JP6612003B1 - Information processing apparatus, information processing method, and information processing program - Google Patents

Abstract

The information acquisition unit (101) acquires behavior history information indicating a history of behavior during travel of the vehicle. The influence estimation unit (105) estimates the influence of the traveling of the vehicle on the vehicle element, which is an element of the vehicle, based on the behavior history during traveling of the vehicle indicated in the behavior history information. The diagnosis unit (106) diagnoses the state of the vehicle element based on the influence of the traveling of the vehicle on the vehicle element estimated by the influence estimation unit (105).

Description

  The present invention relates to a technique for diagnosing a state of a vehicle element that is an element of a vehicle.

When an abnormality occurs in a vehicle element (hereinafter referred to as “vehicle element” or simply “element”) while the vehicle is traveling, the abnormality is notified to the user of the vehicle. For example, the abnormality of the vehicle element is notified to the user by a method such as lighting of a warning light on a meter panel, lighting of a display light, or output of a warning sound. When the user is notified of the abnormality, the user checks the vehicle or replaces the vehicle element having the abnormality. Further, the user diagnoses the state of the vehicle element through daily inspection or periodic inspection, and replaces the element if necessary.
The vehicle element is an element that is mounted, added, mounted, assembled, filled, or applied to the vehicle. Vehicle elements are affected by the running of the vehicle. For example, the vehicle element is consumed as the vehicle travels. The vehicle elements include engines, doors, lights, ECUs (Electronic Control Units), mirrors, glasses, suspensions, etc., tires, batteries, engine oil, cooling water, brake pads, and the like.
Of vehicle elements, replacement of consumables such as engine oil and tires is generally performed based on a predetermined travel distance or use period. However, it is known that the life of consumables is shortened if special traveling such as sudden start, sudden braking, and repeated short-distance travel is frequently performed.
For this reason, it is desirable that the state diagnosis of the vehicle element is performed based on a specific driving environment and driving conditions.

  In Patent Document 1, a vehicle state analysis system is disclosed. More specifically, in Patent Document 1, vehicle driving environment data, driving state data, and reference control data related to engine control are collected. Then, the collected traveling environment data, traveling state data, and reference control data are notified to the vehicle management center. The vehicle management center compares the reference control data notified from the vehicle with the standard control data of the vehicle, and diagnoses whether there is an abnormality in the vehicle. Then, the vehicle management center requests the user to check the vehicle or repair the failure according to the diagnosis result.

JP 2007-76402 A

In Patent Literature 1, it is determined whether or not a vehicle element is abnormal by comparing a control amount for the vehicle element with a standard value. However, it is difficult to apply the technique of Patent Document 1 to vehicle elements that cannot calculate the control amount, such as tires and brake pads. In particular, for vehicle elements such as engine oil and cooling water whose state cannot be directly observed, it is difficult to determine a standard value as a reference for diagnosis.
As another method, a method of detecting the occurrence of vibration or abnormal noise accompanying an abnormality of the vehicle element by attaching a sensor to the vehicle element has been studied. However, there are vehicle elements that are difficult to mount sensors, and it is difficult to apply the method to all vehicle elements.

  The present invention has been made in view of such circumstances, and a main object thereof is to obtain a configuration capable of accurately diagnosing the state of a vehicle element.

An information processing apparatus according to the present invention includes:
An information acquisition unit for acquiring behavior history information indicating a history of behavior of the vehicle while traveling;
An influence estimator that estimates the influence of the vehicle traveling on the vehicle element, which is an element of the vehicle, based on the behavior history of the vehicle during traveling indicated in the behavior history information;
And a diagnosis unit that diagnoses the state of the vehicle element based on the influence on the vehicle element caused by traveling of the vehicle estimated by the influence estimation unit.

  According to the present invention, it is possible to accurately diagnose the state of the vehicle element.

1 is a diagram illustrating a configuration example of a diagnostic system according to Embodiment 1. FIG. FIG. 3 is a diagram illustrating a hardware configuration example of a server device according to the first embodiment. FIG. 3 is a diagram illustrating a hardware configuration example of the in-vehicle device according to the first embodiment. FIG. 3 is a diagram illustrating a functional configuration example of a server apparatus according to the first embodiment. FIG. 3 is a diagram illustrating a functional configuration example of the in-vehicle device according to the first embodiment. The figure which shows the example of the vehicle management information which concerns on Embodiment 1. FIG. FIG. 5 is a diagram showing an example of element notification information according to the first embodiment. FIG. 5 is a diagram showing an example of behavior history information according to the first embodiment. FIG. 4 is a diagram illustrating an example of diagnosis result information according to the first embodiment. The figure which shows the example of the vehicle element management information which concerns on Embodiment 1. FIG. FIG. 6 is a diagram showing an example of element state information according to the first embodiment. 5 is a flowchart illustrating an operation example of the server apparatus according to the first embodiment. 5 is a flowchart showing an example of learning processing according to the first embodiment. 5 is a flowchart illustrating an example of model generation processing according to Embodiment 1. The figure which shows the example of the driving | running | working condition information which concerns on Embodiment 1, driving | running | working environment information, and vehicle specific information. FIG. 4 is a diagram illustrating an example of diagnostic model information according to the first embodiment. 5 is a flowchart illustrating an example of a diagnostic process according to the first embodiment. 5 is a flowchart showing an example of element state diagnosis processing (before travel) according to the first embodiment. 6 is a flowchart showing an example of element state diagnosis processing (after traveling) according to the first embodiment. FIG. 4 is a diagram illustrating a functional configuration example of a server device according to a second embodiment. FIG. 6 is a diagram illustrating a functional configuration example of an in-vehicle device according to a second embodiment. 10 is a flowchart showing an operation example of the in-vehicle device according to the second embodiment. 9 is a flowchart illustrating an example of model acquisition processing according to Embodiment 2. The figure which shows the example of the vehicle information which concerns on Embodiment 2. FIG. The figure which shows the example of the vehicle element information which concerns on Embodiment 2. FIG. 10 is a flowchart illustrating an example of a diagnostic process according to the second embodiment. 10 is a flowchart illustrating an example of a diagnostic process according to the third embodiment. The figure which shows the example of the behavior history information (vehicle speed) which concerns on Embodiment 4. FIG. The figure which shows the category classification | category result which concerns on Embodiment 4. FIG. The figure which shows the example of the driving information which concerns on Embodiment 4. FIG. FIG. 10 shows an example of analysis result information according to the fourth embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings. In the following description of the embodiments and drawings, the same reference numerals denote the same or corresponding parts.

Embodiment 1 FIG.
*** Explanation of configuration ***
** Explanation of diagnostic system 500 **
FIG. 1 shows a configuration example of a diagnostic system 500 according to the present embodiment.
As shown in FIG. 1, the diagnosis system 500 includes a server device 100 and a plurality of in-vehicle devices 300. The in-vehicle device 300 is mounted on the vehicle 200.
In FIG. 1, only two vehicles 200 are drawn, but the number of vehicles 200 is not limited to two.
The server device 100 is an example of an information processing device. The operations performed by the server device 100 are examples of an information processing method and an information processing program.
The server device 100 and the in-vehicle device 300 communicate with each other. For example, the server apparatus 100 and the in-vehicle apparatus 300 perform communication using a mobile communication network such as a wireless LAN (Local Area Network) such as Wi-Fi, 3G, or LTE (Long Term Evolution) (registered trademark).
The server device 100 receives behavior history information indicating a history of behavior during travel of the vehicle 200 from the in-vehicle device 300. The behavior during travel of the vehicle 200 is a response of the vehicle 200 to a driver's operation and a response of the vehicle 200 to an action from a traveling environment such as a road surface. The server device 100 performs an analysis using the behavior history information, diagnoses the state of the vehicle element, and notifies the in-vehicle device 300 of the diagnosis result. Details of the behavior history information will be described later.

