Battery information processing method, battery information processing device, battery information processing system, and computer program

Abstract

To provide a battery information processing method, a battery information processing device, a battery information processing system, and a computer program for promoting inspection of a battery based on collected performance data.SOLUTION: In a battery information processing system 100, an information processing device 1 includes: an acquisition unit for acquiring weather information for a prediction target period; a prediction unit for predicting possibility of a dead battery occurring during the prediction target period based on the acquired weather information; and an output unit for outputting information of the predicted possibility that the dead battery occurs.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a battery information processing method, a battery information processing device, a battery information processing system, and a computer program that promote inspection and replacement based on inspection performance data for vehicle batteries. [Background technology]

[0002] Batteries installed in vehicles can be inspected, replaced, purchased, etc. not only at dealers that inspect the entire vehicle, but also at service providers such as fuel supply facilities, inspection service providers, and auto parts retailers that sell consumables.

[0003] Rescue services are provided in the event of vehicle trouble. Problems include dead batteries, flat tires, and wheels falling off the vehicle, with dead batteries remaining the most common problem even in recent years. To prevent dead batteries, regular inspections and replacement as they deteriorate are recommended, but it is not easy to motivate users to inspect their batteries unless a problem or a symptom of a problem occurs.

[0004] Patent Document 1 discloses that a device installed in a maintenance facility of a maintenance business stores information on the maintenance of each part of a vehicle, including the battery, in association with user identification data based on input from an operator of the maintenance business. The system disclosed in Patent Document 1 outputs a message to the user's user terminal urging replacement or inspection based on the maintenance history. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2005-004239 Summary of the Invention [Problem to be solved by the invention]

[0006] Regarding battery inspections, battery retailers may empirically predict the timing and circumstances in which battery failures will increase. However, due to the difficulty in accumulating inspection records, promotional activities for inspections and replacements in preparation for battery failures have been carried out individually by dealers, inspection service providers, etc.

[0007] The present invention has been made in consideration of the above circumstances, and aims to provide a battery information processing method, a battery information processing device, a battery information processing system, and a computer program that can promote battery inspections based on collected performance data. [Means for solving the problem]

[0008] In one embodiment of the information processing method of the present disclosure, a computer acquires weather information for a prediction period, predicts the possibility of a battery running out during the prediction period based on the acquired weather information, and outputs information regarding the predicted battery running out. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a schematic diagram of a battery information processing system according to a first embodiment. [Figure 2] FIG. 2 is a block diagram showing the internal configuration of an information processing device and an information terminal device. [Figure 3] 10 is a flowchart illustrating an example of a procedure for collecting measurement results. [Figure 4] FIG. 10 is an explanatory diagram of collected measurement result data. [Figure 5] 10 is a flowchart illustrating an example of an analysis process procedure for measurement results. [Figure 6] 10 is a flowchart illustrating an example of a prediction processing procedure. [Figure 7] 10 is a flowchart showing an example of a procedure for outputting the occurrence rate of a battery requiring attention or inspection. [Figure 8] FIG. 10 is a diagram showing an example of a display of predicted values ​​of the occurrence rate of battery warnings and replacements. [Figure 9] FIG. 10 is a diagram showing an example of a display of predicted values ​​of the occurrence rate of battery warnings and replacements. [Figure 10] FIG. 10 is a block diagram showing the configuration of an information processing device according to a second embodiment. [Figure 11] This is an overview of the trained model that outputs the occurrence rate of attention and replacement required. [Figure 12] 1 is a flowchart illustrating an example of a procedure for creating a trained model. [Figure 13] 10 is a flowchart illustrating an example of a prediction processing procedure using a trained model. [Figure 14] FIG. 10 is a schematic diagram of a battery information processing system according to a third embodiment. [Figure 15] FIG. 2 is a block diagram showing the configuration of a user terminal device. [Figure 16] FIG. 10 is a diagram showing an example of the contents of data relating to battery use. [Figure 17] 13 is a flowchart showing an example of a procedure for a process of presenting information to a user in the third embodiment. [Figure 18] FIG. 10 is an explanatory diagram showing an example of a screen displayed on a user terminal device. [Figure 19] FIG. 10 is an explanatory diagram showing an example of a screen displayed on a user terminal device. DETAILED DESCRIPTION OF THE INVENTION

[0010] In one embodiment of the battery information processing method of the present disclosure, a computer acquires weather information for a prediction period, predicts the possibility of a battery running out during the prediction period based on the acquired weather information, and outputs information regarding the predicted battery running out.

[0011] With the above configuration, a forecast of the possibility of a dead battery is output based on weather information. The prediction method may be a method based on the correlation between weather information and the possibility of a dead battery, as described below, or a method based on a table showing the correspondence between weather information and the possibility of a dead battery.

[0012] In the battery information processing method, the computer predicts the possibility of a dead battery occurring during the prediction period based on the acquired weather information for the prediction period, based on the correlation between past inspection results for different batteries and weather information for a unit period in which inspections were performed on the different batteries.

[0013] With the above configuration, the possibility of a dead battery occurring during the prediction period is predicted. It has been empirically predicted that there is a correlation between the likelihood of a dead battery occurring and weather information. Since it is now possible to collect inspection results using a tester, the correlation between the collected inspection results and the weather information at the location where the inspection was conducted can be determined in advance. With the above configuration, if predicted weather information for the prediction period can be obtained, the inspection results can be predicted based on the correlation, and this makes it possible to predict the possibility of a dead battery occurring. A battery that has deteriorated to the point where an inspection determines that it needs to be replaced is more likely to die, and the possibility of a dead battery occurring can be predicted from the inspection results.

[0014] It is possible to predict the possibility of a dead battery, and the information processing device can then output the prediction information to a display device or paper medium. The output prediction information makes it possible to grasp, like a weather forecast, the likelihood of a dead battery occurring and the likelihood of a battery needing replacement. Staff at facilities that perform battery replacements, or sales representatives, can determine that they should increase the number of inspections and take proactive measures to prevent dead batteries from occurring.

[0015] If the forecast period is not a short-term period such as the current day or the next day, but a medium- to long-term period such as one week, one month, or six months from now, it will also be possible to adjust battery inventory at facilities that perform battery replacement based on the forecast.Predictions of the possibility of a dead battery occurring based on weather information, i.e., predictions of the percentage of cases where replacement is deemed necessary, may be used to forecast battery demand.

[0016] In the battery information processing method, a parameter specifying a correlation between the proportion of past inspections in which the inspection results are determined to be other than good and the weather information for a unit period in which the inspection results were performed may be calculated by regression analysis.The parameter specifying the calculated correlation may be used to calculate the proportion of batteries that are determined to be other than good when inspected based on the weather information for the prediction period.The possibility of a dead battery occurring can be predicted based on a comparison between the calculated proportion and a threshold value.

[0017] With the above configuration, if there is a high correlation between the weather information and the inspection results, it is possible to estimate the proportion of batteries that will be judged as being other than good based on the weather information using a parameter that specifies the correlation obtained by regression analysis. Batteries that are judged as being other than good are more likely to die than batteries that are judged as being good.

