Anomaly prediction system, anomaly prediction device, classification generation device, anomaly prediction method, and anomaly prediction program

Abstract

The purpose of the present disclosure is to provide, inter alia, an abnormality prediction system capable of accurately predicting internal abnormality. In the present invention, an abnormality prediction system (100) comprises: a road information database (300) that stores road information in which road position information and road classification in which roads are classified in accordance with the effect on the internal abnormality of a vehicle are associated with each other; and an abnormality prediction device (200) that can communicate with the road information database (300). The abnormality prediction device (200): acquires a travel road history of a designated vehicle, for which internal abnormality is to be predicted; acquires the road information from the road information database for a road included in the travel road history; and predicts the internal abnormality of the designated vehicle on the basis of the road information for the road included in the travel road history of the designated vehicle.

Description

Anomaly prediction system, anomaly prediction device, classification generation device, anomaly prediction method, and non-transitory computer-readable medium having anomaly prediction program stored thereon

[0001] The present disclosure relates to an anomaly prediction system, an anomaly prediction device, a classification generation device, an anomaly prediction method, and a non-transitory computer-readable medium having an anomaly prediction program stored thereon.

[0002] In recent years, there has been a demand for predicting vehicle failure locations in advance from the perspective of improving convenience for vehicle owners and reducing the workload of repair shops such as dealerships. It is known that certain parts of a vehicle tend to fail more easily when the vehicle is driven on roads with specific conditions. Therefore, it is thought that it would be possible to predict failure locations based on the vehicle's driving road history.

[0003] For example, Patent Document 1 discloses a technology that classifies the area in which a vehicle travels into multiple areas based on geographical information, sets the likelihood of wear for each part for each area, and predicts which parts of the vehicle are likely to have a breakdown.

[0004] Japanese Patent Application Laid-Open No. 2004-234375

[0005] Even for roads with similar geographic information, the parts that are prone to failure may differ for vehicles traveling on each road depending on individual road conditions, etc. Therefore, there is room for further improvement in the accuracy of predicting failed parts.

[0006] The present disclosure has been made to solve such problems, and aims to provide an anomaly prediction system, an anomaly prediction device, a classification generation device, an anomaly prediction method, and a non-transitory computer-readable medium storing an anomaly prediction program that are capable of accurately predicting internal anomalies.

[0007] The abnormality prediction system according to the present disclosure includes a road information database that stores road information linking road position information with road classifications that classify roads according to the impact they have on internal abnormalities of the vehicle, and an abnormality prediction device that can communicate with the road information database, wherein the abnormality prediction device acquires a driving road history of a target vehicle for which an internal abnormality is to be predicted, acquires the road information from the road information database for roads included in the driving road history, and predicts an internal abnormality of the target vehicle based on the road information for the roads included in the driving road history of the target vehicle.

[0008] The abnormality prediction device according to the present disclosure includes a travel road history acquisition unit that acquires the travel road history of a target vehicle for which an internal abnormality is to be predicted; a road information acquisition unit that acquires road information for roads included in the travel road history from a predetermined road information database that stores road information that links road position information with road classifications that classify the roads according to the impact the roads have on internal abnormalities of the vehicle; and a prediction unit that predicts an internal abnormality of the target vehicle based on the road information for the roads included in the travel road history of the target vehicle.

[0009] The classification generation device according to the present disclosure includes a vehicle data acquisition unit that acquires vehicle data linking the road driving history of a plurality of vehicles with the vehicle state of each of the plurality of vehicles while driving on the road; a geographic information acquisition unit that acquires geographic information of roads included in the vehicle data from a predetermined map information database; and a classification generation unit that generates a road classification according to the impact on an internal abnormality of the vehicle based on the vehicle data and the geographic information, and registers the road classification in a road information database.

[0010] The abnormality prediction method according to the present disclosure includes a computer acquiring a driving road history of a target vehicle for which an internal abnormality is to be predicted, acquiring road information for roads included in the driving road history from a predetermined road information database that stores road information linking road position information with road classifications that classify the roads according to the impact the roads have on internal abnormalities of the vehicle, and predicting an internal abnormality of the target vehicle based on the road information for the roads included in the driving road history of the target vehicle.

[0011] A non-transitory computer-readable medium according to the present disclosure stores an abnormality prediction program that causes a computer to execute the following processes: a process of acquiring a driving road history of a target vehicle for which an internal abnormality is to be predicted; a process of acquiring road information for roads included in the driving road history from a predetermined road information database that stores road information that links road position information with road classifications that classify the roads according to the impact the roads have on internal abnormalities of the vehicle; and a process of predicting an internal abnormality of the target vehicle based on the road information for the roads included in the driving road history of the target vehicle.

[0012] The present disclosure makes it possible to provide an anomaly prediction device, a system, a method, and a non-transitory computer-readable medium storing a program that can accurately predict internal anomalies.

