Information processing method, information processing device, and information processing program

Abstract

A server (2) comprises: an acquisition unit (211) which acquires apparatus data and accumulates the apparatus data in memory (22); a determination unit (212) which calculates the accuracy of a machine-learning model in a case of machine-training a machine-learning model by using the apparatus data accumulated in the memory (22), and determines at least one of a reducible data item or a reducible sampling rate so that the calculated accuracy meets a reference accuracy; and a transmission unit (213) which transmits, to an apparatus (1), control data that causes the apparatus data to be transmitted from the apparatus 1 with at least one of the reduced data item or the reduced sampling rate.

Description

[Technical Field]

[0001] The present disclosure relates to an information processing method and the like of an information processing device connected to one or more devices via a communication network. [Background technology]

[0002] Patent Document 1 discloses a metadata / log information management method that automatically deletes log information older than one month when reference to log information is limited to the past one month.

[0003] However, Patent Document 1 does not disclose anything about reducing the amount of device data when device data transmitted from a device is used as learning data, and therefore further improvement is needed. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-318146 Summary of the Invention

[0005] The present disclosure has been made to solve such problems, and aims to provide a technology that can maintain the accuracy of a machine learning model developed using device data, even when the amount of device data sent from the device is reduced.

[0006] An information processing method according to one embodiment of the present disclosure is an information processing method in an information processing device connected to one or more devices via a communication network, which acquires device data including predetermined data items and transmitted from the one or more devices at a predetermined sampling rate and stores it in memory, and when it is detected that the amount of device data stored in the memory has reached a standard data amount or greater, calculates the accuracy of the machine learning model when the machine learning model is trained using the device data stored in the memory, determines at least one of the data items that can be reduced and the sampling rate that can be reduced so that the calculated accuracy meets the standard accuracy, and sends control data to the one or more devices to cause the one or more devices to transmit the device data using at least one of the reduced data items and the reduced sampling rate.

[0007] According to the present disclosure, even if the amount of device data sent from a device is reduced, the accuracy of a machine learning model created using the device data can be maintained. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a diagram illustrating an example of an overall configuration of an information processing system according to a first embodiment of the present disclosure. [Figure 2] 2 is a block diagram showing an example of the configuration of the device shown in FIG. 1. FIG. [Figure 3] FIG. 2 is a block diagram illustrating an example of a configuration of a server according to the first embodiment of the present disclosure. [Figure 4] 10 is a flowchart showing an example of processing when devices transmit and receive device data in the information processing system according to the first embodiment of the present disclosure. [Figure 5] 10 is a flowchart showing an example of processing when a server transmits control data to a device in the first embodiment of the present disclosure. [Figure 6] FIG. 10 is a block diagram illustrating an example of a configuration of a server according to a second embodiment of the present disclosure. [Figure 7]11 is a flowchart showing an example of processing when a server transmits control data to a device in the second embodiment of the present disclosure. [Figure 8] 10 is a flowchart showing details of a selection process. DETAILED DESCRIPTION OF THE INVENTION

[0009] (Findings underlying this disclosure) In recent years, for vehicles equipped with battery packs, there has been consideration of developing a machine learning model to collect battery data from the vehicle in the cloud and use machine learning to estimate the battery state, etc.

[0010] Here, if the number of data items of the collected battery data is increased and the sampling rate of the collected battery data is increased, a highly accurate machine learning model can be generated.

[0011] However, as the number of data items and the sampling rate increase, the amount of data stored in the cloud memory also increases, which increases the cost of managing battery data on the cloud. Furthermore, in order to make the battery data usable as learning data on the cloud, a conversion process must be performed to convert the binary battery data into a predetermined data format, which also increases the management cost.

[0012] Furthermore, as the number of data items and the sampling rate increase, the cost of transmitting device data increases accordingly, so it is not useful to unnecessarily increase the number of data items and the sampling rate.

[0013] On the other hand, it is necessary to retain useful data items that contribute greatly to improving the accuracy of machine learning models.

[0014] The above-mentioned Patent Document 1 is a technology for reducing the data volume of acquired log information, but is not a technology for reducing the data volume of log information before acquisition, and therefore cannot solve these problems.

[0015] The present disclosure has been made to solve these problems, and aims to provide a technology that can maintain the accuracy of a machine learning model that is machine-learned using device data, even when the amount of device data transmitted from the device is reduced. One aspect of the present disclosure will be described below.

[0016] An information processing method according to one embodiment of the present disclosure is an information processing method in an information processing device connected to one or more devices via a communication network, which acquires device data including predetermined data items and transmitted from the one or more devices at a predetermined sampling rate and stores it in memory, and when it is detected that the amount of device data stored in the memory has reached a standard data amount or greater, calculates the accuracy of the machine learning model when the machine learning model is trained using the device data stored in the memory, determines at least one of the data items that can be reduced and the sampling rate that can be reduced so that the calculated accuracy meets the standard accuracy, and sends control data to the one or more devices to cause the one or more devices to transmit the device data using at least one of the reduced data items and the reduced sampling rate.

[0017] According to this configuration, at least one of the data items that can be reduced and the sampling rate that can be reduced is determined so that the accuracy of the machine learning model that uses the device data as training data meets the standard accuracy, and control data for transmitting the device data using at least one of the data items after the reduction and the sampling rate after the reduction is transmitted to the device. Therefore, even if the amount of device data transmitted from the device is reduced, the accuracy of the machine learning model trained using the device data can be maintained.