[0018] In the battery information processing method, the computer may acquire weather information for different regions, predict the possibility of a dead battery occurring based on the correlation between the inspection results and the weather information from the acquired weather information for each different region, and output information on the possibility of a dead battery occurring by region.

[0019] With the above configuration, the possibility of a dead battery occurring is predicted for each area using different weather information for each area, and the prediction is output for each area. By outputting the possibility of a dead battery occurring for each area, it becomes possible to grasp the distribution of areas where a battery replacement is required and other areas.

[0020] In the battery information processing method, the computer may calculate the correlation between past inspection results for different batteries and weather information for a unit period in which the inspections were performed for the different batteries, for each region in which the inspections were performed, and may predict the possibility of a dead battery occurring based on the correlation for each region from the weather information obtained for each different region.

[0021] With the above configuration, the correlation between the past inspection results for different batteries and the weather information for the unit period during which the inspections were carried out for the different batteries is calculated for each area, and used for each region. It is expected that accuracy can be maintained even when the correlation between the weather and the possibility of a dead battery differs from area to area.

[0022] The correlation may be determined not only by region but also by season.

[0023] In the battery information processing method, the computer may obtain, as a learning model, a correlation between past inspection results for different batteries and weather information for a unit period in which the different batteries were inspected. In this case, when weather information for a prediction period is input to the learning model, the computer predicts the possibility of a dead battery occurring during the prediction period from a predicted value output from the learning model of the proportion of batteries that are judged to be other than good when inspected.

[0024] With the above configuration, in cases where the correlation between weather information and battery inspection results is not high unless other data such as humidity is also taken into consideration in addition to one piece of data, for example, temperature data, the correlation can be identified using a learning model that can identify relationships based on multiple variables.

[0025] In the battery information processing method, the learning model may be trained using training data that includes the weather information as input data and the percentage of inspection results that were determined to be other than good, relative to the number of past inspections under the weather conditions indicated by the weather information, as output data.

[0026] With the above configuration, when weather information is input, the learning model is trained to output the percentage of batteries that are judged to be other than good when inspected under the weather conditions indicated by the weather information, i.e., the likelihood that they will be judged to need replacement. Batteries that are likely to be judged to need replacement are more likely to die.

[0027] In the battery information processing method, the computer may learn the learning model for each different region. In this case, the computer acquires weather information for each different region, inputs the acquired weather information for each different region into the learning model, predicts the possibility of a dead battery for each region, and outputs the predicted possibility of a dead battery for each different region.

[0028] With the above configuration, a trained model that learns the correlation between past inspection results for different batteries and meteorological information for a unit period during which the inspections were performed for the different batteries is created for each region and used for each area. It is expected that accuracy can be maintained even when the correlation between weather and the possibility of a dead battery differs from region to region.

[0029] In the battery information processing method, the computer may display characters with different colors, patterns, shades, animations, or expressions on a map including different areas depending on the predicted possibility of a dead battery occurring.

[0030] With the above configuration, the possibility of a dead battery can be visually grasped in a weather forecast-like manner.

[0031] In the battery information processing method, the weather information may include at least one of minimum temperature, maximum temperature, average temperature, humidity, wind strength, temperature in the air, and weather.

[0032] In addition to the correlation between the minimum temperature and the likelihood of a dead battery, other weather information may be used. The correlation may be determined using multiple explanatory variables.

[0033] In the battery information processing method, the computer may output a message recommending that the battery be inspected, in accordance with the information on the predicted possibility of the battery running out.

[0034] With the above configuration, the possibility of a dead battery can be predicted based on weather information, and accordingly, promotion of battery inspection services can be implemented with a basis. When there is a high possibility of a dead battery, advertisements for battery inspection, battery replacement, etc. may be output.

[0035] In the battery information processing method, the computer may output a message regarding inspection of the target battery based on information regarding the predicted possibility of a battery failure and the usage history of the target battery.

[0036] With the above configuration, it is possible to avoid annoying the user by outputting a message urging an inspection of a battery that has a history of inspection or purchase even though the battery has just been inspected or replaced.

[0037] The battery information processing device includes an acquisition unit that acquires weather information for a prediction target period, a prediction unit that predicts the possibility of a battery running out during the prediction target period based on the acquired weather information, and an output unit that outputs information on the predicted possibility of a battery running out.

[0038] The battery information processing system includes a terminal device having a display unit and an information processing device that transmits and receives data via communication with the terminal device, wherein the terminal device specifies a prediction period and transmits a request to the information processing device, and when the information processing device receives the request, it acquires weather information for the specified prediction period, predicts the possibility of a battery running out during the prediction period based on the acquired weather information, and transmits information on the predicted possibility of a battery running out to the terminal device that made the request, and the terminal device displays text or an image corresponding to the information on the possibility of a battery running out transmitted in response to the request on the display unit.

[0039] The computer program causes the computer to acquire weather information for the prediction period, predict the possibility of a dead battery occurring during the prediction period based on the acquired weather information, and output information on the predicted possibility of a dead battery occurring.

[0040] The present invention will be specifically described with reference to the drawings showing embodiments thereof.

[0041] (First embodiment) 1 is a schematic diagram of a battery information processing system 100 according to a first embodiment. The battery information processing system 100 includes an information processing device 1, an information terminal device 2 capable of communicating with the information processing device 1, and a battery tester 3. The information processing device 1 is managed, for example, by a business that provides information on batteries installed in vehicles (automobiles). The information terminal device 2 is managed by a service providing facility S that inspects, sells, and / or replaces batteries. The tester 3 is used at the service providing facility S.

[0042] The battery is a lead-acid battery that is a power source for starting the engine installed in the vehicle. The battery may be a battery that is pre-installed in the vehicle, or a battery sold by the service providing facility S.

[0043] The service providing facility S inspects, sells, replaces, etc. the batteries. The service providing facility S is, for example, a facility that provides vehicle fuel (gasoline, diesel, liquefied petroleum gas, etc.). The service providing facilities S are set up in various locations and are given facility identification data that allows them to be identified from each other. The services provided by the service providing facility S are not limited to those mentioned above, and may also include, for example, retail of vehicle accessories, vehicle inspection and maintenance, vehicle purchase and sales, bodywork and painting, etc.

[0044] Tester 3 is installed in service providing facility S and used by facility staff. Tester 3 is a device that measures the battery condition (deterioration state, charge state, voltage, etc.) and outputs the measurement results on a screen and / or paper medium. Tester 3 has a detachable non-transitory storage medium inside, and writes the measurement results and information on the date and time the measurement was made to the non-transitory storage medium each time a measurement is made. Tester 3 may be equipped with a wireless communication device, and may be able to communicate wirelessly with information terminal device 2 and transmit the measurement results to information terminal device 2.