** Description of hardware configuration example of server device 100 **
FIG. 2 shows a hardware configuration example of the server apparatus 100.
The server device 100 is a computer.
The server device 100 includes a processor 911, a main storage device 912, an auxiliary storage device 913, and a communication device 914 as hardware.
Further, as illustrated in FIG. 4, the server device 100 includes an information acquisition unit 101, an information storage unit 102, a diagnostic model generation unit 103, a diagnostic model storage unit 104, an influence estimation unit 105, and a diagnostic unit 106 as functional configurations. . The functional configuration of the server apparatus 100 will be described later.
The auxiliary storage device 913 stores programs that realize the functions of the information acquisition unit 101, the diagnostic model generation unit 103, the influence estimation unit 105, and the diagnosis unit 106.
These programs are loaded from the auxiliary storage device 913 to the main storage device 912. The processor 911 executes these programs, and performs operations of an information acquisition unit 101, a diagnosis model generation unit 103, an influence estimation unit 105, and a diagnosis unit 106, which will be described later.
FIG. 2 schematically illustrates a state in which the processor 911 is executing a program that realizes the functions of the information acquisition unit 101, the diagnostic model generation unit 103, the influence estimation unit 105, and the diagnosis unit 106.
The information storage unit 102 and the diagnostic model storage unit 104 are realized by the main storage device 912 or the auxiliary storage device 913.

** Explanation of hardware configuration example of in-vehicle device 300 **
FIG. 3 shows a hardware configuration example of the in-vehicle device 300.
The in-vehicle device 300 is a computer.
The in-vehicle device 300 includes a processor 931, a main storage device 932, an auxiliary storage device 933, and a communication device 934 as hardware.
Further, as shown in FIG. 5, the in-vehicle device 300 includes a communication unit 301, a diagnosis notification display unit 302, an element notification information acquisition unit 303, a behavior history information generation unit 304, a sensor information collection unit 305, vehicle control as functional configurations. A unit 306 and a storage unit 307. The functional configuration of the in-vehicle device 300 will be described later.
The auxiliary storage device 933 stores programs that realize the functions of the communication unit 301, the diagnosis notification display unit 302, the element notification information acquisition unit 303, the behavior history information generation unit 304, the sensor information collection unit 305, and the vehicle control unit 306. ing.
These programs are loaded from the auxiliary storage device 933 to the main storage device 932. The processor 931 executes these programs, and the operations of a communication unit 301, a diagnosis notification display unit 302, an element notification information acquisition unit 303, a behavior history information generation unit 304, a sensor information collection unit 305, and a vehicle control unit 306, which will be described later. I do.
In FIG. 3, the processor 931 executes a program that realizes the functions of the communication unit 301, the diagnosis notification display unit 302, the element notification information acquisition unit 303, the behavior history information generation unit 304, the sensor information collection unit 305, and the vehicle control unit 306. The state is shown schematically.
The storage unit 307 is realized by the main storage device 932 or the auxiliary storage device 933.

** Description of functional configuration example of server device 100 **
FIG. 4 shows a functional configuration example of the server apparatus 100.

The information acquisition unit 101 acquires vehicle management information, element notification information, and behavior history information from the in-vehicle device 300.
The vehicle management information is information shown in FIG. 6, for example. Details of the vehicle management information will be described later.
The element notification information is, for example, information illustrated in FIG. Details of the element notification information will be described later.
The behavior history information is, for example, information illustrated in FIG. Details of the behavior history information will be described later.
The process performed by the information acquisition unit 101 corresponds to the information acquisition process.

The information storage unit 102 stores the vehicle management information, element notification information, and behavior history information acquired by the information acquisition unit 101.
Further, the information storage unit 102 stores diagnosis result information and vehicle element management information generated by the diagnosis unit 106 every time the diagnosis unit 106 makes a diagnosis.
The diagnosis result information is, for example, information shown in FIG. Details of the diagnosis result information will be described later.
The vehicle element management information is information shown in FIG. 10, for example. Details of the vehicle element management information will be described later.

The diagnostic model generation unit 103 generates a diagnostic model using the behavior history information and element state information. The element state information indicates the state of the vehicle element. The element state information is, for example, information shown in FIG.
The diagnostic model generation unit 103 generates a diagnostic model by learning the influence of the traveling state of the vehicle 200 and the traveling environment of the vehicle 200 on the vehicle elements. Note that the traveling state is a characteristic in traveling of the vehicle 200 such as a lot of sudden start / less, a lot of sudden braking, or the like. The traveling environment is an environment in which the vehicle 200 travels such as traveling on a rough road, traveling on an uphill / downhill road, and traveling at night.
The diagnosis model generation unit 103 refers to the generation rule of the diagnosis model, analyzes the correlation between the driving state information, the driving environment information, the vehicle specific information, and the element state information, and generates a diagnosis model. Details of the travel status information, the travel environment information, and the vehicle specific information will be described later.
The diagnostic model generation unit 103 performs correlation analysis using a general machine learning method such as a random forest, SVM (Support Vector Machine), or a neural network. The diagnostic model generation rule indicates a diagnostic model generation unit. The generation unit of the diagnostic model is a region where the vehicle 200 is used, a type of vehicle element, a vehicle type, a model year of the vehicle 200, and the like. The region is a country, a city, or the like where the vehicle 200 is used. The type of vehicle element includes the manufacturer of the vehicle element, the product name of the vehicle element, the date of manufacture, and the like.
The diagnosis model is used when the influence estimation unit 105 estimates the influence on the vehicle element due to the traveling of the vehicle 200.
Details of the diagnostic model will be described later.

  The diagnostic model storage unit 104 stores the diagnostic model generated by the diagnostic model generation unit 103.

The influence estimation unit 105 estimates the influence on the vehicle element due to the traveling of the vehicle 200 based on the behavior history during traveling of the vehicle 200 indicated in the behavior history information. The influence of the vehicle 200 on the vehicle element is a change in physical quantity related to the vehicle element. Changes in physical quantities include changes in temperature, current value, voltage value, and dimensions. Hereinafter, the change in the physical quantity related to the vehicle element estimated by the influence estimation unit 105 is referred to as the change in the state value of the vehicle element, and the change amount in the state value is referred to as the state change amount. For example, the tire groove depth is the tire state value, and the tire groove depth change amount is the tire state change amount. The brake pad thickness is the brake pad state value, and the brake pad thickness change amount is the brake pad state change amount. Further, the remaining amount of the battery liquid is a state value of the battery liquid, and the change amount of the remaining amount of the battery liquid is the state change amount of the battery liquid.
The influence estimation unit 105 derives the state change amount of the vehicle element using the diagnosis model stored in the diagnosis model storage unit 104.
The process performed by the influence estimation unit 105 corresponds to an influence estimation process.

The diagnosis unit 106 diagnoses the state of the vehicle element based on the state change amount of the vehicle element derived by the influence estimation unit 105. Then, the diagnosis unit 106 transmits a diagnosis notification indicating the diagnosis result to the in-vehicle device 300.
The process performed by the diagnosis unit 106 corresponds to a diagnosis process.

** Description of functional configuration example of in-vehicle device 300 **
The communication unit 301 communicates with the server device 100.
Specifically, the communication unit 301 transmits vehicle management information, element notification information, and behavior history information to the server device 100. Further, the communication unit 301 receives a diagnosis notification from the server device 100.

The diagnosis notification display unit 302 displays the diagnosis notification received by the communication unit 301.
As a result, the user of the vehicle 200 can know whether the vehicle element needs to be inspected or replaced. The diagnosis notification display unit 302 may be realized by a car navigation device, for example.

  The element notification information acquisition unit 303 reads vehicle management information and element notification information to be transmitted to the server device 100 from the storage unit 307. The element notification information acquisition unit 303 outputs the read vehicle management information and element notification information to the communication unit 301.

  The behavior history information generation unit 304 generates behavior history information to be transmitted to the server device 100. The behavior history information generation unit 304 outputs the generated behavior history information to the communication unit 301.

  The sensor information collection unit 305 collects sensor information from sensors (not shown) arranged on the vehicle 200. The sensor information collection unit 305 collects sensor information from sensors such as a vehicle front camera, a vehicle rear camera, a LIDAR, a sonar, a V2X vehicle-mounted device, an illuminance sensor, a rain sensor, and a locator.

  The vehicle control unit 306 controls the vehicle 200. For example, the vehicle control unit 306 performs control such as engine control, brake control, steering control, and headlight control.

  The storage unit 307 stores vehicle management information and element notification information.

