Management Device, Management Method, and Storage Medium

Abstract

The management device includes: an information acquisition unit that acquires battery information related to the usage state of a secondary battery mounted on the vehicle and information related to the user from the vehicle; a first feature quantity derivation unit that derives a first feature quantity indicating the state of the secondary battery based on a result obtained by applying the battery information to a battery state detection recognition model for identifying the state of the secondary battery; a second feature quantity derivation unit that derives a second feature quantity indicating the characteristics of the user based on the information related to the user; and a selection unit that selects a battery suitable for the user based on a result obtained by inputting the first feature quantity and the second feature quantity to a matching model that outputs a result indicating the compatibility between the user and the battery according to the first feature quantity and the second feature quantity.

Description

Technical Field

[0001] The present invention relates to a management device, a management method, and a storage medium. Background Art

[0002] In electric vehicles such as electric motor vehicles and hybrid vehicles, storage batteries (secondary batteries) such as lithium ion batteries are used. In order to stably supply storage batteries in the future, it is effective to consider actively utilizing secondary use. Conventionally, technologies related to the following device and method have been disclosed, in which the device and method are for providing energy management and preservation of a secondary-use storage battery through the use of a secondary service port (for example, refer to Patent Document 1).

[0003] Prior Art Documents

[0004] Patent Documents

[0005] Patent Document 1: Japanese Unexamined Patent Application Publication No. 2013-243913 Summary of the Invention

[0006] Problems to be Solved by the Invention

[0007] However, when a user purchases a vehicle or a storage battery through a dealer or the like, the usage method of the vehicle or the storage battery cannot be assumed, and an appropriate storage battery cannot be provided.

[0008] The present invention has been made in consideration of such a situation, and provides a management device, a management method, and a program capable of recommending a storage battery suitable for a user.

[0009] Solutions to the Problems

[0010] The management device, management method, and program of the present invention adopt the following configuration.

[0011] (1): A management device according to an aspect of the present invention includes: an information acquisition unit that acquires battery information related to the usage state of a secondary battery mounted on the vehicle and information related to the user from the vehicle; a first feature quantity derivation unit that derives a first feature quantity indicating the state of the secondary battery based on a result obtained by applying the battery information to a battery state detection learning model for identifying the state of the secondary battery; a second feature quantity derivation unit that derives a second feature quantity indicating the characteristics of the user based on the information related to the user; and a selection unit that selects a storage battery suitable for the user based on a result obtained by inputting the first feature quantity and the second feature quantity to a matching model that outputs a result indicating the compatibility between the user and the storage battery according to the first feature quantity and the second feature quantity.

[0012] (2): In the solution of (1) above, the information acquisition unit acquires vehicle information related to the driving state of the vehicle as information related to the user, and the second feature quantity derivation unit derives the second feature quantity based on the result obtained by applying the vehicle information to a user classification model that identifies the characteristics of the user.

[0013] (3): In the solution of (1) or (2) above, the information acquisition unit acquires a detection value indicating the usage state of the secondary battery as the battery information, and the first feature quantity derivation unit derives a feature quantity for identifying the state of the secondary battery by representing the following result using a three-dimensional space model defined by the capacity of the secondary battery, the SOC-OCV curve of the secondary battery, and the internal resistance of the secondary battery, as the first feature quantity, where this result is obtained by applying the battery information to the battery state detection knowledge model.

[0014] (4): In the solution of (3) above, the information acquisition unit acquires information indicating current, voltage, and temperature when the secondary battery is charged and discharged as the detection value.

[0015] (5): A management method according to an aspect of the present invention causes a computer to perform the following processing: acquire battery information related to the usage state of a secondary battery mounted on a vehicle and information related to a user from the vehicle; derive a first feature quantity indicating the state of the secondary battery based on the result obtained by applying the battery information to a battery state detection knowledge model for identifying the state of the secondary battery; derive a second feature quantity indicating the characteristics of the user based on the information related to the user; and select a secondary battery suitable for the user based on the result obtained by inputting the first feature quantity and the second feature quantity to a matching model that outputs a result indicating the compatibility between the user and the secondary battery according to the first feature quantity and the second feature quantity.

