JP2019138542A - Air condition control device, air conditioning control system, air conditioning method, and program - Google Patents

Abstract

To generate a control model of high accuracy for air condition control with computation resources of a limited air conditioning control device.SOLUTION: An air conditioning communication unit 110 receives operation data from an air conditioner 300. An operation data storage unit included in a learning data management unit 140 stores the operation data received by the air conditioning communication unit 110. A server communication unit 130 transmits the operation data received by the air conditioning communication unit 110 to a server 200, and receives selection information being information showing a learning data group selected from the operation data group stored in an operation data storage unit from the server 200. A model generation unit 150 generates a control model by machine learning using the learning data group shown by the selection information in the case that the server communication unit 130 receives the selection information. An air conditioning control unit 160 controls the air conditioner 300 with control contents based on the control model through the air conditioning communication unit 110.SELECTED DRAWING: Figure 2

Description

  The present invention relates to an air conditioning control device, an air conditioning control system, an air conditioning control method, and a program.

  Currently, a technique for realizing air conditioning control using a control model generated by machine learning using operation data as learning data is known. Here, in order to generate a high-accuracy control model, it is necessary to learn an enormous amount of operation data as learning data, which requires a large amount of calculation resources. On the other hand, an air conditioning control device that performs air conditioning control does not include a high-performance processor and a large-capacity memory, and may not include sufficient computing resources.

  Therefore, a technique that can generate a highly accurate control model even when the air conditioning control device does not have sufficient computing resources has been proposed. For example, Patent Literature 1 describes a technology in which a server installed outside a vehicle generates a highly accurate control model, and an in-vehicle system uses the control model received from the server for air conditioning control.

JP 2008-1000066 A

  However, in the configuration in which the air conditioning control device does not generate the control model as in the technique described in Patent Document 1, for example, when communication between the server and the air conditioning control device is interrupted, there is a disadvantage that the control model cannot be updated. . For this reason, a technique for generating a highly accurate control model for air-conditioning control with a limited calculation resource of the air-conditioning control apparatus is desired.

  The present invention has been made in view of the above problems, and provides an air conditioning control device, an air conditioning control system, an air conditioning control method, and a program for generating a highly accurate control model for air conditioning control with limited calculation resources. The purpose is to provide.

In order to achieve the above object, an air conditioning control device according to the present invention includes:
An air conditioning communication means for receiving operation data from the air conditioner;
Operation data storage means for storing and storing the operation data received by the air conditioning communication means;
The operation data received by the air-conditioning communication means is transmitted to the server, and selection information which is information indicating a learning data group selected from the operation data group stored in the operation data storage means is received from the server. Server communication means;
When the selection information is received by the server communication means, model generation means for generating a control model by machine learning using the learning data group indicated by the selection information;
Air-conditioning control means for controlling the air-conditioner via the air-conditioning communication means with control contents based on the control model.

  In the present invention, a control model is generated by machine learning using a learning data group selected from the accumulated operation data group. That is, according to the present invention, the air conditioning control device can generate a highly accurate control model for air conditioning control with limited computing resources.

Configuration diagram of an air conditioning control system according to Embodiment 1 Functional block diagram of the air conditioning control system according to the first embodiment Functional block diagram of a learning data management unit according to the first embodiment The figure which shows the structure of the driving | operation data memorize | stored in the driving | operation data storage part which concerns on Embodiment 1. FIG. The figure which shows the screen which presents update alert information The flowchart which shows the air-conditioning control process which the air-conditioning control apparatus which concerns on Embodiment 1 performs. The flowchart which shows the learning data selection process which the server which concerns on Embodiment 1 performs Functional block diagram of the learning data management unit according to the second embodiment The figure which shows the structure of the driving | operation data memorize | stored in the driving | operation data storage part which concerns on Embodiment 2. FIG. The figure which shows the screen which presents various information information The flowchart which shows the air-conditioning control process which the air-conditioning control apparatus which concerns on Embodiment 2 performs. The flowchart which shows the display process which the air-conditioning control apparatus which concerns on Embodiment 2 performs.

(Embodiment 1)
First, an air conditioning control system 1000 according to an embodiment of the present invention will be described with reference to FIG. The air conditioning control system 1000 is a system that generates a control model by machine learning using operation data acquired from the air conditioner 300 as learning data, and controls the air conditioner 300 using the generated control model. In the present embodiment, generating a control model includes not only generating a new control model but also updating an existing control model.

  As shown in FIG. 1, the air conditioning control system 1000 includes an air conditioning control device 100 and a server 200. The air conditioning control device 100 and at least one air conditioner 300 are connected to each other via the air conditioning network 500. The air conditioning control device 100 and the server 200 are connected to each other via a wide area network 600.

  In this embodiment, a neural network is used as the control model. The neural network includes an input layer, an intermediate layer, and an output layer. The learning data includes learning target data and data other than the learning target. Data other than the learning target included in the learning data is input to the input layer as an input value. It is assumed that the number of units in the intermediate layer is determined in advance. From the output layer, an output value as learning target data included in the learning data is output. For example, machine learning is performed using a learning data set including a plurality of learning data (hereinafter referred to as “learning data group”) according to the following procedure A1 to procedure A6.

  Procedure A1: One learning data is selected from the learning data group. Procedure A2: Data other than the learning target included in the selected learning data is input to the neural network. Procedure A3: The output value of the neural network is calculated. Procedure A4: Learning is performed by the back propagation method using the learning target data included in the selected learning data as a teacher signal. Procedure A5: Procedure A1 to procedure A4 are repeated until all learning data is selected from the learning data group. Procedure A6: The average value of all the learning data of the error between the output value in the procedure A3 and the learning target data included in the learning data is equal to or less than a predetermined threshold value, or the threshold value in which the number of repetitions in the procedure A5 is predetermined Step A5 is repeated until

  The operation data includes data to be controlled and data other than the control target. The data to be controlled included in the operation data corresponds to the data to be learned included in the learning data. Data other than the control target included in the operation data corresponds to data other than the learning target included in the learning data. When obtaining the data to be controlled using the control model, the output value as the data to be controlled can be obtained from the neural network by supplying data other than the control target to the neural network constituting the control model. In the present embodiment, the data to be learned that is the data to be controlled is the set temperature of the air conditioner 300, and the data other than the data to be learned that is data other than the control target is the suction temperature of the air conditioner 300 and the air conditioner 300. And various data including the liquid tube temperature.