The vehicle management information is information shown in FIG. 6, for example.
The vehicle management information includes a vehicle ID, a region, and specification information. The vehicle ID is an identifier that can uniquely identify the vehicle 200. The vehicle ID is, for example, a vehicle identification number. The region is a traveling region of the vehicle 200. The region may be specified by a city name, or may be specified by position information such as latitude and longitude. The spec information indicates, for example, the vehicle weight, vehicle length, vehicle width, wheel alignment, and the like of the vehicle 200.

The element notification information is, for example, information illustrated in FIG.
The element notification information includes an element ID, an element type ID, and a vehicle element use start date. The element ID is an identifier that can uniquely identify the vehicle element. The element type ID is information for uniquely identifying a product arranged in the vehicle 200 as a vehicle element. The element ID is a name of a vehicle element such as a tire, a battery, or a brake. The element type ID is an identifier for identifying the manufacturer of the vehicle element, the product name, and the like. The element type ID is, for example, a product number. The use start date indicates the date and time when the use of the vehicle element is started.
The element notification information is written in the storage unit 307 at the time of manufacturing the vehicle 200 or replacing the vehicle element, for example.

*** Explanation of operation ***
Next, the operation in the diagnostic system 500 according to the present embodiment will be described.
Hereinafter, the operation of the server apparatus 100 will be mainly described.

FIG. 12 shows an outline of the operation of the server apparatus 100.
The operation of the server device 100 is divided into a learning process (step S11) and a diagnostic process (step S12).

In the learning process (step S <b> 11), the diagnostic model generation unit 103 generates a diagnostic model by learning the influence of the traveling state of the vehicle 200 and the traveling environment of the vehicle 200 on the vehicle elements.
In the diagnosis process (step S12), the influence estimation unit 105 derives the state change amount of the vehicle element using the diagnosis model. In the diagnosis process (step S12), the diagnosis unit 106 diagnoses the state of the vehicle element based on the state change amount and notifies the in-vehicle device 300 of the diagnosis result.

  FIG. 13 shows details of the learning process (step S11).

  First, the information acquisition unit 101 acquires element state information (before travel) from the in-vehicle device 300 (step S111). Then, the information acquisition unit 101 outputs the acquired element state information (before travel) to the diagnostic model generation unit 103. The element state information (before traveling) is element state information obtained before the vehicle 200 travels.

The element state information is, for example, information shown in FIG.
The element state information describes a vehicle element in the vehicle 200. In the example of FIG. 11, tires, batteries, brake pads, and engine oil are described. The vehicle elements are not limited to these.
In addition, the state quantity of the vehicle element is described in the element state information. In the example of FIG. 11, the value of the depth of the tire groove is described as the state quantity of the tire. Other state quantities include brake pad thickness, battery deterioration state (State of Health, SOH), charge state (State of Charge, SOC), engine oil and cooling water amounts and components, and the like. The state quantity is not limited to these.
In addition, the element state information includes the vehicle element use start date and the state quantity collection date.
The element state information is generated by the behavior history information generation unit 304 of the in-vehicle device 300.
The behavior history information generation unit 304 generates element state information using sensor information collected by the sensor information collection unit 305 or measurement values measured by the user. The behavior history information generation unit 304 uses the sensor information collected by the sensor information collection unit 305 for the state values that can be measured by the sensor. On the other hand, the measured value measured by the user is used for the state value that cannot be measured by the sensor. A user measures the state value of a vehicle element using a gauge etc., for example.
The communication unit 301 transmits element state information (before travel) to the server device 100, and in the server device 100, the information acquisition unit 101 receives the element state information (before travel).

Next, the information acquisition unit 101 acquires behavior history information (step S112).
Then, the information acquisition unit 101 outputs the acquired behavior history information to the diagnostic model generation unit 103.

The behavior history information is, for example, information illustrated in FIG.
In the behavior history information, a history of behavior during traveling of the traveling vehicle 200 is shown.
In the behavior history information, changes in the state values of the headlight state, the blinker state, the accelerator position, the brake position, the shift lever position and the like over time are described as the behavior history of the vehicle 200. The behavior history information also describes changes over time such as the vehicle speed and the steering drive angle as the behavior history of the vehicle 200. The behavior history information also describes a change over time in sensor values measured by a vehicle height sensor, an acceleration sensor, or the like as a behavior history of the vehicle 200. Furthermore, the behavior history information includes obstacles detected by the front camera etc., pedestrians, current position acquired by the locator, map information output from the car navigation device, passenger status output from the driver monitoring device, etc. May be included.
The behavior history information is time-series data as shown in FIG. 8, and the in-vehicle device 300 collects the state at a period determined for each item. For example, state values such as a headlight state, a blinker state, an accelerator position, a brake position, and a shift lever position are collected at a cycle of 100 ms. On the other hand, state values such as steering and steering drive angle are collected at a cycle of 10 ms, for example.
In the vehicle 200, the behavior history information generation unit 304 generates behavior history information. For example, the behavior history information generation unit 304 generates behavior history information using the sensor information collected by the sensor information collection unit 305. In addition, the behavior history information generation unit 304 generates behavior history information using a control value output by the vehicle control unit 306 for controlling the vehicle 200.
And the communication part 301 of the vehicle-mounted apparatus 300 transmits behavior history information, and the information acquisition part 101 of the server apparatus 100 receives behavior history information.

Next, the information acquisition part 101 acquires element state information (after driving | running | working) from the vehicle equipment 300 (step S113). Then, the information acquisition unit 101 outputs the acquired element state information (after traveling) to the diagnostic model generation unit 103.
The element state information (after traveling) acquired in step S113 describes the state of the vehicle element after traveling. The element state information (after traveling) acquired in step S113 is the same as the element state information (before traveling) acquired in step S111. However, the state quantity indicated in the element state information (after traveling) may be different from the state quantity in the element state information (before traveling). For example, the depth of the tire groove may become shallower due to traveling in the element state information (after traveling).

In the server apparatus 100, the above steps S111 to S113 are performed on the plurality of vehicles 200. Element state information (before traveling), behavior history information, and element state information (after traveling) obtained from the in-vehicle devices 300 of the plurality of vehicles 200 are accumulated in a storage area allocated to the diagnostic model generation unit 103.
When the number of samples necessary for learning for generating a diagnostic model is obtained, step S114 is performed.
In step S114, the diagnosis model generation unit 103 analyzes the correlation among the element state information (before traveling), the behavior history information, and the element state information (after traveling), and generates a diagnosis model.
Details of the diagnostic model generation processing will be described with reference to FIG.

  First, the diagnostic model generation unit 103 generates travel information, environment information, and vehicle specific information from the behavior history information for each vehicle 200 (step S1151).

The travel information describes the amount of change in vehicle speed, acceleration, total travel distance, and the like of the vehicle 200.
The environmental information describes the vibration amount of the vehicle 200, the inclination angle of the road surface, and the like.
The vehicle specific information describes the total vehicle weight and the like.
The diagnostic model generation unit 103 can obtain the vehicle speed change amount by, for example, obtaining a difference in vehicle speed per unit time. Further, the diagnostic model generation unit 103 can obtain the amount of vibration of the vehicle 200 by obtaining the degree of change in the vehicle height of the vehicle 200 from the measured values of the vehicle height sensor and the acceleration sensor. Further, the diagnostic model generation unit 103 obtains the total weight of the passenger using the number of passengers of the vehicle 200 and the average weight value of one passenger, and adds the obtained total weight to the vehicle weight value. The total vehicle weight can be obtained. Further, if the server device 100 holds the relationship information between the change amount of the output value of the vehicle height sensor and the loading amount, the diagnostic model generation unit 103 obtains the total weight of the passenger from the output value of the vehicle height sensor. Can do. The travel information, the environment information, and the vehicle specific information are information on the amount of change obtained by sampling the behavior history information that is time-series data at regular intervals. That is, traveling information, environmental information, and vehicle specific information are also time series data.

  Next, the diagnostic model generation unit 103 generates traveling state information and traveling environment information for each vehicle 200 (step S1152).