[0045] The information terminal device 2 is installed in the service providing facility S and used by facility staff or sales personnel of the service providing facility S. The information terminal device 2 may be a laptop or desktop personal computer, or may be a tablet terminal. The information terminal device 2 may be a special computer, tablet terminal, etc. that can be operated by the user and used for fuel settlement, etc.

[0046] A virtual private network N1 of a battery inspection service provider is installed in the service providing facility S, and information terminal devices 2 installed in each of the service providing facilities S can be communicatively connected to the private network N1. The information terminal devices 2 may be communicatively connected to the private network N1 via an access point AP installed in the service providing facility S. The private network N1 can be communicatively connected to the information processing device 1 via a carrier network or a public network N2, which is the Internet.

[0047] The information processing device 1 is a server device capable of transmitting and receiving data to and from the information terminal device 2. The information processing device 1 collects inspection results of the battery using a tester 3 from the information terminal device 2 and has a battery database (DB: Data Base) 111 in which the inspection results are recorded. The information processing device 1 predicts data related to battery demand based on the data collected and recorded in the battery DB 111 and provides this to the information terminal device 2. In the first embodiment, the data related to battery demand is provided as an index value indicating the likelihood that the battery will be determined to require attention or replacement based on the inspection results.

[0048] The following describes the configuration and processing of each device for realizing the prediction of data related to battery demand and the provision of information by the above-described battery information processing system 100. Figure 2 is a block diagram showing the internal configuration of the information processing device 1 and the information terminal device 2.

[0049] The information processing device 1 is a server computer or a laptop or desktop personal computer. In the following description, the information processing device 1 is described as being configured with a single server computer, but may also be configured as a system in which multiple server computers are connected via a network for communication and perform distributed processing. The information processing device 1 includes a processing unit 10, a storage unit 11, and a communication unit 12.

[0050] The processing unit 10 is a processor using a CPU (Central Processing Unit) and / or a GPU (Graphics Processing Unit). The processing unit 10 collects, analyzes, and provides information on performance data based on an information processing program 1P stored in the storage unit 11.

[0051] The storage unit 11 uses a nonvolatile memory such as a hard disk, flash memory, or SSD (Solid State Drive). The storage unit 11 stores data referenced by the processing unit 10. The storage unit 11 stores an information processing program 1P. The information processing program 1P may be an information processing program 9P stored in a non-transitory storage medium 9 that is read by the processing unit 10 and copied to the storage unit 11. The information processing program 1P may be downloaded from another program server device via the communication unit 12 and stored therein.

[0052] The storage unit 11 stores a battery DB 111 of battery data. The battery DB 111 may be stored in an external storage device and may be readable and writable by the processing unit 10.

[0053] The communication unit 12 realizes communication with the information terminal device 2 via the Internet or a public network N2 including a carrier network. Specifically, the communication unit 12 is a network card. The communication unit 12 may be a wireless communication module that connects to a carrier network, or may be a wireless communication module for Wi-Fi (registered trademark). The processing unit 10 can send and receive data to and from the information terminal device 2 via the communication unit 12.

[0054] The information terminal device 2 includes a processing unit 20, a storage unit 21, a communication unit 22, a display unit 23, an operation unit 24, and an acquisition unit 25.

[0055] The processing unit 20 is a processor that uses a CPU and / or a GPU. The processing unit 20 transmits and receives data to and from the information processing device 1.

[0056] The storage unit 21 uses a non-volatile memory such as a flash memory, SSD, or hard disk. The storage unit 21 stores data referenced by the processing unit 20. The storage unit 21 stores various application programs including a Web browser program 2W. The storage unit 21 stores terminal identification data that identifies the information terminal device 2 itself and / or facility identification data that identifies the service providing facility S where the information terminal device 2 is installed.

[0057] The communication unit 22 realizes communication via the private network N1. The communication unit 22 may be a wireless communication device or a wired communication device. The processing unit 20 can send and receive data to and from the information processing device 1 via the communication unit 22.

[0058] The display unit 23 is a display such as a liquid crystal display, an organic EL display, etc. The processing unit 20 displays a web page provided from the information processing device 1 based on a web browser program on the display unit 23. The processing unit 20 can display an index value indicating the likelihood that the battery will be determined to require attention or replacement on the display unit 23, based on data received from the information processing device 1.

[0059] The operation unit 24 is a user interface that can input and output data to and from the processing unit 20. The operation unit 24 may be a physical button. The operation unit 24 may be a touch panel built into the display unit 23. The operation unit 24 may be a voice input unit.

[0060] The acquisition unit 25 is a device for acquiring measurement results for the battery from the tester 3. The acquisition unit 25 reads measurement data from, for example, a non-temporary storage medium (a small non-volatile storage medium) that is detachable from the tester 3. The acquisition unit 25 may be, for example, a USB (Universal Serial Bus) interface, and may acquire the measurement results from the tester 3 via a wired connection. The acquisition unit 25 may also acquire the measurement results from the tester 3 via wireless communication. The acquisition unit 25 may receive data input via the display unit 23 and the operation unit 24.

[0061] In the battery information processing system 100 configured as above, the process in which the information processing device 1 collects the measurement results from the tester 3, the process of analyzing them, the process of predicting data related to battery demand, and an example of outputting the prediction will be described in order.

[0062] [Measurement result collection] 3 is a flowchart showing an example of a procedure for collecting measurement results. At each service providing facility S, facility staff periodically, such as once a week, removes the non-transitory storage medium from the tester 3 and causes the information terminal device 2 to read data from the non-transitory storage medium. The battery information processing system 100 executes the following process to read and collect data.

[0063] A facility staff member using the information terminal device 2 starts a web browser program and attempts to access a web page provided by the web server function of the information processing device 1.

[0064] As a result, the processing unit 20 of the information terminal device 2 acquires the web page data from the information processing device 1 (step S201), and displays a screen for uploading the measurement results from the acquired web page data on the display unit 23 (step S202). The upload screen includes an interface for specifying the acquisition (read) destination of the measurement results. When the facility staff performs an operation to select the interface, a screen showing the reference results of the acquisition destination non-transitory storage medium is displayed. The facility staff selects the non-transitory storage medium connected to the acquisition unit 25 of the information terminal device 2.

[0065] The processing unit 20 acquires the measurement results of the tester 3 from the non-temporary storage medium using the acquisition unit 25 (step S203). An interface for accepting an instruction to send the measurement result data in the selected non-temporary storage medium is displayed on the web page of the information terminal device 2. When the interface for accepting the sending instruction is selected, the processing unit 20 associates the acquired measurement results with the facility identification data and transmits them to the information processing device 1 (step S204).

[0066] The information processing device 1 receives the measurement results transmitted from the information terminal device 2 via a web page (step S101), and calculates statistical data of the received measurement results (step S102). In step S102, the processing unit 10 of the information processing device 1 calculates the number of battery inspections per unit period for each facility, the number of batteries determined to require caution, the number of batteries determined to require replacement, the number of newly sold batteries, etc.

