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

Abstract

To provide an information processing device, information processing method, and information processing program, which enable reduction in computation cost when estimating the state of a battery.SOLUTION: An information processing device is provided, comprising an acquisition unit for acquiring state information regrading the state of a battery installed in a vehicle, a determination unit for determining whether the acquired state information satisfies predetermined conditions regarding the battery or not, and an output unit for outputting the state information as a battery diagnosis target when the predetermined conditions are satisfied.SELECTED DRAWING: Figure 5

Description

Technical Field

[0001] The present invention relates to an information processing apparatus, an information processing method, and an information processing program for suppressing the amount of data of an object for estimating the state of a battery.

Background Art

[0002] Patent Document 1 discloses a battery system that estimates battery capacity maintenance using an estimation model obtained by performing machine learning with usage patterns related to battery temperature, current, and charge capacity, and measurement values of the capacity degradation rate per unit time of the battery as teacher data.

[0003] Patent Document 2 discloses a remaining life prediction device that predicts the remaining life of a battery to be predicted using a learned model obtained by learning the remaining life of a battery based on learning data including time series data of degradation indicators and remaining life at a predetermined past time point of the battery.

[0004] Patent Document 3 discloses a battery state estimation device that estimates the state of a whole battery pack by simplifying a battery pack including a plurality of battery cells into a single battery cell.

[0005] Patent Document 4 discloses a battery degradation determination device characterized by measuring the AC impedance characteristics of a lithium secondary battery including an electrolyte layer containing a positive electrode, a negative electrode, and a separator, expressing it with a pseudo-electronic equivalent circuit, and determining the generation of dendrites from changes in the resistance value derived from the negative electrode and changes in capacitors.

Prior Art Documents

Patent Documents

[0006]

Patent Document 1

Patent Document 2

Patent Document 3

[0007] Incidentally, in a server that estimates the state of batteries installed in vehicles, collecting state information about the battery status from multiple vehicles can result in a massive amount of data. Therefore, performing a process to determine the battery status from the collected state information can be computationally expensive and may lead to processing delays.

[0008] The present invention aims to provide an information processing device, an information processing method, and an information processing program that can reduce computational costs when estimating the state of a battery. [Means for solving the problem]

[0009] The information processing device according to claim 1 includes an acquisition unit that acquires status information relating to the state of a battery mounted in a vehicle, a determination unit that determines whether the acquired status information satisfies predetermined conditions relating to the battery, and an output unit that outputs the battery as a target for diagnosis if the predetermined conditions are met. The acquisition unit acquires the status information, which includes the number of times the vehicle has been started and turned on, and the time it has been turned on. The determination unit determines that the status information satisfies the predetermined conditions if at least one of the following conditions is met: the number of times the vehicle has been started is equal to or greater than a first threshold, and the time the vehicle has been started is equal to or greater than a second threshold. The first threshold is set to increase as the time the vehicle has been started and turned on in the status information increases, and the second threshold is set to increase as the number of times the vehicle has been started and turned on in the status information increases.

[0010] The information processing device described in claim 1 acquires state information indicating the state of a battery installed in a vehicle, and if the state information satisfies predetermined conditions, it extracts the state information that satisfies those conditions as target data. In other words, according to the information processing device, state information that satisfies predetermined conditions is extracted from the acquired state information as target data. This makes it possible to reduce computational costs when estimating the state of the battery. Furthermore, it is possible to exclude battery status information from the target data when the battery is under low load conditions. Moreover, depending on the degree to which the battery is under low load, battery status information can be excluded from the target data more appropriately.

[0015] The information processing device according to claim 2 includes: an acquisition unit that acquires the lowest voltage output by a battery mounted in the vehicle when the vehicle is started; a determination unit that determines whether the acquired lowest voltage satisfies a predetermined condition that a target indicating the degree of variation in the lowest voltage of the vehicle in the past and present is equal to or greater than a third threshold; and an output unit that, if the predetermined condition is met, outputs the battery as a target for diagnosis. The determination unit, in two consecutive starts of the vehicle, uses the cumulative value obtained by squaring the difference between the minimum voltage currently output by the battery and the minimum voltage output by the battery in the previous start as an index, and uses this cumulative value accumulated over a predetermined number of starts of the vehicle to determine whether the predetermined conditions are met. ru.

[0016] According to the information processing device described in claim 2, state information can be extracted while taking into account the unstable state of the battery, such as the charging capacity and the charging tolerance. Furthermore, it can clearly identify unstable battery conditions and extract status information.