[0018] In the above information processing method, the specified data item may include a plurality of data items, and in the determination, the priority of each of the plurality of data items may be obtained, and one or more candidate data items may be determined as candidates for the data items to be retained in order of the highest priority.

[0019] According to this configuration, the priority of each of multiple data items is obtained, and one or more candidate data items that are candidates for data items to be retained are determined in descending order of priority, so that data items that can be reduced can be determined while retaining data items with high priorities.

[0020] In the above information processing method, the determination may involve calculating, for each candidate data item, the smallest sampling rate whose accuracy satisfies the standard accuracy as the candidate sampling rate, generating one or more pairs including each candidate sampling rate and a candidate data item corresponding to each candidate sampling rate, and determining, among the pairs, the candidate sampling rate and the candidate data item included in the pair with the smallest amount of data as the reduced sampling rate and the reduced data item.

[0021] According to this configuration, for each candidate data item, the minimum sampling rate at which the accuracy of the machine learning model satisfies the standard accuracy is calculated as the candidate sampling rate, one or more pairs including each candidate sampling rate and the candidate data item corresponding to each candidate sampling rate are generated, and the candidate sampling rate and candidate data item included in the pair with the smallest amount of data among the pairs are determined as the reduced sampling rate and reduced data items. Therefore, the reduced sampling rate and reduced data items can be determined with high accuracy.

[0022] In the above information processing method, the priority may be calculated based on the importance of each data item calculated when the equipment data stored in the memory is subjected to machine learning using a predetermined machine learning algorithm.

[0023] According to this configuration, the priority is determined based on the importance of the data item calculated when machine learning is performed on the equipment data stored in memory using a specified machine learning algorithm, making it easy to determine the priority of each data item.

[0024] In the above information processing method, the machine learning algorithm may be a random forest.

[0025] This configuration makes it easy to determine priorities using an existing machine learning algorithm called random forest.

[0026] In the above information processing method, each candidate data item may include one or more data items combined in descending order of priority.

[0027] According to this configuration, the candidate data items are configured from one or more data items combined in descending order of priority, so that data items with high priority can be preferentially retained.

[0028] In the above information processing method, each device may further be selected as either a first device that satisfies a predetermined selection criterion or a second device that does not satisfy the selection criterion, and in transmitting the control data, the control data may not be transmitted to the first device but may be transmitted to the second device.

[0029] According to this configuration, at least one of the reduced data items and the reduced sampling rate is applied only to second devices that do not satisfy the selection criteria, so that it is possible to focus on acquiring device data from first devices that maintain at least one of the pre-reduced data items and the pre-reduced sampling rate, and to efficiently collect device data necessary to generate a highly accurate machine learning model.

[0030] In the above information processing method, the selection may involve calculating a selection score for each device based on the device data stored in the memory, and selecting a device whose selection score is equal to or greater than a selection reference value as the first device.

[0031] According to this configuration, a device whose selection score calculated based on the device data is equal to or greater than the selection reference value is selected as the first device, so that the first device and the second device can be selected taking into consideration the contents of the device data sent from each device.

[0032] In the above information processing method, the selection standard value has a value corresponding to the proportion of the first device among the first device and the second device, and the proportion may be the maximum proportion that makes it possible to reduce the learning cost when machine learning the device data transmitted from the first device and the second device to less than or equal to a standard learning cost.

[0033] According to this configuration, the first device and the second device are selected based on the maximum ratio that makes it possible to make the learning cost equal to or less than the reference learning cost when machine learning is performed on the device data transmitted from the first device and the second device, thereby maximizing the proportion of the first device within a range in which the learning cost does not exceed the reference learning cost.

[0034] In the information processing method, the selection score may have a value according to a frequency of transmission of the device data.

[0035] According to this configuration, a device that transmits device data frequently is selected as the first device, so that device data can be acquired with a focus on devices that transmit device data frequently, and the device data required to generate a highly accurate machine learning model can be collected efficiently.

[0036] In the above information processing method, the device may include a battery, and the selection score may have a value corresponding to at least one of the frequency of transmission of the device data, the frequency of use of the battery, the discharge range of the battery, and the frequency of obtaining the open circuit voltage of the battery.

[0037] According to this configuration, an equipment that has a high frequency of transmitting equipment data, a high frequency of battery use, a high battery discharge range, and a high frequency of obtaining the battery's open circuit voltage is selected as the first equipment, so that equipment data can be acquired intensively from that equipment, and the equipment data necessary to generate a highly accurate machine learning model can be efficiently collected.

[0038] In the information processing method, the device data may be data relating to a battery provided in the device.

[0039] This configuration makes it possible to generate a machine learning model related to batteries.

[0040] An information processing device according to another aspect of the present disclosure is an information processing device connected to one or more devices via a communication network, and includes: an acquisition unit that acquires device data including predetermined data items and transmitted from the one or more devices at a predetermined sampling rate and stores the data in a memory; a determination unit that, when it detects that the amount of the device data stored in the memory has reached a standard data amount or greater, calculates the accuracy of the machine learning model when the machine learning model is trained using the device data stored in the memory, and determines at least one of the data items that can be reduced and the sampling rate that can be reduced so that the calculated accuracy meets the standard accuracy; and a transmission unit that transmits control data to the one or more devices to cause the one or more devices to transmit the device data using at least one of the data items after reduction and the sampling rate after reduction.

[0041] According to this configuration, it is possible to provide an information processing device that achieves the effects of the above information processing method.