[0013] 1 is a block diagram showing the configuration of an anomaly prediction system according to embodiment 1. FIG. 2 is a flowchart showing the flow of an anomaly prediction method according to embodiment 1. FIG. 3 is a block diagram showing the configuration of an anomaly prediction system according to embodiment 2. FIG. 4 is a block diagram showing the configuration of a classification generation device according to embodiment 2. FIG. 5 is a flowchart showing the flow of classification generation processing according to embodiment 2. FIG. 6 is a block diagram showing the configuration of an anomaly prediction device according to embodiment 2. FIG. 7 is a flowchart showing the flow of an anomaly prediction processing according to embodiment 2. FIG. 8 is a block diagram showing the configuration of an anomaly prediction system according to embodiment 3. FIG. 9 is a block diagram showing the configuration of a classification generation device according to embodiment 3. FIG. 10 is a flowchart showing the flow of influence information generation processing in embodiment 3. FIG. 11 is a flowchart showing the flow of an anomaly prediction processing according to embodiment 3. FIG. 12 is a block diagram showing the configuration of an anomaly prediction device according to embodiment 4. FIG. 13 is a flowchart showing the flow of an anomaly prediction processing according to embodiment 4.

[0014] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In each drawing, the same or corresponding elements are designated by the same reference numerals, and for clarity of explanation, duplicate explanations will be omitted as necessary.

[0015] <First Embodiment> Fig. 1 is a block diagram showing the configuration of an abnormality prediction system 100 according to a first embodiment. The abnormality prediction system 100 includes an abnormality prediction device 200 and a road information database 300. The abnormality prediction device 200 and the road information database 300 are each connected to a network 400. Therefore, the abnormality prediction device 200 can communicate with the road information database 300 via the network 400. The network 400 may be a wired communication line or a wireless communication line. The network 400 may include the Internet.

[0016] The road information database 300 stores road information in which location information 310 is linked to road classification 320. The location information 310 is information indicating the location of a road. The road classification 320 classifies roads according to the effect that the road has on an internal abnormality of the vehicle. An internal abnormality of the vehicle is, for example, a failure of a component provided in the vehicle. The road information database 300 stores road information for a plurality of roads.

[0017] The abnormality prediction device 200 is a device that predicts internal abnormalities in a vehicle. The abnormality prediction device 200 is a device that can be operated, for example, by an employee of a repair shop that repairs vehicles, such as a vehicle dealership. Hereinafter, a vehicle for which an internal abnormality is predicted may be referred to as a target vehicle. The abnormality prediction device 200 includes a traveled road history acquisition unit 210, a road information acquisition unit 220, and a prediction unit 230. The traveled road history acquisition unit 210 acquires a traveled road history of a target vehicle for which an internal abnormality is predicted. The traveled road history includes a history of roads on which the vehicle has traveled. The road information acquisition unit 220 acquires road information from a road information database 300 for roads included in the traveled road history acquired by the traveled road history acquisition unit 210. The prediction unit 230 predicts an internal abnormality in the target vehicle based on the road information acquired by the road information acquisition unit 220.

[0018] FIG. 2 is a flowchart showing the flow of the abnormality prediction method according to the first embodiment. First, the traveled road history acquisition unit 210 acquires the traveled road history of a target vehicle for which an internal abnormality is to be predicted (step S101). Next, the road information acquisition unit 220 acquires road information from the road information database 300 for roads included in the traveled road history acquired in step S101 (step S102). Next, the prediction unit 230 predicts an internal abnormality of the target vehicle based on the road information acquired in step S102 (step S103). In this way, the abnormality prediction method according to the first embodiment predicts an internal abnormality of the target vehicle based on road classifications classified according to the impact of the road on the vehicle's internal abnormality. Therefore, the location of the abnormality can be predicted with high accuracy.

[0019] The abnormality prediction device 200 includes a processor, a memory, and a storage device (not shown). The storage device stores a computer program that implements the processing of the abnormality prediction method according to the first embodiment. The processor then loads the computer program from the storage device into the memory and executes the computer program. This allows the processor to realize the functions of the traveled road history acquisition unit 210, the road information acquisition unit 220, and the prediction unit 230.

[0020] Furthermore, the traveled road history acquisition unit 210, the road information acquisition unit 220, and the prediction unit 230 may each be realized by dedicated hardware. Furthermore, some or all of the components of each device may be realized by general-purpose or dedicated circuits, processors, etc., or a combination of these. These may be configured by a single chip, or by multiple chips connected via a bus. Some or all of the components of each device may be realized by a combination of the above-mentioned circuits, etc., and programs. Furthermore, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an FPGA (Field-Programmable Gate Array), etc. may be used as the processor.

[0021] Furthermore, when some or all of the components of the anomaly prediction device 200 are realized by multiple information processing devices, circuits, etc., the multiple information processing devices, circuits, etc. may be centrally or decentralized. For example, the information processing devices, circuits, etc. may be realized as a client-server system, a cloud computing system, or the like, in a form in which each is connected via a communication network. Furthermore, the functions of the anomaly prediction device 200 may be provided in a SaaS (Software as a Service) format.

[0022] <Embodiment 2> Embodiment 2 is a specific example of the above-described embodiment 1. Fig. 3 is a block diagram showing the configuration of an abnormality prediction system 600 according to embodiment 2. The abnormality prediction system 600 includes a classification generation device 700, an abnormality prediction device 800, a vehicle malfunction information database 900, and a road information database 300. The classification generation device 700, the abnormality prediction device 800, the vehicle malfunction information database 900, and the road information database 300 are communicably connected via a network 400. Below, descriptions that overlap with embodiment 1 will be omitted as appropriate.