[0067] The processing unit 10 stores the calculated statistical data in the battery DB 111 in association with the facility identification data (step S103), and ends the process. In step S103, the processing unit 10 may store the measurement results for each battery (inspection date and time, judgment results such as good / caution / replacement required, etc.). The information processing device 1 performs the processes of steps S101 to S103 for the measurement results transmitted from each information terminal device 2.

[0068] Fig. 4 is an explanatory diagram of collected measurement result data. Fig. 4 shows statistical data of the measurement results stored in the battery DB 111 and facility data including information such as the location associated with facility identification data of each service providing facility S.

[0069] In the example shown in Fig. 4, for a service providing facility S in Kyoto Prefecture in the Kinki region, the number of inspections performed is counted and stored for each day in association with facility identification data "000101." In addition, the judgment results of "good," "caution," and "replacement required" are counted and stored in association with the facility identification data.

[0070] [Analysis of measurement results] Next, the analysis of the measurement results collected in the battery DB 111 will be described. FIG. 5 is a flowchart showing an example of the analysis processing procedure for the measurement results. The information processing device 1 executes the following processing periodically or based on the amount of data. The period may be once every three years, once a year, once a month, etc. The amount of data may be the point in time when 1,000 pieces of data have been collected for each region. The information processing device 1 may execute the following processing only once.

[0071] The processing unit 10 of the information processing device 1 selects the area for which weather information is to be released by the Japan Meteorological Agency, such as a prefecture (step S111). The release area may be a prefecture forecast area, which is divided into multiple regions in Hokkaido and between the main island and other islands in Okinawa, or may be a regional division such as the Tohoku region or the Tokai region. Regional divisions may also be divided into sea side, mountain side, southern, northern, eastern, and western regions.

[0072] The processing unit 10 extracts facility identification data of the service providing facility S included in the selected announcement area (step S112). The processing unit 10 reads out the measurement results for a target period from the battery DB 111 among the measurement results (statistical data) stored in association with the extracted facility identification data (step S113). The target period may be, for example, the past year, or a specified period such as April to June or November to February of the previous year.

[0073] From the measurement results read out in step S113, the processing unit 10 calculates the ratio of the number of batteries determined to require caution or replacement to the number of battery inspections per unit period (hereinafter referred to as the occurrence rate of batteries requiring caution or replacement) (step S114). The unit period is, for example, one day, but may also be other calendar cycles such as one week or one month. In the example of the explanatory diagram of Figure 4, if the unit period is one day, the occurrence rate of batteries requiring caution or replacement in Kyoto Prefecture on June 1, 2021 is 20%, the occurrence rate of batteries requiring caution or replacement on June 2, 2021 is 25%, and the occurrence rate of batteries requiring caution or replacement on June 3, 2021 is 31%.

[0074] The processing unit 10 acquires weather information for the unit period in the target period for the announcement area selected in step S111 (step S115). In step S115, the processing unit 10 acquires temperature data from the Japan Meteorological Agency. In step S115, the processing unit 10 acquires, for example, data on the minimum temperature for each day over the past year.

[0075] The processing unit 10 stores the weather information for each unit period acquired in step S115 in association with the occurrence rate of caution / replacement required calculated for each unit period in step S114 (step S116). In step S116, the processing unit 10 stores data having the minimum temperature and the occurrence rate of caution / replacement required as components as weather information. For example, the data is (Data 1): (18.5°C, 20%), (Data 2): (12.3°C, 45%), etc.

[0076] The processing unit 10 uses the weather information acquired in step S116 to calculate a parameter specifying the correlation between the occurrence rate of caution / replacement required and the weather information (step S117). In step S117, the processing unit 10 calculates a correlation coefficient of the occurrence rate of caution / replacement required when the data of the lowest temperature is used as a variable.

[0077] The processing unit 10 stores the parameters calculated in step S117 for each announcement area (step S118), and determines whether or not the processing has been performed for all announcement areas (step S119).

[0078] If it is determined that the processing has been performed for all prefectures or announcement areas (S119: YES), the processing unit 10 ends the processing.

[0079] If it is determined that the processing has not been performed for all prefectures or announcement regions (S119: NO), the processing unit 10 returns the processing to step S111 and selects another prefecture or announcement region.

[0080] 5, parameters that represent the relationship between temperature data and the occurrence rate of warnings and replacements required in battery measurement results are calculated and stored for each announcement region. If there is insufficient data for each announcement region, the weather information associated with the occurrence rate in step S116 may be for each announcement region, or data may be aggregated down to the regional division (Hokkaido / Tohoku / Kanto / Koshinetsu / Tokai / Kinki / Shikoku / Chugoku / Kyushu / Okinawa) when calculating correlation parameters in step S117. Alternatively, data may be collected for only a representative region in each regional division to calculate parameters that identify correlations, and these parameters may be used for the entire regional division.

[0081] In the above analysis, a parameter specifying the correlation between the occurrence rate of warning / replacement warnings and weather information is calculated and stored. However, the correspondence between weather information and the possibility of a dead battery may be a table showing the correspondence between the occurrence rate and weather information, specifically, minimum temperature.

[0082] [Prediction processing process] The information processing device 1 executes the following prediction process at a cycle corresponding to the prediction target period and the unit period, such as once a week or every day, etc. Fig. 6 is a flowchart showing an example of the prediction process procedure.

[0083] The processing unit 10 of the information processing device 1 selects a region division to be predicted (step S131). The processing unit 10 selects a weather announcement area included in the selected region division (step S132).

[0084] The processing unit 10 acquires weather forecast information for the selected announcement area for a forecast period (step S133). The forecast period may be, for example, forecast information for the minimum temperature for each day or forecast information for the average temperature for one week.

[0085] The processing unit 10 calculates a predicted value of the occurrence rate of battery caution and replacement required during the prediction period using the acquired weather forecast information and correlation parameters stored for each announcement area (step S134).The processing unit 10 stores the calculated predicted value of the occurrence rate of battery caution and replacement required for each announcement area (step S135).

[0086] The processing unit 10 determines whether or not all the announcement districts included in the region division selected in step S131 have been selected (step S136). If it is determined that all the announcement districts have not been selected (S136: NO), the processing unit 10 returns the process to step S132 to select another announcement district.

[0087] If it is determined that all the announcement areas have been selected (S136: YES), the processing unit 10 determines whether all the regional divisions have been selected (step S137). If it is determined that all the regional divisions have not been selected (S137: NO), the processing unit 10 returns the process to step S131 and selects another regional division.

[0088] If it is determined that all the district divisions have been selected (S137: YES), the processing unit 10 ends the prediction process.

[0089] When using a table showing the correspondence relationship between weather information and minimum temperatures, upon acquiring predicted weather information, the processing unit 10 reads out the occurrence rate corresponding to the acquired weather information (minimum temperature).

[0090] [Output process] According to the procedure shown in FIG. 6, predicted values ​​of the occurrence rate of warnings and replacements required when the battery is inspected during a prediction target period are stored periodically for each regional division and each announcement area. The predicted values ​​of the occurrence rate of warnings and replacements required correspond to the predicted possibility (frequency) of a dead battery occurring when the battery is not inspected. The stored predicted values ​​for each prediction target period can be output sequentially. Specifically, a function for calling up the predicted value is included in the description data of a Web page provided to the information terminal device 2 by the Web server function of the information processing device 1, and an image corresponding to the called predicted value is displayed on the Web page.

