JP7147573B2 - Server device and learning method - Google Patents

Description

The present disclosure relates to server devices and the like.

For example, Patent Literature 1 discloses an air conditioning system with a learning function. In addition, in Patent Document 1, when the storage unit has a learning function, control by standard specification settings (for example, automatic driving using the detection result of a human sensor) reflects the preferences and behavior patterns of residents, etc. It is described that a suitable temperature environment is realized for a resident or the like.

JP 2015-117933 A

By the way, a method has also been proposed in which a server collects data related to an air conditioning system and generates a learning model. For example, the server collects user operation information as learning data together with environmental information such as room temperature and outside temperature, and then uses each of these learning data to determine the optimal air conditioner operation when environmental information is input. Generate a learning model that outputs information.

In addition, such a server generally has a plurality of learning VMs (Virtual Machines), and each learning VM learns using predetermined customer (air conditioning system) learning data, Generating a learning model for each customer. A learning VM is an example of a learning unit. For example, if there are n customers (#0 to #n) and three learning VMs (#0 to #2), learning VM #0 is customer #0, #3, #6, . -2, the learning VM #1 learns the collected data of customers #1, #4, #7, . , #8, . . . , #n.

However, with the above generation method, the time required for learning may vary among the learning VMs. For example, learning VM #0 processed all of the learning data for customers #0, #3, #6, . , . . Since learning data is acquired periodically (for example, every 5 minutes), a learning VM that has completed processing early will wait until it acquires the next learning data, which wastes computational resources. become.

In view of such a problem, an object of the present disclosure is to provide a server device and a learning method that do not cause a waiting time in a learning VM even if the learning processing time varies.

A server device of one aspect has a queue management unit and a plurality of learning units. The queue management unit is used to generate a learning model used by the control unit that controls the air conditioner, and collects data for learning including a data set of driving history information and operation information for a plurality of learning items from the adapter. Each time the data for learning is acquired, the data for learning is stored in a queue serving as a first-in, first-out memory based on the order of acquisition. A plurality of learning units extract learning data stored at the head of the plurality of learning data stored in the queue and execute learning processing for the learning model. The stored learning data is taken out and the learning process is repeatedly executed.

As one aspect, even if the learning processing time varies, it is possible to suppress the occurrence of waiting time in the learning VM (learning unit).

FIG. 1 is a diagram showing an example of an air conditioning system according to this embodiment. FIG. 2 is a block diagram showing an example of the configuration of the adapter. FIG. 3 is a block diagram showing an example of the configuration of the server device. FIG. 4 is a diagram illustrating an example of first-in first-out processing of data in a queue. FIG. 5 is an explanatory diagram showing an example of the contents of driving history data. FIG. 6 is a diagram showing an example of the data structure of collection patterns. FIG. 7 is a diagram showing an example of the data structure of the model memory. FIG. 8 is a flow chart showing an example of the processing operation of the queue management unit according to the embodiment. FIG. 9 is a flowchart illustrating an example of processing operations of a learning VM according to this embodiment.

Hereinafter, embodiments of the server device, the learning method, etc. disclosed in the present application will be described in detail based on the drawings. Note that the disclosed technology is not limited by the present embodiment. Further, each embodiment shown below may be modified as appropriate within a range that does not cause contradiction.

FIG. 1 is a diagram showing an example of an air conditioning system according to this embodiment. Air conditioning system 1 shown in FIG. Although indoor units 2A to 2C and adapters 50A to 50C are shown here, the air conditioning system 1 may have other indoor units and adapters.

The indoor unit 2A is, for example, part of an air conditioner that is placed indoors and heats or cools the air in the room. The user of the indoor unit 2A can remotely operate the indoor unit 2A by operating the remote controller 9A. The indoor unit 2A has a main body 3A and a control section 4A that controls the main body 3A. The main body 3A is provided with an indoor fan and an indoor heat exchanger, and the indoor air that has undergone heat exchange with the refrigerant in the indoor heat exchanger is blown out from the main body 3A to heat, cool, dehumidify, etc. the room. will be

The indoor unit 2B has a main body 3B and a control section 4B. Descriptions regarding the indoor unit 2B, the main body 3B, and the control section 4B are the same as those regarding the indoor unit 2A, the main body 3A, and the control section 4A. A user of the indoor unit 2B can remotely operate the indoor unit 2B by operating the remote controller 9B.