  Here, in order to generate a high-accuracy control model, it is necessary to learn an enormous amount of operation data as learning data, which requires a large amount of calculation resources. On the other hand, it may not be desirable to provide a high-performance processor and a large-capacity memory in the air-conditioning control apparatus 100 in order to give the air-conditioning control apparatus 100 a great amount of computing resources. Therefore, in the present embodiment, the air conditioning control device 100 does not learn all of the enormous amount of operation data as learning data, but uses a relatively small amount of operation data selected from the enormous amount of operation data as learning data. To learn as.

  In this embodiment, this enormous amount of operation data is operation data acquired from the air conditioner 300 during the latest predetermined period. The latest predetermined period is, for example, the latest one month. The number of the enormous amount of operation data is, for example, several hundred to several tens of thousands. On the other hand, the number of operation data selected as learning data is, for example, several tens to several hundreds.

  The operation data selected as the learning data is preferably representative operation data out of an enormous amount of operation data so that a highly accurate control model can be generated. On the other hand, a process for selecting optimum operation data requires a large amount of calculation resources. Therefore, in the present embodiment, the server 200 provided with a high-performance processor and a large-capacity memory executes a process of selecting optimal operation data.

  The air conditioning control device 100 generates a control model using a relatively small number of operation data selected from a huge amount of operation data as learning data, and controls the air conditioner 300 using the control model. The air conditioning control device 100 includes, for example, a processor 11, a flash memory 12, a user interface 13, a first communication interface 14, and a second communication interface 15.

  The processor 11 controls the overall operation of the air conditioning control device 100. The processor 11 is, for example, a CPU (Central Processing Unit) incorporating a ROM (Read Only Memory), a RAM (Random Access Memory), an RTC (Real Time Clock), and the like. The CPU operates according to a basic program stored in the ROM, for example, and uses the RAM as a work area. The flash memory 12 is a non-volatile memory that stores various types of information. For example, the flash memory 12 stores an application program executed by the processor 11 and operation data acquired from the air conditioner 300.

  The user interface 13 is a user interface of the air conditioning control device 100. That is, the user interface 13 detects an operation performed by the user and supplies a signal indicating the detection result to the processor 11. The user interface 13 presents information to the user according to control by the processor 11. The user interface 13 is a touch screen, for example. The first communication interface 14 is an interface for connecting the air conditioning control device 100 to the air conditioning network 500. The second communication interface 15 is an interface for connecting the air conditioning control device 100 to the wide area network 600. The second communication interface 15 includes, for example, a LAN (Local Area Network) interface such as a NIC (Network Interface Card).

  The server 200 is a server that selects a relatively small number of operation data as learning data from a huge amount of operation data. The server 200 selects learning data by generating and evaluating a control model, for example. The server 200 includes, for example, a processor 21, a hard disk 22, and a communication interface 23.

  The processor 21 controls the overall operation of the server 200. The processor 21 is, for example, a CPU incorporating a ROM, RAM, RTC, and the like. The hard disk 22 is a non-volatile storage device that stores various types of information. The hard disk 22 stores, for example, an application program executed by the processor 21 and a huge amount of operation data. The communication interface 23 is an interface for connecting the server 200 to the wide area network 600. The communication interface 23 includes a LAN interface such as a NIC, for example.

  The air conditioner 300 performs air conditioning of a predetermined space in accordance with control by the air conditioning control device 100. The number of air conditioners 300 controlled by the air conditioning control device 100 may be any number. In the present embodiment, description will be given focusing on one air conditioner 300. The air conditioner 300 is, for example, an outdoor unit or an indoor unit. The air conditioner 300 includes, for example, a processor 31, a device load 32, a communication interface 33, and a user interface 34.

  The processor 31 controls the overall operation of the air conditioner 300. The processor 31 is, for example, a CPU incorporating a ROM, RAM, RTC, and the like. The equipment load 32 is a load provided in the air conditioner 300. The equipment load 32 is, for example, a refrigerant circuit, a louver, or a fan. The communication interface 33 is an interface for connecting the air conditioner 300 to the air conditioning network 500. The user interface 34 is a user interface of the air conditioner 300. That is, the user interface 34 detects an operation performed by the user or presents information to the user. The user interface 34 is, for example, a touch screen or a remote controller.

  The air conditioning network 500 is a network that connects the air conditioning control device 100 and at least one air conditioner 300 to each other. The air conditioning network 500 includes, for example, a cable including a pair of communication lines. The wide area network 600 is a network for connecting the air conditioning control device 100 and the server 200. The wide area network 600 is, for example, the Internet.

  Next, functions of the air conditioning control system 1000 will be described with reference to FIG. As shown in FIG. 2, the air conditioning control device 100 functionally includes an air conditioning communication unit 110, an operation data transfer unit 120, a server communication unit 130, a learning data management unit 140, a model generation unit 150, An air conditioning control unit 160 and a display unit 170 are provided. The air conditioning communication unit corresponds to, for example, the air conditioning communication unit 110. The server communication unit corresponds to the server communication unit 130, for example. The model generation unit corresponds to the model generation unit 150, for example. The air conditioning control means corresponds to the air conditioning control unit 160, for example. The update display unit corresponds to the display unit 170, for example.

  The air conditioning communication unit 110 communicates with the air conditioner 300 via the air conditioning network 500. The air conditioning communication unit 110 receives operation data from the air conditioner 300. In addition, the air conditioning communication unit 110 transmits the control signal supplied from the air conditioning control unit 160 to the air conditioner 300. The function of the air conditioning communication unit 110 is realized by the function of the first communication interface 14, for example. The operation data transfer unit 120 transfers operation data collected from the air conditioner 300 via the air conditioning communication unit 110 to the server 200 via the server communication unit 130. The function of the operation data transfer unit 120 is realized by the function of the processor 11, for example.

  The server communication unit 130 communicates with the server 200 via the wide area network 600. The server communication unit 130 transmits the operation data received by the air conditioning communication unit 110 to the server 200. Further, the server communication unit 130 receives selection information from the server 200. The selection information is information indicating a learning data group selected from the driving data group stored in the driving data storage unit 142. The function of the server communication unit 130 is realized by the function of the second communication interface 15, for example.