[0023] The abnormality prediction system 600 is an information system for predicting internal abnormalities in a target vehicle whose owner has reported an abnormality to a repair shop. The target vehicle is, for example, an automobile, but may also be a vehicle other than an automobile, such as a motorcycle or an electric kick scooter. The vehicle malfunction information database 900 stores vehicle malfunction information in which malfunction information 920 is linked to a driving road history 910. The malfunction information 920 is information including the location of the malfunction in the vehicle. The location of the malfunction in the vehicle is, for example, a component that constitutes the vehicle, such as the brakes, gearbox, engine, battery, or tires. The malfunction information 920 may also include information regarding the type of malfunction. The type of malfunction is, for example, the state of damage or the degree of wear or consumption. The vehicle malfunction information database 900 stores vehicle malfunction information for multiple vehicles.

[0024] Next, the configuration of the classification generating device 700 will be described in detail with reference to Fig. 4. Fig. 4 is a block diagram showing the configuration of the classification generating device 700. The classification generating device 700 includes a memory 710, a communication unit 720, a storage unit 730, and a control unit 740.

[0025] The memory 710 is a storage area that temporarily stores the processing contents of the control unit 740, and is a volatile storage device such as a RAM (Random Access Memory). The communication unit 720 is an interface that communicates with the outside of the classification generation device 700. The storage unit 730 is a storage device that stores a program 731 and the like. The program 731 is a computer program that implements the classification generation processing according to the second embodiment.

[0026] The control unit 740 includes a vehicle data acquisition unit 741, a geographic information acquisition unit 742, and a classification generation unit 743. The control unit 740 is a control device that controls the operation of the classification generation device 700, and is, for example, a processor such as a CPU. The control unit 740 loads the program 731 from the storage unit 730 into the memory 710 and executes it. In this way, the control unit 740 realizes the functions of the vehicle data acquisition unit 741, the geographic information acquisition unit 742, and the classification generation unit 743.

[0027] The vehicle data acquisition unit 741 acquires vehicle data of multiple vehicles. The vehicle data is data that links the vehicle's driving road history with the vehicle's state while traveling on that road. The vehicle state is the vehicle's driving state, such as the vehicle's acceleration / deceleration and steering. The vehicle data is, for example, data collected by a connected car using various sensors or the like to describe its own state while traveling. In this case, the multiple vehicles from which the vehicle data acquisition unit 741 acquires vehicle data are connected cars.

[0028] The geographic information acquisition unit 742 acquires geographic information of roads included in the vehicle data acquired by the vehicle data acquisition unit 741 from a predetermined map information database. The predetermined map information database is an existing map information database, such as the Geographic Information System (GIS) of the Geospatial Information Authority of Japan. The geographic information is information related to the geography of the road, including road location information and information on geographic conditions. The geographic conditions are geographical conditions such as topography, climate, and soil, and specifically, for example, conditions such as whether the road is a coastal road, a mountain road, or a road in an urban area.

[0029] The classification generation unit 743 generates a road classification based on the vehicle data acquired by the vehicle data acquisition unit 741 and the geographic information acquired by the geographic information acquisition unit 742, and registers the generated road classification in the road information database 300. Specifically, for example, the classification generation unit 743 identifies a combination of geographic information of a road on which the vehicle traveled and the state of the vehicle while traveling on that road by comparing the vehicle data with the geographic information. Depending on the state of the vehicle while traveling on that road and the geographic information of the road, the parts of the vehicle that are prone to failure, that is, the impact on internal abnormalities of the vehicle, may change. Therefore, the classification generation unit 743 generates a road classification based on a combination of geographic information of a road on which the vehicle traveled and the state of the vehicle while traveling on that road, and links the generated road classification to the road and registers it in the road information database 300.

[0030] Next, the operation of the classification generating device 700 during classification generation will be described with reference to Fig. 5. Fig. 5 is a flowchart showing the flow of classification generation processing.

[0031] First, the vehicle data acquisition unit 741 acquires vehicle data for multiple vehicles (step S201). Next, the geographic information acquisition unit 742 extracts roads traveled by each vehicle from the traveled road history included in the vehicle data acquired in step S201, and acquires geographic information for the roads from a predetermined map information database (step S202). Next, the classification generation unit 743 generates road classifications based on the vehicle data acquired in step S201 and the geographic information acquired in step S202, and registers the generated road classifications in the road information database 300 (step S203). In this way, the classification generation device 700 according to the second embodiment generates road classifications classified according to the effect on internal abnormalities of the vehicle, and registers the road classifications in the road information database 300.

[0032] Next, the configuration of the abnormality prediction device 800 will be described in detail with reference to Fig. 6. Fig. 6 is a block diagram showing the configuration of the abnormality prediction device 800. The abnormality prediction device 800 includes a memory 810, a communication unit 820, a storage unit 830, and a control unit 840.

[0033] The memory 810 is a storage area that temporarily stores the processing contents of the control unit 840, and is a volatile storage device such as a RAM (Random Access Memory). The communication unit 820 is an interface that communicates with the outside of the abnormality prediction device 800. The storage unit 830 is a storage device that stores a program 831 and the like. The program 831 is a computer program that implements the abnormality prediction processing according to the second embodiment.