[0023] Claim 4 The information processing method described above is for status information relating to the state of the battery installed in the vehicle. The status information includes the number of times the vehicle was started and turned on, and the duration of the time the vehicle was turned on. The acquired state information is If the number of activations related to the state information is greater than or equal to a first threshold set so that the threshold increases as the activation time included in the state information increases, and if the activation time related to the state information is greater than or equal to a second threshold set so that the threshold increases as the number of activations included in the state information increases, then the state information The battery meets the specified conditions. and The system makes a determination, and if the predetermined conditions are met, it outputs the battery as a target for diagnosis.

[0024] Claim 4 The information processing method described herein acquires status information indicating the state of a battery installed in a vehicle, and if the status information satisfies predetermined conditions, it extracts the status information that satisfies those conditions as target data. In other words, according to this information processing method, status information that satisfies predetermined conditions is extracted from the acquired status information as target data. This makes it possible to reduce computational costs when estimating the state of the battery. Furthermore, it is possible to exclude battery status information from the target data when the battery is under low load conditions. Moreover, depending on the degree to which the battery is under low load, battery status information can be excluded from the target data more appropriately.

[0025] Claim 5 The information processing program described above provides status information regarding the state of the battery installed in the vehicle. The status information includes the number of times the vehicle was started and turned on, and the duration of the time the vehicle was turned on. The acquired state information is If the number of activations related to the state information is greater than or equal to a first threshold set so that the threshold increases as the activation time included in the state information increases, and if the activation time related to the state information is greater than or equal to a second threshold set so that the threshold increases as the number of activations included in the state information increases, then the state information The battery meets the specified conditions. and The computer is instructed to perform a process to determine if the predetermined conditions are met and to output the battery as a target for diagnosis.

[0026] Claim 4 The computer on which the information processing program described in the claim is executed acquires state information indicating the state of a battery mounted on a vehicle, and when the state information satisfies a predetermined condition, extracts, as target data, the state information that satisfies the condition. That is, according to the computer, among the acquired state information, the state information that satisfies a predetermined condition is extracted as target data. Thereby, when estimating the state of the battery, the calculation cost can be suppressed. In addition, the state information of the battery in a situation where a load is less likely to be applied can be excluded from the target data. Further, according to the degree to which a load is less likely to be applied to the battery, the state information of the battery can be more appropriately excluded from the target data. The information processing method described in claim 5 is an information processing method in which a computer performs a process to obtain the lowest voltage output by a battery installed in a vehicle when the vehicle is started, determine whether the obtained lowest voltage satisfies a predetermined condition that an index indicating the degree of variation in the lowest voltage of the vehicle in the past and present is 3rd threshold or higher, and if the predetermined condition is met, output the battery as a target for diagnosis, wherein the determination process uses, for two consecutive starts of the vehicle, the cumulative value obtained by squaring the difference between the lowest voltage currently output by the battery and the lowest voltage output by the battery in the previous start, accumulated over a predetermined number of starts of the vehicle, as the index to determine whether the predetermined condition is met. According to the information processing method described in claim 5, state information can be extracted while taking into account the unstable state of the battery, such as the charging capacity and the charging tolerance. Furthermore, state information can be extracted while clearly identifying the unstable state of the battery. The information processing program described in claim 6 is an information processing program that causes a computer to execute a process to obtain the lowest voltage output by the battery installed in the vehicle when the vehicle is started, determine whether the obtained lowest voltage satisfies a predetermined condition that an index indicating the degree of variation in the lowest voltage of the vehicle in the past and present is 3rd threshold or higher, and if the predetermined condition is met, output the battery as a target for diagnosis, wherein the determination process uses the cumulative value obtained by squaring the difference between the lowest voltage currently output by the battery and the lowest voltage output by the battery in the previous instance during two consecutive starts of the vehicle, and accumulating this difference value over a predetermined number of starts of the vehicle, as the index to determine whether the predetermined condition is met. According to the computer on which the information processing program described in claim 6 is executed, state information can be extracted while taking into account the unstable state of the battery, such as the charging capacity and the charging tolerance. Furthermore, state information can be extracted while clearly identifying the unstable state of the battery.

Advantages of the Invention

[0027] According to the present invention, when estimating the state of a battery, the calculation cost can be suppressed.