[0091] 7 is a flowchart showing an example of a procedure for outputting the occurrence rate of battery warnings and inspections required. The processing unit 20 of the information terminal device 2 starts the following process when it receives an access operation to a battery-related portal site on a web browser program from a facility staff member of the service providing facility S or a sales representative of the service providing facility S.

[0092] The processing unit 20 transmits a request for a web page of the portal site to the information processing device 1 (step S241). The request may include facility identification data of the service providing facility S where the information terminal device 2 is installed. The request may also include account data of the operating staff member, sales representative, etc.

[0093] The information processing device 1 receives a request for a web page from a portal site (step S141) and transmits the web page data to the request source based on the request (step S142). The web page includes an image of a distribution chart showing the occurrence rates of cautions and replacements required when inspecting a battery, and the image is written to change depending on the occurrence rate.

[0094] The processing unit 20 of the information terminal device 2 receives the web page data through the web browser program (step S242). Based on the received data, the processing unit 20 displays the portal site and, when displaying an image of the distribution map of occurrence rates included in the web page, requests the image by providing a regional division or announcement area (step S243).

[0095] The image request from the web browser program is detected by the information processing device 1, which is a web server (step S143). The processing unit 10 reads out from the storage unit 11 the predicted value of the occurrence rate associated with the identification data of the given regional division or announcement area (step S144). The processing unit 10 determines whether the read-out predicted value is equal to or greater than a predetermined first threshold (step S145), and if it is determined that the read-out predicted value is equal to or greater than the predetermined first threshold (S145: YES), it transmits an image indicating "high frequency" to the information terminal device 2 (step S146). The first threshold is, for example, 50%, and the processing unit 10 determines "high frequency" when the occurrence rate of caution / replacement required relative to the number of inspections is predicted to be 50% or more. In other words, in this case, the frequency of dead batteries occurring is predicted to be high.

[0096] If it is determined that the predicted value is not equal to or greater than the predetermined first threshold (S145: NO), the processing unit 10 determines whether the predicted value is equal to or greater than a second threshold that is lower than the first threshold (step S147). The second threshold is, for example, 40%, and the processing unit 10 determines that the occurrence rate of caution or replacement required relative to the number of inspections is "medium frequency" when it is predicted to be less than 50% and equal to or greater than 40%. In this case, the frequency of dead batteries is predicted to be medium.

[0097] If it is determined that the frequency is equal to or greater than the second threshold (S147: YES), the processing unit 10 transmits an image indicating "medium frequency" to the information terminal device 2 (step S148). If it is determined that the frequency is less than the second threshold (S147: NO), the processing unit 10 transmits an image indicating "low frequency" to the information terminal device 2 (step S149). In this case, it is predicted that the frequency of battery dead occurrences is low.

[0098] The processing unit 20 of the information terminal device 2 receives the image using the Web browser program (step S244), displays the received image in the Web page in accordance with the description data of the Web page (step S245), and ends the process.

[0099] 8 and 9 show examples of displaying predicted values ​​of the occurrence rate of battery warnings and replacement warnings. The display examples of FIGS. 8 and 9 show examples of Web page 231 output to display unit 23 of information terminal device 2 by the process shown in FIG. 7. Web page 231 in FIG. 8 includes a schematic map of Japan. The map of Japan on Web page 231 is displayed divided into regional divisions. As shown in FIG. 8, the map of Japan on Web page 231 displays character icons (images) 232 with facial expressions indicating "high frequency," "medium frequency," and "low frequency" for each regional division. The map of Japan can be selected on the Web browser for each regional division, and the selected regional division is displayed. The calculated predicted value of the occurrence rate may be displayed together with icon 232.

[0100] Figure 9 is an enlarged view of the map of Japan shown in Figure 8 when a regional division is selected. Figure 9 shows an enlarged map of the Tohoku region divided into the prefectures that are the announcement areas. On the enlarged map of the Tohoku region, icons (images) 233 are displayed for each prefecture, each of which is depicted with a character's facial expression to indicate "high frequency," "medium frequency," or "low frequency."

[0101] In the examples of Figures 8 and 9, "high frequency", "medium frequency", and "low frequency" are displayed as icons 232, 233, which are easily recognized by the facial expressions of characters. Alternatively, the high and low frequency may be grasped as a heat map by using different colors, patterns, shades, or animations for each area on a map of each announcement area. In Figure 9, the high and low frequency is displayed with different shades of hatching depending on the high and low frequency, making it easy to recognize the high and low frequency.

[0102] As shown in FIGS. 8 and 9 , by using a tester 3 for battery inspections, measurement results are collected in the information processing device 1, and the occurrence rate of warnings and battery replacements when inspecting batteries based on the collected measurement results can be grasped like a weather forecast. Facility staff, sales representatives, etc. who visually check the occurrence rates shown in FIGS. 8 and 9 can determine that if the occurrence rate is high and the "high frequency" icons 232 and 233 are displayed, they should increase the number of inspections and proactively take measures to prevent battery failure. If sales representatives can obtain forecast values ​​for a predetermined number of days in advance, such as three days in advance, they can adjust battery inventory for each facility in anticipation of an increase in the number of battery replacements. Battery manufacturer personnel may also use a terminal device equivalent to the information terminal device 2 to check the forecast of the occurrence rate of warnings and battery replacements when inspecting batteries. This can also be used by battery manufacturers to predict battery demand.

[0103] The information processing device 1 may not only display an icon or a map shade according to the frequency, but also display a message on a web page for each announced area recommending that the number of inspections be increased depending on the frequency. In this case, the facility staff of the service providing facility S may present the reason to the customer that the battery is likely to run out and that it is advisable to inspect the battery.

[0104] In the first embodiment, the information processing device 1 uses daily minimum temperature data as weather information and calculates parameters (variables and intercepts of a linear regression equation) that specify the correlation between the minimum temperature data and the occurrence rate of warnings or replacements when the battery is inspected. The processing unit 10 may also obtain daily or weekly average temperature data as weather information to determine the correlation with the occurrence rate, or may obtain weekly minimum temperature data or maximum temperature data to determine the correlation with the occurrence rate. The processing unit 10 may also use weather data such as sunny / cloudy / rainy as an explanatory variable, or may use both temperature data and humidity data as explanatory variables. Temperature data may be obtained for each secondary subdivision area subdivided down to the municipal level.

[0105] Additionally, in the first embodiment, the information processing device 1 predicted the occurrence rate of battery inspection warnings and battery replacement warnings, for example, once a week, based on daily weather forecasts. However, the frequency of the occurrence rate prediction may be based on medium- to long-term weather information, rather than daily weather information. For example, the processing unit 10 of the information processing device 1 may predict the occurrence rate of battery replacement warnings in the medium to long term based on average temperature data (higher than average / average / lower than average) related to medium- to long-term forecasts provided by the Japan Meteorological Agency. This allows supply and demand from battery manufacturers to be adjusted according to the medium to long-term forecasts.

