of changing the set temperature at "12:25". The temperature at “12:25” is “29 ° C”. The activity of "Group L” at “12:25” is "Kokugo". The change in the set temperature is from “28 ° C” to "26 ° C”.
  • FIG. 41 (e) is a diagram showing the intermediate data DM2 of the fourth embodiment.
  • the midway data DM2 is created after the set temperature change operation data DV3 is created, and is the state of the room until the set temperature change operation is performed in the set temperature change operation data DV3, and the state of the person who performed the set temperature change operation. Represents.
  • the learning data generation unit 76 generates learning data based on the set temperature change operation data and the intermediate data.
  • the learning data of FIG. 42 is created from the set temperature change operation data DV1 of FIG. 41 (a) and the set temperature change operation data DV2 of FIG. 41 (b). That is, X1 to X6 are created from the set temperature change operation data DV1. X7 to X9 are created from the time (9:15) of the set temperature change operation data DV2, the temperature (25 ° C.), and the activity (music) of the group L. Z is created from the set temperature (28 ° C.) before the change operation of the set temperature change operation data DV1 and the set temperature (28 ° C.) after the change operation of the set temperature change operation data DV2. Since the operation for returning the set temperature has been performed, Z is set to "there is an operation for returning the set temperature".
  • the learning data of FIG. 43 is created from the set temperature change operation data DV1 of FIG. 41 (a) and the intermediate data DM1 of FIG. 41 (c). That is, X1 to X6 are created from the set temperature change operation data DV1. X7 to X9 are created from the time (9:00), the temperature (24 ° C.), and the activity (music) of the group L of the midway data DM1. Since the midway data is the data at the time when the set temperature has not been changed, Z is set to "no return operation of the set temperature".
  • the learning data of FIG. 44 is created from the set temperature change operation data DV2 of FIG. 41 (b) and the set temperature change operation data DV3 of FIG. 41 (d). That is, X1 to X6 are created from the set temperature change operation data DV2. X7 to X9 are created from the time (12:25) of the set temperature change operation data DV3, the temperature (29 ° C.), and the activity (national language) of the group L. Z is created from the set temperature (25 ° C.) before the change operation of the set temperature change operation data DV2 and the set temperature (26 ° C.) after the change operation of the set temperature change operation data DV3. Since the operation for returning the set temperature has not been performed, Z is set to "no operation for returning the set temperature".
  • the learning data of FIG. 45 is created from the set temperature change operation data DV2 of FIG. 41 (b) and the intermediate data DM2 of FIG. 41 (e). That is, X1 to X6 are created from the set temperature change operation data DV2. X7 to X9 are created from the time (11:00), the temperature (28 ° C.), and the position (reception seat) of the user S in the midway data DM2. Since the midway data is the data at the time when the set temperature has not been changed, Z is set to "no return operation of the set temperature".
  • the data acquisition unit 71 acquires the learning data of FIGS. 42 to 45 and data equivalent thereto.
  • the model generation unit 72 generates a trained model using the training data of FIGS. 42 to 45 and data equivalent thereto.
  • the inference device 1 is a group at the first time of a group in which the set temperature change operation of the air conditioner is performed from the first temperature to the second temperature at the first time, and a second after the first time. Based on the activity of the group at the time, it is inferred whether or not the group performs an operation of returning the set temperature from the second temperature to the first temperature at the second time.
  • the control device 6 controls the air conditioner 2 based on the result of inference by the inference device. When it is inferred that the group performs an operation of returning the set temperature from the second temperature to the first temperature at the second time, the control device 6 returns the set temperature of the air conditioner 2 to the first set temperature. ..
  • the inference data generation unit 77 generates inference data based on the operation of changing the set temperature of the air conditioner 2.
  • the inference data generation unit 77 generates factor data from the inference data.
  • the data acquisition unit 73 acquires the position of the user at the first time and the position at the second time, which are factor data.
  • the inference unit 74 performs an operation of returning the set temperature from the second temperature to the first temperature at the second time from the activity at the first time and the activity at the second time of the group. From the activity at the first time and the activity at the second time of the group acquired by the data acquisition unit 73 using the model of inferring whether or not the group is the first from the second temperature at the second time. Infer whether or not to perform the operation to return the set temperature to the temperature.