The indoor unit 2C has a main body 3C and a controller 4C. Descriptions regarding the indoor unit 2C, the main body 3C, and the control section 4C are the same as those regarding the indoor unit 2A, the main body 3A, and the control section 4A. A user of the indoor unit 2C can remotely operate the indoor unit 2C by operating the remote controller 9C.

The adapter 50A has a communication function that connects the indoor unit 2A and the access point 4 by wireless communication, and a control function that AI (Artificial Intelligence) controls the indoor unit 2A. The adapter 50B has a communication function for connecting the indoor unit 2B and the access point 4 by wireless communication, and a control function for AI-controlling the indoor unit 2B. The adapter 50C has a communication function for connecting the indoor unit 2C and the access point 4 by wireless communication, and a control function for AI-controlling the indoor unit 2C.

In the following description, the indoor units 2A, 2B, and 2C are collectively referred to as the indoor unit 2 unless otherwise distinguished. Also, the adapters 50A, 50B, and 50C are collectively referred to as an adapter 50. FIG.

The access point 4 is, for example, a device that connects the adapter 50A and the communication network 8 by wireless communication using WLAN (Wireless Local Area Network) or the like. The communication network 8 is, for example, a communication network such as the Internet. The communication terminal 7 is a terminal device such as a smartphone owned by a user. The user can use the communication terminal 7 from outside to transmit the operating conditions of the indoor unit 2 (operating mode such as cooling/heating, set temperature, etc.).

The relay device 6 is a device that relays various data related to AI control between the adapter 50 and the server device 100 .

The server device 100 has a function of generating a learning model for the AI that controls the indoor units 2, a database that stores data for learning, and the like. The server device 100 is arranged in, for example, a data center.

FIG. 2 is a block diagram showing an example of the configuration of the adapter. Here, as an example, description will be made using the adapter 50A. As shown in FIG. 2, the adapter 50A has a first communication section 51, a second communication section 52, a storage section 53, and a CPU (Central Processing Unit) . The first communication unit 51 is a communication IF (Interface) such as a UART (Universal Asynchronous Receiver Transmitter) that communicates with the CPU 54 and the control unit 4A in the indoor unit 2A. The second communication unit 52 is a communication unit such as a communication IF such as WLAN that connects the CPU 54 and the access point 4 for communication. The storage unit 53 has, for example, a ROM (Read Only Memory) and a RAM (Random Access Memory), and stores various information such as data and programs. The CPU 54 controls the adapter 50 as a whole.

The storage unit 53 in the adapter 50A shown in FIG. 2 includes a driving history memory 53A that temporarily stores driving history data acquired from the indoor unit 2A, a model memory 53B that stores learning models acquired from the server device 100, and a weather forecast. and an external memory 53C for storing external data such as.

The CPU 54 has an acquisition section 54A, a transmission section 54B, a reception section 54C, a setting section 54D, and a prediction control section 54E.

The acquisition unit 54A acquires the driving history data and the operation history data from the indoor unit 2A at predetermined intervals, for example, at acquisition timings of every 5 minutes. Acquisition unit 54A stores the driving history data and the operation history data obtained in a 5-minute cycle in driving history memory 53A.

The transmission unit 54B transmits the driving history data stored in the driving history memory 53A and the operation history data to the server device 100 via the communication network 8 .

The receiving unit 54C receives the learning model from the server device 100 via the communication network 8, and stores the received learning model in the model memory 53B.

The setting unit 54D applies the learning model stored in the model memory 53B to the predictive control unit 54E.

The predictive control unit 54E controls the control unit 4A in the indoor unit 2A based on the learning model applied by the setting unit 54D. For convenience of explanation, the predictive control unit 54E controls the control unit 4A in the indoor unit 2A based on the learning model. 3A may be controlled directly. Also, the predictive control unit 54E transmits a signal including a control mode based on the learning model to the control unit 4A. That is, the prediction control unit 54E may indirectly control the main body 2A via the control unit 4A, and can be changed as appropriate.

By the way, the hardware configuration of the adapters 50B and 50C is similar to that of the adapter 50A. It should be noted that the targets of processing by the adapter 50B are the indoor unit 2B, the main body 3B, and the control unit 4B. The targets of processing by the adapter 50C are the indoor unit 2C, the main body 3C, and the control unit 4C.