  The learning data management unit 140 accumulates the operation data collected by the operation data transfer unit 120 and manages the operation data based on selection information obtained through the server communication unit 130. The function of the learning data management unit 140 is realized by the cooperation of the processor 11 and the flash memory 12, for example.

  Next, the function of the learning data management unit 140 will be described in detail with reference to FIG. The learning data management unit 140 includes an operation data adding unit 141, an operation data storage unit 142, an identifier adding unit 143, and a learning data output unit 144. The operation data adding means corresponds to the operation data adding unit 141, for example. The operation data storage means corresponds to, for example, the operation data storage unit 142. The identifier assigning means corresponds to the identifier assigning unit 143, for example.

  The operation data adding unit 141 receives newly collected operation data from the operation data transfer unit 120 and stores it in the operation data storage unit 142 as new data. The new data is a candidate for learning data. The function of the operation data adding unit 141 is realized by the function of the processor 11, for example. The driving data storage unit 142 stores driving data that is a candidate for learning data. That is, the operation data storage unit 142 stores and accumulates the operation data received by the air conditioning communication unit 110. The operation data stored as new data in the operation data storage unit 142 is treated as learning data, preliminary data, or invalid data by the identifier assignment by the identifier assignment unit 143.

  The learning data is operation data used for generating the control model. The preliminary data is operation data that is not immediately used for generating the control model, but may be used for generating the control model in the future. Invalid data is data that is not used to generate a control model. The invalid data is operation data that is rewritten with new data, and can be said to be operation data that is no longer stored in the operation data storage unit 142. The function of the operation data storage unit 142 is realized by the function of the flash memory 12, for example.

  The identifier assigning unit 143 updates the selection state of the operation data group stored in the operation data storage unit 142 based on the selection information received from the server 200 via the server communication unit 130. That is, when the selection information is received by the server communication unit 130, the identifier assigning unit 143 assigns an identifier indicated by the selection information to each of the operation data included in the operation data group stored in the operation data storage unit 142. To do. The selection information is, for example, one of a first identifier, a second identifier, and a third identifier that is given to each of the operation data included in the operation data group stored in the operation data storage unit 142. This is information indicating the identifier. The function of the identifier assigning unit 143 is realized by the function of the processor 11, for example.

  A 1st identifier is an identifier which shows that driving | operation data is effective as learning data, for example. The operation data to which the first identifier is assigned is treated as learning data with the selection state set to valid. That is, the learning data group includes operation data to which the first identifier is assigned among the operation data included in the operation data group stored in the operation data storage unit 142. A 2nd identifier is an identifier which shows that driving | operation data is invalid as learning data, for example. The operation data to which the second identifier is assigned is set to invalid in the selection state and is treated as invalid data.

  In other words, when the operation data is received by the air conditioning communication unit 110, the operation data adding unit 141 uses the operation data received by the air conditioning communication unit 110 in the operation data group stored in the operation data storage unit 142. The operation data storage unit 142 stores the data instead of the operation data to which the second identifier is assigned. The third identifier is, for example, an identifier indicating that the operation data is a reserve of learning data. The operation data to which the third identifier is assigned is treated as spare data with the selection state set to spare.

  The operation data group stored in the operation data storage unit 142 will be described with reference to FIG. The operation data storage unit 142 stores an operation data group with one operation data as one record. One record constituting the operation data includes a data ID, a selection state, and a plurality of data strings. The data string includes at least data 1 and data 2. It is assumed that the upper limit value of the number of records that can be stored in the operation data storage unit 142 is predetermined. The upper limit is, for example, several tens to several hundreds.

  The data ID is an ID for identifying operation data. For example, the air conditioning control device 100 gives a data ID to the operation data when transmitting the operation data to the server 200. In addition, selection information is information which shows data ID and the said identifier about each of the driving | operation data group memorize | stored in the driving | operation data storage part 142, for example. The selection state is a selection state as learning data of operation data. The selection state is, for example, valid, invalid, spare, new, or none. When the number of operation data groups stored in the operation data storage unit 142 is less than the upper limit, none is set as the selection state of operation data corresponding to the empty record, that is, operation data not yet stored. . However, when operating data and invalid data that are not yet stored are handled in the same manner, invalidity and none can be integrated.

  Data 1 is the suction temperature, and is data other than the control target. Data 2 is a set temperature and is data to be controlled. That is, in this embodiment, the control model obtains the set temperature from data including at least the suction temperature.

  The learning data output unit 144 selects a learning data group to be used for generating a control model based on each selection state of the driving data group stored in the driving data storage unit 142. Specifically, the learning data output unit 144 selects, as learning data, driving data to which the first identifier is assigned among driving data included in the driving data group stored in the driving data storage unit 142. Then, the learning data output unit 144 supplies the selected learning data group to the model generation unit 150. The function of the learning data output unit 144 is realized by the function of the processor 11, for example.

  When the selection information is received by the server communication unit 130, the model generation unit 150 receives a learning data group from the learning data management unit 140. The model generation unit 150 generates a control model by machine learning using the received learning data group. The function of the model generation unit 150 is realized by the cooperation of the processor 11 and the flash memory 12, for example.

  The air conditioning control unit 160 controls the air conditioner 300 via the air conditioning communication unit 110 with the control content based on the control model generated by the model generation unit 150. The air conditioning control unit 160 supplies data other than the control target included in the latest operation data to the control model, and acquires an output value corresponding to the control target data from the control model. The air conditioning control unit 160 transmits a control signal corresponding to the output value to the air conditioner 300 via the air conditioning communication unit 110. The function of the air conditioning control unit 160 is realized by the function of the processor 11, for example.

  The display unit 170 displays the state of the air conditioning control device 100 and the state of the air conditioner 300. For example, when a control model is generated by the model generation unit 150, the display unit 170 displays update notification information that is information for notifying that the control model has been updated. The function of the display unit 170 is realized by the cooperation of the processor 11 and the user interface 13, for example.

  FIG. 5 shows a screen 400 displayed by the display unit 170. The screen 400 includes a first area specified by the frame 410 and a second area specified by the frame 420. In the first area, for example, an image indicating the operation state of the air conditioner 300 is displayed. The operation state is, for example, an operation mode. In the second region, for example, an image for notifying that new operation data is valid as learning data and the control model is updated is displayed. The image displayed in the second area corresponds to the update notification information described above.