Brief Description of the Drawings

[0028] [Figure 1] It is a diagram showing a schematic configuration of an information processing system according to each embodiment. [Figure 2] It is a block diagram showing a hardware configuration of a vehicle according to each embodiment. [Figure 3] It is a block diagram showing a functional configuration of an in-vehicle device according to each embodiment. [Figure 4] It is a block diagram showing a hardware configuration of a center server according to each embodiment. [Figure 5] It is a block diagram showing a functional configuration of a center server according to the first embodiment. [Figure 6] It is a graph showing the relationship between the startup time and the startup count for explaining the threshold according to each embodiment. [Figure 7]This flowchart shows the process flow for extracting target information, which is performed in the center server of the first embodiment. [Figure 8] This is a block diagram showing the functional configuration of the center server in the second embodiment. [Figure 9] This flowchart shows the process flow for extracting target information, which is performed in the center server of the second embodiment. [Figure 10] This is a block diagram showing the functional configuration of the center server in the third embodiment. [Figure 11] This flowchart shows the process flow for extracting target information, which is performed in the center server of the third embodiment. [Figure 12] This flowchart shows the process flow for generating a trained model, which is executed in the center server of the third embodiment. [Modes for carrying out the invention]

[0029] [First Embodiment] This section describes an information processing system including the information processing device of the present invention. The information processing system is a system that extracts target data for diagnosing the state of a battery installed in a vehicle using information about the state of the battery installed in the vehicle (hereinafter referred to as "state information") obtained from an in-vehicle device installed in the vehicle. In this embodiment, the vehicle described is an engine-powered vehicle equipped with an engine. However, it is not limited to this. The vehicle may be an electric vehicle (EV), a hybrid electric vehicle (HEV), or a fuel cell vehicle (FCV).

[0030] (Overall structure) As shown in Figure 1, the information processing system 10 of the embodiment of the present invention comprises a vehicle 12 and a center server 30 as an information processing device. The vehicle 12 is also equipped with an on-board unit 20, which is connected to the center server 30 via a network N.

[0031] Although Figure 1 shows one vehicle 12 including an in-vehicle unit 20 connected to one center server 30, the number of vehicles 12, in-vehicle units 20, and center servers 30 is not limited to this.

[0032] The in-vehicle unit 20 is a device that acquires status information related to the vehicle 12 and transmits it to the center server 30. Here, the status information according to this embodiment is data related to the battery status detected from each device installed in the vehicle 12. For example, the status information according to this embodiment is data including the number of times the ignition was turned on in order to start the engine using the battery (hereinafter referred to as "start count"), the duration from when the ignition was turned on to when it was turned off (hereinafter referred to as "start time"), and the minimum voltage output by the battery.

[0033] The center server 30 is installed, for example, at the manufacturer that produces the vehicle 12 or at a car dealer affiliated with that manufacturer. The center server 30 acquires status information from the in-vehicle device 20 and extracts target data for diagnosing the battery status from the acquired status information. The extracted target data may be transmitted to an external device that diagnoses the battery status, or it may be stored as target data.

[0034] (vehicle) As shown in Figure 2, the vehicle 12 according to this embodiment is configured to include an on-board unit 20, a plurality of on-board devices 22, and a battery 24.

[0035] The in-vehicle unit 20 consists of a CPU (Central Processing Unit) 20A, ROM (Read Only Memory) 20B, RAM (Random Access Memory) 20C, input / output interface (I / F) 20D, and wireless communication interface (I / F) 20E. The CPU 20A, ROM 20B, RAM 20C, I / O interface 20D, and wireless communication interface 20E are interconnected via an internal bus 20G so that they can communicate with each other.

[0036] The CPU20A is the central processing unit, which executes various programs and controls various components. Specifically, the CPU20A reads programs from the ROM20B and executes them using the RAM20C as its working area.

[0037] ROM20B stores various programs and data. In this embodiment, ROM20B stores a collection program 100 that collects status information of the vehicle 12 from the in-vehicle device 22. Upon execution of the collection program 100, the in-vehicle device 20 performs a process to transmit the status information to the center server 30. RAM20C temporarily stores programs or data as a work area.

[0038] The input / output interface 20D is an interface for communicating with the in-vehicle equipment 22. The input / output interface 20D is connected to the ignition switch 22A and the voltage sensor 22B as part of the in-vehicle equipment 22. The ignition switch 22A outputs a signal indicating that it has been turned ON in order to start the engine. The voltage sensor 22B detects the voltage output by the battery 24 when the engine is started and outputs a signal indicating the voltage value to the in-vehicle unit 20 as a result of the detection.

[0039] The wireless communication interface (I / F20E) is a wireless communication module for communicating with the center server (30). This wireless communication module utilizes communication standards such as 5G, LTE, and Wi-Fi (registered trademark). The wireless communication interface (I / F20E) is connected to network N.

[0040] As shown in Figure 3, in the in-vehicle device 20 of this embodiment, the CPU 20A functions as the collection unit 200 and the output unit 210 by executing the collection program 100.