The diagnosis model generation unit 103 determines the driving state and driving environment of the vehicle 200 from the behavior history information and the driving information and environment information generated in step S1152.
The traveling situation is a characteristic in traveling of the vehicle 200 such as a sudden start frequency, a sudden brake frequency, a sharp curve frequency, a low speed travel frequency, and a short distance travel frequency. The traveling environment is a characteristic in the environment in which the vehicle 200 travels, such as a bad road traveling frequency, an uphill / downhill traveling frequency, and a night traveling frequency.
For example, the diagnostic model generation unit 103 can obtain the sudden start frequency based on the amount of change in the vehicle speed when the accelerator pedal is operated. Further, the diagnostic model generation unit 103 can obtain the sudden braking frequency from the amount of change in the vehicle speed when the brake pedal is operated. Further, the diagnostic model generation unit 103 can obtain the sharp curve frequency based on the horizontal acceleration during the steering operation. Further, the diagnosis model generation unit 103 can determine the rough road traveling time from the amount of vibration, and calculate the rough road traveling frequency by calculating the ratio of the rough road traveling time to the total traveling time. Further, the diagnostic model generation unit 103 can determine the uphill road traveling time by determining the uphill road traveling time from the road surface inclination rate and calculating the ratio of the uphill road traveling time in the total traveling time. The diagnostic model generation unit 103 can determine the headlight usage time and calculate the nighttime driving frequency by calculating the ratio of the headlight usage time to the total driving time.
The diagnostic model generation unit 103 generates information indicating the sudden start frequency, the sudden brake frequency, the sharp curve frequency, and the like calculated as described above as travel state information. Further, the diagnostic model generation unit 103 generates information indicating the rough road traveling frequency, the ascending / descending road traveling frequency, the night traveling frequency, and the like calculated as described above as traveling environment information.
The driving situation information and the driving environment information are information indicating a frequency or a ratio, and are not time series data.
Note that each of the sudden start frequency, the sudden brake frequency, and the sharp curve frequency may be classified into a plurality of categories such as large, medium, and small depending on the magnitude of the degree.

  Then, as illustrated in FIG. 15, the diagnosis model generation unit 103 associates the vehicle specific information obtained in step S1151 with the traveling state information obtained in step S1152 and the traveling environment information for each vehicle 200.

Next, the diagnostic model generation unit 103 classifies information (step S1153).
Specifically, the diagnosis model generation unit 103 uses the element type ID based on the element type ID as the driving condition information, the driving environment information, the vehicle specific information, the element state information (before driving), and the element state information (after driving). Sort by each.
Further, the diagnosis model generation unit 103 classifies the driving state information, the driving environment information, the vehicle specific information, the element state information (before driving), and the element state information (after driving) based on the driving area of each vehicle 200 for each area. To do. For example, if the vehicle management information shown in FIG. 6 is received together with the element state information (before travel) in step S111 in FIG. 13, the diagnostic model generation unit 103 can obtain the travel region of the vehicle 200.
As described above, the diagnosis model generation unit 103 classifies the information collected by the plurality of vehicles 200 for each element type-area.
In the present embodiment, the diagnostic model generation unit 103 classifies information for each element type-region, but may classify information only by element type. Further, the diagnosis model generation unit 103 may classify information by another classification method. For example, the diagnosis model generation unit 103 may identify the vehicle type or year from the vehicle ID, and classify the information for each vehicle type or year.

Next, the diagnostic model generation unit 103 generates a diagnostic model (step S1154).
Specifically, the diagnostic model generation unit 103 generates a diagnostic model according to the classification performed in step S1153. In the above-described example, the diagnostic model generation unit 103 generates a diagnostic model according to the element type-classification for each region.
The diagnostic model generation unit 103 generates a diagnostic model by analyzing the correlation between the driving state information, the driving environment information, and the vehicle specific information, and the element state information (before driving) and the element state information (after driving). The diagnostic model generation unit 103 analyzes the correlation using a general machine learning method such as random forest, SVM, or neural network.
The diagnosis model generation unit 103 generates a model in which the state change amount of the vehicle element is output when the driving state information, the driving environment information, and the vehicle specific information are input as the diagnosis model. For example, if a tire is to be diagnosed, a sudden start frequency, a sudden brake frequency, a sharp curve frequency (running situation information), a rough road running frequency (driving environment information), and a total vehicle weight (vehicle specific information) are input. A diagnostic model in which a change amount (state change amount) of the tire groove is output is generated.

  The diagnosis model generation unit 103 may perform learning using the change amount (numerical value) of the state value between the element state information (before traveling) and the element state information (after traveling) as it is. The diagnostic model generation unit 103 performs learning after classifying the amount of change in the state value between the element state information (before travel) and the element state information (after travel) into categories such as large, medium, and small. May be. The diagnosis model generation unit 103 can apply a method suitable for each vehicle element based on the correlation analysis result.

As another method, the diagnostic model generation unit 103 performs the principal component analysis on the basis of the driving state information, the driving environment information, and the vehicle specific information, and then the element state information (before driving) and the element state information (after driving). ) Between the change amount of the state value and the principal component analysis result. For example, the diagnostic model generation unit 103 can learn using the results of performing the principal component analysis for each driving situation information, driving environment information, and vehicle specific information. More specifically, the diagnosis model generation unit 103 performs a principal component analysis based on the sudden start frequency, the sudden brake frequency, and the sharp curve frequency of the traveling state information acquired from the plurality of vehicles 200, and indicates a traveling state value. Ask for. Then, the diagnosis model generation unit 103 learns a correlation between the value indicating the obtained traveling state and the amount of change in the state value between the element state information (before traveling) and the element state information (after traveling).
As another method, the diagnostic model generation unit 103 may perform a principal component analysis based on the sudden braking frequency and the sudden curve frequency to obtain the braking / driving force influence degree. In this case, the diagnostic model generation unit 103 learns a correlation between the braking / driving force influence degree and the amount of change in the state value between the element state information (before traveling) and the element state information (after traveling).

The diagnostic model generation unit 103 stores the generated diagnostic model in the diagnostic model storage unit 104. Further, the diagnostic model generation unit 103 generates the diagnostic model information illustrated in FIG. 16 and stores the generated diagnostic model information in the diagnostic model storage unit 104.
The diagnosis model information is information for managing a diagnosis model to be applied for each category in the vehicle type, year, vehicle element, region, and the like. In the example of FIG. 16, a diagnostic model applied to a vehicle model made in 2017: XXXX is shown. In the example of FIG. 16, the diagnostic model applied for every vehicle element-area is shown.
In the diagnostic processing described later, the diagnostic unit 106 can identify the diagnostic model to be applied by referring to the diagnostic model information.

FIG. 17 shows the details of the diagnostic process (S12 in FIG. 12).
Steps S <b> 121 and S <b> 122 are processes performed before the vehicle 200 travels. Step S123 and step S124 are processes performed after the vehicle 200 travels.

In the vehicle 200, as a process before the start of traveling, the element notification information acquisition unit 303 reads vehicle management information and element notification information from the storage unit 307, for example, triggered by engine start or door unlocking. Then, the element notification information acquisition unit 303 outputs the vehicle management information and the element notification information to the communication unit 301. And the communication part 301 transmits vehicle management information and element notification information to the server apparatus 100. FIG.
The vehicle management information is information shown in FIG. The element notification information is information shown in FIG.

In the server device 100, the information acquisition unit 101 receives the vehicle management information and the element notification information transmitted from the in-vehicle device 300 (step S121).
The information acquisition unit 101 stores the received vehicle management information and element notification information in the information storage unit 102 and outputs them to the influence estimation unit 105.

Next, the diagnosis unit 106 performs element state diagnosis (before travel) (step S122).
The diagnosis unit 106 performs element state diagnosis (before travel) using the vehicle element management information at the time of the previous diagnosis held in the information storage unit 102 and the element notification information received in step S121.
The vehicle element management information is information shown in FIG. The vehicle element management information includes an element ID, an element type ID, a use start date, a final diagnosis date, and a diagnosis model version. The element ID, element type ID, and use start date are the same as those shown in the element notification information of FIG. The last diagnosis date indicates the date and time when the diagnosis unit 106 last diagnosed the vehicle element with respect to the target vehicle 200. The diagnostic model version indicates the version of the diagnostic model to be applied for each vehicle element.
Details of the element state diagnosis process (before travel) will be described with reference to FIG.

  First, the diagnosis unit 106 compares, for each vehicle element, the use start date of the element notification information (FIG. 7) received in step S121 and the final diagnosis date of the vehicle element management information (FIG. 10) (step S1221). .