[0016] (6): A program according to an aspect of the present invention causes a computer to perform the following processing: acquire battery information related to the usage state of a secondary battery mounted on a vehicle and information related to a user from the vehicle; derive a first feature quantity indicating the state of the secondary battery based on the result obtained by applying the battery information to a battery state detection knowledge model for identifying the state of the secondary battery; derive a second feature quantity indicating the characteristics of the user based on the information related to the user; and select a secondary battery suitable for the user based on the result obtained by inputting the first feature quantity and the second feature quantity to a matching model that outputs a result indicating the compatibility between the user and the secondary battery according to the first feature quantity and the second feature quantity.

[0017] Advantages of the Invention

[0018] According to (1) to (6), it is possible to recommend a storage battery suitable for the user. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 FIG. is a diagram showing an example of a management system 1 including the management device of the present invention.

[0020] Figure 2 FIG. is a diagram showing an example of the configuration of the vehicle 10.

[0021] Figure 3 FIG. is a diagram showing an example of the configuration of the management server 300.

[0022] Figure 4 FIG. is a diagram showing an example of the storage battery state detection acquisition model M1.

[0023] Figure 5 FIG. is a diagram showing an example of a three-dimensional space model for identifying the state of the storage battery.

[0024] Figure 6 FIG. is a diagram showing an example of the user characteristic detection acquisition model M2.

[0025] Figure 7 FIG. is a diagram showing an example of a radar chart showing the characteristics of the user.

[0026] Figure 8 FIG. is a diagram showing an example of the matching model M3.

[0027] Figure 9 FIG. is a diagram showing an example of a summary of the processing performed by a part of the processing unit 330 of the management server 300.

[0028] Figure 10 FIG. is a reference diagram for explaining a specific example of the first embodiment.

[0029] Figure 11 FIG. is a flowchart showing an example of the flow of the processing performed by the processing unit 330.

[0030] Figure 12 FIG. is a diagram showing an example of the configuration of the management server 300A.

[0031] Figure 13 FIG. is a diagram showing an example of the user characteristic detection acquisition model M4.

[0032] Figure 14 FIG. is a diagram showing an example of a summary of the processing performed by a part of the processing unit 330 of the management server 300A.

[0033] Figure 15 FIG. is a reference diagram for explaining a specific example of the second embodiment. Detailed Implementation Modes

[0034] [First Implementation Mode]

[0035] Hereinafter, with reference to the drawings, implementation modes of the management device, management method, and program of the present invention will be described. Figure 1 is a diagram showing an example of a management system 1 including the management device of the present invention. As Figure 1 shown, the management system 1 includes, for example, a vehicle 10, a user terminal 80, a management server 300, and a store terminal 500. The vehicle 10, the user terminal 80, the management server 300, and the store terminal 500 are connected via a network NW. It should be noted that the network NW includes, for example, the Internet, a WAN (Wide Area Network), a LAN (Local Area Network), a provider device, a wireless base station, and the like.

[0036] The vehicle 10 is, for example, an electric motor vehicle equipped with a secondary battery or an electric motor vehicle capable of replacing the secondary battery. It should be noted that the vehicle 10 only needs to be a vehicle capable of storing electric power from the outside or a vehicle equipped with a secondary battery for supplying driving electric power, and may also be a hybrid motor vehicle or a fuel cell vehicle. In addition, the vehicle 10 may also be a four-wheeled vehicle, a three-wheeled vehicle, a straddle-type vehicle, an electric assist bicycle, a cultivator, a management machine, a walking assist device, a kick board, etc. that are equipped with or capable of replacing a secondary battery.

[0037] The user terminal 80 is a terminal owned by a user and includes, for example, a smart phone, a tablet terminal, a personal computer, and the like.

[0038] The management server 300 manages, for example, the usage status of the secondary battery mounted on the vehicle 10 based on information received from the vehicle 10 and the like. The management server 300 selects a battery suitable for the user based on the usage status of the secondary battery and the like. For details, see the description below.

[0039] The store terminal 500 is, for example, a computer installed in a store such as a dealership and includes a keyboard, a mouse, a display, and the like. When a clerk inputs the matters answered by the user, the store terminal 500 generates user response information and sends it to the management server 300 via the network NW.

[0040] [Vehicle]

[0041] Figure 2This is a diagram showing an example of the configuration of vehicle 10. Vehicle 10 includes, for example, a motor 12, drive wheels 14, a braking device 16, vehicle sensors 20, a battery device 30, a battery sensor 40, a communication device 50, a charging port 70, a converter 72, and a PCU (Power Control Unit) 100. The PCU 100 is an example of a control device.