[0106] In the first embodiment, an index value (probability) indicating the likelihood that a battery will be determined to require attention or replacement based on the inspection results is predicted as data related to battery demand. However, the information processing device 1 may also predict the likelihood that a battery will run out and require replacement as data related to battery demand. Alternatively, the information processing device 1 may predict the required number of batteries that will be determined to require replacement as data related to battery demand. This directly predicts the required number of batteries, i.e., realizes demand prediction.

[0107] (Second embodiment) In the second embodiment, the correlation between weather information and the occurrence rate of warnings and replacements required when a battery is inspected is determined using a learning model with multiple explanatory variables as input, rather than regression analysis using a single explanatory variable, the minimum temperature. The processing of the information processing device 1 in the battery information processing system 100 of the second embodiment is the same as the processing in the first embodiment, except for the analysis processing and prediction processing of the measurement results. The learned model, analysis processing, and prediction processing in the second embodiment will be described below.

[0108] 10 is a block diagram showing the configuration of an information processing device 1 in the second embodiment. The configuration of an information terminal device 2 is the same as that in the first embodiment, so a detailed description will be omitted.

[0109] In the information processing device 1 of the second embodiment, a trained model 1M is stored in the memory unit 11. There may be only one trained model 1M, or trained and stored by announcement area, regional division, or season. The trained model 1M may be a trained model 9M stored in a non-temporary storage medium 9 that is read by the processing unit 10 and stored in the memory unit 11, or it may be a trained model that is downloaded from an external server (not shown) via a communication medium and stored.

[0110] FIG. 11 is a schematic diagram of the trained model 1M that outputs the occurrence rate of caution and replacement required. The trained model 1M is a model that configures and trains a neural network so that it outputs the occurrence rate of caution and replacement required when multiple weather information is input. The multiple weather information may include data on the minimum temperature of the day, data on the minimum temperature of the previous day, data on the maximum temperature of the day, the weather of the day (sunny / cloudy / rainy / snowy, etc.), the humidity of the day, the wind strength of the day, and the temperature above the ground of the day. The trained model 1M may input not only weather information but also calendar data. The calendar data may include data such as the date, month, season, day of the week, and whether it is a Sunday or the day before a holiday.

[0111] [Analysis and learning of measurement results] The information processing device 1 of the second embodiment performs a correlation analysis between the occurrence rate of warnings and replacements required when a battery is inspected and weather information by creating, i.e., learning, a trained model 1M. FIG. 12 is a flowchart showing an example of the procedure for creating the trained model 1M. The processing unit 10 of the information processing device 1 selects an area where weather information is released by the Japan Meteorological Agency, such as a prefecture (step S151).

[0112] The processing unit 10 extracts facility identification data of the service providing facility S included in the selected announcement area (step S152). The processing unit 10 reads out the measurement results for the target period from the battery DB 111 among the measurement results stored in association with the extracted facility identification data (step S153).

[0113] The processing unit 10 calculates the ratio of the number of batteries judged to require caution or replacement to the number of batteries inspected per unit period (hereinafter referred to as the occurrence rate of batteries requiring caution or replacement) from the measurement results read out in step S153 (step S154).

[0114] The processing unit 10 acquires weather information for a unit period in the target period in the announcement area selected in step S151 (step S155). In step S155, the processing unit 10 acquires various types of data including temperature from the Japan Meteorological Agency.

[0115] The processing unit 10 stores the weather information for each unit period acquired in step S155 as training data in association with the occurrence rate of caution / replacement required information calculated for each unit period in step S154 (step S156).

[0116] The processing unit 10 determines whether or not the process of associating the weather information with the occurrence rates of caution and replacement required for all announcement areas has been performed (step S157). If it is determined that the process has not been performed for all announcement areas (S157: NO), the processing unit 10 returns the process to step S151 and executes the process for the other announcement areas.

[0117] If it is determined that processing has been performed for all announcement areas (S157: YES), the processing unit 10 uses the training data stored in step S156 for each announcement area, and calculates an error function with the output when the weather information is input into the neural network, using the occurrence rate of caution / replacement as the correct label, and performs parameter learning in the intermediate layer (step S158).

[0118] The processing unit 10 determines whether the neural network under training satisfies a predetermined condition through training (step S159). The predetermined condition may be that the number of training attempts has reached a predetermined number, or that the error from the correct answer evaluated by the error function has fallen below a predetermined amount.

[0119] If it is determined that the predetermined condition is satisfied (S159: YES), the processing unit 10 ends the learning process, stores the parameters (step S160), and ends the process. As a result, the neural network is created as a trained model 1M.

[0120] If it is determined that the predetermined condition is not satisfied (S159: NO), the processing unit 10 returns the process to step S158 and continues learning.

[0121] 12 has been described as being performed by the information processing device 1, the learning process may be executed by another processing device, and the information processing device 1 may acquire the trained model 1M as a result of the process. The trained model 1M may be created for each region or each season.

[0122] [Prediction processing process] The information processing device 1 uses the created trained model 1M to execute the following prediction process at a cycle corresponding to the prediction target period and the unit period, such as once a week or daily. FIG. 13 is a flowchart showing an example of a prediction process procedure using the trained model 1M. Among the process procedures shown in the flowchart of FIG. 13, steps that are common to the process procedures shown in the flowchart of FIG. 6 in the first embodiment are assigned the same step numbers, and detailed descriptions thereof will be omitted.

[0123] The processing unit 10 of the information processing device 1 selects a region division to be predicted (S131), and selects a weather announcement area included in the selected region division (S132).

[0124] The processing unit 10 acquires weather forecast information for the forecast period for the selected announcement area (S133), and inputs the acquired weather forecast information to the trained model 1M (step S164). The processing unit 10 acquires the predicted values ​​of the occurrence rate of battery warnings and replacements output from the trained model 1M (step S165), and stores the acquired predicted values ​​of the occurrence rate of warnings and replacements for each announcement area (step S166).

[0125] The processing unit 10 determines whether or not all the presentation districts included in the region division selected in step S131 have been selected (S136). If it is determined that all the presentation districts have not been selected (S136: NO), the processing unit 10 returns the process to step S132 to select another presentation district.

[0126] If it is determined that all the announcement areas have been selected (S136: YES), the processing unit 10 determines whether all the regional divisions have been selected (S137). If it is determined that all the regional divisions have not been selected (S137: NO), the processing unit 10 returns the process to step S131 and selects another regional division.

[0127] If it is determined that all the district divisions have been selected (S137: YES), the processing unit 10 ends the prediction process.

[0128] As explained in the second embodiment, based on the trained model 1M that uses multiple explanatory variables, the occurrence rate of warnings and battery replacements when inspecting a battery can be grasped like a weather forecast. If there is a large amount of predictable data that correlates with the occurrence rate of dead batteries, i.e., battery replacements, using this data can be expected to improve the accuracy of predictions.