[0042] An information processing program according to yet another aspect of the present disclosure is an information processing program that causes a computer to function as an information processing device connected to one or more devices via a communication network, and causes a processor of the information processing device to acquire device data including predetermined data items and transmitted from the one or more devices at a predetermined sampling rate and store it in memory, and when it is detected that the amount of the device data stored in the memory has exceeded the predetermined data amount, calculate the accuracy of a machine learning model trained using the device data stored in the memory, determine at least one of the data items that can be reduced and the sampling rate that can be reduced so that the calculated accuracy meets a standard accuracy, and send control data to the one or more devices that causes the device data to be transmitted from the one or more devices using at least one of the data items after the reduction and the sampling rate after the reduction.

[0043] According to this configuration, it is possible to provide an information processing program that achieves the effects of the above-described information processing method.

[0044] The present disclosure can also be realized as an information processing system operated by such an information processing program. Needless to say, such a computer program can be distributed on a computer-readable non-transitory recording medium such as a CD-ROM or via a communication network such as the Internet.

[0045] Note that each of the embodiments described below represents a specific example of the present disclosure. The numerical values, shapes, components, steps, and step orders shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Furthermore, among the components in the following embodiments, components that are not described in the independent claims that represent the highest concept are described as optional components. Furthermore, in all of the embodiments, the respective contents can be combined.

[0046] (Embodiment 1) 1 is a diagram illustrating an example of the overall configuration of an information processing system according to a first embodiment of the present disclosure. The information processing system includes one or more devices 1 and a server 2. The devices 1 and the server 2 are connected to each other so as to be able to communicate with each other via a network NT. The network NT is configured as a wide-area communication network including, for example, an Internet communication network, a mobile phone communication network, a satellite communication network, etc.

[0047] The device 1 transmits device data to the server 2. The device 1 is, for example, a vehicle such as an electric car, an electric bicycle, or an electric kick scooter. However, this is just one example, and the device 1 may also be, for example, a household electrical appliance such as a refrigerator, a washing machine, a microwave oven, an oven, a television, or audio equipment. Alternatively, the device 1 may be an automobile driven by an engine. An electric vehicle may include not only an automobile driven only by an electric motor, but also an automobile such as a plug-in hybrid car.

[0048] The device 1 may also be configured as a battery management device 11 (see FIG. 2) that is part of an electric vehicle. The battery management device 11 is a device that manages the battery provided in the electric vehicle.

[0049] The server 2 is configured, for example, as a cloud server including one or more computers. The server 2 acquires device data transmitted from the device 1. The server 2 transmits control data for the device 1 to the device 1. The control data is software that allows a processor in the device 1 to control the device 1, and corresponds to firmware, for example. In this embodiment, the control data includes information specifying the sampling rate of the device data that the device 1 transmits to the server 2, and information specifying the data items of the device data that the device 1 transmits to the server 2. The device 1 may have a function to receive control data wirelessly, called OTA (over the air).

[0050] The device data includes one or more data items. If the device 1 is an electric vehicle, the data items include, for example, discharge voltage, charge voltage, discharge current, discharge voltage, battery temperature, battery status information, error information, SOC (State of Charge), SOH (State of Health), and OCV (Open Circuit Voltage). The battery status information is information indicating the current status of the battery, and includes, for example, the charge status and discharge status. However, this is just an example. If the device 1 is a vehicle, the data items may include, for example, the vehicle acceleration, GPS information indicating the vehicle's position, and the vehicle's angular velocity. Furthermore, if the device 1 is an electrical appliance, the device data may include operation data of the electrical appliance. The operation data may include, for example, the operating mode, set temperature, power-on information, and power-off information of the electrical appliance. In addition to the data items, the device data further includes a timestamp indicating the date and time the device data was generated and a device ID (identifier) ​​of the device 1 that sent the data.

[0051] Hereinafter, the device 1 will be described as an electric vehicle, and the device data will be described as including battery-related data items such as discharge voltage, charge voltage, discharge current, discharge voltage, battery temperature, battery status information, error information, SOC, SOH, and open circuit voltage, but the present disclosure is not limited to this.

[0052] Fig. 2 is a block diagram showing an example of the configuration of the device 1 shown in Fig. 1. The device 1 is, for example, an electric vehicle. The device 1 includes a battery management device 11, a battery 12, and a communication device 13. The battery management device 11 is a device that manages the battery 12. The battery management device 11 includes a control unit 111, a communication unit 112, and a sensor 113.

[0053] The control unit 111 is composed of a processor such as a central processing unit, and controls the battery 12 by executing control data. The control unit 111 generates device data including data items specified by the control data at a sampling rate specified by the control data. The initial control data, which has not been updated, includes information specifying all data items that can be transmitted to the predetermined server 2. The initial control data also includes information specifying the maximum sampling rate among the sampling rates assumed to be capable of communication between the server 2 and the device 1. The sampling rate is the number of times device data is transmitted per unit time, and is expressed as the reciprocal of the transmission cycle (sampling cycle) of the device data.

[0054] The control unit 111 may generate device data using sensing data including, for example, values ​​detected by the sensor 113. The control unit 111 inputs the generated device data to the communication device 13 using the communication unit 112. The control unit 111 may generate the SOC, SOH, status information, etc. using the sensing data. The control unit 111 may acquire the OCV by having a voltage sensor detect the open circuit voltage of the battery 12 when a predetermined time has elapsed since the battery 12 entered a rest state in which it is not being charged or discharged. The predetermined time may be, for example, two hours or four hours.