[0042] The motor 12 is, for example, a three-phase alternating current motor. The rotor of the motor 12 is connected to the drive wheels 14. The motor 12 uses the supplied electric power to output power to the drive wheels 14. In addition, the motor 12 generates electricity using the kinetic energy of the vehicle when the vehicle decelerates.

[0043] The braking device 16 includes, for example, a brake caliper, a hydraulic cylinder that transmits hydraulic pressure to the brake caliper, and an electric motor that generates hydraulic pressure in the hydraulic cylinder. The braking device 16 may include a mechanism that transmits the hydraulic pressure generated by the operation of the brake pedal to the hydraulic cylinder via a master hydraulic cylinder as a backup. It should be noted that the braking device 16 is not limited to the structure described above and may also be an electronically controlled hydraulic braking device that transmits the hydraulic pressure of the master hydraulic cylinder to the hydraulic cylinder.

[0044] The vehicle sensors 20 include, for example, a throttle opening sensor, a vehicle speed sensor, and a brake pedal depression amount sensor. The throttle opening sensor is installed on a throttle pedal, which is an example of an operating member that receives an acceleration instruction from the driver, detects the operation amount of the throttle pedal, and outputs it as the throttle opening to the PCU 100. The vehicle speed sensor includes, for example, wheel speed sensors installed on each wheel and a speed computer, synthesizes the wheel speeds detected by the wheel speed sensors to derive the vehicle speed (vehicle speed), and outputs it to the PCU 100. The brake pedal depression amount sensor is installed on the brake pedal, detects the operation amount of the brake pedal, and outputs it as the brake pedal depression amount to the PCU 100.

[0045] The PCU 100 includes, for example, a converter 110, a VCU (Voltage Control Unit) 120, and a control unit 130. The converter 110 is, for example, an AC-DC converter. The DC side terminal of the converter 110 is connected to a DC line DL. The battery device 30 is connected to the DC line DL via the VCU 120. The converter 110 converts the alternating current generated by the motor 12 into direct current and outputs it to the DC line DL. The VCU 120 is, for example, a DC-DC converter. The VCU 120 boosts the electric power supplied from the battery device 30 and outputs it to the DC line DL.

[0046] The control unit 130 includes, for example, a motor control unit 131, a brake control unit 133, and a battery / VCU control unit 135. The motor control unit 131, the brake control unit 133, and the battery / VCU control unit 135 may also be replaced with relatively independent control devices, such as control devices like a motor ECU, a brake ECU, and a battery ECU. The control unit 130 controls the operations of various parts of the vehicle 10, such as the converter 110, the VCU 120, and the battery device 30.

[0047] The control unit 130 is implemented, for example, by a hardware processor such as a CPU (Central Processing Unit) executing a program (software). Some or all of these components may also be implemented by hardware (including a circuitry section) such as an LSI (Large Scale Integration), an ASIC (Application Specific Integrated Circuit), an FPGA (Field-Programmable Gate Array), or a GPU (Graphics Processing Unit), or may be implemented through the cooperation of software and hardware.

[0048] The program may be pre-stored in a storage device (non-transitory storage medium) such as an HDD (Hard Disk Drive) or a flash memory, or may be stored in a removable storage medium (non-transitory storage medium) such as a DVD or a CD-ROM, and installed by mounting the storage medium on a drive device.

[0049] Based on the output of the vehicle sensor 20, the motor control unit 131 controls the motor 12. Based on the output of the vehicle sensor 20, the brake control unit 133 controls the brake device 16.

[0050] The battery / VCU control unit 135 controls the output of the battery device 30. For example, based on the output of a battery sensor 40 of a battery 32 (described later) installed in the battery device 30, the battery / VCU control unit 135 calculates the SOC (State Of Charge) of the battery 32 and outputs it to the VCU 120. The VCU 120 raises the voltage of the DC line DL according to an instruction from the battery / VCU control unit 135. Details of the battery device 30 are described later.

[0051] The battery sensor 40 includes, for example, a current sensor 41, a voltage sensor 43, a temperature sensor 45, etc. The battery sensor 40 detects, for example, the current value, voltage value, temperature, etc. of the charge and discharge of the battery 32. The battery sensor 40 outputs the detected current value, voltage value, temperature, etc. to the control unit 130 and the communication device 50. It should be noted that the battery sensor 40 can be housed in the housing of the battery device 30 or installed outside the housing. Hereinafter, the current value, voltage value, temperature, etc. detected by the battery sensor 40 are referred to as battery parameters.