[0034] The control unit 840 includes a traveling road history acquisition unit 841, a road information acquisition unit 842, and a prediction unit 843. The control unit 840 is a control device that controls the operation of the abnormality prediction device 800, and is, for example, a processor such as a CPU. The control unit 840 loads the program 831 from the storage unit 830 into the memory 810 and executes it. In this way, the control unit 840 realizes the functions of the traveling road history acquisition unit 841, the road information acquisition unit 842, and the prediction unit 843.

[0035] Abnormality prediction device 800 is a device that can be operated by employees of a repair shop that repairs vehicles, such as a vehicle dealership, and is equipped with, for example, hardware (not shown), such as an input device through which the employee makes various inputs and a display device that displays the results of internal abnormality predictions. When a vehicle owner develops a problem with the vehicle, the owner contacts the repair shop to that effect. Upon receiving the contact from the owner, the repair shop employee inputs into abnormality prediction device 800 that an internal abnormality will be predicted for the vehicle, i.e., the target vehicle.

[0036] When the abnormality prediction device 800 receives an input indicating that an internal abnormality is to be predicted for the target vehicle, the traveling road history acquisition unit 841 acquires the traveling road history of the target vehicle. The traveling road history of the target vehicle includes the history of roads on which the target vehicle has traveled. The traveling road history of the target vehicle is, for example, a record of a GPS (Global Positioning System) equipped in the target vehicle. The traveling road history acquisition unit 841 can acquire the traveling road history of the target vehicle by acquiring the GPS record of the target vehicle. In addition, the traveling road history acquisition unit 841 acquires the traveling road histories of multiple vehicles from the vehicle malfunction information database 900.

[0037] The road information acquisition unit 842 acquires road information from the road information database 300 for roads included in the travel road history of the target vehicle acquired by the travel road history acquisition unit 841. In addition, the road information acquisition unit 842 acquires road information from the road information database 300 for roads included in the travel road histories of multiple vehicles acquired by the travel road history acquisition unit 841.

[0038] The prediction unit 843 predicts an internal abnormality of the target vehicle based on the traveled road history of the target vehicle acquired by the traveled road history acquisition unit 841 and the road information acquired by the road information acquisition unit 842. Specifically, the prediction unit 843 first compares the road classification of the road included in the traveled road history of the target vehicle with the road classification of the road included in the traveled road history of multiple vehicles. The traveled road history usually includes multiple roads. Each road included in the traveled road history may be associated with a different road classification. Hereinafter, the set of road classifications associated with each road included in the traveled road history may be referred to as the road classification breakdown. The prediction unit 843 compares the road classification breakdown of the target vehicle with the road classification breakdown of the multiple vehicles, and identifies similar vehicles whose road classification breakdown is similar to that of the target vehicle from among the multiple vehicles whose malfunction information is registered in the vehicle malfunction information database 900. Since the similar vehicles have similar road classification breakdowns to that of the target vehicle, it is estimated that they are likely to have the same internal abnormality as the target vehicle. Therefore, the prediction unit 843 acquires failure information of similar vehicles from the vehicle failure information database 900 and predicts an internal abnormality of the target vehicle.

[0039] The comparison method used by the prediction unit 843 to compare the breakdown of road categories is not particularly limited and can be set as appropriate. For example, the prediction unit 843 may weight each road category according to the travel distance on each road included in the traveled road history, and compare the target vehicle with multiple vehicles.

[0040] Next, the operation of the abnormality prediction device 800 when predicting an abnormality will be described with reference to Fig. 7. Fig. 7 is a flowchart showing the flow of the abnormality prediction process.

[0041] When an employee inputs a command to predict an internal abnormality for a target vehicle into the abnormality prediction device 800, the traveling road history acquisition unit 841 acquires the traveling road history of the target vehicle (step S301). Next, the road information acquisition unit 842 extracts roads on which the target vehicle has traveled from the traveling road history of the target vehicle acquired in step S301, and acquires road information for the extracted roads from the road information database 300 (step S302). Next, the traveling road history acquisition unit 841 acquires the traveling road histories of multiple vehicles from the vehicle malfunction information database 900 (step S303). Next, the road information acquisition unit 842 extracts roads on which each vehicle has traveled from the traveling road histories of the multiple vehicles acquired in step S303, and acquires road information for the extracted roads from the road information database 300 (step S304). Note that in the example shown in FIG. 7 , steps S303 and S304 are performed after steps S301 and S302. However, steps S303 and S304 may be performed before steps S301 and S302, or may be performed in parallel with steps S301 and S302.

[0042] Next, the prediction unit 843 compares the road information acquired in step S302 with the road information acquired in step S304, and identifies a similar vehicle that is similar to the target vehicle from among the multiple vehicles (step S305). Next, the prediction unit 843 acquires malfunction information of the similar vehicle identified in step S305 from the vehicle malfunction information database 900 (step S306). Next, the prediction unit 843 predicts an internal abnormality of the target vehicle based on the malfunction information acquired in step S306 (step S307).

[0043] The abnormality prediction device 800 outputs the prediction result made in step S307 to a display device or the like. An employee of the repair shop can check the displayed prediction result and, based on the prediction result, order parts that are likely to be needed to repair the target vehicle from the manufacturer or the like before the owner visits. Therefore, when the owner visits the repair shop with the target vehicle, the employee can identify the abnormal part and repair the abnormal part on the same day.