FIG. 3 is a block diagram showing an example of the configuration of the server device 100. As shown in FIG. The server device 100 shown in FIG. 3 has a communication unit 110, a storage unit 120, and a CPU . The communication unit 110 is a communication IF that connects the CPU 130 and the relay device 6 for communication. The storage unit 120 has, for example, an HDD (Hard Disk Drive), ROM, RAM, etc., and stores various information such as data and programs. The CPU 130 controls the server device 100 as a whole.

Storage unit 120 in server device 100 shown in FIG. 3 has queue storage unit 120A, collection pattern memory 120B, and model memory 120C.

The queue 120A is a memory that holds driving history data and operation history data for learning in a first-in, first-out list structure. When data is taken out from the queue 120A, the data for learning that was put in first is taken out in order. In the following description, each set of driving history data and operation history data will be referred to as data (learning data). A set of driving history data and operation history data is an example of a data set. Putting data into the tail end of the queue 120A is written as "enqueue", and taking it out is written as "dequeue".

FIG. 4 is a diagram illustrating an example of first-in first-out processing of data in a queue. At step S10 in FIG. 4, learning data 10-1 to 10-4 are stored in the queue 120A in order from the top. Here, when the learning data 10-5 is enqueued, the learning data 10-5 is stored after the last learning data 10-4, as shown in step S11.

In step S12 of the steps in FIG. 4, when dequeued, the learning data 10-1 stored at the head of the queue 120A is taken out. Then, as shown in step S13, the learning data 10-2 to 10-5 are stored in order in the queue 120A.

Next, an example of the contents of the driving history data included in the learning data will be described. FIG. 5 is an explanatory diagram showing an example of the contents of driving history data. The driving history data has a plurality of items, and each item is associated with an item number for uniquely identifying the item. For example, items in the operation history data include operation status, operation mode, set temperature, indoor temperature, indoor humidity, air volume, wind direction, motion sensor, radiation sensor, indoor heat exchanger temperature, outdoor temperature, compressor rotation speed, outdoor Air volume, operating current, outdoor heat exchanger temperature, and the like. Furthermore, the operation history data includes, for example, discharge temperature, compressor temperature, expansion valve opening, radiator temperature, start failure history, abnormal stop history, emergency operation history, air conditioner ID, installation location, facility type, and the like. .

The operating state is the ON-OFF state of the operation of the indoor unit 2 . The operation mode is an operation mode such as cooling or heating of the indoor unit 2 . The set temperature is the indoor target temperature in which the indoor unit 2 is used. The room temperature is the actual temperature in the room where the indoor unit 2 is used. The indoor humidity is the actual humidity in the room where the indoor unit 2 is used. The air volume is the air volume of the conditioned air blown out from the indoor unit 2 . The wind direction is the wind direction of the conditioned air blown out from the indoor unit 2 . The human sensor is the result of detection by the sensor of the presence or absence of people in the room and the amount of activity. The radiation sensor is the result of detection by sensors of the temperature of the floor and walls in the room. The indoor heat exchanger temperature is the temperature of an indoor heat exchanger (not shown) forming part of the body 2A of the indoor unit 2 . The outdoor temperature is the actual outdoor temperature. The compressor rotation speed is the operating rotation speed of a compressor provided in an outdoor unit (not shown) connected to the indoor unit 2 by a refrigerant pipe. The outdoor air volume is the air volume of an outdoor fan provided in the outdoor unit. The operating current is, for example, the operating current of the entire air conditioner such as the indoor unit 2 and the outdoor unit. The outdoor heat exchanger temperature is the temperature of an outdoor heat exchanger provided in the outdoor unit. The discharge temperature is the temperature of the refrigerant discharged from the compressor. Compressor temperature is the temperature at the bottom of the compressor. The expansion valve opening is the opening of an electronic expansion valve provided in the outdoor unit. The radiator temperature is the temperature of the power semiconductor that drives and controls the compressor. The start failure history is a history of compressor start failures. The abnormal stop history is a history of abnormal stop. The emergency operation history is the execution history of emergency operation. The time stamp is the year, month, day, hour, minute, and second at the time of data acquisition. The air conditioner ID is an ID given to the indoor unit 2 to identify the air conditioner such as the indoor unit 2 . The installation location is the address of the location where the air conditioner is installed. The facility type is the type of facility such as a store, restaurant, or factory where the air conditioner such as the indoor unit 2 is installed.