[0052] The communication device 50 includes a wireless module for connecting to wireless communication networks such as a wireless LAN and a cellular network. The wireless LAN can be, for example, in a form such as Wi-Fi (registered trademark), Bluetooth (registered trademark), Zigbee (registered trademark). The cellular network can be, for example, a third-generation mobile communication network (3G), a fourth-generation mobile communication network (Long term evolution: LTE (registered trademark)), or a fifth-generation mobile communication network (5G), etc. The communication device 50 can also obtain the current value, voltage value, temperature, etc. output from the battery sensor 40 and send them to the outside.

[0053] The charging port 70 is provided facing the outside of the vehicle body of the vehicle 10. The charging port 70 is connected to an external charger 200 via a charging cable 220. The charging cable 220 includes a first plug 222 and a second plug 224. The first plug 222 is connected to the external charger 200, and the second plug 224 is connected to the charging port 70. The electricity supplied from the external charger 200 is supplied to the charging port 70 via the charging cable 220.

[0054] In addition, the charging cable 220 includes a signal cable attached to the power cable. The signal cable mediates communication between the vehicle 10 and the external charger 200. Therefore, a power connector and a signal connector are provided on each of the first plug 222 and the second plug 224.

[0055] The converter 72 is provided between the battery device 30 and the charging port 70. The converter 72 converts the current introduced from the external charger 200 via the charging port 70, for example, alternating current, into direct current. The converter 72 outputs the converted direct current to the battery device 30.

[0056] [Management Server]

[0057] Figure 3FIG. 0 is a diagram showing an example of the configuration of the management server 300. The management server 300 includes, for example, a communication unit 310, a processing unit 330, and a storage unit 350. The communication unit 310 includes, for example, a wireless module for connecting to a wireless communication network such as a wireless LAN or a cellular network. The wireless LAN may be, for example, a method such as Wi-Fi (registered trademark), Bluetooth (registered trademark), or Zigbee (registered trademark). The cellular network may be, for example, a third-generation mobile communication network (3G), a fourth-generation mobile communication network (Long Term Evolution: LTE (registered trademark)), or a fifth-generation mobile communication network (5G).

[0058] The storage unit 350 may be, for example, a storage device (non-transitory storage medium) such as an HDD (Hard Disk Drive) or a flash memory, or may be a control circuit that enables or disables writing of information to or reading of information from the storage device based on the HDD, flash memory, etc. In the storage unit 350, for example, battery management information 351, user management information 352, a battery state detection acquisition model M1, a user characteristic detection acquisition model M2, a matching model M3, etc. are stored. These information are written by the processing unit 330 and read by the processing unit 330.

[0059] The processing unit 330 includes, for example, an information acquisition unit 331, a first feature quantity derivation unit 332, a second feature quantity derivation unit, and a selection unit 334. The processing unit 330 is implemented, for example, by a processor such as a CPU executing a program (software) stored in the storage unit 350. In addition, some or all of these functional units included in the processing unit 330 may also be implemented by hardware (including a circuitry unit) such as an LSI, an ASIC, an FPGA, or a GPU, or may be implemented by a combination of software and hardware. The program may be pre-stored in a storage device (non-transitory storage medium) such as an HDD or a flash memory, or may be stored in a removable storage medium (non-transitory storage medium) such as a DVD or a CD-ROM, and installed by mounting the storage medium on a drive device.

[0060] The information acquisition unit 331 acquires battery information and a vehicle ID related to the usage state of the battery 32 mounted on the vehicle 10 from the vehicle 10, and stores them as battery management information 351 in the storage unit 350. In the battery information, for example, the detection results of battery parameters (for example, current value, voltage value, temperature, etc.) acquired from the battery sensor 40 are included. In the battery management information 351, battery information corresponding to the vehicle ID is included. The vehicle ID is identification information for identifying each vehicle.