[0129] (Third embodiment) In the first and second embodiments, the facility staff, the sales representative of the service provider, or the battery manufacturer's representative could visually check the predicted occurrence rate of warnings and replacements when the battery was inspected. In the third embodiment, the user and the service provider can check the predicted occurrence rate of warnings and replacements when the battery was inspected in the form of a forecast of the risk of dead batteries.

[0130] 14 is a schematic diagram of a battery information processing system 100 according to the third embodiment. The battery information processing system 100 according to the third embodiment includes an information processing device 1, an information terminal device 2, a tester 3, and a user terminal device 4 used by a user of a vehicle equipped with a battery.

[0131] In the third embodiment, as in the first and second embodiments, the information processing device 1 collects and analyzes the measurement results of the tester 3 at each service providing facility S, and identifies the correlation between weather information and the occurrence rate of warnings and replacements when a battery is inspected. From the information terminal device 2, a web page showing predicted values ​​of the occurrence rate for a prediction target period on a map can be obtained. In addition, in the third embodiment, if the status data of the battery used by each user is stored, a service is realized in which the user terminal device 4 warns the user of the possibility of a dead battery.

[0132] In the battery information processing system 100 of the third embodiment, the hardware configuration of each device other than the user terminal device 4 is the same as the configuration of the first embodiment, so the same reference numerals are used and detailed description will be omitted. FIG. 15 is a block diagram showing the configuration of the user terminal device 4. The user terminal device 4 is a general-purpose computer such as a smartphone, tablet terminal, or personal computer used by a user. The user terminal device 4 includes a processing unit 40, a storage unit 41, a communication unit 42, a display unit 43, and an operation unit 44.

[0133] The processing unit 40 is a processor that uses a CPU and / or a GPU. The processing unit 40 transmits and receives data to and from the information processing device 1.

[0134] The storage unit 41 uses a nonvolatile memory such as a flash memory, an SSD, or a hard disk. The storage unit 41 stores an application program 4P. The application program 4P is a program that causes a general-purpose computer to function as the user terminal device 4 in the battery information processing system 100 of the third embodiment when executed by the processing unit 40. The application program 4P is, for example, a program used for managing points related to use of a service providing facility S that offers battery retail, exchange, or inspection services, or for announcing campaigns. The application program 4P may also be a program provided by another service provider that sells batteries. The storage unit 41 stores user identification data of a user who uses the application program 4P on the user terminal device 4.

[0135] The application program 4P in the storage unit 41 may be an application program 8P stored in the non-temporary storage medium 8 that has been read and stored by the processing unit 40, or may be an application program 8P that has been downloaded from an external server device and stored.

[0136] The communication unit 42 realizes communication via a public network N2 including the Internet or a carrier network. The communication unit 42 may be a wireless communication device or a wired communication device. The processing unit 40 can transmit and receive data to and from the information processing device 1 via the communication unit 42.

[0137] The display unit 43 is a display such as a liquid crystal display, an organic EL display, etc. The processing unit 40 displays a web page provided from the information processing device 1 based on a web browser program on the display unit 43. The processing unit 40 can display an index value indicating the likelihood of the battery running out on the basis of data received from the information processing device 1.

[0138] The operation unit 44 is a user interface capable of inputting and outputting data to and from the processing unit 40. In the following description, the operation unit 44 is a touch panel built into the display unit 43. The operation unit 44 may be a physical button. The operation unit 44 may also be a voice input unit.

[0139] In the third embodiment, if data related to the use of the battery installed in the user's vehicle is stored in the storage unit 41 of the user terminal device 4 or the battery DB 111 of the information processing device 1 in association with user identification data, this data is used. FIG. 16 is a diagram showing an example of the content of data related to battery use. When the user starts the application program 4P using the user terminal device 4, the application program 4P functions to allow the user to input data such as the purchase date and inspection date of the purchased (replaced) battery. By inputting this data, the purchase date and inspection date of the battery are stored locally in the user terminal device 4 or in the battery DB 111 of the information processing device 1 in association with the user identification data, as shown in FIG. 16. Then, the user terminal device 4 can notify the user of the next inspection date, etc., based on the period of time that has elapsed since the purchase date or inspection date, using the application program 4P.

[0140] In the third embodiment, information is presented to the user based on data on battery usage stored as shown in Figure 16 and predicted values ​​of the occurrence rate of battery warnings and replacements based on weather information.

[0141] 17 is a flowchart showing an example of a procedure for processing information presentation for a user in the third embodiment. The processing unit 40 of the user terminal device 4 acquires a weather information announcement area corresponding to the location of the user's vehicle or the user's residential area (step S401). In step S401, the processing unit 40 may acquire an announcement area that has been previously associated with user identification data, such as prefecture data, or may accept a selection from the user. Furthermore, if the user terminal device 4 is a smartphone, the current location may be identified using a GPS function, and the announcement area corresponding to the identified current location may be acquired.

[0142] The processing unit 40 sends a request to the information processing device 1 to obtain a predicted value of the occurrence rate of caution or replacement when a battery is inspected in the acquired announcement area (step S402), and obtains the predicted value from the information processing device 1 (step S403).

[0143] The information processing device 1 receives a request for obtaining a predicted value of the occurrence rate of caution / replacement requiring a specified announcement area from the user terminal device 4 (step S171), and the processing unit 10 reads out the predicted value for the prediction target period obtained by analysis based on the specified announcement area (step S172). The processing unit 10 transmits the read predicted value to the user terminal device 4 (step S173).

[0144] The user terminal device 4 determines whether the acquired predicted value is equal to or greater than a first threshold (step S404). The first threshold is, for example, 50%, which is a threshold that is considered to be "high frequency" in the announcement area.

[0145] If it is determined that the battery life is equal to or greater than the first threshold (S404: YES), the processing unit 40 determines whether a predetermined period of time has passed since the most recent inspection date or purchase date, based on data related to battery usage (step S405). The predetermined period of time may be, for example, 8 months, 10 months, or 1 year.

[0146] If it is determined that the predetermined period has elapsed (S405: YES), the processing unit 40 displays a message on the display unit 43 urging the user to inspect the battery of the user's vehicle because there is a possibility that the battery may run out (step S406), and then ends the processing.

[0147] If it is determined in step S405 that the predetermined period has not elapsed (S405: NO), the processing unit 40 displays a message on the display unit 43 urging caution as the battery is likely to run out (step S407), and terminates the processing.

[0148] If it is determined in step S405 that the predicted value is less than the first threshold (S404: NO), the processing unit 40 determines whether the predicted value is equal to or greater than a second threshold that is lower than the first threshold (step S408). The second threshold is, for example, 40%, which is a threshold that is considered to be "medium frequency" in the announcement area.

[0149] If it is determined that the difference is equal to or greater than the second threshold (S408: YES), the processing unit 40 advances the process to step S407.