[0041] The data collection unit 200 has the function of collecting status information output from each on-board device 22 of the vehicle 12. Here, the data collection unit 200 collects the number of starts, the start time, and the minimum voltage when the engine is started as status information.

[0042] The output unit 210 has the function of outputting the status information collected by the collection unit 200 to the center server 30 using the wireless communication interface 20E.

[0043] (Central Server) As shown in Figure 4, the center server 30 is configured to include a CPU 30A, ROM 30B, RAM 30C, storage 30D, and communication I / F 30E. The CPU 30A, ROM 30B, RAM 30C, storage 30D, and communication I / F 30E are interconnected via an internal bus 30F so that they can communicate with each other. The functions of the CPU 30A, ROM 30B, RAM 30C, and communication I / F 30E are the same as those of the CPU 20A, ROM 20B, RAM 20C, and wireless communication I / F 20E of the in-vehicle unit 20 described above. Note that the communication I / F 30E may also perform wired communication.

[0044] The storage device 30D, which serves as the recording medium, is composed of an HDD (Hard Disk Drive) or an SSD (Solid State Drive) and stores various programs and data. In this embodiment, the storage device 30D stores an information processing program 120 and a state information database (hereinafter referred to as "state information DB") 130. Alternatively, the ROM 30B may store the information processing program 120 and the state information DB 130.

[0045] The information processing program 120 is a program for controlling the center server 30. Upon execution of the information processing program 120, the center server 30 executes various processes, including the process of acquiring status information and the process of extracting target data from the status information.

[0046] The status information DB130 stores status information received from the in-vehicle unit 20, as well as the extracted target data.

[0047] As shown in Figure 5, in the center server 30 of this embodiment, the CPU 30A functions as an acquisition unit 300, a setting unit 310, a determination unit 320A, an output unit 330, and a storage unit 340A by executing the information processing program 120.

[0048] The acquisition unit 300 has the function of acquiring status information transmitted from the on-board unit 20 of the vehicle 12. In this embodiment, the acquisition unit 300 acquires status information including the number of starts, the start time, and the minimum voltage when the engine is started.

[0049] The setting unit 310 uses the status information to set a threshold for the number of startups (hereinafter referred to as the "threshold related to the number of startups") and a threshold for the startup time (hereinafter referred to as the "threshold related to the time"). Here, the threshold related to the number of startups is an example of the "first threshold," and the threshold related to the time is an example of the "second threshold."

[0050] Figure 6, shown here as an example, is a graph illustrating the relationship between the average number of monthly startups and the average monthly startup time for a battery.

[0051] As an example, as shown in Figure 6, the setting unit 310 sets thresholds for the number of startups and the startup time included in the status information, based on the status information of a degraded battery acquired in the past. Here, the setting unit 310 sets a higher threshold 400 for the number of startups as the startup time included in the status information increases, and sets a higher threshold 410 for the time as the number of startups included in the status information increases.

[0052] The setting unit 310 sets a threshold 400 related to the number of startups to be larger depending on the length of the startup time, and sets a threshold 410 related to time to be larger depending on the length of the number of startups, thereby excluding state information when the battery 24 is in a low state of degradation from the target data. In other words, as shown in Figure 6, even if the number of startups included in the state information is small, if the startup time is long, the state information is excluded from the target data as the battery 24 is considered to be in a low state of degradation. Similarly, even if the startup time included in the state information is small, if the number of startups is large, the state information is excluded from the target data as the battery 24 is considered to be in a low state of degradation.

[0053] The determination unit 320A compares the number of startups and startup time included in the status information with the threshold 400 for the number of startups and the threshold 410 for the time set by the setting unit 310 to determine whether predetermined conditions are met. For example, the determination unit 320A determines whether the number of startups included in the status information is equal to or greater than the threshold 400 for the number of startups, and if it is equal to or greater than the threshold 400 for the number of startups, it determines that predetermined conditions are met. The determination unit 320A also determines whether the startup time included in the status information is equal to or greater than the threshold 410 for the time, and if it is equal to or greater than the threshold 410 for the time, it determines that predetermined conditions are met.

[0054] The output unit 330 outputs status information as target data if the determination unit 320A determines that predetermined conditions have been met.

[0055] The memory unit 340A stores the state information output as target data and the acquired state information, respectively.

[0056] (Control flow) The flow of each process performed in the information processing system 10 of this embodiment will be explained using the flowchart in Figure 7. Each process in the center server 30 is performed by the CPU 30A of the center server 30, which functions as an acquisition unit 300, a setting unit 310, a determination unit 320A, an output unit 330, and a storage unit 340A. The process for extracting state information shown in Figure 7 is executed, for example, when an instruction to extract state information is input.