  Functionally, the server 200 includes a communication unit 210, an operation data storage unit 220, and a learning data selection unit 230. The communication unit corresponds to the communication unit 210, for example. The operation data storage unit corresponds to, for example, the operation data storage unit 220. The learning data selection unit corresponds to the learning data selection unit 230, for example.

  The communication unit 210 communicates with the air conditioning control device 100 via the wide area network 600. The communication unit 210 receives the operation data transmitted by the server communication unit 130. In addition, the communication unit 210 transmits selection information, which is information indicating the learning data group selected by the learning data selection unit 230, to the air conditioning control device 100. The function of the communication unit 210 is realized by the cooperation of the processor 21 and the communication interface 23, for example.

  The operation data accumulation unit 220 stores and accumulates operation data received by the communication unit 210. The operation data group stored in the operation data storage unit 220 includes the operation data group stored in the operation data storage unit 142 and is larger than the operation data group stored in the operation data storage unit 142. The operation data included in the operation data group stored in the operation data storage unit 220 includes a selected state. The function of the operation data storage unit 220 is realized by the function of the hard disk 22, for example.

  When the operation data is received by the communication unit 210, the learning data selection unit 230 learns from the operation data group stored in the operation data storage unit 142 based on the operation data group stored in the operation data storage unit 220. Select a data group. The learning data selection unit 230 updates the selection state included in the operation data according to the selection result. The function of the learning data selection unit 230 is realized by the cooperation of the processor 21 and the hard disk 22, for example.

  Here, as described above, the communication unit 210 transmits selection information, which is information indicating the learning data group selected by the learning data selection unit 230, to the air conditioning control device 100. This selection information indicates any one of the first identifier and the third identifier as an identifier given to the operation data to which the first identifier is given. The selection information is information indicating any one of the first identifier and the second identifier as an identifier given to the operation data to which the third identifier is given. In other words, the operation data that has been selected as the learning data most recently is not set as invalid data immediately but is set as preliminary data when not selected as learning data. On the other hand, if the operation data that has not been selected as learning data most recently is not selected as learning data, it is not set as preliminary data but is immediately set as invalid data.

  Note that the new data may be handled as operation data that has been selected as learning data, or may be handled as operation data that has not been selected as learning data. That is, when the new data is not selected as the learning data, the third identifier may be given and treated as preliminary data, or the second identifier may be given and treated as invalid data. Further, the selection information may be information indicating the selection state for all the operation data stored in the operation data storage unit 142, or the selection state is changed among the operation data stored in the operation data storage unit 142. It may be information indicating a selection state for the operation data. The selection information is information including one or more combinations of data IDs and selection states, for example.

  The air conditioner 300 functionally includes a communication unit 310, a device control unit 320, a controlled unit 330, and an operation reception unit 340. The communication unit 310 communicates with the air conditioning control device 100 via the air conditioning network 500. For example, the communication unit 310 transmits operation data to the air conditioning control device 100. In addition, the communication unit 310 receives a control signal from the air conditioning control device 100. The function of the communication unit 310 is realized by the cooperation of the processor 31 and the communication interface 33, for example.

  The device control unit 320 controls the controlled unit 330 according to the control signal received from the communication unit 310. The function of the device control unit 320 is realized by the function of the processor 31, for example. The controlled unit 330 operates in accordance with a control signal supplied from the device control unit 320. The function of the controlled unit 330 is realized by the function of the device load 32, for example. The operation reception unit 340 receives an operation on the air conditioner from the user. The function of the operation reception part 340 is implement | achieved by the function of the user interface 34, for example.

  Next, the air conditioning control process executed by the air conditioning control device 100 will be described with reference to the flowchart shown in FIG. The air conditioning control process is started when the power of the air conditioning control device 100 is turned on. In addition, the control model which the air-conditioning control apparatus 100 learns is a control model for inputting the operation data of the air conditioner 300 and automatically controlling the set temperature. In addition, it is assumed that the operation data when the set temperature is changed by the user manually operating the air conditioner 300 is set as a candidate for learning data.

  First, the air conditioning communication unit 110 collects operation data from the air conditioner 300 (step S101). Specifically, the air conditioning communication unit 110 transmits a data request command to the air conditioner 300 and receives a response command from the air conditioner 300. And the air-conditioning communication part 110 acquires the operation data contained in a response command. When the air conditioning communication unit 110 completes the process of step S101, the learning data management unit 140 determines whether or not there is a user operation (step S102). That is, the learning data management unit 140 determines whether or not the set temperature when the control is performed immediately before in step S111 matches the set temperature included in the collected operation data. If these set temperatures do not match, it is determined that there has been a user operation, that is, a manual operation by the user.

  If learning data management part 140 discriminates that there was user operation (Step S102: YES), it will store driving data as new data (Step S103). That is, the operation data adding unit 141 stores the newly acquired operation data in place of the operation data stored in the operation data storage unit 142 with the selected state set to invalid or none. This operation data is given a new selection state.

  When the learning data management unit 140 completes the process of step S103, the operation data transfer unit 120 assigns a data ID to the operation data stored as new data and transmits it to the server 200 (step S104). After the operation data transfer unit 120 completes the process of step S104, the server communication unit 130 receives selection information from the server 200 (step S105). When the server communication unit 130 completes the process of step S105, the learning data management unit 140 updates the identifier given to the driving data based on the selection information (step S106).

  When the learning data management unit 140 completes the process of step S106, the model generation unit 150 generates a control model (step S107). That is, the model generation unit 150 performs learning of the control model using the learning data group that the learning data output unit 144 collects and outputs the operation data whose selection state is valid. Specifically, the model generation unit 150 generates or updates a control model in accordance with the procedure A1 to procedure A6.

  When the model generation unit 150 completes the process of step S107, the display unit 170 displays the update notification information (step S108). For example, as shown in FIG. 5, the display unit 170 displays a screen 400 that notifies that the control model has been updated. When it is determined that there is no user operation (step S102: NO), or when the display unit 170 completes the process of step S108, the air conditioning control unit 160 determines whether the elapsed time from the user operation is equal to or greater than the threshold value. Is determined (step S109). For example, the air conditioning control unit 160 determines whether the elapsed time from the user operation is 30 minutes or more.