[0044] In this way, the abnormality prediction device 800 according to the second embodiment identifies similar vehicles whose road classifications are similar to those of the target vehicle and predicts internal abnormalities of the target vehicle based on the failure information of the similar vehicles, thereby enabling accurate prediction of the location of the abnormality. Furthermore, because the abnormality prediction device 800 predicts internal abnormalities using GPS records of the target vehicle, it is possible to predict internal abnormalities even in vehicles that are not equipped with various sensors, such as connected cars.

[0045] <Third Embodiment> The third embodiment is a modification of the second embodiment described above. In the third embodiment, an internal abnormality in a target vehicle is predicted based on impact information linked to a road classification. FIG. 8 is a block diagram showing the configuration of an abnormality prediction system 1000 according to the third embodiment. The abnormality prediction system 1000 differs from the abnormality prediction system 600 shown in FIG. 3 in that it includes a classification generation device 1100 instead of the classification generation device 700, and further includes an impact information database 1200. The other configuration overlaps with the second embodiment, etc., and therefore description thereof will be omitted as appropriate.

[0046] The impact information database 1200 stores impact information in which road classifications 1210 are linked to failure tendency information 1220. The failure tendency information 1220 is information that indicates the tendency of failures that are likely to occur in vehicles that travel on roads linked to the road classifications. The failure tendency information 1220 includes the tendency of failure locations in a vehicle. The failure locations in a vehicle are, for example, parts that make up the vehicle, such as brakes, gearboxes, engines, batteries, and tires. The failure tendency information 1220 may also include information regarding the tendency of failure modes. The failure mode is, for example, the state of damage, or the degree of wear or consumption. The impact information database 1200 stores impact information for a plurality of road classifications.

[0047] Next, the configuration of the classification generating device 1100 will be described in detail with reference to Fig. 9. Fig. 9 is a block diagram showing the configuration of the classification generating device 1100. The classification generating device 1100 differs from the classification generating device 700 shown in Fig. 4 in that it includes a control unit 1140 instead of the control unit 740. In addition to the configuration shown in the control unit 740, the control unit 1140 includes a failure information acquisition unit 1144 and an impact information generation unit 1145.

[0048] The malfunction information acquisition unit 1144 acquires malfunction information of multiple vehicles from the vehicle malfunction information database 900. The impact information generation unit 1145 generates impact information based on the driving road history included in the vehicle data acquired by the vehicle data acquisition unit 741 and the malfunction information acquired by the malfunction information acquisition unit 1144, and registers the generated impact information in the impact information database 1200. The impact information generation unit 1145 may generate malfunction trend information included in the impact information by performing statistical processing on the malfunction information of multiple vehicles. For example, when the malfunction information of multiple vehicles includes the degree of brake wear, the impact information generation unit 1145 may calculate a representative value from these multiple degrees of brake wear and use the calculated representative value as the degree of brake wear in the malfunction trend information. The representative value may be an average value, a mode value, a median value, a maximum value, a minimum value, or the like. The impact information generation unit 1145 generates impact information by linking the road classification linked to the road included in the traveled road history with failure tendency information that indicates the tendency of failures that are likely to occur in vehicles that have traveled on that road.

[0049] Next, the operation of the classification generating device 1100 when generating impact information will be described with reference to Fig. 10. Fig. 10 is a flowchart showing the flow of impact information generation processing.

[0050] First, the vehicle data acquisition unit 741 acquires vehicle data for multiple vehicles (step S401). Next, the malfunction information acquisition unit 1144 acquires malfunction information for multiple vehicles from the vehicle malfunction information database 900 (step S402). Next, the impact information generation unit 1145 generates impact information based on the vehicle data acquired in step S401 and the malfunction information acquired in step S402, and registers the generated impact information in the impact information database 1200 (step S403).

[0051] Next, the operation of the abnormality prediction device 800 in the third embodiment will be described with reference to Fig. 11. Fig. 11 is a flowchart showing the flow of the abnormality prediction process.

[0052] When an employee inputs a command to predict an internal abnormality for a target vehicle into the abnormality prediction device 800, the traveled road history acquisition unit 841 acquires the traveled road history of the target vehicle (step S501). Next, the road information acquisition unit 842 extracts roads on which the target vehicle has traveled from the traveled road history of the target vehicle acquired in step S501 and acquires road information for the extracted roads from the road information database 300 (step S502). Next, the prediction unit 843 acquires impact information linked to the road classification included in the road information acquired in step S502 from the impact information database 1200 (step S503). Next, the prediction unit 843 predicts an internal abnormality for the target vehicle based on the impact information acquired in step S503 (step S504).

[0053] In this way, the abnormality prediction system 1000 according to the third embodiment predicts internal abnormalities of the target vehicle based on impact information that links failure tendency information to road classification, and therefore the abnormality prediction device 800 can accurately predict the location where an abnormality is occurring without referring to the vehicle failure information database 900.

[0054] <Fourth Embodiment> The fourth embodiment is a modification of the second embodiment described above. In the fourth embodiment, an internal abnormality is predicted using medical interview information obtained from an owner. FIG. 12 is a block diagram showing the configuration of an abnormality prediction device 1300 according to the fourth embodiment. The abnormality prediction device 1300 differs from the abnormality prediction device 800 shown in FIG. 6 in that it includes a control unit 1340 instead of the control unit 840. In addition to the components included in the control unit 840, the control unit 1340 includes an input receiving unit 1344.