[0061] In addition, the information acquisition unit 331 acquires information related to the user from the vehicle 10. It should be noted that the information acquisition unit 331 may also receive information related to the user from the user terminal 80 and the store terminal 500 via the network NW. The information related to the user includes, for example, user response information containing the user's answers to specified questions, and user IDs as identification information for identifying each user. The specified questions include, for example, the frequency of driving, the time period when driving frequently, the area often visited, whether often traveling far or driving nearby, etc. For example, the information acquisition unit 331 associates the user ID with the user response information and stores it in the storage unit 350 as part of the user management information 352.

[0062] The first feature quantity derivation unit 332 derives a first feature quantity indicating the state of the storage battery 32 based on the result obtained by applying the storage battery information to the storage battery state detection knowledge model M1, and outputs the derived result to the selection unit 334.

[0063] Figure 4 It is a diagram showing an example of the storage battery state detection knowledge model M1. Figure 4 In the shown example, the storage battery state detection knowledge model M1 is a model that inputs the input current value (I), voltage value (V), and temperature (T) and obtains the first feature quantities (y1, y2,..., y100). It should be noted that Figure 4 The number of intermediate layers, weight coefficients, and the number of first feature quantities shown are an example and are not limited thereto. In addition, the number of inputs to the model is not limited thereto, as long as it is two or more of the current value, voltage value, and temperature. In addition, as will be described later, time series change information of the storage battery 32, deterioration information of the storage battery 32, etc. can also be input into the model. In addition, the storage battery information input into the model is not limited to the current value, voltage value, and temperature. For example, it can also be the SOC (State of Charge: charge rate) calculated from the current value and voltage value, the resistance value of the storage battery 32 calculated from the current value and voltage value, etc.

[0064] The first feature quantity derivation unit 332 may also derive a feature quantity for identifying the state of the storage battery by representing the first feature quantity of the storage battery obtained using the storage battery state detection knowledge model M1 by, for example, a three-dimensional space model, and output it as the first feature quantity to the selection unit 334. Figure 5 It is a diagram showing an example of a three-dimensional space model for identifying the state of the storage battery. The three-dimensional space model is, for example, a space model defined by the three dimensions of the power capacity value of the storage battery, the internal resistance of the storage battery, and the SOC-OCV curve characteristics of the storage battery. The first feature quantity derivation unit 332 is based on Figure 5 the state transition in the shown three-dimensional space model, and derives the first feature quantity for identifying the state of the storage battery.

[0065] In addition, the first feature quantity derivation unit 332 may also output, as the first feature quantity, the feature quantity that classifies the shape of the radar chart by representing the first feature quantity of the storage battery obtained by using the storage battery state detection learned model M1 in a radar chart, for example, and thereby identifies the state of the storage battery, to the selection unit 334. It should be noted that the first feature quantity derivation unit 332 may also represent the feature quantity as a contour chart or the like for identification.

[0066] The second feature quantity derivation unit 333 derives a second feature quantity representing the characteristics of the user based on information related to the user.

[0067] For example, the second feature quantity derivation unit 333 derives a second feature quantity representing the characteristics of the user based on the result obtained by applying the user response information to the user characteristic detection learned model M2, and outputs the derived result to the selection unit 334.

[0068] Figure 6 It is a diagram showing an example of the user characteristic detection learned model M2. Figure 6 In the example shown, the user characteristic detection learned model M2 is a model that takes the user response item 1, the user response item 2,..., the user response item X as inputs and obtains the second feature quantities (y1, y2,..., y100). It should be noted that Figure 6 the number of intermediate layers, the weight coefficients, and the number of second feature quantities shown are examples and are not limited thereto. In addition, the number of inputs to the model is not limited thereto.

[0069] In addition, the second feature quantity derivation unit 333 may also output, as the second feature quantity, the feature quantity that classifies the shape of the radar chart by representing the second feature quantity of the user characteristics obtained by using the user characteristic detection learned model M2 in a radar chart, for example, and thereby identifies the characteristics of the user, to the selection unit 334. Figure 7 It is a diagram showing an example of the radar chart showing the characteristics of the user. The radar chart has the first feature quantities A to F as vertices. In the figure, user patterns α and β representing the characteristics of different users are shown. It should be noted that the second feature quantity derivation unit 333 may also represent the feature quantity as a contour chart or the like for identification.

[0070] Based on the result obtained by inputting the first feature quantity and the second feature quantity to the matching model M3, the selection unit 334 selects a storage battery suitable for the user (hereinafter referred to as the optimal storage battery). The matching model M3 outputs a result representing the compatibility between the user and the storage battery based on the first feature quantity and the second feature quantity.