  If it is determined that the elapsed time from the user operation is not equal to or greater than the threshold value (step S109: NO), the air conditioning control unit 160 returns the process to step S101. That is, in this case, the air conditioning control unit 160 respects the user's intention and maintains the control state based on the user operation. On the other hand, when it is determined that the elapsed time from the user operation is equal to or greater than the threshold (step S109: YES), the air conditioning control unit 160 calculates the control content from the control model (step S110). For example, the air conditioning control unit 160 determines a control value, which is a control content, according to the procedure from procedure B1 to procedure B2 described below.

  Procedure B1: Data other than the control target included in the latest operation data is input to the neural network. The data other than the control target is data other than the set temperature. Procedure B2: The output of the neural network is calculated, and the output value is set as the control value. This control value is set as the set temperature, and the control content is determined.

  After completing the process of step S110, the air conditioning controller 160 controls the air conditioner with the calculated control content (step S111). In other words, the air conditioning control unit 160 transmits a control signal indicating control with the calculated control value to the air conditioner 300. Note that when the control value of the data to be controlled included in the acquired latest operation data is the same as the calculated control value, the control signal may not be transmitted. After completing the process of step S111, the air conditioning control unit 160 returns the process to step S101.

  Next, the learning data selection process executed by the server 200 will be described with reference to FIG. The learning data selection process starts when the server 200 is powered on.

  First, the communication unit 210 determines whether or not operation data has been received from the air conditioning control device 100 (step S201). If it is determined that the operation data is not received from the air conditioning control device 100 (step S201: NO), the communication unit 210 returns the process to step S201. On the other hand, when determining that the operation data has been received from the air conditioning control device 100 (step S201: YES), the communication unit 210 stores the operation data in the operation data storage unit 220 (step S202).

  When the communication unit 210 completes the process of step S202, the learning data selection unit 230 performs the air conditioning control device based on the operation data group stored in the operation data storage unit 220 by the processes of steps S203 to S208 described below. 100 selects an operation data group to be held as a learning data group.

  First, the learning data selection unit 230 identifies combinations that are candidates for the learning data group (step S203). For example, among the operation data groups stored in the operation data storage unit 142, all learning data group candidates that can be extracted from the operation data groups whose selection states are valid, backup, or new are specified. The candidate for the learning data group is a combination of an arbitrary number of pieces of operation data equal to or less than the upper limit value of the number of pieces of operation data that can be stored in the operation data storage unit 142. For example, when the upper limit value of the number of operation data that can be stored in the operation data storage unit 142 is 100 and the number of operation data that is selected, valid, spare, or new is 80, this All combinations that can be extracted from the 80 driving data groups are specified as candidates for the learning data group. The candidate for the learning data group is a combination of 1 to 80 driving data.

  When completing the process of step S203, the learning data selection unit 230 selects one combination from all the specified combinations (step S204). When the learning data selection unit 230 completes the process of step S204, the learning data selection unit 230 generates a control model (step S205). In step S204, the learning data selection unit 230 generates a control model by the same method as the method executed by the model generation unit 150 in step S107.

  When completing the process of step S205, the learning data selection unit 230 calculates an evaluation value of the generated control model (step S206). For example, the learning data selection unit 230 calculates the evaluation value of the generated control model using all the operation data stored in the operation data storage unit 220. Specifically, the generated evaluation value is calculated according to the following procedure C1 to procedure C5.

  Procedure C1: One operation data is selected from the operation data group stored in the operation data storage unit 220. Procedure C2: Data other than the control target included in the selected operation data is input to the neural network. Procedure C3: The output value of the neural network is calculated. Procedure C4: An error between a control value that is data to be controlled included in the selected operation data and an output value is calculated. Step C5: Steps C1 to C4 are executed until all the operation data stored in the operation data storage unit 220 are selected, and the average value of errors is used as the evaluation value. The smaller the evaluation value is, the better the control model is and the more accurate the control model is.

  When completing the process of step S206, the learning data selection unit 230 determines whether or not all combinations have been selected (step S207). If the learning data selection unit 230 determines that not all combinations have been selected (step S207: NO), the process returns to step S204. On the other hand, when the learning data selection unit 230 determines that all combinations have been selected (step S207: YES), the learning data selection unit 230 specifies the combination having the smallest evaluation value (step S208).

  When the learning data selection unit 230 completes the process of step S208, the learning data selection unit 230 transmits selection information based on the identified combination to the air conditioning control device 100 (step S209). For example, the learning data selection unit 230 generates and transmits selection information indicating a data ID and an identifier corresponding to the changed selection state for operation data set in a selection state different from the existing selection state.

  For example, among the driving data included in the learning data group, the data ID of the driving data whose existing selection state is other than valid is associated with the first identifier for giving validity. In addition, among the operation data not included in the learning data group, the data ID of the operation data in which the existing selection state is valid is associated with the third identifier for assigning a reserve. In addition, among the operation data not included in the learning data group, the data ID of the operation data whose existing selection state is backup is associated with the second identifier for giving invalidity. After completing the process of step S209, the learning data selection unit 230 returns the process to step S201.

  As described above, in the present embodiment, the air conditioning control device 100 generates a control model using the learning data group selected by the server 200 rich in computing resources. For this reason, the air conditioning control device 100 can generate a highly accurate control model without providing abundant calculation resources in the air conditioning control device 100. In particular, when the control target is the air conditioner 300, the amount of operation data is large. For this reason, compared with the case where a control object is an illuminating device, for example, the necessity to narrow down learning data is high and the effect acquired is also large.

  In the present embodiment, when the control model is updated, update notification information is displayed. For this reason, the user can notice the change point of the control and can execute the operation check promptly. In particular, when the accumulation of operation data has progressed and the control content is stable, control has been switched by accurately capturing events that affect the characteristics of operation data, such as changes in personnel assignments within a building, for example. And that the control content is appropriate.

  Further, in the present embodiment, operation data that is not immediately used for learning but is likely to be used for learning in the future is retained as preliminary data. For this reason, driving data that can be used in the future can be effectively used for learning. On the other hand, operation data that is unlikely to be used for learning in the future is set as invalid data. For this reason, useless storage of storage data is suppressed, and the amount of memory used can be reduced.