[0055] The input receiving unit 1344 receives information input by an employee operating an input device or the like. When an employee is notified by a vehicle owner that a problem has occurred with the vehicle, the employee interviews the owner about the problem information. The problem information includes specific details of the vehicle problem, such as "an abnormal noise occurs when braking." The employee inputs the information heard, i.e., medical interview information including the vehicle problem information, into an input device or the like. The input receiving unit 1344 receives input of medical interview information.

[0056] In the fourth embodiment, the prediction unit 843 predicts an internal abnormality of the target vehicle based on the medical history information received by the input receiving unit 1344, the driving road history of the target vehicle acquired by the driving road history acquisition unit 841, and the road information acquired by the road information acquisition unit 842. Specifically, the prediction unit 843 first narrows down locations where an internal abnormality is likely to occur based on the medical history information. Specifically, for example, if the medical history information is "abnormal noise occurs when braking," the prediction unit 843 determines that an internal abnormality is likely to occur in the brakes and their peripheral components. Next, the prediction unit 843 compares the road classification of the road included in the driving road history of the target vehicle with the road classification of roads included in the driving road histories of multiple vehicles, and identifies similar vehicles that are similar to the target vehicle. Next, the prediction unit 843 acquires failure information of similar vehicles from the vehicle failure information database 900 and predicts an internal abnormality for the locations where an internal abnormality is likely to occur, which have been narrowed down based on the medical history information.

[0057] Next, the operation of the abnormality prediction device 1300 when predicting an abnormality will be described with reference to Fig. 13. Fig. 13 is a flowchart showing the flow of the abnormality prediction process.

[0058] When an employee inputs medical interview information about the target vehicle into the abnormality prediction device 800, the input receiving unit 1344 receives the input of the medical interview information (step S601). Next, the prediction unit 843 narrows down the locations where an internal abnormality is likely to occur based on the medical interview information received in step S601 (step S602).

[0059] Next, the traveling road history acquisition unit 841 acquires the traveling road history of the target vehicle (step S603). Next, the road information acquisition unit 842 extracts roads on which the target vehicle has traveled from the traveling road history of the target vehicle acquired in step S603, and acquires road information for those roads from the road information database 300 (step S604). Next, the traveling road history acquisition unit 841 acquires the traveling road histories of multiple vehicles from the vehicle malfunction information database 900 (step S605). Next, the road information acquisition unit 842 extracts roads on which each vehicle has traveled from the traveling road histories of the multiple vehicles acquired in step S605, and acquires road information for those roads from the road information database 300 (step S606).

[0060] Next, the prediction unit 843 compares the road information acquired in step S604 with the road information acquired in step S606, and identifies a similar vehicle to the target vehicle from among the multiple vehicles (step S607). Next, the prediction unit 843 acquires malfunction information of the similar vehicle identified in step S607 from the vehicle malfunction information database 900 (step S608). Next, the prediction unit 843 predicts an internal abnormality of the target vehicle at the location narrowed down in step S602 based on the malfunction information acquired in step S607 (step S609).

[0061] In this way, the abnormality prediction device 1300 according to the fourth embodiment narrows down the locations where an internal abnormality is likely to occur based on the medical interview information, and then predicts the internal abnormality, thereby enabling more accurate prediction of the location where an abnormality has occurred.

[0062] Although the above-described embodiment has been described as a hardware configuration, the present disclosure is not limited to this. Any processing in the present disclosure can also be realized by causing a CPU to execute a computer program.

[0063] In the above examples, the program can be stored and supplied to a computer using various types of non-transitory computer-readable media. Non-transitory computer-readable media include various types of tangible storage media. Examples of non-transitory computer-readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROMs (Read Only Memory), CD-Rs, CD-RWs, DVDs (Digital Versatile Discs), and semiconductor memories (e.g., mask ROMs, PROMs (Programmable ROMs), EPROMs (Erasable PROMs), flash ROMs, and RAMs (Random Access Memory)). The program may also be supplied to a computer by various types of transitory computer-readable media. Examples of transitory computer-readable media include electrical signals, optical signals, and electromagnetic waves. The temporary computer-readable medium can supply the program to the computer via a wired communication path such as an electric wire or an optical fiber, or via a wireless communication path.

[0064] The present disclosure is not limited to the above-described embodiments, and may be modified as appropriate without departing from the spirit and scope of the present disclosure. In addition, the present disclosure may be implemented by appropriately combining the respective embodiments.

[0065] Some or all of the above embodiments can be described as, but are not limited to, the following supplementary notes.

[0066] (Appendix A1) An abnormality prediction system comprising: a road information database that stores road information linking road position information with road classifications that classify roads according to the impact the roads have on internal abnormalities of a vehicle; and an abnormality prediction device that can communicate with the road information database, wherein the abnormality prediction device obtains a driving road history of a target vehicle for which an internal abnormality is to be predicted, obtains the road information from the road information database for roads included in the driving road history, and predicts an internal abnormality of the target vehicle based on the road information for the roads included in the driving road history of the target vehicle.