  • the data acquisition unit 73 acquires factor data X1 to X9.
  • the inference unit 74 outputs the prediction data Z using the trained model stored in the trained model storage device 75 and the factor data X1 to X9 acquired by the data acquisition unit 73.
  • the factor data X1 to X9 are data input to the input unit of the model.
  • the prediction data Z is data output from the output unit of the model. That is, by inputting the factor data X1 to X9 acquired by the data acquisition unit 73 into this trained model, it is possible to output the data Z indicating the presence or absence of the set temperature return operation inferred from the factor data X1 to X9. can.
  • the factor data X1 to X9 are the same as those shown in FIG. 27.
  • the inference data generation unit 77 generates the set temperature change operation data when the set temperature change operation is performed.
  • the inference data generation unit 77 represents the state in the room at the time of predicting whether or not the set temperature return operation is performed (prediction time point) and the state of the group in which the set temperature change operation is performed. To generate.
  • FIG. 46 is a diagram showing the set temperature change operation data DV of the fourth embodiment. This data is created when the "1st year 2nd group" executes the operation of changing the set temperature at "8:50".
  • the temperature at "8:50” is “23 ° C”.
  • the activity of "1st year 2nd group” at “8:50” is "music”.
  • the change in the set temperature is from “27 ° C” to "26 ° C”.
  • FIG. 47 is a diagram showing the state data DK at the time of prediction according to the fourth embodiment.
  • “1st year 2nd group” is the target person who executed the operation to change the set temperature
  • the prediction time is "9:00”
  • the temperature at the prediction time is "25 ° C”
  • it is at the prediction time. It shows that the activity of "1st grade 2nd group” is "science”.
  • FIG. 48 is a diagram showing an example of factor data X1 to X9 input to the inference device 1 of the fourth embodiment.
  • the factor data X1 to X9 in FIG. 48 are created from the set temperature change operation data DV in FIG. 46 and the state data DK at the time of prediction in FIG. 47. That is, X1 to X6 are created from the set temperature change operation data DV. X7 to X9 are created from the activity (science) of "1 year 2 groups" at the time (9:00), temperature (25 ° C), and "9:00" of the state data DK at the time of prediction.
  • the data acquisition unit 73 acquires the factor data X1 to X9 shown in FIG. 48. By inputting the factor data X1 to X9 of FIG. 48 into the trained neural network, the inference unit 74 obtains data Z indicating the presence or absence of the set temperature return operation.
  • Embodiment 5 ⁇ Learning phase>
  • the data acquisition unit 71 is the first in which the air conditioner is installed at the first time of the user who has performed the operation of changing the set temperature of the air conditioner from the first temperature to the second temperature at the first time.
  • Input data including the presence / absence in the room and the presence / absence in the first room at the second time after the first time, and the user sets the temperature from the second temperature to the first temperature at the second time.
  • Acquire learning data including teacher data indicating whether or not to execute the return operation.
  • Presence / absence data can be acquired using known technology such as an entry / exit management system.
  • the model generation unit 72 uses the learning data to obtain a second time from the input data including the presence / absence in the first room at the first time of the user and the presence / absence in the first room at the second time. Generates a trained model for inferring data indicating whether or not the user performs an operation of returning the set temperature from the second temperature to the first temperature.
  • the data acquisition unit 71 acquires learning data including input data and teacher data.
  • the learning data is data in which factor data X1 to X9 and teacher data Z are associated with each other.
  • FIG. 49 is a diagram showing the input data of the fifth embodiment and the teacher data (prediction data).
  • the input data includes factor data X1 to X9.
  • the factor data X1 is the user S who has performed the operation of changing the set temperature.
  • the factor data X2 is the time t0 (first time) when the set temperature is changed.
  • the factor data X3 is the temperature at time t0.
  • the factor data X4 is the presence / absence in the first room in which the user's air conditioner 2 is installed at time t0.
  • the factor data X5 is a set temperature (Tb) (first temperature) before the change operation at time t0.
  • the factor data X6 is a set temperature (Ta) (second temperature) after the change operation at time t0.
  • the factor data X7 is the time t1 (second time) after the time t0.
  • the factor data X8 is the air temperature at time t1.
  • the factor data X9 is the presence / absence in the first room in which the air conditioner 2 is installed at time t1.
  • the teacher data (correct answer data) Z is data indicating whether or not the user S performs an operation of returning the set temperature from Ta to Tb at time t1.