[0071] Figure 8 It is a diagram showing an example of the matching model M3. Figure 8The matching model M3 of the example shown takes the first feature quantity and the second feature quantity as inputs and obtains the third feature quantity (yy1, yy2,..., yy100) for identifying the optimal battery. It should be noted that Figure 8 The number of intermediate layers, weight coefficients, and the number of third feature quantities shown are an example and are not limited thereto. It should be noted that in Figure 8 In the example shown, an example of inputting the first feature quantity and the second feature quantity to the matching model M3 is described, but it is not limited thereto. The input to the model can also be information indicating the state of the battery identified based on the first feature quantity and information indicating the characteristics of the user identified based on the second feature quantity.

[0072] In addition, the selection unit 334 can also identify the optimal battery by, for example, representing the third feature quantity obtained using the matching model M3 with a radar chart and classifying the shape of the radar chart.

[0073] Figure 9 This is a brief example of the processing performed by a part of the processing unit 330 of the management server 300. The first feature quantity derivation unit 332 derives the first feature quantity indicating the state of the battery 32 based on the result obtained by applying battery information such as current (I), voltage (V), and temperature (T) to the battery state detection learning model M1, and outputs the derived result to the selection unit 334. On the other hand, the second feature quantity derivation unit 333 derives the second feature quantity indicating the characteristics of the user based on the result obtained by applying the user response information to the user characteristic detection learning model M2, and outputs the derived result to the selection unit 334. The selection unit 334 selects the optimal battery based on the result obtained by inputting the first feature quantity and the second feature quantity to the matching model M3.

[0074] Figure 10 This is a reference diagram for explaining a specific example of the first embodiment. For example, the management server 300 manages battery information related to used batteries and derives the first feature quantity related to the used batteries. In addition, the management server 300 derives the second feature quantity related to the user based on the user response information received from the user terminal 80 or the store terminal 500. Moreover, the management server 300 selects the optimal battery through matching based on the first feature quantity related to the used battery and the second feature quantity related to the user, and sends the selection result to the store terminal 500. In this way, the dealer can recommend a used battery suitable for the user to the user.

[0075] Figure 11It is a flowchart showing an example of the process of the processing performed by the processing unit 330. First, the information acquisition unit 331 stores the information received from the vehicle 10 in the storage unit 350 (step S101). The first feature quantity derivation unit 332 derives a first feature quantity indicating the state of the secondary battery 32 based on the result obtained by applying battery information such as current (I), voltage (V), temperature (T), etc. to the battery state detection learning model M1 for identifying the state of the secondary battery (step S103). The second feature quantity derivation unit 333 derives a second feature quantity indicating the characteristics of the user based on the result obtained by applying the user response information to the user characteristic detection learning model M2 (step S105). The selection unit 334 selects the optimal battery based on the result obtained by inputting the first feature quantity and the second feature quantity into the matching model M3 (step S107).

[0076] [Summary of the Embodiment]

[0077] As described above, the management server 300 of the present embodiment includes: an information acquisition unit 331 that acquires battery information related to the usage state of the secondary battery mounted on the vehicle 10 and information related to the user from the vehicle 10; a first feature quantity derivation unit 332 that derives a first feature quantity indicating the state of the secondary battery based on the result obtained by applying the battery information to the battery state detection learning model for identifying the state of the secondary battery; a second feature quantity derivation unit 333 that derives a second feature quantity indicating the characteristics of the user based on the information related to the user; and a selection unit 334 that selects a battery suitable for the user based on the result obtained by inputting the first feature quantity and the second feature quantity into a matching model that outputs a result indicating the compatibility between the user and the battery according to the first feature quantity and the second feature quantity, thereby being able to recommend a battery suitable for the user.

[0078] [Second Embodiment]

[0079] Next, the second embodiment will be described. In the second embodiment, it is different in that the information acquisition unit 331 acquires vehicle information related to the driving state of the vehicle 10 as information related to the user. Hereinafter, the points different from the first embodiment will be described, and the same points will be omitted.

[0080] Figure 12 It is a diagram showing an example of the configuration of the management server 300A. The management server 300A is different from the management server 300 in that the vehicle management information 353 is stored in the storage unit 350 in place of the user management information 352, and the user characteristic detection learning model M4 is stored in the storage unit 350 in place of the user characteristic detection learning model M2.