If the use start date is newer than the last diagnosis date for any vehicle element (YES in step S1221), the diagnosis unit 106 initializes the cumulative change amount of the corresponding vehicle element in the diagnosis result information (FIG. 9). (Step S1222).
If the use start date is newer than the last diagnosis date, it is considered that the corresponding vehicle element has been replaced. For this reason, the diagnosis unit 106 initializes the cumulative change amount of the diagnosis result information (FIG. 9).
The cumulative change amount is a cumulative value of the state change amount from the initial travel of the vehicle 200 or the replacement of vehicle elements. For example, the cumulative change amount of the tire is a total decrease amount of the tire groove from the initial driving of the vehicle 200 or the replacement of the tire.

  On the other hand, in any vehicle element, when the use start date is not newer than the last diagnosis date (NO in step S1221), the process of step S1223 is performed. Further, the process of step S1223 is also performed after the process of step S1222 is performed.

In step S1223, the diagnosis unit 106 determines whether or not the cumulative change amount of the diagnosis result information (FIG. 9) exceeds the threshold value for each vehicle element.
That is, the diagnosis unit 106 determines whether the maintenance inspection threshold value or the replacement threshold value of the diagnosis result information (FIG. 9) is “excess”.

  If the cumulative change amount of any vehicle element does not exceed the threshold (NO in step S1223), the diagnosis unit 106 ends the process.

On the other hand, when the cumulative change amount exceeds the threshold value in any vehicle element (YES in step S <b> 1223), diagnosis unit 106 transmits a diagnosis notification (before traveling) to in-vehicle device 300.
As shown in FIG. 9, when the maintenance check threshold value of the right front tire is “exceeded”, the diagnosis unit 106 displays a diagnosis notification (before running) indicating a message “Let's check the right front tire”. Is transmitted to the in-vehicle device 300.

  In the in-vehicle device 300, the communication unit 301 receives a diagnosis notification (before travel), and the diagnosis notification display unit 302 displays a message of diagnosis notification (before travel).

When the element state diagnosis process (before traveling) (step S122) is completed and the vehicle 200 ends traveling, the information acquisition unit 101 acquires behavior history information in step S123 of FIG. That is, the information acquisition unit 101 receives behavior history information from the in-vehicle device 300.
In the in-vehicle device 300, the behavior history information generation unit 304 generates behavior history information at a constant period based on the control value of the vehicle control unit 306 and the sensor information collected by the sensor information collection unit 305 while the vehicle 200 is traveling. . Also, the behavior history information generation unit 304 stores the generated behavior history information in a predetermined storage area. Then, when the traveling of the vehicle 200 ends, the communication unit 301 collectively transmits the accumulated behavior history information to the server device 100. The communication unit 301 determines the end of traveling of the vehicle 200 by stopping the engine, operating the brake pedal, or operating the side brake, for example.
Instead, the behavior history information generation unit 304 generates behavior history information at a fixed period, and the communication unit 301 transmits the generated behavior history information every time behavior history information is generated. Good.
The behavior history information is information shown in FIG.
The information acquisition unit 101 stores the received behavior history information in the information storage unit 102.

Next, the influence estimation unit 105 and the diagnosis unit 106 perform element state diagnosis processing (after traveling) (step S124).
That is, the influence estimation unit 105 derives a state change amount for each vehicle element using the diagnosis model. In addition, the diagnosis unit 106 performs diagnosis for each vehicle element using the state change amount derived by the influence estimation unit 105.
Hereinafter, the details of the element state diagnosis process (after traveling) will be described with reference to FIG.

First, the influence estimation part 105 produces | generates driving information, environmental information, and vehicle specific information from behavior history information (step S1241).
The method for generating the travel information, the environment information, and the vehicle specific information is as described above. That is, the influence estimation unit 105 generates the travel information, the environment information, and the vehicle specific information in the same manner as the generation method of the travel information, the environment information, and the vehicle specific information by the diagnostic model generation unit 103 when generating the diagnostic model.

Next, the influence estimation part 105 produces | generates driving condition information and driving environment information (step S1242).
The method for generating the driving situation information and the driving environment information is as described above. That is, the influence estimation unit 105 generates the driving situation information and the driving environment information in the same manner as the generation method of the driving situation information and the driving environment information by the diagnostic model generation unit 103 when generating the diagnostic model.

  Further, as shown in FIG. 15, the influence estimation unit 105 associates the vehicle specific information obtained in step S1241, the traveling state information obtained in step S1242, and the traveling environment information.

  Next, the influence estimation unit 105 derives a state change amount for each vehicle element (step S1243).

The influence estimation unit 105 derives a state change amount for each vehicle element using the driving state information, the driving environment information, the vehicle specific information, and the diagnostic model stored in the diagnostic model storage unit 104. That is, the influence estimation unit 105 acquires the diagnosis model described in the diagnosis model information (FIG. 16) from the diagnosis model storage unit 104, and derives the state change amount for each vehicle element using the acquired diagnosis model. .
If the diagnostic model to be applied is a diagnostic model obtained based on the category classification, the state change amount output from the diagnostic model is expressed in categories such as large, medium, and small.
In the following, for the sake of simplification of description, the description will be given using an example in which a numerical value is obtained as the state change amount.
The influence estimation unit 105 outputs the obtained state change amount of each vehicle element to the diagnosis unit 106.

  Next, the diagnosis part 106 diagnoses a state for every vehicle element (step S1244).

The diagnosis unit 106 adds the state change amount derived by the influence estimation unit 105 to the cumulative change amount of the diagnosis result information (FIG. 9). The accumulated change amount of the diagnosis result information (FIG. 9) is the accumulated change amount obtained at the time of the previous diagnosis, that is, before the vehicle 200 starts to travel. That is, the accumulated change amount of the diagnosis result information (FIG. 9) is a cumulative value of the state change amount of the vehicle element from the initial travel of the vehicle 200 to the previous diagnosis. By adding the state change amount derived by the influence estimation unit 105 and the accumulated change amount of the diagnosis result information (FIG. 9), the accumulated value of the state change amount of the vehicle element from the first run of the vehicle 200 to the previous diagnosis is added. (Hereinafter referred to as “new cumulative change amount”).
Next, the diagnosis unit 106 compares the new cumulative change amount with the predetermined maintenance inspection threshold value and replacement threshold value. The maintenance inspection threshold is a threshold for transmitting a message prompting the user of the vehicle 200 to perform maintenance inspection of the vehicle element. The replacement threshold is a threshold for transmitting a message prompting the user of the vehicle 200 to replace the vehicle element.
For example, when the vehicle element is a tire, the initial value of the tire groove is assumed to be 8 mm. The maintenance inspection threshold is assumed to be 5 mm (remaining tire groove is 3 mm), and the replacement threshold is assumed to be 6 mm (remaining tire groove is 2 mm). If the new cumulative change amount exceeds 5 mm, the diagnosis unit 106 determines that a tire maintenance check is necessary. Further, when the new cumulative change amount exceeds 6 mm, the diagnosis unit 106 determines that the tire needs to be replaced.

In addition, the diagnosis unit 106 predicts the timing at which the vehicle element needs to be inspected when the new cumulative change amount does not exceed the maintenance inspection threshold. For example, the diagnosis unit 106 predicts at least one of a travel distance and a period until the vehicle element needs to be replaced as a timing at which the vehicle element needs to be inspected.
For example, when the vehicle element is a tire, the new cumulative change amount is assumed to be 4.98 mm. Further, it is assumed that the current state change amount is 0.2 μm / km. In this case, the remaining amount up to the maintenance inspection threshold is 0.02 mm. Since the current state change amount is 0.2 μm / km, when the same traveling as this time is performed, the diagnosis unit 106 determines that the maintenance inspection is necessary after traveling 100 km. Further, when the average daily travel distance of the vehicle 200 is known, the diagnosis unit 106 may divide 100 km by the average travel distance to obtain the number of days until the maintenance inspection is necessary.
In the above, the example of calculating the travel distance or the period until the vehicle element needs to be inspected has been described. However, the diagnosis unit 106 uses the same procedure to determine the travel distance until the vehicle element needs to be replaced. Or the period can be predicted.