  • the model generation unit 72 uses the learning data to change the user from the second temperature (Ta) to the first temperature (Tb) at the second time (t1) from the input data including the factor data X1 to X9. Generate a trained model to infer data indicating whether or not to perform the operation to return the set temperature.
  • the model generation unit 72 generates a trained model by so-called supervised learning according to, for example, a neural network model.
  • the data input to the input layer is X1 to X9
  • the data output from the output layer is Z.
  • the learning data generation unit 76 generates the set temperature change operation data.
  • FIG. 50 is a diagram showing the structure of the set temperature change operation data of the fifth embodiment.
  • the set temperature change operation data includes the user S, the time, the temperature, the presence or absence of the user S in the first room where the air conditioner is installed, the set temperature before the change operation, and the setting after the change operation. Including temperature.
  • the user S represents a person who has performed the set temperature change operation.
  • the time represents the time when the set temperature change operation is performed by the user S.
  • the air temperature represents the air temperature at the time when the set temperature change operation is performed by the user S.
  • the presence / absence in the first room in which the air conditioner of the user S is installed indicates the presence / absence in the first room at the time when the set temperature change operation of the person who performed the set temperature change operation is performed.
  • the set temperature before the change operation represents the set temperature before the set temperature change operation by the user S.
  • the set temperature after the change operation represents the set temperature after the set temperature change operation by the user S.
  • the learning data generation unit 76 creates the intermediate data related to the set temperature change operation data after the set temperature change operation data is created.
  • the midway data represents the state of the room until the set temperature change operation is performed, and the state of the person who performed the set temperature change operation.
  • FIG. 51 is a diagram showing the structure of mid-career data of the fifth embodiment.
  • the mid-career data includes the user S, the time, the temperature, and the presence / absence of the user S in the first room where the air conditioner is installed.
  • the user S represents a person who has performed the set temperature change operation.
  • the time represents a time tx before the time when the set temperature change operation is performed by the user S.
  • the air temperature represents the air temperature at time tx.
  • the presence / absence of the user S in the first room in which the air conditioner is installed indicates the presence / absence of the user S in the first room at time tx.
  • FIG. 52A is a diagram showing the set temperature change operation data DV1 of the fifth embodiment. This data is created when “Mr. A” executes the operation of changing the set temperature at "8:45". The temperature at “8:45” is “22 ° C”. “Mr. A” at “8:45” is “in the room”. The change in the set temperature is from “28 ° C” to "25 ° C”.
  • FIG. 52B is a diagram showing the set temperature change operation data DV2 of the fifth embodiment. This data is created when "Mr. A” executes the operation of changing the set temperature at "9:15". The temperature at “9:15” is “25 ° C”. “Mr. A” in “9:15” is “in the room”. The change in the set temperature is from “25 ° C” to "28 ° C”.
  • FIG. 52 (c) is a diagram showing the intermediate data DM1 of the fifth embodiment.
  • the midway data DM1 is created after the set temperature change operation data DV2 is created, and is the state of the room until the set temperature change operation is performed in the set temperature change operation data DV2, and the state of the person who performed the set temperature change operation. Represents.
  • FIG. 52 (d) is a diagram showing the set temperature change operation data DV3 of the fifth embodiment. This data is created when "Mr. A” executes the operation of changing the set temperature at "12:25". The temperature at “12:25” is “29 ° C”. “Mr. A” at “12:25” is “in the room”. The change in the set temperature is from “28 ° C” to "26 ° C”.
  • FIG. 52 (e) is a diagram showing the intermediate data DM2 of the fifth embodiment.
  • the midway data DM2 is created after the set temperature change operation data DV3 is created, and is the state of the room until the set temperature change operation is performed in the set temperature change operation data DV3, and the state of the person who performed the set temperature change operation. Represents.
  • the learning data generation unit 76 generates learning data based on the set temperature change operation data and the intermediate data.