[0067] (Appendix A2) The abnormality prediction system described in Appendix A1 further comprises a vehicle malfunction information database capable of communicating with the abnormality prediction device and storing vehicle malfunction information linking the driving road histories of a plurality of vehicles with malfunction information for each of the plurality of vehicles, wherein the abnormality prediction device identifies a similar vehicle from the plurality of vehicles that has a driving road history similar to that of the target vehicle based on the driving road history and the road information of the target vehicle, and predicts an internal abnormality of the target vehicle based on the malfunction information of the similar vehicle.

[0068] (Appendix A3) The abnormality prediction system described in Appendix A1 further comprises a classification generation device capable of communicating with the road information database, wherein the classification generation device acquires vehicle data linking the driving road histories of multiple vehicles with the vehicle states of each of the multiple vehicles while driving on that road, acquires geographic information of roads included in the vehicle data from a predetermined map information database, generates the road classification based on the vehicle data and the geographic information, and registers the road classification in the road information database.

[0069] (Appendix A4) The abnormality prediction system described in Appendix A3, further comprising an impact information database capable of communicating with the abnormality prediction device and the classification generation device, and storing impact information linking the road classification with failure trend information indicating a tendency of failures that are likely to occur in vehicles that have traveled on the road, wherein the classification generation device acquires failure information of the plurality of vehicles, and generates impact information linking the road classification linked to the road included in the travel road history with the failure trend information indicating a tendency of failures that are likely to occur in vehicles that have traveled on the road, based on the travel road history and the failure information of the plurality of vehicles, and registers the impact information in the road information database, and the abnormality prediction device acquires the road classification linked to the road included in the travel road history of the target vehicle, and predicts an internal abnormality of the target vehicle based on the impact information linked to the road classification.

[0070] (Appendix A5) The abnormality prediction system described in Appendix A1, wherein the abnormality prediction device accepts input of medical interview information including defect information of the vehicle, and predicts an internal abnormality of the vehicle based on the medical interview information, the driving road history, and the road information.

[0071] (Appendix B1) An abnormality prediction device comprising: a travel road history acquisition means for acquiring the travel road history of a target vehicle for which an internal abnormality is to be predicted; a road information acquisition means for acquiring road information about roads included in the travel road history from a predetermined road information database that stores road information linking road position information with road classifications that classify the roads according to the impact the roads have on internal abnormalities of the vehicle; and a prediction means for predicting an internal abnormality of the target vehicle based on the road information about the roads included in the travel road history of the target vehicle.

[0072] (Appendix B2) The abnormality prediction device described in Appendix B1, wherein the prediction means identifies a similar vehicle from among a plurality of vehicles that has a similar driving road history to that of the target vehicle based on the driving road history and the road information of the target vehicle, and predicts an internal abnormality of the target vehicle based on failure information of the similar vehicle obtained from a predetermined vehicle failure information database that stores vehicle failure information linking the driving road histories of the plurality of vehicles with failure information of each of the plurality of vehicles.

[0073] (Appendix C1) A classification generation device comprising: a vehicle data acquisition means for acquiring vehicle data linking the driving road history of a plurality of vehicles with the vehicle state of each of the plurality of vehicles while driving on that road; a geographic information acquisition means for acquiring geographic information of roads included in the vehicle data from a predetermined map information database; and a classification generation means for generating road classifications that classify roads according to the impact they have on internal abnormalities of the vehicle based on the vehicle data and the geographic information, and registering the road classifications in a road information database.

[0074] (Appendix C2) The classification generation device described in Appendix C1 further comprises a failure information acquisition means for acquiring failure information of the plurality of vehicles; and an impact information generation means for generating impact information that links road classifications linked to roads included in the traveled road history with failure tendency information that indicates the tendency of failures that are likely to occur in vehicles that have traveled on that road, based on the traveled road history and the failure information of the plurality of vehicles, and registering the impact information in a road information database.

[0075] (Appendix D1) An abnormality prediction method, in which a computer obtains a driving road history of a target vehicle for which an internal abnormality is to be predicted, obtains road information for roads included in the driving road history from a predetermined road information database that stores road information linking road position information with road classifications that classify the roads according to the impact the roads have on internal abnormalities of the vehicle, and predicts an internal abnormality of the target vehicle based on the road information for the roads included in the driving road history of the target vehicle.

[0076] (Appendix E1) A non-transitory computer-readable medium storing an abnormality prediction program that causes a computer to execute the following processes: a process of acquiring the driving road history of a target vehicle for which an internal abnormality is to be predicted; a process of acquiring road information for roads included in the driving road history from a predetermined road information database that stores road information that links road position information with road classifications that classify the roads according to the impact the roads have on internal abnormalities of the vehicle; and a process of predicting an internal abnormality of the target vehicle based on the road information for the roads included in the driving road history of the target vehicle.

[0077] Although the present invention has been described above with reference to the embodiments (and examples), the present invention is not limited to the above-described embodiments (and examples). Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention.