  When the output from the diagnosis model is expressed in the category of the state change amount such as large, medium, and small, the diagnosis unit 106 diagnoses the state of the vehicle element as follows, for example.

  When the vehicle element is a tire, it is assumed that the amount of change in the tire groove is classified into large, medium, and small categories. In this case, the diagnosis unit 106 holds a conversion table between categories and numerical values. In the conversion table, for example, 0.3 μm / km is defined as a numerical value corresponding to the category “large”. Further, 0.2 μm / km is defined as a numerical value corresponding to the category “medium”. Further, 0.1 μm / km is defined as a numerical value corresponding to the category “small”. The diagnosis unit 106 uses the category value notified from the effect estimation unit 105, the travel distance obtained from the behavior history information, and the conversion table to obtain a numerical value of the state change amount. Thereafter, the diagnosis unit 106 adds the obtained numerical value of the state change amount to the cumulative change amount of the diagnosis result information (FIG. 9).

Next, the diagnosis unit 106 generates a diagnosis notification (after traveling) that notifies the diagnosis result. Then, the diagnosis unit 106 transmits the generated diagnosis notification to the in-vehicle device 300.
For example, when the new cumulative change amount of the tire (front right) exceeds the maintenance inspection threshold, the diagnosis unit 106 displays a diagnosis notification (after traveling) that indicates a message “Let's check the right front tire”. ) Is generated. Further, for example, when the new cumulative change amount of the tire (front right) exceeds the replacement threshold, the diagnosis unit 106 displays a diagnosis notification (running that will replace the right front tire). After).
Further, for example, when the new cumulative change amount of the tire (front right) does not exceed the maintenance inspection threshold, the diagnosis unit 106 displays a message “Let's check the right front tire after traveling 100 km”. Generate the indicated diagnostic notification (after travel). Further, for example, when the new cumulative change amount of the tire (front right) does not exceed the replacement threshold, the diagnosis unit 106 displays a message “After 150 km, let's replace the right front tire”. Generate a diagnostic notification (after travel).
Further, when the current state change amount is larger than the state change amount of the other vehicle 200, the diagnosis unit 106 may generate a diagnosis notification (after traveling) that indicates a message that prompts improvement of the driving method. For example, if the amount of wear on the tire is large, a diagnostic notification (after driving) will be generated with the message "It was a driving that had a great influence on the tire. Be careful because there is a tendency to start and brake suddenly" To do. That is, the diagnosis unit 106 notifies the user of the vehicle 200 of a driving method that reduces the influence on the vehicle elements due to the traveling of the vehicle 200.
Then, the diagnosis unit 106 transmits the generated diagnosis notification (after traveling) to the in-vehicle device 300.

  In the in-vehicle device 300, the communication unit 301 receives a diagnosis notification (after travel), and the diagnosis notification display unit 302 displays a message of diagnosis notification (after travel).

The example in which the diagnosis notification is transmitted only from the server apparatus 100 to the in-vehicle apparatus 300 has been described.
For example, the server device 100 may transmit a diagnosis notification to a user terminal held by a user of the vehicle 200. The user terminal is, for example, a smartphone or a tablet terminal.

  Further, the server device 100 may transmit a diagnosis notification to a server device of a dealer of the vehicle 200. In this case, since the dealer can grasp the state of the vehicle element based on the diagnosis notification, the dealer can appropriately notify the inspection time to the user. Further, the dealer can appropriately prepare the necessary replacement parts.

Further, at the time of maintenance and inspection of the vehicle 200, a diagnosis terminal used by a dealer maintenance inspector may be connected to the in-vehicle device 300, and a diagnosis notification may be transmitted from the in-vehicle device 300 to the diagnosis terminal. The diagnosis terminal and the in-vehicle device 300 can be connected using, for example, an OBD (On-Board Diagnostics) interface.
Further, the diagnosis terminal may transmit the abnormality of the vehicle element detected at the time of the maintenance inspection or the measurement result obtained at the time of the maintenance inspection to the server device 100.

*** Explanation of the effect of the embodiment ***
According to the present embodiment, the state of the vehicle element can be accurately diagnosed.
Further, according to the present embodiment, it is possible to make a diagnosis for vehicle elements whose state cannot be directly observed during vehicle travel.
Moreover, according to this Embodiment, the failure which generate | occur | produces by driving | running | working can be prevented beforehand by performing a diagnosis before driving | running | working of a vehicle.
In addition, since the diagnosis performed in the present embodiment is based on the state change amount of the vehicle element, the replacement time can be determined with higher accuracy than the determination of the replacement time based on the travel distance or the use period. it can.
In the present embodiment, since diagnosis can be performed for each type of vehicle element, it is possible to perform diagnosis in consideration of variation in the state change amount for each type of vehicle element.
Further, in the present embodiment, since diagnosis can be performed for each region, it is possible to perform diagnosis in consideration of the variation in the state change amount due to the difference in the climate of the traveling region of the vehicle.
Further, in the present embodiment, since diagnosis can be performed for each vehicle type or year, it is possible to perform a diagnosis in consideration of variations in the state change amount depending on the vehicle type or year.

Embodiment 2. FIG.
In the present embodiment, an example in which a vehicle element is diagnosed in the in-vehicle device 300 will be described.
In the following, differences from the first embodiment will be mainly described.
Note that matters not described below are the same as those in the first embodiment.

*** Explanation of configuration ***
FIG. 20 shows a functional configuration example of the server apparatus 100 according to the present embodiment.

In FIG. 20, compared with the configuration of FIG. 4, the influence estimation unit 105 and the diagnosis unit 106 are omitted, and a diagnosis model transmission unit 107 is added.
The diagnostic model transmission unit 107 transmits the diagnostic model stored in the diagnostic model storage unit 104 to the in-vehicle device 300 when requested by the in-vehicle device 300.
The function of the diagnostic model transmission unit 107 is also realized by a program in the same manner as the information acquisition unit 101 and the like. A program for realizing the function of the diagnostic model transmission unit 107 is executed by the processor 911.

  FIG. 21 shows a functional configuration example of the in-vehicle device 300 according to the present embodiment.

In FIG. 21, the element notification information acquisition unit 303 is omitted and a diagnosis model storage unit 308, an influence estimation unit 309, and a diagnosis unit 310 are added as compared with the configuration illustrated in FIG. 5.
The functions of the influence estimation unit 309 and the diagnosis unit 310 are also realized by a program, similar to the communication unit 301 and the like. A program for realizing the functions of the influence estimation unit 309 and the diagnosis unit 310 is executed by the processor 931.
The diagnostic model storage unit 308 is realized by the main storage device 932 or the auxiliary storage device 933.
In the present embodiment, the in-vehicle device 300 corresponds to an information processing device. Moreover, in this Embodiment, the operation | movement performed by the vehicle-mounted apparatus 300 corresponds to the information processing method and information processing program.

The diagnostic model storage unit 308 stores the diagnostic model transmitted from the server device 100 and received by the communication unit 301.
The influence estimation unit 309 performs the same operation as the influence estimation unit 105 described in the first embodiment. That is, the influence estimation unit 309 derives the state change amount of the vehicle element using the diagnostic model.
The diagnosis unit 310 performs the same operation as the diagnosis unit 106 described in the first embodiment. That is, the diagnosis unit 310 diagnoses the state of the vehicle element based on the state change amount of the vehicle element derived by the influence estimation unit 309.

*** Explanation of operation ***
In the server apparatus 100, only the learning process (S11) is performed among the processes shown in FIG.
The details of the learning process (S11) are as shown in FIGS.
In the server device 100, after the learning process (S <b> 11), the diagnostic model transmission unit 107 stores the diagnostic model stored in the diagnostic model storage unit 104 when the in-vehicle device 300 requests transmission of the diagnostic model. Is transmitted to the in-vehicle device 300.

FIG. 22 shows an outline of the operation of the in-vehicle device 300 according to the present embodiment.
The operation of the in-vehicle device 300 is divided into a model acquisition process (step S31) and a diagnosis process (step S32).