  • the learning data of FIG. 53 is created from the set temperature change operation data DV1 of FIG. 52 (a) and the set temperature change operation data DV2 of FIG. 52 (b). That is, X1 to X6 are created from the set temperature change operation data DV1. X7 to X9 are created from the time (9:15) of the set temperature change operation data DV2, the temperature (25 ° C.), and the presence / absence (in-room) of the user S. Z is created from the set temperature (28 ° C.) before the change operation of the set temperature change operation data DV1 and the set temperature (28 ° C.) after the change operation of the set temperature change operation data DV2. Since the operation for returning the set temperature has been performed, Z is set to "there is an operation for returning the set temperature".
  • the learning data of FIG. 54 is created from the set temperature change operation data DV1 of FIG. 52 (a) and the intermediate data DM1 of FIG. 52 (c). That is, X1 to X6 are created from the set temperature change operation data DV1. X7 to X9 are created from the time (9:00), the temperature (24 ° C.), and the presence / absence (absence) of the user S in the midway data DM1. Since the midway data is the data at the time when the set temperature has not been changed, Z is set to "no return operation of the set temperature".
  • the learning data of FIG. 55 is created from the set temperature change operation data DV2 of FIG. 52 (b) and the set temperature change operation data DV3 of FIG. 52 (d). That is, X1 to X6 are created from the set temperature change operation data DV2. X7 to X9 are created from the time (12:25) of the set temperature change operation data DV3, the temperature (29 ° C.), and the presence / absence (in-room) of the user S. Z is created from the set temperature (25 ° C.) before the change operation of the set temperature change operation data DV2 and the set temperature (26 ° C.) after the change operation of the set temperature change operation data DV3. Since the operation for returning the set temperature has not been performed, Z is set to "no operation for returning the set temperature".
  • the learning data of FIG. 56 is created from the set temperature change operation data DV2 of FIG. 52 (b) and the intermediate data DM2 of FIG. 52 (e). That is, X1 to X6 are created from the set temperature change operation data DV2. X7 to X9 are created from the time (11:00), the temperature (28 ° C.), and the presence / absence (absence) of the user S in the midway data DM2. Since the midway data is the data at the time when the set temperature has not been changed, Z is set to "no return operation of the set temperature".
  • the data acquisition unit 71 acquires the learning data of FIGS. 53 to 56 and data equivalent thereto.
  • the model generation unit 72 generates a trained model using the training data of FIGS. 53 to 56 and data equivalent thereto.
  • the reasoning device 1 is a first room in which the air conditioner at the first time of the user who has performed the operation of changing the set temperature of the air conditioner from the first temperature to the second temperature at the first time is installed.
  • the user sets the temperature from the second temperature to the first temperature at the second time based on the presence / absence in the first room and the presence / absence in the first room of the user at the second time after the first time. Infer whether to perform the return operation.
  • the control device 6 controls the air conditioner 2 based on the result of inference by the inference device. When it is inferred that the user performs an operation of returning the set temperature from the second temperature to the first temperature at the second time, the control device 6 sets the set temperature of the air conditioner 2 to the first set temperature. return.
  • the inference data generation unit 77 generates inference data based on the operation of changing the set temperature of the air conditioner 2.
  • the inference data generation unit 77 generates factor data from the inference data.
  • the data acquisition unit 73 acquires the presence / absence of the factor data in the first room (the room in which the air conditioner is installed) at the first time of the user and the presence / absence of the user in the first room at the second time. ..
  • the user is first from the second temperature at the second time from the presence / absence in the first room at the first time and the presence / absence in the first room at the second time.
  • the presence or absence of the user in the first room at the first time and the second at the second time acquired by the data acquisition unit 73. From the presence or absence in the first room, it is inferred whether or not the user performs an operation of returning the set temperature from the second temperature to the first temperature at the second time.
  • the data acquisition unit 73 acquires factor data X1 to X9.
  • the inference unit 74 outputs the prediction data Z using the trained model stored in the trained model storage device 75 and the factor data X1 to X9 acquired by the data acquisition unit 73.
  • the factor data X1 to X9 are data input to the input unit of the model.
  • the prediction data Z is data output from the output unit of the model. That is, by inputting the factor data X1 to X9 acquired by the data acquisition unit 73 into this trained model, it is possible to output the data Z indicating the presence or absence of the set temperature return operation inferred from the factor data X1 to X9. can.