(Embodiment 2)
In the second embodiment, an air conditioning control system 1000 capable of maintaining appropriate air conditioning control even when communication between the air conditioning control device 100 and the server 200 is interrupted for some reason will be described. As can be seen from a comparison between FIG. 3 and FIG. 8, the air conditioning control system 1000 according to the second embodiment and the air conditioning control system 1000 according to the second embodiment mainly process the learning data management unit 140 and the display unit 170. The process is different. Here, the storage status display unit and the recovery status display unit correspond to the display unit 170, for example.

  First, the operation data storage unit 142 stores saved data in addition to new data, preliminary data, and learning data. The saved data is operation data received by the air conditioning communication unit 110 and stored in the operation data storage unit 142 while communication between the air conditioning control device 100 and the server 200 is interrupted. That is, the operation data adding unit 141 stores the operation data acquired during the communication interruption between the air conditioning control device 100 and the server 200 as saved data. As shown in FIG. 9, the operation data set in the evacuation data is given an identifier indicating that the operation data was evacuated as a selected state.

  As shown in FIG. 10, the screen 400 displayed by the display unit 170 is designated by a frame 430 in addition to the first area designated by the frame 410 and the second area designated by the frame 420. A third region. In the third area, for example, any one of normal communication notification information, accumulation status notification information, and recovery status notification information is displayed.

  The communication normal notification information is information for notifying that the communication between the air conditioning control device 100 and the server 200 is normal. The accumulation status notification information is information for notifying how much evacuation data is accumulated while communication between the air conditioning control device 100 and the server 200 is interrupted. The recovery status notification information is information that notifies the extent to which the recovery processing related to the update of the control model is in progress when the communication interruption between the air conditioning control device 100 and the server 200 is resolved. The normal communication notification information is, for example, information displayed in an area designated by a frame 431. The accumulation status notification information is, for example, information displayed in the area specified by the frame 432. The recovery status notification information is, for example, information displayed in the area specified by the frame 433.

  The identifier assigning unit 143 assigns a fourth identifier to the operation data received by the air conditioning communication unit 110 while the communication between the server communication unit 130 and the server 200 is interrupted. The fourth identifier is an identifier indicating, for example, saved data. When the operation data is received by the air conditioning communication unit 110 while the communication between the server communication unit 130 and the server 200 is interrupted, the model generation unit 150 includes the first of the operation data included in the operation data group. A control model is generated by machine learning using a learning data group including operation data to which an identifier is assigned and operation data to which a fourth identifier is assigned. That is, the model generation unit 150 generates a control model including not only valid data but also saved data during communication interruption.

  The display unit 170 displays accumulation state notification information that is information for notifying the accumulation state while communication between the server communication unit 130 and the server 200 is interrupted. The accumulation status includes the upper limit value of the number of operation data to which the fourth identifier that can be accumulated in the operation data storage unit 142 and the operation data to which the fourth identifier accumulated in the operation data storage unit 142 is assigned. And the accumulation status based on the number of For example, the storage status is notified based on the ratio of the number of stored save data to the upper limit of the number of save data that can be stored and the estimated time until the number of stored save data reaches the upper limit. .

  Further, when communication between the server communication unit 130 and the server 200 is restored, the first process, the second process, and the third process are repeated until there is no operation data to which the fourth identifier is assigned. Executed. The first process is a process in which the server communication unit 130 transmits the operation data to which the fourth identifier is assigned in the operation data group to the server 200 and receives selection information from the server 200. The second process is a process in which the identifier assigning unit 143 assigns an identifier indicated by the selection information to each of the operation data included in the operation data group. The third process is a process in which the model generation unit 150 generates a control model by machine learning using a learning data group indicated by selection information.

  In addition, the display unit 170 is recovery status notification information that is a notification of the recovery status from when the communication between the server communication unit 130 and the server 200 is recovered until the operation data to which the fourth identifier is assigned disappears. Is displayed. The restoration status includes, for example, the number of operation data to which the fourth identifier is assigned while communication between the server communication unit 130 and the server 200 is interrupted, and the operation data to which the fourth identifier is currently assigned. And the recovery status based on the number of For example, of the operation data set as evacuation data, the ratio of operation data set as operation data other than evacuation data, or all of the operation data set as evacuation data is set as operation data other than evacuation data The predicted time until is notified as the recovery status.

  The display data output unit 145 supplies information displayed on the display unit 170 to the display unit 170. For example, if the display data output unit 145 determines that the communication normal notification information should be displayed, the display data output unit 145 supplies the communication normal notification information to the display unit 170. When the display data output unit 145 determines that the storage state notification information should be displayed, the display data output unit 145 supplies the storage state notification information to the display unit 170. When the display data output unit 145 determines that the recovery status notification information should be displayed, the display data output unit 145 supplies the recovery status notification information to the display unit 170.

  Next, the air conditioning control process executed by the air conditioning control device 100 will be described with reference to the flowchart shown in FIG. The air conditioning control process is started when the power of the air conditioning control device 100 is turned on.

  First, the air conditioning communication unit 110 collects operation data from the air conditioner 300 (step S301). When the air conditioning communication unit 110 completes the process of step S301, the learning data management unit 140 determines whether there is a user operation (step S302). When the learning data management unit 140 determines that there is a user operation (step S302: YES), the learning data management unit 140 determines whether communication with the server 200 is possible (step S303). When learning data management unit 140 determines that communication with server 200 is not possible (step S303: NO), it stores the operation data as saved data (step S304). When the learning data management unit 140 completes the process of step S304, the model generation unit 150 generates a control model including saved data (step S305). That is, the model generation unit 150 generates a control model using a driving data group including valid data and saved data as a learning data group.

  On the other hand, if the learning data management unit 140 determines that communication with the server 200 is possible (step S303: YES), the learning data management unit 140 stores the operation data as new data (step S306). When the learning data management unit 140 completes the process of step S306, the operation data transfer unit 120 assigns a data ID to the operation data stored as saved data or new data, and transmits it to the server 200 (step S307). Note that when a plurality of operation data that is saved data or new data is stored, for example, the operation data stored earliest is transmitted. After the operation data transfer unit 120 completes the process of step S307, the server communication unit 130 receives selection information from the server 200 (step S308). When the server communication unit 130 completes the process of step S308, the learning data management unit 140 updates the identifier given to the driving data based on the selection information (step S309).

  After completing the process of step S309, the learning data management unit 140 determines whether there is saved data or new data (step S310). If the learning data management unit 140 determines that there is saved data or new data (step S310: YES), it returns the process to step S307. On the other hand, when the learning data management unit 140 determines that there is no saved data or new data (step S310: NO), the model generation unit 150 generates a control model (step S311).