[0081] Figure 13This is a diagram showing an example of the user characteristic detection and acquisition model M4. Figure 12 In the shown example, the user characteristic detection and acquisition model M4 is a model that takes the driving distance (SL), driving time (ST), and average speed (SS) as inputs to obtain the second characteristic quantities (y1, y2,..., y100). It should be noted that the driving distance is, for example, the cumulative driving distance of vehicle 10 since its start of use. Additionally, the driving time is, for example, the cumulative driving time of vehicle 10 since its start of use. Also, the average speed is a value obtained by dividing the cumulative driving distance of vehicle 10 since its start of use by the cumulative driving time. It should be noted that Figure 12 The number of intermediate layers, weight coefficients, and the number of second characteristic quantities shown are an example and are not limited thereto. Also, the number of inputs to the model is not limited to this, as long as it is two or more of the driving distance, driving time, and speed.

[0082] Additionally, the second characteristic quantity derivation unit 333 can also output, as the second characteristic quantity to the selection unit 334, a characteristic quantity that represents the user's characteristics by, for example, classifying the shape of a radar chart that represents the second characteristic quantity of the user characteristics obtained using the user characteristic detection and acquisition model M4.

[0083] Figure 14 This is a brief example of the processing performed by a part of the processing unit 330 of the management server 300A. The first characteristic quantity derivation unit 332 derives the first characteristic quantity representing the state of the storage battery 32 based on the result obtained by applying battery information such as current (I), voltage (V), and temperature (T) to the storage battery state detection and acquisition model M1, and outputs the derived result to the selection unit 334. On the other hand, the second characteristic quantity derivation unit 333 derives the second characteristic quantity representing the user's characteristics based on the result obtained by applying vehicle information to the user characteristic detection and acquisition model M4, and outputs the derived result to the selection unit 334. The selection unit 334 selects the optimal storage battery based on the result obtained by inputting the first characteristic quantity and the second characteristic quantity into the matching model M3.

[0084] Figure 15This is a reference diagram for explaining a specific example of the second embodiment. For example, the management server 300A manages battery information related to the battery 32 mounted on the vehicle 10 of user A, and derives a first characteristic quantity related to the battery being used by user A. In addition, the management server 300 derives a second characteristic quantity related to user B based on the vehicle information received from the vehicle 10 of user B. Moreover, the management server 300 selects the optimal battery suitable for user B through matching based on the first characteristic quantity related to multiple batteries and the second characteristic quantity related to user B, and sends the selection result to the store terminal 500. In this way, the dealer can recommend a new battery suitable for user B to user B. For example, the management server 300A can specify the size, number of stacked layers, series-parallel number, etc. of the battery and select the optimal battery.

[0085] The above-described embodiment can be expressed as follows.

[0086] A management device configured to include:

[0087] A storage device storing a program; and

[0088] A hardware processor,

[0089] By executing the program stored in the storage device by the hardware processor, the following processing is performed:

[0090] Obtain battery information related to the usage status of the secondary battery mounted on the vehicle and information related to the user from the vehicle;

[0091] Based on the result obtained by applying the battery information to the battery state detection knowledge model for identifying the state of the secondary battery, derive a first characteristic quantity representing the state of the secondary battery;

[0092] Based on the information related to the user, derive a second characteristic quantity representing the characteristics of the user;

[0093] Based on the result obtained by inputting the first characteristic quantity and the second characteristic quantity into a matching model that outputs a result representing the compatibility between the user and the battery according to the first characteristic quantity and the second characteristic quantity, select a battery suitable for the user.

[0094] The specific embodiments of the present invention have been described above using the embodiments, but the present invention is in no way limited to such embodiments, and various modifications and substitutions can be made without departing from the gist of the present invention.