[0057] In step S100, the CPU 30A acquires status information related to the vehicle 12, including the number of times it is started per month and the time it is started per month.

[0058] In step S101, the CPU 30A uses the state information to set a threshold 400 related to the number of times and a threshold 410 related to time.

[0059] In step S102, CPU 30A determines whether the number of startups included in the state information is 400 or more, which is the threshold for the number of startups. If the number of startups is 400 or more, which is the threshold for the number of startups (step S102: YES), CPU 30A proceeds to step S103. On the other hand, if the number of startups is not 400 or more, which is the threshold for the number of startups (the number of startups is less than 400), which is the threshold for the number of startups (step S102: NO), CPU 30A proceeds to step S106.

[0060] In step S103, CPU 30A determines whether the startup time included in the state information is greater than or equal to the time threshold of 410. If the startup time is greater than or equal to the time threshold of 410 (step S103: YES), CPU 30A proceeds to step S104. On the other hand, if the startup time is not greater than or equal to the time threshold of 410 (the startup time is less than the time threshold of 410) (step S103: NO), CPU 30A proceeds to step S106.

[0061] In step S104, the CPU 30A outputs status information as target data.

[0062] In step S105, the CPU 30A stores the state information output as the target data.

[0063] In step S106, the CPU 30A stores the acquired state information.

[0064] In step S107, the CPU 30A determines whether or not to terminate the process of extracting state information. If the process of extracting state information is terminated (step S107: YES), the CPU 30A terminates the process of extracting state information. On the other hand, if the process of extracting state information is not terminated (step S107: NO), the CPU 30A proceeds to step S100 and obtains the state information.

[0065] (Summary of the first embodiment) The center server 30, which serves as the information processing device in this embodiment, acquires status information including the number of times the vehicle 12 is started each month and the time it is started each month. Using this status information, it sets a threshold 400 for the number of starts and a threshold 410 for the time it is started. If the number of starts included in the status information is equal to or greater than the threshold 400 for the number of starts, and the time it is started is equal to or greater than the threshold 410 for the time it is started, it outputs and stores this status information as target data.

[0066] As described above, according to this embodiment, the computational cost can be reduced when estimating the battery state.

[0067] In the above embodiment, a configuration was described in which the state information is output as target data when the conditions are met that the number of startups is 400 or more (a threshold related to the number of startups) and the startup time is 410 or more (a threshold related to the time). However, the embodiment is not limited to this. For example, the state information may be output as target data only if the number of startups is 400 or more (a threshold related to the number of startups). Alternatively, the state information may be output as target data only if the startup time is 410 or more (a threshold related to the time).

[0068] Furthermore, in this embodiment, the threshold 400 related to the number of times and the threshold 410 related to time have been described as being linear. However, the embodiment is not limited to this. The threshold 400 related to the number of times and the threshold 410 related to time may be nonlinear, or any threshold value may be used as long as the threshold value increases in relation to the number of activations and the activation time.

[0069] Furthermore, in this embodiment, a configuration was described in which thresholds are set according to the number of startups and startup time included in the state information. However, the embodiment is not limited to this. Thresholds may be set for each vehicle type.

[0070] [Second Embodiment] In the first embodiment, a method for extracting state information using the number of startups and startup time included in the state information was described. In the second embodiment, a method for extracting state information using the minimum voltage included in the state information will be described.

[0071] Note that the configuration of the information processing system according to this embodiment (see Figure 1), an example of the hardware configuration of the vehicle 12 (see Figure 2), an example of the functional configuration of the in-vehicle unit 20 (see Figure 3), an example of the hardware configuration of the center server 30 (see Figure 4), and a graph showing thresholds (see Figure 6) are the same as in the first embodiment, and therefore their explanation is omitted. The differences from the first embodiment will be explained below. Also, the same reference numerals are used for the same components, and their explanation is omitted.

[0072] As shown in Figure 8, in the center server 30 of this embodiment, the CPU 30A functions as an acquisition unit 300, a derivation unit 350, a determination unit 320B, an output unit 330, and a storage unit 340A by executing the information processing program 120.

[0073] The derivation unit 350 uses the minimum voltage of the battery 24 included in the acquired state information to derive an index (hereinafter referred to as the "index") that indicates the degree of variation in the minimum voltage. For example, in two consecutive starts of the vehicle 12 (engine start and motor start, etc.), the derivation unit 350 derives a squared difference value by squaring the difference between the minimum voltage actually output by the battery 24 and the minimum voltage output in the previous instance, and derives a cumulative value as the index by accumulating the squared difference values ​​for the last five times from the present.