The operation history data includes data used for home air conditioners and data used for commercial air conditioners. Operational history data used in home air conditioners includes, for example, operation status, operation mode, set temperature, indoor temperature, indoor humidity, air volume, wind direction, values detected by human sensors, and values detected by radiation sensors. They are a value, a time stamp, an air conditioner ID, an installation location, and the like. Air conditioners for home use use AI to operate and make proposals in pursuit of comfort and energy saving, so for example, set temperature, operation mode, indoor and ambient environment, etc. are necessary data for home use.

Operation history data used for commercial air conditioners includes, for example, operation status, operation mode, set temperature, indoor temperature, indoor humidity, air volume, wind direction, values detected by human sensors, and values detected by radiation sensors. These are the detected values, the indoor heat exchanger temperature, the outdoor temperature, the compressor rotation speed, the outdoor air volume, the operating current, the outdoor heat exchanger temperature, and the like. Further, other operation history data includes, for example, discharge temperature, compressor temperature, expansion valve opening, radiator temperature, start failure history, abnormal stop history, emergency operation history, time stamp, air conditioner ID, installation location, Facility type, etc. In commercial air conditioners, AI predicts failures and the need for maintenance of each device. is determined by AI. In addition to the above, operational history data necessary for commercial air conditioners is, for example, data used for failure prediction. In addition, the rotation speed of the compressor and fan motor used in the air conditioner are stopped while the air conditioner is stopped, and each operation history data is not generated. and data such as outdoor heat exchanger temperature shall not be obtained while the air conditioner is stopped.

The operation history data indicates the user's operation history for the indoor unit 2 . For example, the operation history data includes changed temperature setting, air volume, air velocity, and the like.

The collected pattern memory 120B is a memory that stores a collected pattern 120BB that associates a learning model with driving history data used to generate the learning model. FIG. 6 is a diagram showing an example of the data structure of collection patterns. As shown in FIG. 6, in the collection pattern 120BB, learning model identification information is associated with item numbers. The learning model identification information is information that uniquely identifies the generated learning model. The learning target item number is information that uniquely identifies an item of the driving history data used when generating the learning model. For example, an item of driving history data used when generating a learning model is an example of a "learning item."

For example, when generating a learning model with learning model identification information "E001", it indicates that the data of item numbers "1 to 7" among all the items described in FIG. . When generating the learning model with the learning model identification information “E002”, it indicates that the data of the item numbers “1 to 11” among all the items described in FIG. 6 are used to generate the learning model. When generating the learning model with the learning model identification information “E003”, it indicates that the data of the item numbers “1 to 15” among all the items described with reference to FIG. 6 are used to generate the learning model.

The model memory 120C stores the learning model generated by the learning section 130C. FIG. 7 is a diagram showing an example of the data structure of the model memory. As shown in FIG. 7, the model memory 120C associates learning model identification information with learning models.

The CPU 130 of the server device 100 has a queue management section 131 , a learning section 132 and a notification section 133 .

The queue management unit 131 receives learning data from the adapter 50 . The queue management unit 131 is a processing unit that enqueues the received learning data in the queue 120A in the order of reception. For example, as described in steps S10 and S11 of FIG. 4, when learning data 10-5 is received, learning data 10-5 is enqueued after learning data 10-4.

The learning unit 132 has a learning VM 132a, a learning VM 132b, and a learning VM 132c. The learning VMs 132a to 132c dequeue the learning data stored in the queue 120A and generate a learning model based on the dequeued learning data. It is assumed that the learning model identification information of the learning models learned by the learning VMs 132a-132c is assigned in advance to the learning VMs 132a-132c. For example, the learning VM 132a is assigned the learning model identification information “E001”, the learning VM 132a is assigned the learning model identification information “E002”, and the learning VM 132b is assigned the learning model identification information “E003”. It is assumed that there is When creating a new learning model, the learning VMs 132a-132c create new learning model identification information.

The learning VM 132a dequeues the learning data stored in the queue 120A, and among all the items of the driving history data of the dequeued learning data, the learning target item numbers "1 to 7" defined in the collection pattern 120B. A learning model with learning model identification information “E001” is generated using the data of the corresponding item. After completing the generation of the learning model using the dequeued learning data, the learning VM 132a again dequeues the learning data stored in the queue 120A, and repeats the above processing. The learning VM 132a updates the previous learning model stored in the model memory 120C with the generated learning model.