[0095] Explanation of reference numerals:

[0096] 1... Management system

[0097] 10…Vehicle

[0098] 12…Motor

[0099] 14…Drive wheel

[0100] 16…Brake device

[0101] 20…Vehicle sensor

[0102] 30…Battery device

[0103] 32…Battery (power storage unit)

[0104] 40…Battery sensor

[0105] 41…Current sensor

[0106] 43…Voltage sensor

[0107] 45…Temperature sensor

[0108] 50…Communication device

[0109] 70…Charging port

[0110] 72…Converter

[0111] 100…PCU

[0112] 110…Converter

[0113] 120…VCU

[0114] 130…Control unit

[0115] 131…Motor control unit

[0116] 133…Brake control unit

[0117] 135…Battery·VCU control unit

[0118] 300…Management server

[0119] 310…Communication unit

[0120] 331…Information acquisition unit

[0121] 332…First feature quantity derivation unit

[0122] 333…Second feature quantity derivation unit

[0123] 334…Selection unit

[0124] 330…Processing unit

[0125] 350…Storage unit

[0126] 351…Battery management information

[0127] 352… User management information

[0128] 353… Vehicle management information

[0129] M1… Battery status detection and acquisition model

[0130] M2… User characteristic detection and acquisition model

[0131] M3… Matching model.

Claims

1. A management device, wherein, the management device includes: an information acquisition unit that acquires battery information related to the usage state of a secondary battery mounted on the vehicle and information related to the user from the vehicle; a first feature quantity derivation unit that derives a first feature quantity indicating the state of the secondary battery based on a result obtained by applying the battery information to a battery state detection learning model for identifying the state of the secondary battery; a second feature quantity derivation unit that derives a second feature quantity indicating the characteristics of the user based on the information related to the user; and a selection unit that selects a battery suitable for the user based on a result obtained by inputting the first feature quantity and the second feature quantity to a matching model that outputs a result indicating the compatibility between the user and the battery according to the first feature quantity and the second feature quantity, the information acquisition unit acquires, as the battery information, a detection value indicating the usage state of the secondary battery, the first feature quantity derivation unit identifies the state of the battery by representing the following result using a three-dimensional space model defined by the capacity of the secondary battery, the SOC-OCV curve of the secondary battery, and the internal resistance of the secondary battery, and derives the first feature quantity based on the transition of the state of the battery in the three-dimensional space model, the result being obtained by applying the battery information to the battery state detection learning model.

2. The management device according to claim 1, wherein, the information acquisition unit acquires vehicle information related to the driving state of the vehicle as information related to the user, the second feature quantity derivation unit derives the second feature quantity based on a result obtained by applying the vehicle information to a user characteristic detection learning model for identifying the characteristics of the user.

3. The management device according to claim 1, wherein, the information acquisition unit acquires, as the detection value, information indicating current, voltage, and temperature when the secondary battery is charged and discharged.

4. A management method, wherein, the management method causes a computer to perform the following processes: acquire battery information related to the usage state of a secondary battery mounted on the vehicle and information related to the user from the vehicle; derive a first feature quantity indicating the state of the secondary battery based on a result obtained by applying the battery information to a battery state detection learning model for identifying the state of the secondary battery; derive a second feature quantity indicating the characteristics of the user based on the information related to the user; select a battery suitable for the user based on a result obtained by inputting the first feature quantity and the second feature quantity to a matching model that outputs a result indicating the compatibility between the user and the battery according to the first feature quantity and the second feature quantity; acquire, as the battery information, a detection value indicating the usage state of the secondary battery; and The state of the storage battery is identified by representing the following result using a three-dimensional space model defined by the capacity of the secondary battery, the SOC-OCV curve of the secondary battery, and the internal resistance of the secondary battery, and the first feature amount is derived based on the transition of the state of the storage battery in the three-dimensional space model, the result being obtained by applying the storage battery information to the storage battery state detection knowledge model.

5. A storage medium storing a program, wherein, the program causes a computer to perform the following processing: acquire storage battery information related to the usage state of a secondary battery mounted on the vehicle and information related to a user from the vehicle; derive a first feature amount representing the state of the secondary battery based on a result obtained by applying the storage battery information to a storage battery state detection knowledge model for identifying the state of the secondary battery; derive a second feature amount representing the characteristics of the user based on the information related to the user; select a storage battery suitable for the user based on a result obtained by inputting the first feature amount and the second feature amount to a matching model that outputs a result indicating the compatibility between the user and the storage battery according to the first feature amount and the second feature amount; acquire, as the storage battery information, a detection value representing the usage state of the secondary battery; and The state of the storage battery is identified by representing the following result using a three-dimensional space model defined by the capacity of the secondary battery, the SOC-OCV curve of the secondary battery, and the internal resistance of the secondary battery, and the first feature amount is derived based on the transition of the state of the storage battery in the three-dimensional space model, the result being obtained by applying the storage battery information to the storage battery state detection knowledge model.

Images