[0074] Here, as the battery 24 deteriorates, its charging capacity and charging tolerance decrease, and the output voltage becomes unstable. Therefore, when comparing the minimum voltage output by the battery 24 during two consecutive starts of the vehicle 12, the difference in minimum voltage becomes larger for a deteriorated battery 24. Also, since the difference in minimum voltage may be large by chance, in this embodiment, the degree of variation in minimum voltage is determined by using a cumulative value obtained by accumulating multiple difference values, thereby determining the state information while taking into account the inclusion of accidental data.

[0075] In this embodiment, we have described a method of accumulating the difference values ​​of the most recent five measurements. However, we are not limited to this. We may use the most recent three measurements, the most recent seven measurements, or any number of times we may accumulate the squared difference values. Furthermore, in this embodiment, we have described a method of deriving the squared difference value by squaring the difference values. However, we are not limited to this. For example, we may derive the absolute value of the difference value, or we may derive the mean squared error by squaring the difference value between the average value of past lowest voltages and the acquired lowest voltage, or we may derive the variance of the lowest voltage, or we may derive any value as long as the value to be derived is a positive number.

[0076] The determination unit 320B compares the derived cumulative value with a predetermined threshold to determine whether a predetermined condition is met. For example, the determination unit 320B determines whether the cumulative value is equal to or greater than a predetermined threshold (for example, whether the cumulative value is 5 or greater), and if the cumulative value is equal to or greater than the predetermined threshold, it determines that the predetermined condition is met. Here, the predetermined threshold is an example of a "third threshold".

[0077] (Control flow) The flow of each process performed in the information processing system 10 of this embodiment will be explained using the flowchart in Figure 9. Each process in the center server 30 is performed by the CPU 30A of the center server 30 functioning as an acquisition unit 300, a derivation unit 350, a determination unit 320B, an output unit 330, and a storage unit 340A. The process for extracting state information shown in Figure 9 is executed, for example, when an instruction to extract state information is input. In Figure 9, steps that are the same as those in the extraction process shown in Figure 7 are denoted by the same reference numerals as in Figure 7, and their explanation is omitted.

[0078] In step S108, the CPU 30A uses the lowest voltage included in the acquired state information to derive the squared difference of the lowest voltages related to the startup of the vehicle 12 for two consecutive times, and derives a cumulative value by accumulating the squared difference of the most recent five times.

[0079] In step S109, the CPU 30A determines whether the derived cumulative value is greater than or equal to a predetermined threshold. If the cumulative value is greater than or equal to the predetermined threshold (step S109: YES), the CPU 30A proceeds to step S104. On the other hand, if the cumulative value is not greater than or equal to the predetermined threshold (the cumulative value is less than the predetermined threshold) (step S109: NO), the CPU 30A proceeds to step S106.

[0080] (Summary of the second embodiment) In this embodiment, the center server 30, which serves as an information processing device, acquires the minimum voltage of the battery 24 of the vehicle 12 on a monthly basis as status information. Using this status information, it derives a cumulative value related to the minimum voltage as an indicator. If the cumulative value is equal to or greater than a predetermined threshold, it outputs and stores the status information as target data.

[0081] As described above, according to this embodiment, state information can be extracted while taking into account the unstable state of the battery.

[0082] In this embodiment, we have described a method for estimating the battery state using only the degree of variation in the minimum voltage as an indicator. However, we are not limited to this. For example, the battery state may be estimated using multiple combinations of the startup time and number of startups according to the first embodiment and the indicator according to the second embodiment.

[0083] [Third Embodiment] In the second embodiment, a method for extracting state information using an index derived from acquired state information was described. In the third embodiment, a method for extracting state information using a trained model on which machine learning has been performed for state information extraction will be described.

[0084] Note that the configuration of the information processing system according to this embodiment (see Figure 1), an example of the hardware configuration of the vehicle 12 (see Figure 2), an example of the functional configuration of the in-vehicle unit 20 (see Figure 3), an example of the hardware configuration of the center server 30 (see Figure 4), and a graph showing thresholds (see Figure 6) are the same as in the first embodiment, and therefore their explanation is omitted. The differences from the first embodiment will be explained below. Also, the same reference numerals are used for the same components, and their explanation is omitted.

[0085] As shown in Figure 10, in the center server 30 of this embodiment, the CPU 30A functions as an acquisition unit 300, a determination unit 320C, an output unit 330, a storage unit 340B, and a generation unit 360 by executing the information processing program 120.