The learning VM 132b dequeues the learning data stored in the queue 120A, and among all the items of the driving history data of the dequeued learning data, the learning target item numbers "1 to 11" defined in the collection pattern 120B. A learning model with learning model identification information “E002” is generated using the data of the corresponding item. After completing the generation of the learning model using the dequeued learning data, the learning VM 132b again dequeues the learning data stored in the queue 120A, and repeats the above processing. The learning VM 132b updates the previous learning model stored in the model memory 120C with the generated learning model.

The learning VM 132c dequeues the learning data stored in the queue 120A, and among all the items of the driving history data of the dequeued learning data, the learning target item numbers "1 to 7" defined in the collection pattern 120B. A learning model with learning model identification information “E001” is generated using the data of the corresponding item. After completing the generation of the learning model using the dequeued learning data, the learning VM 132c again dequeues the learning data stored in the queue 120A, and repeats the above process. The learning VM 132c updates the previous learning model stored in the model memory 120C with the generated learning model.

The notification unit 130E is a processing unit that transmits each learning model stored in the model memory 120C to the adapter 50. FIG.

Next, the operation of the queue management unit 131 of the server device 100 according to this embodiment will be described. FIG. 8 is a flow chart showing an example of the processing operation of the queue management unit according to the embodiment. As shown in FIG. 8, the queue management unit 131 of the server device 100 determines whether learning data has been received from the adapter 50 (step S101). When the queue management unit 131 has not received the learning data from the adapter 50 (step S101, No), the process proceeds to step S101 again.

On the other hand, when the queue management unit 131 receives learning data from the adapter 50 (step S101, Yes), the queue management unit 131 enqueues the learning data received from the adapter 50 into the queue 120A (step S102).

When continuing the process (step S103, Yes), the queue management unit 131 proceeds to step S101. If the queue management unit 131 does not continue the processing (step S103, No), the processing ends.

Next, operations of the learning VMs 132a to 132c included in the learning unit 132 will be described. As an example, the operation of the learning VM 132a will be described. Since the operations of the learning VMs 132b and 132c are the same as the operations of the learning VM 132a, description thereof will be omitted. FIG. 9 is a flowchart illustrating an example of processing operations of a learning VM according to this embodiment.

The learning VM 132a dequeues the learning data from the queue 120A (step S201). The learning VM 132a generates a learning model using the learning data (step S202). When the learning model generation is completed, the learning VM 132a stores the generated learning model in the model memory 120C (step S203).

If the learning VM 132a continues the process (step S204, Yes), the process proceeds to step S201. If the learning VM 132a does not continue the process (step S204, No), the process ends.

As described above, the server device 100 according to the present embodiment enqueues learning data received from the adapter 50 into the queue 120A, and each of the learning VMs 132a to 132c dequeues the learning data from the queue 120A. Generate a learning model. In this way, each of the learning VMs 132a to 132c dequeues the learning data from the queue 120A after generating the learning data. Therefore, even if the learning processing time varies, the learning VMs do not have to wait. There is no

When generating a learning model, each of the learning VMs 132a to 132c acquires learning data corresponding to the learning model to be generated based on the collection pattern 120B from data of all items of the driving history data. This eliminates the need to store learning data for each learning model even when different learning models are generated, enabling effective utilization of memory resources.

By the way, although the queue management unit 131 described in FIG. 3 enqueues the learning data in the queue 120A in the order in which the learning data is received from the adapter 50, the enqueue is not limited to this. Other processes 1 to 3 of the queue management unit 131 will be described below.

Other processing 1 of the queue management unit 131 will be described. In other processing 1, it is assumed that learning data received by the queue management unit 131 is given information on the number of times the indoor unit 2 is operated. For example, the queue management unit 131 temporarily holds a plurality of learning data received from the adapter 50 for a certain period of time (for example, 1 minute), and prioritizes learning data with a large number of operations among the held plurality of learning data. and enqueue it in the queue 120A. The queue management unit 131 repeatedly executes the above process at regular intervals.

Other processing 2 of the queue management unit 131 will be described. In other processing 1, it is assumed that learning data received by the queue management unit 131 is given unique information (MAC address, etc.) of the indoor unit 2 . For example, the queue management unit 131 temporarily holds a plurality of learning data received from the adapter 50 for a certain period of time (for example, 1 minute), and among the held plurality of learning data, the MAC to which a high priority order is set. Learning data to which an address has been assigned is preferentially enqueued in the queue 120A. The queue management unit 131 repeatedly executes the above process at regular intervals. It is assumed that the priority of each MAC address is set in advance.