[0055] The communication unit 112 is configured with a communication circuit compatible with an in-vehicle network such as a CAN (Controller Area Network), and inputs the device data generated by the control unit 111 to the communication device 13 via the in-vehicle network.

[0056] The sensors 113 include, for example, a current sensor, a voltage sensor, and a temperature sensor. The current sensor detects the discharge current and discharge voltage of the battery 12. The voltage sensor detects the discharge voltage and charge voltage of the battery 12. The temperature sensor detects the temperature of the battery 12.

[0057] The battery 12 is a rechargeable secondary battery such as a lithium ion battery or a nickel-metal hydride battery.

[0058] The communication device 13 is configured as a communication device for connecting the device 1 to the network NT using wireless communication such as BLE (Bluetooth Low Energy). The communication device 13 acquires the device data generated by the control unit 111 via the communication unit 112 and transmits the device data to the server 2. This allows the device 1 to transmit the device data to the server 2 at a predetermined sampling rate.

[0059] 3 is a block diagram showing an example of the configuration of the server 2 according to the first embodiment of the present disclosure. The server 2 includes a processor 21, a memory 22, and a communication circuit 23. The processor 21 is configured with a central processing unit or the like, and includes an acquisition unit 211, a determination unit 212, and a transmission unit 213. The processor 21 realizes the acquisition unit 211 to the transmission unit 213 by executing an information processing program stored in the memory 22. Note that the acquisition unit 211 to the transmission unit 213 may be configured with dedicated electric circuits.

[0060] The acquisition unit 211 acquires, using the communication circuit 23, device data that includes predetermined data items and is transmitted from the device 1 at a predetermined sampling rate, and stores the acquired data in the device database 221 of the memory 22. The predetermined data items are data items specified by the control data of the device 1. The predetermined sampling rate is the sampling rate specified by the control data of the device 1. Because the device data is in binary format, the machine learning model 222 cannot distinguish between data items, etc. Therefore, the acquisition unit 211 inputs the device data into a predetermined conversion formula, thereby converting the data format of the device data into a data format that enables the machine learning model 222 to identify data items, etc. Then, the acquisition unit 211 stores the device data whose data format has been converted in the device database 221.

[0061] The determination unit 212 detects whether the amount of device data stored in the device database 221 has reached or exceeded a reference data amount. The reference data amount is, for example, a predetermined data amount suitable for having the machine learning model 222 perform machine learning using the device data.

[0062] When the determination unit 212 detects that the amount of device data has reached or exceeded the reference data amount, the determination unit 212 calculates the accuracy of the machine learning model 222 when the machine learning model 222 is trained using the device data stored in the device database 221. Then, the determination unit 212 determines the reducible data items and the reducible sampling rate so that the calculated accuracy satisfies the reference accuracy.

[0063] For example, the determination unit 212 may cause the machine learning model 222 to perform machine learning using predetermined data items as input data and predetermined data items as output data (teaching data) among the data items constituting the equipment data. The teaching data may be, for example, SOC, SOH, error information, etc.

[0064] The determining unit 212 may calculate the accuracy of the machine learning model 222 by, for example, dividing a dataset into a training dataset and a validation dataset, performing machine learning on the training dataset to the machine learning model 222, and using a validation method to calculate the accuracy of the machine learning model 222 on the validation dataset. Examples of the validation method that can be used include cross-validation and holdout validation. Examples of the cross-validation that can be used include K-fold cross-validation and LOOCV (leave-out cross validation). For example, the coefficient of determination, root mean square error, and mean absolute error can be used to measure the accuracy of a regression model, and the accuracy rate and precision can be used to measure the accuracy of a classification model.

[0065] A predetermined value is adopted as the standard accuracy. For example, when a value indicating low accuracy such as root mean square error is adopted as the accuracy value, the determination unit 212 may determine that the standard accuracy is satisfied if the accuracy value is equal to or less than the standard accuracy. Also, when a value indicating high accuracy such as accuracy rate is adopted as the accuracy value, the determination unit 212 may determine that the standard accuracy is satisfied if the accuracy value is equal to or more than the standard accuracy.

[0066] The determination unit 212 determines the priority of each data item and determines one or more candidate data items as candidates for data items to be retained in descending order of priority. The determination unit 212 may calculate the priority of each data item based on the importance of each data item calculated when machine learning is performed on the equipment data stored in the equipment database 221 using a predetermined machine learning algorithm. Random forest may be used as the predetermined machine learning algorithm. However, this is just one example, and a machine learning algorithm other than random forest may be used as long as it is capable of calculating the importance. For example, the determination unit 212 may determine the priority of each data item in descending order of importance for each data item. In this embodiment, the machine learning model 222 is random forest, and therefore the determination unit 212 can obtain the importance of each data item by having the machine learning model 222 perform machine learning on the equipment data. The data items for which the priority and importance are calculated are data items of the equipment data other than the data items determined as training data. In addition, if priority setting information for each data item is stored in advance in memory 22, determination unit 212 may determine the priority of each data item by obtaining the setting information from memory 22.

[0067] The determining unit 212 may generate one or more candidate data items by combining one or more data items in descending order of priority.