[0086] The determination unit 320C extracts the target state information using a trained model that has undergone machine learning to extract state information. For example, the trained model is a classification model that has undergone machine learning to classify whether the state information corresponds to the target data, using state information including the number of startups, startup time, and minimum voltage acquired in the past as training data, and whether the state information is suitable as target data.

[0087] The determination unit 320C inputs the acquired state information into the trained model and determines whether the state information satisfies predetermined conditions based on the trained model's determination of whether the target data is correct or not. For example, if the trained model determines that the input state information corresponds to the target data, the determination unit 320C determines that the predetermined conditions have been met.

[0088] In this embodiment, the trained model has been described in the form of a classification model. However, it is not limited to this. The trained model may be a regression model or a neural network model. For example, a trained model as a regression model may derive a threshold 400 related to the number of repetitions and a threshold 410 related to time, and determine whether the state information satisfies predetermined conditions. Alternatively, a trained model as a neural network model may derive a cumulative value related to the minimum voltage as an index, and determine whether the cumulative value satisfies predetermined conditions.

[0089] The memory unit 340B stores the state information as target data and the acquired state information. Furthermore, the memory unit 340B stores the trained model generated by the generation unit 360, which will be described later. Here, the memory unit 340B stores the validity of the target data determined for the state information, associating it with the state information.

[0090] The generation unit 360 performs machine learning using previously acquired state information to generate a trained model.

[0091] (Control flow) The flow of each process performed in the information processing system 10 of this embodiment will be explained using the flowchart in Figure 11. Each process in the center server 30 is performed by the CPU 30A of the center server 30 functioning as an acquisition unit 300, a determination unit 320C, an output unit 330, a storage unit 340B, and a generation unit 360. The process for extracting state information shown in Figure 11 is executed, for example, when an instruction to extract state information is input. In Figure 11, steps that are the same as those in the extraction process shown in Figure 7 are denoted by the same reference numerals as in Figure 7, and their explanation is omitted.

[0092] In step S110, the CPU 30A determines whether the state information input to the trained model corresponds to the target data. If the state information corresponds to the target data (step S110: YES), the CPU 30A proceeds to step S104. On the other hand, if the state information does not correspond to the target data (the state information is different from the target data) (step S110: NO), the CPU 30A proceeds to step S106.

[0093] Next, the process of generating a trained model, which is performed in the information processing system 10 of this embodiment, will be explained using the flowchart in Figure 12. The generation process shown in Figure 12 is executed, for example, when an instruction to perform the process of generating a trained model is input.

[0094] In step S200, the CPU 30A acquires state information, including the number of startups, startup time, and minimum voltage acquired in the past, as learning data, and whether the target data corresponding to the acquired state information is correct or incorrect.

[0095] In step S201, CPU30A uses the acquired training data to perform machine learning and generate a trained model.

[0096] In step S202, the CPU 30A inputs state information into the generated trained model and evaluates the trained model using the validity of the target data output from the trained model.

[0097] In step S203, CPU 30A determines whether or not to terminate the process of generating the trained model. If the process of generating the trained model is terminated (step S203: YES), the process proceeds to step S204. On the other hand, if the process of generating the trained model is not terminated (step S203: NO), CPU 30A proceeds to step S200 to acquire the training data.

[0098] In step S204, the CPU 30A stores the generated trained model.

[0099] (Summary of the third embodiment) In this embodiment, the center server 30, which serves as an information processing device, extracts state information using a trained model.

[0100] As described above, according to this embodiment, it is possible to extract state information by reflecting state information acquired in the past.

[0101] [remarks] In addition, the various processes that CPU 20A and CPU 30A read and execute software (programs) in the above embodiment may be executed by various processors other than the CPUs. Examples of such processors include PLDs (Programmable Logic Devices) such as FPGAs (Field-Programmable Gate Arrays) whose circuit configuration can be changed after manufacturing, and dedicated electrical circuits that are processors with circuit configurations specifically designed to execute specific processes, such as ASICs (Application Specific Integrated Circuits). Furthermore, each of the above processes may be executed by one of these various processors, or by a combination of two or more processors of the same or different types (for example, multiple FPGAs, and a combination of a CPU and an FPGA). More specifically, the hardware structure of these various processors is an electrical circuit that combines circuit elements such as semiconductor elements.

[0102] Furthermore, in the above embodiment, each program was described as being pre-stored (installed) on a computer-readable non-temporary recording medium. For example, the data collection program 100 in the in-vehicle unit 20 is pre-stored in ROM 20B, and the information processing program 120 in the center server 30 is pre-stored in storage 30D. However, the program is not limited to this, and each program may be provided in a form recorded on a non-temporary recording medium such as a CD-ROM (Compact Disc Read Only Memory), DVD-ROM (Digital Versatile Disc Read Only Memory), and USB (Universal Serial Bus) memory. Alternatively, the program may be downloaded from an external device via a network.