Other processing 3 of the queue management unit 131 will be described. In other processing 1, it is assumed that learning data received by the queue management unit 131 is provided with weather forecast information around the indoor unit 2 . For example, the queue management unit 131 selects only learning data attached to weather forecast information that satisfies a predetermined condition and enqueues it in the queue 120A. The predetermined condition is a condition that the air temperature is equal to or higher than a certain temperature, or a condition that the temperature is lower than a certain temperature. Alternatively, the condition is that the change in outside air temperature is equal to or greater than the threshold. It is assumed that the predetermined condition is set in advance.

By the way, the case where the adapter 50 transmits the driving history data of the indoor unit 2 to the server device 100 via the relay device 6 has been exemplified, but the driving history data etc. 100, and can be changed as appropriate.

Also, each constituent element of each part illustrated does not necessarily need to be physically configured as illustrated. In other words, the specific form of distribution and integration of each part is not limited to the one shown in the figure, and all or part of it can be functionally or physically distributed and integrated in arbitrary units according to various loads and usage conditions. can be configured as

Furthermore, the various processing functions performed by each device are implemented on a CPU (Central Processing Unit) (or a microcomputer such as an MPU (Micro Processing Unit) or MCU (Micro Controller Unit)), in whole or in part. You can make it run. In addition, various processing functions may be executed in whole or in part on a program analyzed and executed by a CPU (or a microcomputer such as an MPU or MCU) or on hardware based on wired logic. Needless to say.

1 air conditioning system 2A, 2B, 2C indoor unit 3A, 3B, 3C main body 4A, 4B, 4C control unit 50A, 50B, 50C adapter 51 first communication unit 52 second communication unit 53, 120 storage unit 53A operation history Memory 53B, 120C Model memory 53C External memory 54, 130 CPU
54A acquisition unit 54B transmission unit 54C reception unit 54D setting unit 54E prediction control unit 100 server device 120A queue 120B collection pattern memory 131 queue management unit 132 learning unit 132a, 132b, 132c learning VM
133 Notifier

Claims (6)

The learning data is acquired from an adapter that is used to generate a learning model used by a control unit that controls an air conditioner and that collects learning data including data sets of driving history information and operation information for a plurality of learning items. a queue management unit that stores the learning data in a queue serving as a first-in first-out memory each time based on the order of acquisition;
out of the plurality of learning data stored in the queue, take out the learning data stored at the head, execute learning processing for the learning model, and when the learning processing is completed, the learning data stored at the head of the queue and a plurality of learning units that take out data for use and repeatedly execute learning processing. When retrieving the learning data stored at the head of the queue, the plurality of learning units retrieve a data set corresponding to a learning item specific to a learning model to be subjected to learning processing, and use the retrieved data set as a learning data set. 2. The server device according to claim 1, wherein the learning process of the learning model is executed as data. Information on the number of times the air conditioner is operated is added to each of the plurality of learning data acquired from the adapter, and the queue management unit stores the plurality of learning data based on the information on the number of operations. 3. The server device according to claim 1, wherein the order of storing in the queue is controlled. Identification information of the air conditioner is assigned to each of the plurality of learning data acquired from the adapter, and the queue management unit stores the plurality of learning data in the queue based on the identification information. 4. The server device according to claim 1, wherein the order is controlled. The plurality of learning data acquired from the adapter is provided with weather forecast information for the area where the air conditioner is installed, and the queue management unit performs the plurality of learning data based on the weather forecast information. 5. The server device according to any one of claims 1 to 4, wherein learning data to be stored in said queue is selected from data for learning. the computer
The learning data is acquired from an adapter that is used to generate a learning model used by a control unit that controls an air conditioner and that collects learning data including data sets of driving history information and operation information for a plurality of learning items. a step of storing the learning data in a queue serving as a first-in, first-out memory each time, based on the order of acquisition;
out of the plurality of learning data stored in the queue, take out the learning data stored at the head, execute learning processing for the learning model, and when the learning processing is completed, the learning data stored at the head of the queue and a step of executing a plurality of learning VMs (Virtual Machines) for taking out data for learning and repeatedly executing learning processing.

Images