[0068] The determination unit 212 calculates the smallest sampling rate for each candidate data item whose accuracy satisfies the standard accuracy as the candidate sampling rate, and generates one or more pairs including each candidate sampling rate and the candidate data item corresponding to each candidate sampling rate. After generating the pairs, the determination unit 212 determines the candidate sampling rate and candidate data item included in the pair with the smallest amount of data as the post-reduced sampling rate and post-reduced data item. The post-reduced data item refers to the data item to be retained. Hereinafter, the post-reduced sampling rate will be referred to as the optimal sampling rate, and the post-reduced data item will be referred to as the optimal data item.

[0069] The transmitting unit 213 transmits to the device 1 control data that causes the device 1 to transmit device data with the optimum data items and the optimum sampling rate.

[0070] The memory 22 is configured with a non-volatile rewritable storage device such as a solid state drive or a hard disk drive, and stores a device database 221 and a machine learning model 222. The device database 221 accumulates device data transmitted from the device 1. The device database 221 is a database in which one record is assigned to one piece of device data. This record stores the value of the data item of the device data, a timestamp indicating the date and time the device data was generated, and the device ID of the device 1 that transmitted the data, in association with each other.

[0071] The machine learning model 222 is a machine learning model used by the determination unit 212 to calculate the optimal data item, optimal sampling rate, and importance. A random forest can be used as the machine learning model 222. However, this is just one example, and a machine learning model other than a random forest may also be used.

[0072] Note that the machine learning model 222 is merely a machine learning model used to calculate the optimal data item, optimal sampling rate, and importance, and is different from the objective machine learning model used in actual operation scenes. The objective machine learning model is a machine learning model generated by machine learning using a huge amount of device data transmitted from the device 1 that executes the control data generated according to this embodiment as learning data. The generated objective machine learning model is downloaded to the device 1 or an external server, etc., and is used by the device 1 or the external server to calculate predetermined output data such as SOC and SOH.

[0073] However, this is just an example, and the target machine learning model may be the machine learning model 222. Furthermore, the machine learning model used to calculate the optimal data item and the optimal sampling rate may be a different machine learning model from the machine learning model used to calculate the importance.

[0074] The above is the configuration of the information processing system. The operation of the information processing system will be described below. Fig. 4 is a flowchart showing an example of processing when the device 1 transmits and receives device data in the information processing system according to the first embodiment of the present disclosure.

[0075] In step S101, the control unit 111 of the device 1 generates device data using sensing data from the sensor 113. In step S102, the control unit 111 transmits the generated device data to the server 2 via the communication unit 112 and the communication device 13.

[0076] In step S201, the acquisition unit 211 of the server 2 acquires device data using the communication circuit 23. In step S202, the acquisition unit 211 converts the data format of the device data by inputting the device data into a predetermined conversion formula so that the machine learning model 222 can identify the data item, device ID, and timestamp, and stores the converted device data in the device database 221.

[0077] 4 at the sampling rate specified by the control data. As a result, device data is accumulated in the device database 221.

[0078] FIG. 5 is a flowchart showing an example of processing when the server 2 transmits control data to the device 1 in the first embodiment of the present disclosure.

[0079] In step S121, the acquisition unit 211 determines whether the amount of device data accumulated in the device database 221 is equal to or greater than the reference data amount. If the amount of device data is equal to or greater than the reference data amount (YES in step S121), the process proceeds to step S122, and if the amount of device data is less than the reference data amount, the process waits in step S121. Here, if the optimum data items and optimum sampling rate have already been determined, the amount of device data compared with the reference data amount corresponds to the amount of device data accumulated in the device database 221 since the optimum data items and optimum sampling rate were determined last time. On the other hand, if the optimum data items and optimum sampling rate have never been determined, the amount of device data compared with the reference data amount corresponds to the amount of all device data accumulated in the device database 221.

[0080] In step S122, the determination unit 212 determines the priority of each data item constituting the device data. Here, the determination unit 212 reads out device data to be learned from the device database 221, and performs machine learning on the read out device data as learning data in the machine learning model 222, thereby calculating the importance of each data item and determining the priority of each data item in descending order of the calculated importance. For example, if the optimal data items and optimal sampling rate have already been determined, the device data to be learned corresponds to the device data accumulated in the device database 221 during the period from the previous determination of the optimal data items and optimal sampling rate until the determination of YES is made in step S121. On the other hand, if the optimal data items and optimal sampling rate have never been determined, the device data to be learned corresponds to all device data accumulated in the device database 221 during the period until the determination of YES is made in step S121.

[0081] In step S123, the determination unit 212 generates one or more candidate data items by combining one or more data items in descending order of priority. For example, assume that there are three data items A1 to A3, and the data items A1 to A3 have the highest priority. In this case, the determination unit 212 generates candidate data items so that more data items with higher priority are included, such as a candidate data item B1 consisting of data item A1 with the highest priority, a candidate data item B2 consisting of data item A1 and data item A2 with the second highest priority, and a candidate data item B3 consisting of data items A1, A2, and A3 with the third highest priority. The following description will be given using an example in which candidate data items B1 to B3 are generated, but the present disclosure is not limited to this. For example, the number of candidate data items may be any number, such as 5, 10, or 20.

[0082] In step S124, the determining unit 212 calculates the minimum sampling rate whose accuracy satisfies the standard accuracy as the candidate sampling rate for each of the candidate data items B1 to B3. Specifically, the determining unit 212 calculates the candidate sampling rate by the following process.