  • the factor data X1 to X9 are the same as those shown in FIG. 49.
  • the inference data generation unit 77 generates the set temperature change operation data when the set temperature change operation is performed.
  • the inference data generation unit 77 represents the state of the room at the time of predicting whether or not the set temperature return operation is performed (prediction time point) and the state of the person who has performed the set temperature change operation. To generate.
  • FIG. 57 is a diagram showing the set temperature change operation data DV of the fifth embodiment. This data is created when "Mr. A” executes the operation of changing the set temperature at "8:50". The temperature at “8:50” is “23 ° C”. “Mr. A” at “8:50” is “in the room” in the room where the air conditioner is installed. The change in the set temperature is from “27 ° C” to "26 ° C”.
  • FIG. 58 is a diagram showing the state data DK at the time of prediction according to the fifth embodiment.
  • “Mr. A” is the target person who executed the operation to change the set temperature
  • the prediction time is “9:00”
  • the temperature at the prediction time is "25 ° C”
  • “A” at the prediction time is “San” indicates that he is “absent” in the room where the air conditioner is installed.
  • FIG. 59 is a diagram showing an example of factor data X1 to X9 input to the inference device 1 of the fifth embodiment.
  • the factor data X1 to X9 in FIG. 59 are created from the set temperature change operation data DV in FIG. 57 and the state data DK at the time of prediction in FIG. That is, X1 to X6 are created from the set temperature change operation data DV. X7 to X9 are created from the time (9:00) of the state data DK at the time of prediction, the temperature (25 ° C.), and the presence / absence (absence) of "Mr. A" at "9:00".
  • the data acquisition unit 73 acquires the factor data X1 to X9 shown in FIG. 59.
  • the inference unit 74 obtains data Z indicating the presence or absence of the set temperature return operation.
  • the learning device 7 and the inference device 1 are provided inside the air conditioning system 10, but are not limited thereto.
  • the learning device 7 and the inference device 1 may be provided outside the air conditioning system 10 and may be connected to the air conditioning system 10 through the communication device 8 of the air conditioning system 10.
  • the learning device 7 and the inference device 1 may exist on the cloud server.
  • the inference device of the same air conditioning system A uses the trained model generated in the learning device of a certain air conditioning system A, but the present invention is not limited to this.
  • the trained model generated in the learning device of the air conditioning system A may be used by another inference device of the air conditioning system B.
  • the learning device may use learning data created in a plurality of air conditioning systems.
  • the learning device may acquire learning data from a plurality of air conditioning systems used in the same area, or acquire learning data collected from a plurality of air conditioning systems operating independently in different areas. You may.
  • model generation unit As the learning algorithm used in the model generation unit, deep learning that learns the extraction of the feature quantity itself can also be used, and other known methods such as genetic programming, functional logic programming, support vector machine, etc. can be used. Machine learning may be performed according to the above.
  • the corresponding operation can be configured by the hardware or software of the digital circuit.
  • the functions of the inference device 1, the learning device 7, and the control device 6 are realized by using software, the inference device 1, the learning device 7, and the control device 6 are, for example, as shown in FIG. 60, the bus 5003.
  • the processor 5002 and the memory 5001 connected by the above are provided, and the program stored in the memory 5001 can be executed by the processor 5002.
  • the inference device uses the trained model to input data indicating whether or not there is a set temperature return operation or a desired set temperature from the input data acquired by the data acquisition unit.
  • the inference device uses the trained model to input data indicating whether or not there is a set temperature return operation or a desired set temperature from the input data acquired by the data acquisition unit.
  • it is not limited to this.
  • the inference device may output data indicating whether or not there is a set temperature return operation or a desired set temperature from the input data acquired by the data acquisition unit based on rule-based inference or case-based inference. ..
  • the room temperature sensor 3 may be a temperature / humidity sensor. In this case, humidity data may be input in addition to temperature as input X.
  • 1 Inference device 2 Air balancer, 3 Room temperature sensor, 4 Body surface temperature sensor, 5 Biometric sensor, 6 Control device, 7 Learning device, 8 Communication device, 9 Input device, 10 Air harmonization system, 71,73 Data acquisition Unit, 72 model generation unit, 74 inference unit, 75 trained model storage device, 76 learning data generation unit, 77 inference data generation unit, 5001 memory, 5002 processor, 5003 bus.