[0078] 100 Abnormality prediction system 200 Abnormality prediction device 210 Traveled road history acquisition unit 220 Road information acquisition unit 230 Prediction unit 300 Road information database 310 Location information 320 Road classification 400 Network 600 Abnormality prediction system 700 Classification generation device 710 Memory 720 Communication unit 730 Storage unit 731 Program 740 Control unit 741 Vehicle data acquisition unit 742 Geographic information acquisition unit 743 Classification generation unit 800 Abnormality prediction device 810 Memory 820 Communication unit 830 Storage unit 831 Program 840 Control unit 841 Traveled road history acquisition unit 842 Road information acquisition unit 843 Prediction unit 900 Vehicle malfunction information database 910 Traveled road history 920 Malfunction information 1000 Abnormality prediction system 1100 Classification generation device 1140 Control unit 1144 Failure information acquisition unit 1145 Impact information generation unit 1200 Impact information database 1210 Road classification 1220 Failure tendency information 1300 Abnormality prediction device 1340 Control unit 1344 Input reception unit

Claims

1. a road information database that stores road information that links road position information with road classifications that classify the roads according to the influence the roads have on internal abnormalities of the vehicle; an abnormality prediction device capable of communicating with the road information database, The abnormality prediction device a travel road history acquisition means for acquiring a travel road history of a target vehicle for which an internal abnormality is predicted; road information acquisition means for acquiring road information from the road information database for roads included in the traveled road history; a prediction means for predicting an internal abnormality of the target vehicle based on the road information about the road included in the travel road history of the target vehicle; An abnormality prediction system comprising:

2. The system further includes a vehicle malfunction information database that can communicate with the abnormality prediction device and that stores vehicle malfunction information that links the driving road history of a plurality of vehicles with malfunction information of each of the plurality of vehicles, The prediction means provided in the abnormality prediction device includes: identifying a similar vehicle from the plurality of vehicles that has a similar driving road history to that of the target vehicle based on the driving road history and the road information of the target vehicle, and predicting an internal abnormality of the target vehicle based on failure information of the similar vehicle; The anomaly prediction system according to claim 1 .

3. further comprising a classification generating device capable of communicating with the road information database; The classification generation device a vehicle data acquisition means for acquiring vehicle data linking a driving road history of a plurality of vehicles with a vehicle state of each of the plurality of vehicles while driving on the road; geographic information acquisition means for acquiring geographic information of roads included in the vehicle data from a predetermined map information database; a classification generating means for generating the road classification based on the vehicle data and the geographic information and registering the road classification in the road information database; The anomaly prediction system according to claim 1 , comprising:

4. an impact information database capable of communicating with the abnormality prediction device and the classification generation device, which stores impact information linking the road classification with failure tendency information indicating a tendency of failures likely to occur in vehicles that have traveled on the road; The classification generation device a failure information acquisition means for acquiring failure information of the plurality of vehicles; an impact information generating means for generating impact information that links road classifications linked to roads included in the traveled road history with failure tendency information that indicates a tendency of failures that are likely to occur in vehicles that have traveled on the roads, based on the traveled road history and the failure information of the plurality of vehicles, and registering the impact information in the road information database; The abnormality prediction device a prediction means for acquiring a road classification associated with a road included in the traveled road history of the target vehicle, and predicting an internal abnormality of the target vehicle based on impact information associated with the road classification; The abnormality prediction system according to claim 3 .

5. The abnormality prediction device an input receiving means for receiving input of medical inquiry information including defect information of the vehicle; a prediction means for predicting an internal abnormality of the vehicle based on the medical interview information, the traveled road history, and the road information; The anomaly prediction system according to claim 1 , comprising:

6. a travel road history acquisition means for acquiring a travel road history of a target vehicle for which an internal abnormality is predicted; road information acquisition means for acquiring road information for roads included in the traveled road history from a predetermined road information database that stores road information linking road position information with road classifications that classify the roads according to the impact the roads have on internal abnormalities of the vehicle; a prediction means for predicting an internal abnormality of the target vehicle based on the road information about the road included in the travel road history of the target vehicle; An abnormality prediction device comprising:

7. the prediction means identifies a similar vehicle from among a plurality of vehicles that has a similar driving road history to that of the target vehicle based on the driving road history and the road information of the target vehicle, and predicts an internal abnormality of the target vehicle based on failure information of the similar vehicle acquired from a predetermined vehicle failure information database that stores vehicle failure information linking the driving road histories of the plurality of vehicles with failure information of each of the plurality of vehicles; The abnormality prediction device according to claim 6 .

8. a vehicle data acquisition means for acquiring vehicle data linking a driving road history of a plurality of vehicles with a vehicle state of each of the plurality of vehicles while driving on the road; geographic information acquisition means for acquiring geographic information of roads included in the vehicle data from a predetermined map information database; a classification generating means for generating a road classification according to an influence on an internal abnormality of a vehicle based on the vehicle data and the geographical information, and registering the road classification in a road information database; A classification generation device comprising:

9. The computer Acquire the driving road history of the target vehicle for which an internal abnormality is to be predicted; Obtaining road information for roads included in the traveled road history from a predetermined road information database that stores road information linking road position information with road classifications that classify the roads according to the impact the roads have on internal abnormalities of the vehicle; predicting an internal abnormality of the target vehicle based on the road information about the road included in the travel road history of the target vehicle; Anomaly prediction methods.

10. On the computer, A process of acquiring a driving road history of a target vehicle for which an internal abnormality is to be predicted; a process of acquiring road information for roads included in the traveled road history from a predetermined road information database that stores road information linking road position information with road classifications that classify the roads according to the influence the roads have on internal abnormalities of the vehicle; a process of predicting an internal abnormality of the target vehicle based on the road information about the road included in the traveled road history of the target vehicle; An abnormality prediction program that executes the following.