  When the model generation unit 150 completes the process of step S311, the air conditioning control unit 160 determines whether or not the elapsed time from the user operation is equal to or greater than a threshold (step S312). If it is determined that the elapsed time from the user operation is not equal to or greater than the threshold (step S312: NO), the air conditioning control unit 160 returns the process to step S301. On the other hand, when it is determined that the elapsed time from the user operation is equal to or greater than the threshold (step S312: YES), the air conditioning control unit 160 calculates the control content from the control model (step S313). After completing the process of step S313, the air conditioning control unit 160 controls the air conditioner with the calculated control content (step S314). When the air conditioning control unit 160 completes the process of step S314, the process returns to step S301.

  Next, display processing executed by the air conditioning control device 100 will be described with reference to the flowchart shown in FIG. The display process is executed in parallel with the air conditioning control process while the air conditioning control device 100 is powered on.

  First, the learning data management unit 140 determines whether or not it is immediately after generation of a control model (step S401). When the learning data management unit 140 determines that it is immediately after the generation of the control model (step S401: YES), the update notification information is displayed on the display unit 170 (step S402). When it is determined that the learning data management unit 140 is not immediately after generation of the control model (step S401: NO), or when the process of step S402 is completed, the learning data management unit 140 determines whether or not communication with the server 200 is possible (step). S403).

  If the learning data management unit 140 determines that communication with the server 200 is not possible (step S403: NO), the learning data management unit 140 calculates an accumulation rate of saved data (step S404). When the learning data management unit 140 completes the process of step S404, the learning data management unit 140 displays the storage state notification information on the display unit 170 (step S405). When the learning data management unit 140 completes the process of step S405, the process returns to step S401. On the other hand, when the learning data management unit 140 determines that communication with the server 200 is possible (step S403: YES), the learning data management unit 140 determines whether recovery is in progress (step S406).

  If it is determined that the learning data management unit 140 is not recovering (step S406: NO), the normal communication information is displayed on the display unit 170 (step S407). When the learning data management unit 140 completes the process of step S407, the process returns to step S401. On the other hand, when the learning data management unit 140 determines that recovery is in progress (step S406: YES), the learning data management unit 140 calculates a recovery rate of the saved data (step S408). When the learning data management unit 140 completes the process of step S408, the learning data management unit 140 displays the recovery status notification information on the display unit 170 (step S409). When the learning data management unit 140 completes the process of step S409, the process returns to step S401.

  As described above, according to the present embodiment, even when communication between the air conditioning control device 100 and the server 200 is interrupted, learning can be advanced and appropriate air conditioning control can be continued. In the present embodiment, when the communication interruption is resolved, the stored saved data is handled in the same manner as the new data and is used for selecting learning data. Therefore, after the communication interruption is resolved, it can be expected that an appropriate learning data group is selected by the server 200 and a highly accurate control model is generated by the air conditioning control device 100. Moreover, according to this embodiment, since accumulation status alert information, recovery status alert information, communication normal alert information, and the like are displayed, it is possible to inform the user of various situations.

  By displaying the accumulation status notification information, it is possible to notify the user of a guideline for a schedule in which the control model can be restored without missing data. In addition, by displaying the recovery status notification information, it is possible to notify the user of a schedule that can be shifted to normal operation. Further, by displaying the communication normal notification information, it is possible to notify the user that communication is normally performed.

(Modification)
As mentioned above, although embodiment of this invention was described, when implementing this invention, a deformation | transformation and application with a various form are possible. In the present invention, which part of the configuration, function, and operation described in the above embodiment is adopted is arbitrary. Further, in the present invention, in addition to the configuration, function, and operation described above, further configuration, function, and operation may be employed.

  In the above embodiment, the example in which the preliminary data is immediately set as invalid data when the preliminary data is not selected as the learning data has been described. In the present invention, the handling of the preliminary data is not limited to this example. For example, when it is not selected as learning data continuously for a predetermined number of times (for example, 10 times), it may be set as invalid data. In this case, it is preferable that the operation data includes, for example, the number of times of not being selected. In the above-described embodiment, an example in which preliminary data is included in the operation data has been described. In the present invention, the operation data may not include the preliminary data. In this case, for example, a learning data group is selected from an operation data group including valid data and new data.

  In the above-described embodiment, an example in which the candidate for the learning data group is a combination of any number of pieces of operation data equal to or less than the upper limit (for example, 100) of the number of pieces of operation data that can be stored in the operation data storage unit 142 has been described. . In the present invention, for example, the learning data group candidate may be a combination of a predetermined number (for example, 80) of driving data equal to or less than the upper limit value. In such a configuration, the number of learning data group candidates can be suppressed, and the calculation function required for selecting the learning data group can be suppressed.

  In the embodiment described above, the server 200 selects the learning data group based on the evaluation value of the control model created using the learning data group candidates. The server 200 may select a learning data group by clustering, for example. In this case, for example, the operation data group stored in the operation data storage unit 220 is clustered so that the ratio of the outside-class variance to the within-class variance is maximized, and the average value of each cluster is used as the representative value. Then, among the operation data groups stored in the operation data storage unit 142, the operation data group closest to these representative values is extracted from the operation data groups to which valid, reserve, or new is assigned, and the learning data group Choose as. According to such a configuration, it is possible to suppress the calculation function required for selecting the learning data group, and it is possible to employ an inexpensive server 200.

  By applying an operation program that defines the operation of the air conditioning control device 100 or the server 200 according to the present invention to an existing personal computer or information terminal device, the personal computer or the like is used as the air conditioning control device 100 or the server 200 according to the present invention. It is also possible to function. Further, such a program distribution method is arbitrary. For example, the program is stored and distributed in a computer-readable recording medium such as a CD-ROM (Compact Disk Read-Only Memory), a DVD (Digital Versatile Disk), or a memory card. Alternatively, it may be distributed via a communication network such as the Internet.

  Various embodiments and modifications can be made to the present invention without departing from the broad spirit and scope of the present invention. Further, the above-described embodiment is for explaining the present invention, and does not limit the scope of the present invention. That is, the scope of the present invention is shown not by the embodiments but by the claims. Various modifications within the scope of the claims and within the scope of the equivalent invention are considered to be within the scope of the present invention.