[0083] First, the determination unit 212 sets a predetermined minimum sampling rate and reads out from the device database 221 device data that corresponds to the set sampling rate and that is composed of a candidate data item B1 and a data item (e.g., SOC) that will be used as training data. Next, the determination unit 212 causes the machine learning model 222 to perform machine learning using the read device data as training data, and calculates the accuracy of the machine learning model 222 after machine learning. Next, the determination unit 212 determines whether the calculated accuracy satisfies a standard accuracy, and if the calculated accuracy does not satisfy the standard accuracy, increases the sampling rate by a predetermined resolution. Next, the determination unit 212 reads out from the device database 221 device data that corresponds to the increased sampling rate and that is composed of a candidate data item B1 and a data item (e.g., SOC) that will be used as training data. Next, the determination unit 212 causes the machine learning model 222 to perform machine learning using the read device data as training data, and calculates the accuracy of the machine learning model 222 after training. The determination unit 212 repeats this process for the candidate data item B1 until the accuracy of the machine learning model 222 meets the standard accuracy, and calculates the sampling rate when the accuracy meets the standard accuracy as the minimum sampling rate for the candidate data item B1.

[0084] The determination unit 212 also calculates the minimum sampling rate for each of the candidate data items B2 and B3 by applying the same process as for the candidate data item B1. The determination unit 212 then calculates the minimum sampling rates calculated for each of the candidate data items B1, B2, and B3 as the candidate sampling rates R1, R2, and R3 corresponding to the candidate data items B1, B2, and B3, respectively.

[0085] In step S125, the determining unit 212 generates a set M1 of candidate data item B1 and candidate sampling rate R1, a set M2 of candidate data item B2 and candidate sampling rate R2, and a set M3 of candidate data item B3 and candidate sampling rate R3.

[0086] In step S126, the determination unit 212 determines the set with the smallest data amount from among the sets M1 to M3. For example, the determination unit 212 may calculate the data amount (number of bits or number of bytes) per unit time of the candidate sampling rate R1 and the candidate data item B1 as the data amount of the set M1. The determination unit 212 may also calculate the data amounts of the sets M2 and M3 in the same way as for the set M1.

[0087] When the number of data items is small, the accuracy of the machine learning model 222 cannot be made equal to or higher than the reference accuracy unless the sampling rate is set high. On the other hand, when the number of data items is large, the accuracy of the machine learning model 222 can be made equal to or higher than the reference accuracy even if the sampling rate is set low. In this way, there is a trade-off between the number of data items and the sampling rate. Therefore, in this embodiment, the sets M1 to M3 are not evaluated simply using the number of bits of the candidate data items, but rather the sets M1 to M3 are evaluated using the amount of data per unit time of the sets M1 to M3.

[0088] Furthermore, since there is a trade-off between the sampling rate and the number of candidate data items, even if the maximum sampling rate is set for a small number of candidate data items, the accuracy of the machine learning model 222 may not be equal to or greater than the reference accuracy. In this case, the determination unit 212 can exclude candidate data items for which an accuracy equal to or greater than the reference accuracy could not be achieved from the determination candidates for the optimal data item.

[0089] In step S127, the determination unit 212 determines the candidate sampling rate and candidate data item that constitute the set with the smallest amount of data as the optimal sampling rate and optimal data item. For example, if the data amount of set M2 is the smallest, the data items A1 and A2 that constitute candidate data item B2 are determined as the optimal data items, and the candidate sampling rate R2 is determined as the optimal sampling rate.

[0090] In step S128, the determination unit 212 generates control data for causing the device 1 to transmit the device data having the optimal data items at the optimal sampling rate. In step S129, the transmission unit 213 transmits the generated control data to the device 1 using the communication circuit 23.

[0091] In step S111, the communication device 13 of the device 1 receives the control data. In step S112, the control unit 111 of the device 1 acquires the control data via the communication unit 112 and updates the current control data using the acquired control data. As a result, the optimal sampling rate and optimal data items are set in the device 1. Thereafter, the device 1 transmits device data having the optimal data items at the optimal sampling rate to the server 2.

[0092] As described above, according to the first embodiment, the reducible data items and the reducible sampling rate are determined so that the accuracy of the machine learning model 222 that uses the equipment data as training data satisfies the standard accuracy, and control data for transmitting the equipment data having the reduced data items (optimal data items) at the reduced sampling rate (optimal sampling rate) is transmitted to the equipment 1. Therefore, when the equipment data transmitted from the equipment 1 is used as training data for the machine learning model, the amount of equipment data can be reduced while maintaining the accuracy of the machine learning model.

[0093] (Embodiment 2) In the second embodiment, only devices 1 that do not satisfy the selection criteria are made to update their control data.

[0094] 6 is a block diagram showing an example of the configuration of server 2 according to embodiment 2 of the present disclosure. In embodiment 2, the same components as those in embodiment 1 are denoted by the same reference numerals, and description thereof will be omitted. Processor 21A of server 2A includes an acquisition unit 211, a determination unit 212, a device selection unit 214, and a transmission unit 213A.

[0095] The device selection unit 214 selects whether each device 1 corresponds to a first device that satisfies a predetermined selection criterion or a second device that does not satisfy the selection criterion.

[0096] The device selection unit 214 calculates a selection score for each device 1 based on the device data stored in the device database 221, and determines a device 1 whose selection score is equal to or greater than a selection reference value as a first device.