Landscapes

  • Engineering & Computer Science (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • Fuzzy Systems (AREA)
  • Mathematical Physics (AREA)
  • Chemical & Material Sciences (AREA)
  • Combustion & Propulsion (AREA)
  • Mechanical Engineering (AREA)
  • General Engineering & Computer Science (AREA)
  • Air Conditioning Control Device (AREA)

Abstract

La présente invention concerne un système de climatisation comprenant : un climatiseur (2) ; un dispositif d'inférence (1) qui, sur la base de la température de surface corporelle à un premier instant d'un utilisateur qui a mis en œuvre une opération pour faire passer la température de consigne du climatiseur (2) d'une première température à une seconde température au premier instant et la température de surface corporelle de l'utilisateur à un second instant suivant le premier instant, infère si oui ou non l'utilisateur met en œuvre une opération pour ramener la température de consigne de la seconde température à la première température au second instant ; et un dispositif de commande (6) qui commande le climatiseur (2) sur la base du résultat de l'inférence effectuée par le dispositif d'inférence (1).
PCT/JP2020/019342 2020-05-14 2020-05-14 Système de climatisation et dispositif d'apprentissage Ceased WO2021229769A1 (fr)

Priority Applications (3)

Application Number Priority Date Filing Date Title
PCT/JP2020/019342 WO2021229769A1 (fr) 2020-05-14 2020-05-14 Système de climatisation et dispositif d'apprentissage
JP2022522450A JP7430784B2 (ja) 2020-05-14 2020-05-14 空気調和システムおよび学習装置
JP2023190939A JP7570488B2 (ja) 2020-05-14 2023-11-08 学習装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/JP2020/019342 WO2021229769A1 (fr) 2020-05-14 2020-05-14 Système de climatisation et dispositif d'apprentissage

Publications (1)

Publication Number Publication Date
WO2021229769A1 true WO2021229769A1 (fr) 2021-11-18

Family

ID=78525555

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2020/019342 Ceased WO2021229769A1 (fr) 2020-05-14 2020-05-14 Système de climatisation et dispositif d'apprentissage

Country Status (2)

Country Link
JP (2) JP7430784B2 (fr)
WO (1) WO2021229769A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2021229769A1 (fr) * 2020-05-14 2021-11-18 三菱電機株式会社 Système de climatisation et dispositif d'apprentissage