[0103] The processing flow described in the above embodiment is just one example, and unnecessary steps may be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose. [Explanation of symbols]

[0104] 12 vehicles 30. Center Server (Information Processing Unit) 300 Acquisition Department 320A, 320B, 320C judgment section 330 Output section

Claims

1. A unit that acquires status information regarding the state of the battery installed in the vehicle, A determination unit that determines whether the acquired state information satisfies predetermined conditions related to the battery, The system includes an output unit that outputs a battery as a target for diagnosis when the aforementioned predetermined conditions are met, The acquisition unit acquires the status information, including the number of times the vehicle has been started and turned on, and the time the vehicle has been turned on. The determination unit determines that the state information satisfies the predetermined conditions if at least one of the following conditions is met: the number of activations related to the state information is equal to or greater than a first threshold, and the activation time related to the state information is equal to or greater than a second threshold. The first threshold is set to increase as the activation time included in the state information increases, and the second threshold is set to increase as the number of activations included in the state information increases. Information processing device.

2. An acquisition unit that acquires the lowest voltage output by the battery installed in the vehicle when the vehicle is started, A determination unit that determines whether the acquired minimum voltage satisfies a predetermined condition that an index indicating the degree of variation in the minimum voltage of the vehicle in the past and present is equal to or greater than a third threshold, The system includes an output unit that outputs a battery as a target for diagnosis when the aforementioned predetermined conditions are met, The determination unit, in two consecutive starts of the vehicle, uses the cumulative value obtained by squaring the difference between the minimum voltage currently output by the battery and the minimum voltage output by the battery in the previous start as an index, and uses this cumulative value accumulated over a predetermined number of starts of the vehicle to determine whether the predetermined conditions are met. Information processing device.

3. Status information relating to the state of the battery installed in the vehicle, including the number of times the vehicle was started and turned on, and the duration of the time the vehicle was turned on, is acquired. If the acquired state information satisfies at least one of the following conditions: the number of activations related to the state information is greater than or equal to a first threshold set such that the threshold increases as the activation time included in the state information increases; and the activation time related to the state information is greater than or equal to a second threshold set such that the threshold increases as the number of activations included in the state information increases, then it is determined that the state information satisfies a predetermined condition related to the battery. If the above predetermined conditions are met, the battery will be output as a target for diagnosis. An information processing method in which a computer performs the processing.

4. Status information relating to the state of the battery installed in the vehicle, including the number of times the vehicle was started and turned on, and the duration of the time the vehicle was turned on, is acquired. If the acquired state information satisfies at least one of the following conditions: the number of activations related to the state information is greater than or equal to a first threshold set such that the threshold increases as the activation time included in the state information increases; and the activation time related to the state information is greater than or equal to a second threshold set such that the threshold increases as the number of activations included in the state information increases, then it is determined that the state information satisfies a predetermined condition related to the battery. If the above predetermined conditions are met, the battery will be output as a target for diagnosis. An information processing program that causes a computer to perform a task.

5. When the vehicle is started, the lowest voltage output by the battery installed in the vehicle is obtained. It is determined whether the acquired minimum voltage satisfies a predetermined condition that the index indicating the degree of variation in the minimum voltage of the vehicle in the past and present is equal to or greater than a third threshold. If the above predetermined conditions are met, the battery will be output as a target for diagnosis. An information processing method in which a computer performs the processing, The determination process involves, for two consecutive starts of the vehicle, squaring the difference between the minimum voltage currently output by the battery and the minimum voltage output by the battery in the previous start, deriving the difference value, and using the accumulated value accumulated over a predetermined number of starts of the vehicle as the index to determine whether the predetermined conditions are met. Information processing methods.

6. When the vehicle is started, the lowest voltage output by the battery installed in the vehicle is obtained. It is determined whether the acquired minimum voltage satisfies a predetermined condition that the index indicating the degree of variation in the minimum voltage of the vehicle in the past and present is equal to or greater than a third threshold. If the above predetermined conditions are met, the battery will be output as a target for diagnosis. An information processing program that causes a computer to perform a process, The determination process involves, for two consecutive starts of the vehicle, squaring the difference between the minimum voltage currently output by the battery and the minimum voltage output by the battery in the previous start, deriving the difference value, and using the accumulated value accumulated over a predetermined number of starts of the vehicle as the index to determine whether the predetermined conditions are met. Information processing program.

Images