[0097] Here, the selection reference value has a value corresponding to the proportion of the first device among the first and second devices. This proportion is the maximum proportion at which the learning cost when machine learning is performed on the device data transmitted from the first and second devices can be made equal to or less than the reference learning cost. The learning cost is, for example, a predicted value of the cost when the above-mentioned objective machine learning model performs machine learning. Specifically, the learning cost is a predicted processing cost, a predicted expense cost, or an average predicted cost of the predicted processing cost and the predicted expense cost. For example, the device selection unit 214 may calculate the learning cost by calculating the amount of device data used for machine learning and inputting the data amount into a predetermined arithmetic formula. The reference learning cost is, for example, an upper limit of the allowable learning cost, and is a predetermined value.

[0098] The selection score has a value according to at least one of the frequency of device data transmission, the frequency of use of the battery 12, the discharge range of the battery 12, and the frequency of acquisition of the open circuit voltage of the battery 12.

[0099] Using device data from a device 1 that transmits device data frequently increases the likelihood of obtaining a highly accurate objective machine learning model. Therefore, in this embodiment, in order to acquire device data from a device 1 that transmits device data frequently, the device 1 is selected as the first device. From a similar perspective, in this embodiment, in order to acquire device data from a device 1 that has a high frequency of use of the battery 12, a high discharge range of the battery 12, and a high frequency of acquisition of the open circuit voltage of the battery 12, these devices 1 are selected as the first device.

[0100] The transmitting unit 213A does not transmit the control data to the first device, but transmits the control data to the second device.

[0101] 7 is a flowchart showing an example of processing when the server 2 transmits control data to the device 1 in the second embodiment of the present disclosure. Step S231 is the same as step S121 in FIG. 5. In step S232, the determination unit 212 performs optimization processing to determine the optimum data item and the optimum sampling rate. The optimization processing is configured from the processing of steps S122 to S128 in FIG. 5, and therefore description thereof will be omitted.

[0102] In step S233, the device selection unit 214 executes a selection process, the details of which will be described later with reference to FIG.

[0103] In step S234, the transmitting unit 213A transmits control data to the second device selected by the selection process to cause the second device to transmit device data having the optimal data items at the optimal sampling rate.

[0104] In step S211, the communication device 13 of the device 1 receives the control data. In step S212, the communication unit 112 of the second device acquires the control data via the communication device 13 and updates the current control data using the acquired control data. As a result, the optimal sampling rate and optimal data items are set in the second device. Thereafter, the second device will transmit device data having the optimal data items at the optimal sampling rate to the server 2. On the other hand, since no control data has been transmitted to the first device, the first device will transmit control data having default data items at the default sampling rate to the server 2.

[0105] 8 is a flowchart showing the details of the selection process. In step S301, a variable n that specifies the number of first devices is initialized to 1.

[0106] In step S302, the device selection unit 214 calculates the amount of device data from the first device and the second device to be used as learning data when the number of first devices is n, and calculates the learning cost by inputting the amount of data into a predetermined calculation formula.

[0107] In step S303, the device selection unit 214 determines whether the learning cost calculated in step S302 is greater than the reference cost. If the learning cost is equal to or less than the reference learning cost (NO in step S303), the device selection unit 214 increases the variable n by a predetermined number (e.g., 1) (step S304) and returns the process to step S302. On the other hand, if the learning cost is equal to or greater than the reference learning cost (YES in step S303), the process proceeds to step S305. In this way, the process of calculating the learning cost is repeated while increasing the number of first devices until the learning cost becomes greater than the reference learning cost, and the maximum number of first devices that can make the learning cost equal to or less than the reference learning cost is searched for.

[0108] In step S305, the device selection unit 214 calculates the ratio of the number of first devices to the number of first and second devices according to the current value of the variable n.

[0109] In step S306, the device selection unit 214 reads out the device data of all devices 1 whose device data is stored in the device database 221 from the device database 221, and calculates the selection score of each device 1 based on the read device data.

[0110] For example, the selection score is calculated using the following formula:

[0111] Selection score = A1·(frequency of sending device data) + A2·(frequency of using battery 12) + A3·(discharge range of battery 12) + A4·(frequency of acquiring open circuit voltage of battery 12) Here, A1 to A4 are weighting coefficients, each having a predetermined value.

[0112] In this way, the selection score of a device 1 increases as the frequency of device data transmission, the frequency of use of the battery 12, the discharge range of the battery 12, and the open circuit voltage of the battery 12 increase.

[0113] In step S307, the device selection unit 214 ranks the devices 1 in descending order of selection score.

[0114] In step S308, the device selecting unit 214 calculates a reference rank corresponding to the ratio calculated in step S305. For example, if there are 100 devices 1 and the ratio is 0.1, the reference rank is 10.

[0115] In step S309, the device selection unit 214 selects a device 1 whose rank is equal to or higher than the reference rank as the first device. In step S310, the device selection unit 214 selects a device 1 whose rank is lower than the reference rank as the second device. When the process of step S310 ends, the process proceeds to step S234 in FIG. 7.

[0116] Thus, according to embodiment 2, control data is updated only for the second device, so that device data can be acquired primarily from the first device, which is likely to provide device data useful for machine learning, and a highly accurate target machine learning model can be obtained.

[0117] The present disclosure can employ the following modifications.

[0118] (1) In the first and second embodiments, both the optimum data item and the optimum sampling rate are determined, but the present disclosure is not limited to this, and only one of them may be determined.

[0119] (2) In the second embodiment, the selection criterion value is a value corresponding to the ratio of the first device to the second device, but the present disclosure is not limited to this. For example, the selection criterion value may be a predetermined selection score.