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06159763A (ja) * 1992-11-27 1994-06-07 Matsushita Electric Ind Co Ltd 空気調和機用制御装置
JP2003042508A (ja) * 2001-07-25 2003-02-13 Fujita Corp 空調制御方法および空調システム
JP2018091544A (ja) * 2016-12-02 2018-06-14 日立ジョンソンコントロールズ空調株式会社 空気調和機および空調制御方法
US20190271483A1 (en) * 2018-03-05 2019-09-05 Samsung Electronics Co., Ltd. Air conditioner and method for control thereof

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160320081A1 (en) * 2015-04-28 2016-11-03 Mitsubishi Electric Research Laboratories, Inc. Method and System for Personalization of Heating, Ventilation, and Air Conditioning Services
WO2021229769A1 (fr) 2020-05-14 2021-11-18 三菱電機株式会社 Système de climatisation et dispositif d'apprentissage

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH06159763A (ja) * 1992-11-27 1994-06-07 Matsushita Electric Ind Co Ltd 空気調和機用制御装置
JP2003042508A (ja) * 2001-07-25 2003-02-13 Fujita Corp 空調制御方法および空調システム
JP2018091544A (ja) * 2016-12-02 2018-06-14 日立ジョンソンコントロールズ空調株式会社 空気調和機および空調制御方法
US20190271483A1 (en) * 2018-03-05 2019-09-05 Samsung Electronics Co., Ltd. Air conditioner and method for control thereof

Also Published As

Publication number Publication date
JP7570488B2 (ja) 2024-10-21
JPWO2021229769A1 (fr) 2021-11-18
JP2024010203A (ja) 2024-01-23
JP7430784B2 (ja) 2024-02-13

Similar Documents

Publication Publication Date Title
KR102149818B1 (ko) 인테리어 자동 견적 서비스 제공 방법 및 이를 실행하기 위한 시스템
Zhang et al. Discrete-time nonzero-sum games for multiplayer using policy-iteration-based adaptive dynamic programming algorithms
US20190388296A1 (en) Massage chair and method for operating the massage chair
Hwang et al. Fuzzy model based adaptive synchronization of uncertain chaotic systems: robust tracking control approach
JP7570488B2 (ja) 学習装置
EP3620319A1 (fr) Procédé de fonctionnement d'un assistant virtuel d'un véhicule automobile et système principal correspondant
US20240330426A1 (en) Information processing apparatus, information processing method, and storage medium
Acampora et al. Interoperable neuro-fuzzy services for emotion-aware ambient intelligence
CN113251610A (zh) 用于空调控制的方法、装置和空调
CN106471444A (zh) 一种虚拟3d机器人的交互方法、系统及机器人
JP2522102B2 (ja) 空気調和装置の運転制御装置
Zhu et al. A hybrid intelligent control based cyber-physical system for thermal comfort in smart homes
CN106462804A (zh) 一种机器人交互内容的生成方法、系统及机器人
JP6637323B2 (ja) 設備管理装置及びプログラム
CN111932001B (zh) 一种基于多目标优化的应急医疗资源分配方法
Colley et al. Intelligent inhabited environments: Cooperative robotics & buildings
JP6978860B2 (ja) 体操支援方法、体操支援システム、及び体操支援プログラム
JP2021033662A (ja) 環境構築サポートシステムおよびサーバー
WO2025022585A1 (fr) Dispositif de gestion d'informations d'environnement, système de gestion d'informations d'environnement, procédé de gestion d'informations d'environnement et programme
WO2021181566A1 (fr) Système de climatisation et dispositif d'apprentissage
CN118369544A (zh) 设备控制装置和设备控制方法
Cheng et al. Extension of a High-Resolution Intelligence Implementation via Design-to-Robotic-Production and-Operation strategies
Lin et al. ANFIS-based indoor location awareness system for the position monitoring of patients
JP2664783B2 (ja) エレベータの群管理制御装置
JPH0391646A (ja) 情報処理装置とその情報処理装置を用いた空気調整装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20935654

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2022522450

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20935654

Country of ref document: EP

Kind code of ref document: A1