[0150] If it is determined that the battery voltage is less than the second threshold value (S408: NO), the processing unit 40 displays a message on the display unit 43 indicating that the possibility of the battery running out is low (step S409), and ends the processing.

[0151] The processes of steps S403-S405 and S408 may be executed by the information processing device 1 when data relating to the purchase and inspection history of the battery associated with the user identification data is stored in the battery DB 111.

[0152] 18 and 19 are explanatory diagrams showing examples of screens displayed on the user terminal device 4. FIG. 18 is an example of a screen 431 that is displayed when a user uses the user terminal device 4 to start up the application program 4P. The screen 431 is a main screen or a portal screen. The screen 431 displays a menu 432 related to various services. The menu 432 includes a "battery low forecast." When the "battery low forecast" menu 432 is selected (tapped) by the user on the operation unit 44, the processing shown in the flowchart of FIG. 16 is executed.

[0153] 19 shows an example of a "Battery Dead Forecast" screen 433. Screen 433 is displayed when menu 432 is selected. Screen 433 displays text and a map 434 indicating the weather information announcement area corresponding to the residential area registered by the user or the user's current location, as well as an icon 435 corresponding to the likelihood of a dead battery occurring that day. Screen 433 also displays a message 436 for the user along with icon 435.

[0154] Screen 433 includes icons 437 for switching to forecasts for the next day and the day after that, and icon 438 for selecting another announcement area. When icon 437 is selected, processing unit 40 of user terminal device 4 may switch to predicted values ​​based on the weather information for the next day and execute the process shown in the flowchart of Fig. 17. In step S403, processing unit 40 may also acquire predicted values ​​for the next day and the day after that, in which case processing unit 40 executes the processes of S404-S409 for each day.

[0155] A user who views the screen 433 shown in Fig. 19 can recognize the possibility of a dead battery occurring today, the next day, or the day after. The user can also determine in advance whether or not to inspect the battery before a long-distance drive the next day or the day after. This is expected to encourage the user to inspect the battery and, if necessary, replace it to prevent the battery from running out.

[0156] In the third embodiment, the percentage of batteries that are judged to need replacement can be visually confirmed on the user terminal device 4. This allows the user to determine for themselves whether or not they need to be careful about a dead battery, and as a service provider related to battery replacement, it is possible to increase the motivation of users to check their batteries.

[0157] The embodiments disclosed above are illustrative in all respects and are not restrictive. The scope of the present invention is defined by the claims, and includes all modifications within the meaning and scope of the claims. [Explanation of symbols]

[0158] 1. Information processing equipment 10 Processing section 11 Storage section 111 Battery DB 1P Information Processing Program 2. Information terminal device 20 Processing section 23 Display section 3. Tester 4. User terminal equipment 40 Processing section 43 Display section 4P App Program

Claims

1. The computer Obtain weather information for the forecast period, predicting the possibility of a dead battery occurring during the prediction target period from the acquired weather information for the prediction target period based on a correlation between past inspection results for different batteries and weather information for a unit period during which inspections were performed on the different batteries; Outputs information on the predicted possibility of a dead battery Battery information processing method.

2. The computer Calculating a parameter by regression analysis that specifies a correlation between the proportion of inspection results that are judged to be other than good, relative to the number of past inspections, and the meteorological information for the unit period during which the inspection results were performed; Using the parameter specifying the correlation, a ratio of the battery being judged to be other than good when inspected is calculated based on the weather information for the prediction target period; Predict the possibility of a dead battery based on the calculated percentage and a comparison with a threshold. The battery information processing method according to claim 1 .

3. The computer Obtain weather information for different areas, From the acquired weather information for each different area, a possibility of a dead battery occurring is predicted based on a correlation between the inspection results and the weather information; Output information on the possibility of the battery running out for each area 3. The battery information processing method according to claim 1 or 2.

4. The computer A correlation between past inspection results for different batteries and meteorological information for a unit period during which the inspections for the different batteries were carried out is calculated for each area in which the inspections were carried out. Predict the possibility of a dead battery based on the correlation between weather information acquired for different regions. The battery information processing method according to claim 3 .

5. The computer A correlation between past inspection results for different batteries and weather information for a unit period during which the inspections for the different batteries were carried out is calculated as a learning model; When weather information for a prediction period is input to the learning model, the predicted value of the proportion of vehicles that will be judged as being other than good when an inspection is carried out is output from the learning model, Predict the possibility of a dead battery occurring during the prediction period The battery information processing method according to claim 1 .

6. The learning model is trained using training data including the weather information as input data and the proportion of inspection results determined to be other than good, relative to the number of past inspections under the weather conditions indicated by the weather information, as output data. The battery information processing method according to claim 5 .

7. The computer The learning model is trained for each different district, Obtain weather information for different areas, The acquired weather information for each different region is input into the learning model, and the possibility of a dead battery occurring for each region is predicted. The possibility of a battery occurring predicted for each different district is output for each district.

7. The battery information processing method according to claim 5 or 6.

8. The computer displays characters with different colors, patterns, shading, animations, or facial expressions on a map including different districts according to the predicted probability of battery exhaustion.

7. The battery information processing method according to claim 3, 4 or 6.

9. The meteorological information includes at least one of minimum temperature, maximum temperature, average temperature, humidity, wind strength, temperature in the air, and weather. The battery information processing method according to any one of claims 1 to 8.

10. The computer outputs a message recommending the implementation of a battery inspection in accordance with the information on the predicted possibility of the battery running out. The battery information processing method according to any one of claims 1 to 9.

11. The computer outputs a message regarding an inspection of the target battery based on information about the predicted possibility of a dead battery occurring and the usage history of the target battery. The battery information processing method according to any one of claims 1 to 10.

12. an acquisition unit for acquiring weather information for a forecast period; a prediction unit that predicts the possibility of a dead battery occurring during a target prediction period from the acquired weather information for the target prediction period based on a correlation between past inspection results for different batteries and weather information for a unit period during which the different batteries were inspected; and An output section that outputs information on the predicted possibility of a dead battery A battery information processing device comprising:

13. a terminal device including a display unit; an information processing device that transmits and receives data through communication with a terminal device; The terminal device specifies a prediction period and transmits a request to the information processing device; The information processing device includes: When the request is received, the weather information for the specified forecast period is obtained, predicting the possibility of a dead battery occurring during the prediction target period from the acquired weather information for the prediction target period based on a correlation between past inspection results for different batteries and weather information for a unit period during which inspections were performed on the different batteries; transmitting information on the predicted possibility of battery exhaustion to the terminal device that originated the request; The terminal device a text or an image corresponding to the information on the possibility of a dead battery being generated, transmitted in response to the request, displayed on the display unit; Battery information processing system.

14. On the computer, Obtain weather information for the forecast period, predicting the possibility of a dead battery occurring during the prediction target period from the acquired weather information for the prediction target period based on a correlation between past inspection results for different batteries and weather information for a unit period during which inspections were performed on the different batteries; Outputs information on the predicted possibility of a dead battery A computer program that executes a process.

Images