[0120] (3) In step S302 of Fig. 8, the device selection unit 214 calculates the learning cost using a predetermined arithmetic formula, but the present disclosure is not limited to this. The device selection unit 214 may calculate the learning cost from the CPU load factor when machine learning is actually performed using device data. In this case, for example, a predetermined load factor that determines the upper limit of the learning cost can be used as the reference learning cost.

[0121] (4) In the second embodiment, the transmitting unit 213A does not transmit control data to the first device, but may transmit control data that causes the first device to transmit device data having a default number of data items at a default sampling rate. This allows the first device to return to the default data items and sampling rate, for example, even if optimal data items and optimal sampling rate were set in the past.

[0122] (5) In the first and second embodiments, the objective machine learning model is a model that outputs the battery state, such as SOC. However, the present disclosure is not limited to this and may be a model that determines the failure or degradation of an electrical appliance or a model that diagnoses the driving state of a vehicle driver. When generating a model that determines the failure or degradation of an electrical appliance as the objective machine learning model, operation data of the electrical appliance may be used as the equipment data. When generating a model that diagnoses the driving state of a driver as the objective machine learning model, equipment data that includes, as data items, the acceleration of the vehicle, GPS information indicating the position of the vehicle, and the angular velocity of the vehicle may be used. [Industrial Applicability]

[0123] The information processing method of the present disclosure is useful in technical fields in which machine learning is performed using device data collected from devices.

Claims

1. An information processing method in an information processing device connected to one or more devices via a communication network, comprising: acquiring device data including predetermined data items and transmitted from the one or more devices at a predetermined sampling rate and storing the data in a memory; When it is detected that the amount of the device data stored in the memory has reached or exceeded a reference data amount, the accuracy of the machine learning model when the machine learning model is trained using the device data stored in the memory is calculated, and at least one of the data items that can be reduced and the sampling rate that can be reduced is determined so that the calculated accuracy satisfies the reference accuracy; transmitting control data to the one or more devices to cause the one or more devices to transmit the device data at least one of the reduced data items and the reduced sampling rate; Information processing methods.

2. the predetermined data item includes a plurality of data items; In the determination, a priority of each of the plurality of data items is obtained, and one or more candidate data items that are candidates for the data items to be retained are determined in descending order of priority. The information processing method according to claim 1.

3. In the determination, for each of the candidate data items, the smallest sampling rate whose accuracy satisfies the reference accuracy is calculated as the candidate sampling rate, one or more sets including each candidate sampling rate and a candidate data item corresponding to each candidate sampling rate are generated, and the candidate sampling rate and the candidate data item included in the set with the smallest amount of data among each set are determined as the reduced sampling rate and the reduced data item.

3. The information processing method according to claim 2.

4. the priority is calculated based on the importance of each data item calculated when the device data stored in the memory is subjected to machine learning using a predetermined machine learning algorithm; 3. The information processing method according to claim 2.

5. The machine learning algorithm is a random forest.

5. The information processing method according to claim 4.

6. Each candidate data item includes one or more data items combined in the order of highest priority. The information processing method according to claim 2 .

7. Furthermore, each device is selected as either a first device that satisfies a predetermined selection criterion or a second device that does not satisfy the selection criterion; In transmitting the control data, the control data is not transmitted to the first device, but is transmitted to the second device. The information processing method according to claim 1 .

8. In the selection, a selection score of each device is calculated based on the device data stored in the memory, and a device having the selection score equal to or greater than a selection reference value is selected as the first device.

8. The information processing method according to claim 7.

9. the selection reference value has a value corresponding to a ratio of the first device to the first device and the second device, the ratio is the maximum ratio that can reduce the learning cost when machine learning is performed on the device data transmitted from the first device and the second device to a reference learning cost or less.

9. The information processing method according to claim 8.

10. the selection score has a value according to the frequency of transmission of the device data; 9. The information processing method according to claim 8.

11. the device includes a battery; the selection score has a value corresponding to at least one of a frequency of transmission of the device data, a frequency of use of the battery, a discharge range of the battery, and a frequency of acquisition of the open circuit voltage of the battery; The information processing method according to claim 8.

12. The device data is data related to a battery included in the device. The information processing method according to any one of claims 1 to 11.

13. An information processing device connected to one or more devices via a communication network, an acquisition unit that acquires device data including predetermined data items and transmitted from the one or more devices at a predetermined sampling rate and stores the device data in a memory; a determination unit that, when detecting that the amount of the device data stored in the memory has reached or exceeded a reference data amount, calculates the accuracy of the machine learning model when the machine learning model is trained using the device data stored in the memory, and determines at least one of the data items that can be reduced and the sampling rate that can be reduced so that the calculated accuracy satisfies the reference accuracy; a transmitting unit configured to transmit control data to the one or more devices to cause the one or more devices to transmit the device data based on at least one of the data items after reduction and the sampling rate after reduction.

14. An information processing program that causes a computer to function as an information processing device connected to one or more devices via a communication network, A processor of the information processing device acquiring device data including predetermined data items and transmitted from the one or more devices at a predetermined sampling rate and storing the data in a memory; When it is detected that the amount of the device data stored in the memory has reached a predetermined amount or more, the accuracy when a machine learning model is trained using the device data stored in the memory is calculated, and at least one of the data items that can be reduced and the sampling rate that can be reduced is determined so that the calculated accuracy satisfies a standard accuracy; transmitting control data to the one or more devices to cause the one or more devices to transmit the device data at least one of the reduced data items and the reduced sampling rate; An information processing program that executes processing.

Images