  The present invention is applicable to an air conditioning control system.

11, 21, 31 Processor, 12 Flash memory, 13, 34 User interface, 14 First communication interface, 15 Second communication interface, 22 Hard disk, 23, 33 Communication interface, 32 Equipment load, 100 Air conditioning control device, 110 Air conditioning communication Unit, 120 operation data transfer unit, 130 server communication unit, 140 learning data management unit, 141 operation data addition unit, 142 operation data storage unit, 143 identifier assignment unit, 144 learning data output unit, 145 display data output unit, 150 model Generation unit, 160 Air conditioning control unit, 170 Display unit, 200 Server, 210, 310 Communication unit, 220 Operation data storage unit, 230 Learning data selection unit, 300 Air conditioner, 320 Device control unit, 330 Controlled unit, 340 Appendix, 400 screen, 410, 420, 430, 431, 432, 433 frame, 500 air conditioning network, 600 wide area network, 1000 air conditioning control system

Claims (11)

An air conditioning communication means for receiving operation data from the air conditioner;
Operation data storage means for storing and storing the operation data received by the air conditioning communication means;
The operation data received by the air-conditioning communication means is transmitted to the server, and selection information which is information indicating a learning data group selected from the operation data group stored in the operation data storage means is received from the server. Server communication means;
When the selection information is received by the server communication means, model generation means for generating a control model by machine learning using the learning data group indicated by the selection information;
Air conditioning control means for controlling the air conditioner via the air conditioning communication means with control content based on the control model,
Air conditioning control device. The selection information is information indicating one of the first identifier and the second identifier, which is given to each of the operation data included in the operation data group,
When the selection information is received by the server communication means, further comprising identifier giving means for giving an identifier indicated by the selection information to each of the operation data included in the operation data group,
The learning data group is composed of driving data to which the first identifier is assigned among driving data included in the driving data group,
When the operation data is received by the air-conditioning communication means, the operation data received by the air-conditioning communication means is changed to operation data to which the second identifier is assigned among the operation data included in the operation data group. Instead, it further comprises operation data adding means for storing in the operation data storage means.
The air conditioning control device according to claim 1. The selection information is information indicating any one of the first identifier, the second identifier, and the third identifier, which is given to each of the operation data included in the operation data group. ,
The selection information indicates any one of the first identifier and the third identifier as an identifier given to the operation data to which the first identifier is given, and the third identifier As an identifier given to the operation data to which an identifier is given, it is information indicating any one of the first identifier and the second identifier.
The air conditioning control device according to claim 2. The identifier assigning means assigns a fourth identifier to the operation data received by the air conditioning communication means while communication between the server communication means and the server is interrupted,
When the operation data is received by the air conditioning communication unit while communication between the server communication unit and the server is interrupted, the model generation unit includes the operation data included in the operation data group. Generating the control model by machine learning using a learning data group including the operation data to which the first identifier is assigned and the operation data to which the fourth identifier is assigned;
The air conditioning control device according to claim 2 or 3. While communication between the server communication unit and the server is interrupted, an upper limit value of the number of operation data to which the fourth identifier that can be stored in the operation data storage unit is assigned, and the operation data storage unit A storage status display means for displaying storage status notification information, which is information for notification of a storage status based on the number of operation data to which the accumulated fourth identifier is assigned,
The air conditioning control device according to claim 4. When the communication between the server communication unit and the server is restored, the server communication unit transmits the operation data to which the fourth identifier is assigned out of the operation data group to the server and transmits the selection information. Processing received from a server, processing for giving an identifier indicated by the selection information to each of driving data included in the driving data group, and processing for generating the model is indicated by the selection information. The process of generating the control model by machine learning using the learning data group is repeatedly executed until there is no operation data to which the fourth identifier is assigned.
The air conditioning control device according to claim 4 or 5. While communication between the server communication means and the server is restored and until there is no operation data to which the fourth identifier is given, the communication between the server communication means and the server is interrupted. Recovery for displaying recovery status notification information, which is information for reporting the recovery status based on the number of operation data to which the fourth identifier is assigned and the number of operation data to which the fourth identifier is currently assigned. Further comprising a status display means;
The air conditioning control device according to claim 6. In the case where the control model is generated by the model generation means, the apparatus further comprises update display means for displaying update notification information which is information for notification that the control model has been updated.
The air conditioning control device according to any one of claims 1 to 7. An air conditioning control system comprising an air conditioning control device and a server,
The air conditioning control device
An air conditioning communication means for receiving operation data from the air conditioner;
Operation data storage means for storing and storing the operation data received by the air conditioning communication means;
The operation data received by the air-conditioning communication means is transmitted to the server, and selection information which is information indicating a learning data group selected from the operation data group stored in the operation data storage means is received from the server. Server communication means;
When the selection information is received by the server communication means, model generation means for generating a control model by machine learning using the learning data group indicated by the selection information;
Air conditioning control means for controlling the air conditioner via the air conditioning communication means with control content based on the control model,
The server
Communication means for receiving the operation data transmitted by the server communication means;
Operation data storage means for storing and storing the operation data received by the communication means;
When the operation data is received by the communication unit, the learning data group is selected from the operation data group stored in the operation data storage unit based on the operation data group stored in the operation data storage unit Learning data selection means to perform,
The communication means transmits the selection information, which is information indicating the learning data group selected by the learning data selection means, to the air conditioning control device.
Air conditioning control system. Air conditioning controller
Receive operating data from the air conditioner,
Accumulate the operating data,
The received operation data is transmitted to a server, selection information that is information indicating a learning data group selected from the accumulated operation data group is received from the server,
A machine learning using the learning data group indicated by the selection information generates a control model,
Control the air conditioner with control content based on the control model,
Air conditioning control method. Computer
Air conditioning communication means for receiving operation data from the air conditioner,
Operation data storage means for storing and storing the operation data received by the air conditioning communication means;
The operation data received by the air-conditioning communication means is transmitted to the server, and selection information which is information indicating a learning data group selected from the operation data group stored in the operation data storage means is received from the server. Server communication means,
Model generation means for generating a control model by machine learning using the learning data group indicated by the selection information when the selection information is received by the server communication means;
With the control content based on the control model, function as air conditioning control means for controlling the air conditioner via the air conditioning communication means,
program.

Images