In the model acquisition process (step S31), the diagnosis unit 310 requests the server device 100 to transmit a diagnosis model. The communication unit 301 receives the diagnostic model transmitted from the server apparatus 100 and stores the received diagnostic model in the diagnostic model storage unit 308.
In the diagnosis process (step S32), the influence estimation unit 309 derives the state change amount of the vehicle element using the diagnosis model. In the diagnosis process (step S12), the diagnosis unit 310 diagnoses the state of the vehicle element based on the state change amount, and the diagnosis notification display unit 302 displays the diagnosis notification.

FIG. 23 shows the details of the model acquisition process (step S31).
The model acquisition process (step S31) is performed before the vehicle 200 starts to travel.

  First, the diagnosis unit 310 generates a model transmission request for requesting transmission of a diagnostic model, and the communication unit 301 transmits the model transmission request to the server device 100 (step S311).

The model transmission request includes the vehicle information shown in FIG. 24 and the vehicle element information shown in FIG.
In the vehicle information, a vehicle ID, a vehicle type, a model year, and a region are described.
In the vehicle element information, an element ID, an element type ID, a use start date, a final diagnosis date, and a diagnosis model version are described.
The last diagnosis date describes the date and time when the diagnosis unit 310 last diagnosed the vehicle element. The diagnostic model version describes the version of the diagnostic model held in the diagnostic model storage unit 308. When a diagnostic model is not held in the diagnostic model storage unit 308, a null value is described in the diagnostic model version column. The element ID, the element type ID, and the use start date are set when the vehicle 200 is manufactured or when the vehicle element is replaced.

In the server apparatus 100, the information acquisition unit 101 receives a model transmission request and outputs the received model transmission request to the diagnostic model generation unit 103.
The diagnosis model generation unit 103 specifies a diagnosis model corresponding to the vehicle type, year, city, and vehicle element specified by the vehicle information and the vehicle element information. Further, the diagnostic model generation unit 103 determines whether or not the version of the identified diagnostic model is newer than the version indicated in the vehicle element information. If the identified diagnostic model version is newer than the version indicated in the vehicle element information, the diagnostic model generation unit 103 instructs the diagnostic model transmission unit 107 to transmit the diagnostic model to the in-vehicle device 300. The diagnostic model transmission unit 107 transmits the diagnostic model to the in-vehicle device 300 based on an instruction from the diagnostic model generation unit 103.
Moreover, the diagnostic model production | generation part 103 compares the utilization start date of vehicle element information with the last diagnostic date. When there is a vehicle element whose use start date is after the last diagnosis date, the diagnosis model generation unit 103 determines that the vehicle element has been replaced. When the exchanged vehicle element exists, the diagnosis model generation unit 103 instructs the diagnosis model transmission unit 107 to initialize the cumulative change amount of the vehicle element. Based on the instruction from the diagnostic model generation unit 103, the diagnostic model transmission unit 107 transmits a message instructing initialization of the cumulative change amount of the vehicle element to the in-vehicle device 300.

In the in-vehicle device 300, the communication unit 301 receives the diagnostic model in step S312 of FIG.
Then, in step S313, the communication unit 301 stores the received diagnostic model in the diagnostic model storage unit 308.
When a message instructing initialization of the accumulated change amount of any vehicle element is received from the server device 100, the diagnosis unit 310 initializes the accumulated change amount of the corresponding vehicle element. In this embodiment, since the vehicle element 300 is diagnosed by the in-vehicle device 300, the storage unit 307 holds the diagnosis result information of FIG. The diagnosis unit 310 initializes the value of the accumulated change amount of the diagnosis result information held in the storage unit 307.

FIG. 26 shows details of the diagnostic process (step S32).
Step S321 is a process performed before the vehicle 200 travels. Step S322 is a process performed while the vehicle 200 is traveling. Step S323 is a process performed after the vehicle 200 travels.

First, the diagnosis unit 310 performs element state diagnosis processing (before travel) (step S321).
The diagnosis unit 310 performs element state diagnosis processing (before traveling) using the diagnosis result information (FIG. 9) at the time of the previous diagnosis stored in the storage unit 307. Specifically, the diagnosis unit 310 determines whether or not the cumulative change amount of the diagnosis result information (FIG. 9) exceeds a threshold value for each vehicle element. That is, the diagnosis unit 310 determines whether the maintenance inspection threshold value or the replacement threshold value of the diagnosis result information (FIG. 9) is “excess”.
If the cumulative change amount of any vehicle element does not exceed the threshold value, the diagnosis unit 310 ends the process.
On the other hand, when the cumulative change amount exceeds the threshold value in any vehicle element, the diagnosis unit 310 outputs a diagnosis notification (before traveling) to the diagnosis notification display unit 302. The diagnostic notification display unit 302 displays a diagnostic notification message (before traveling).
In the above description, an example in which the diagnosis unit 310 initializes the accumulated change amount of the diagnosis result information (FIG. 9) according to the initialization instruction from the server device 100 has been described. You may compare the use start date of information with the last diagnosis date. In this case, when there is an exchanged vehicle element as a result of the comparison between the use start date and the last diagnosis date, the diagnosis unit 310 initializes the value of the cumulative change amount of the corresponding vehicle element.

Next, during the traveling of the vehicle 200, the behavior history information generation unit 304 generates behavior history information and accumulates the generated behavior history information (step S322).
The behavior history information generation unit 304 generates behavior history information at a constant period based on the control value of the vehicle control unit 306 and the sensor information collected by the sensor information collection unit 305. Also, the behavior history information generation unit 304 stores the generated behavior history information in a predetermined storage area.

Next, the influence estimation unit 309 and the diagnosis unit 310 perform element state diagnosis processing (after travel) (step S323).
That is, the influence estimation unit 309 derives the state change amount for each vehicle element using the diagnosis model. In addition, the diagnosis unit 310 performs diagnosis for each vehicle element using the state change amount derived by the influence estimation unit 309.
The influence estimation unit 105 of the first embodiment uses the behavior history information transmitted from the in-vehicle device 300, but the influence estimation unit 309 uses the behavior history information output from the behavior history information generation unit 304. Except for this point, the operation of the influence estimation unit 309 is the same as the operation of the influence estimation unit 105 described in the first embodiment. The operation of the diagnosis unit 310 is the same as the operation of the diagnosis unit 106 described in the first embodiment. For this reason, detailed description of step S323 is omitted.
When the diagnosis is completed, the diagnosis unit 310 outputs a diagnosis notification for notifying the diagnosis result to the diagnosis notification display unit 302. The diagnosis notification display unit 302 displays a diagnosis notification.

  The in-vehicle device 300 may transmit a diagnosis notification to the user terminal, the server device of the dealer, and the diagnosis terminal of the dealer maintenance worker described in the first embodiment. The advantages of sending a diagnosis notification to the user terminal, the server device of the dealer, and the diagnosis terminal of the dealer maintenance worker are as described in the first embodiment.

*** Explanation of the effect of the embodiment ***
According to the present embodiment, in addition to the effects shown in the first embodiment, an effect that the state of the vehicle element can be accurately diagnosed in the in-vehicle device 300 can be obtained.

  In the above description, an example in which diagnosis of vehicle elements is performed after the vehicle 200 has traveled is shown. Instead of this, the vehicle element may be diagnosed while the vehicle 200 is traveling. When the diagnosis is performed while the vehicle 200 is traveling, the influence estimation unit 309 derives the state change amount at a cycle of, for example, 1 minute. Then, after the traveling of the vehicle 200 is completed, the diagnosis unit 310 performs diagnosis by adding each of the state change amounts obtained periodically to the accumulated change amount.

** Another method for generating a diagnostic model **
In the first and second embodiments, the diagnostic model generation unit 103 generates travel state information, travel environment information, and vehicle specific information from the behavior history information, and correlates this information with the amount of change in the state value of the vehicle element. An example of learning a relationship and generating a diagnostic model has been described.
The diagnostic model generation unit 103 may generate a diagnostic model by another method. For example, the diagnosis model generation unit 103 may learn the correlation between the travel information, the environment information, the vehicle specific information, and the amount of change in the state value of the vehicle element, and generate a diagnosis model. The diagnostic model generation unit 103 may learn the correlation using a technique such as an RNN (Recurrent Natural Network) that can handle time-series data, for example.

** Modification **
Instead of the first embodiment and the second embodiment, the server device 100 and the in-vehicle device 300 may share the processing below.
(1) The in-vehicle device 300 performs the estimation of the influence, and the server device 100 performs the diagnosis.
The configuration of the server device 100 in this case is obtained by omitting the influence estimation unit 105 from the configuration of FIG. Further, the configuration of the in-vehicle device 300 is obtained by omitting the diagnosis unit 310 from the configuration of FIG. The flow of diagnosis is almost the same as in the second embodiment.
In the in-vehicle device 300, the communication unit 301 notifies the server device 100 of the state change amount of the vehicle element extracted by the influence estimation unit 309.
In the server apparatus 100, the diagnosis unit 106 performs diagnosis using the notified state change amount and the previous state change amount.
By setting it as such a system, there exists an effect which can reduce the communication amount between the server apparatus 100 and the vehicle-mounted apparatus 300. FIG.
(2) Although the server apparatus 100 basically performs diagnosis, the in-vehicle apparatus 300 performs simple diagnosis.
The configuration of the server device 100 in this case is as shown in FIG. 4, and the configuration of the in-vehicle device 300 is as shown in FIG.
The flow of diagnosis is almost the same as in the first and second embodiments.
However, in the diagnosis by the in-vehicle device 300, the information input to the diagnosis model is less than that in the second embodiment.
Taking a tire as an example, only the sudden braking frequency and the sharp curve frequency are input to the diagnostic model.
In this method, the in-vehicle device 300 uses the above-mentioned “message for promoting the driving method” (“It was a driving that had a great influence on the tire. Be careful because there is a tendency to start and brake suddenly”). Only the diagnosis necessary for output is performed by the in-vehicle device 300.

Embodiment 3 FIG.
In the present embodiment, a diagnostic model generation method and a vehicle element diagnosis method different from those in the first and second embodiments will be described.
In this embodiment, differences from Embodiments 1 and 2 are mainly described.
Note that matters not described below are the same as those in the first or second embodiment.

*** Explanation of configuration ***
In the present embodiment, the configuration of server device 100 and in-vehicle device 300 may be any of the configurations of first and second embodiments.
Hereinafter, the description will be made on the assumption of the configuration of the first embodiment.

*** Explanation of operation ***
In the present embodiment, the diagnostic model generation unit 103 calculates statistics such as the average value, standard deviation, median value, and standard deviation of each item of behavior history information. In the example of FIG. 8, the diagnostic model generation unit 103 calculates an average value and a standard deviation for each item such as the vehicle speed and acceleration.
Next, the diagnostic model generation unit 103 performs a correlation analysis between the calculated statistical values such as the average value and the standard deviation and the change amount of the state value in the element state information, and generates a diagnosis model. The method for generating a diagnostic model is the same as in the first embodiment.

  Next, with reference to FIG. 27, the element state diagnosis process (after traveling) according to the present embodiment will be described.

  Also in the present embodiment, in-vehicle device 300 transmits behavior history information to server device 100 after traveling of vehicle 200 is completed.

In the server apparatus 100, the influence estimation unit 105 divides the time series data of the behavior history information at regular intervals (for example, 10 seconds), and calculates the average value and standard deviation of each item at regular intervals (step S131).
In the example of FIG. 8, the influence estimation unit 105 calculates an average value and a standard deviation for each item such as a vehicle speed and an acceleration for every fixed period.

  Next, the influence estimation unit 105 inputs the average value and standard deviation of each item for each fixed period to the diagnostic model, and derives the state change amount for each fixed period.

Finally, the diagnosis unit 106 adds the state change amount for each fixed period to the cumulative change amount, and diagnoses the state of the vehicle element (step S133).
Step S133 is the same as step S1244 in FIG.

  In addition, since it demonstrated based on the structure of Embodiment 1 above, the influence estimation part 105 and the diagnostic part 106 are to diagnose. When the method according to the present embodiment is applied to the configuration of the second embodiment, the influence estimation unit 309 and the diagnosis unit 310 perform a diagnosis according to the above procedure.

*** Explanation of the effect of the embodiment ***
According to the present embodiment, it is possible to generate a diagnostic model with less calculation load than in the first and second embodiments, and it is possible to perform a diagnosis.

** Another method for calculating statistics **
In the above, the influence estimation unit 105 calculates the statistic with the value of each item during a certain period (for example, 10 seconds). Instead of this, the influence estimation unit 105 may calculate a statistic based on the value of each item every fixed period (for example, 10 seconds). That is, the influence estimation unit 105 may calculate the statistic using a value at 0 seconds, a value at the time when 10 seconds have elapsed, a value at the time when 20 seconds have elapsed, and the like.
Normally, the behavior of the vehicle does not change frequently in a short time. For this reason, even if data is thinned and a statistic is calculated to perform learning and diagnosis, the accuracy does not decrease. By calculating the statistics by thinning out such data, there is an effect of reducing necessary calculation resources and storage resources.

In addition, the influence estimation unit 105 calculates a statistic using only the value of a time zone in which a characteristic driving situation (steep curve, sudden braking, etc.) with a high degree of influence on changes (deterioration, etc.) of vehicle elements is performed. You may make it calculate.
Also in this case, there is an effect that necessary calculation resources and storage resources can be reduced.

** Another method for generating a diagnostic model **
Here, an example will be described in which a diagnostic model is generated by a learning method different from the learning method described in the first to third embodiments.

In the following, learning about tire wear will be described as an example.
It is well known that the tire wear rate can be calculated from lateral force, braking force, and driving force. The tire wear rate can be obtained by the following equation, for example.

  Each parameter in the above formula is as follows.

  In the tire wear speed calculation formula described above, the acceleration of the vehicle 200 can be acquired from the behavior history information. Further, it is conceivable that values such as a wheel toe angle and a tire weight are included in the specification information (FIG. 6) of the vehicle 200. On the other hand, it is difficult to obtain values such as stiffness from behavior history information. Accordingly, the following is used as a tire wear speed calculation formula using parameters that can be collected by the vehicle 200 as variables.

  Here, “A”, “B”, and “C” are coefficient values for calculating the tire wear speed by lateral force, braking force, and driving force. The diagnostic model generation unit 103 learns the coefficient values of “A”, “B”, and “C” using the behavior history information and the amount of change in the state value of the vehicle element.

Embodiment 4 FIG.
In the first to third embodiments, the behavior history information is used as it is. In the present embodiment, an example will be described in which the amount of information is reduced by symbolizing behavior history information.
In the present embodiment, differences from the first to third embodiments are mainly described.
In addition, the matter which is not demonstrated below is the same as that of Embodiment 1-3.

*** Explanation of configuration ***
In the present embodiment, the configuration of server device 100 and in-vehicle device 300 may be any of the configurations of first and second embodiments.
Hereinafter, the description will be made on the assumption of the configuration of the first embodiment.

*** Explanation of operation ***
In the present embodiment, the element state diagnosis process (after travel) (step S124) in FIG. 17 will be described.

The influence estimation unit 105 classifies the values of the behavior history information received from the in-vehicle device 300 into categories and symbolizes them.
For example, the influence estimation unit 105 classifies the vehicle speed values into a plurality of categories according to the speed range. If the speed range is classified into three stages, for example, the influence estimation unit 105 classifies the speed range of less than 30 km / h as “C”. Further, the influence estimation unit 105 classifies the speed range of 30 km / h to 50 km / h as “B”. In addition, the influence estimation unit 105 classifies the speed range of 50 km / h to 80 km / h as “A”.

Next, the influence estimation unit 105 calculates a change direction and a change amount of the value of the behavior history information.
If it is a vehicle speed, the influence estimation part 105 classify | categorizes the change direction of a vehicle speed with increase (Up, U), decrease (Down, D), and no change (Keep, K).
Further, the influence estimation unit 105 classifies the change amount of the vehicle speed into a large change amount (Large, L), a small change amount (Small, S), and no change (Normal, N).
And the influence estimation part 105 produces | generates the driving information in which the classification result was reflected.

Next, the influence estimation part 105 produces | generates analysis result information using driving | running | working information.
For example, the influence estimation unit 105 generates analysis result information in which the value of the travel information is a condition attribute and the item indicated in the behavior history information is a determination attribute.
For example, when the behavior history information includes the item “braking degree” and the analysis result information using this item “braking degree” is generated, the influence estimation unit 105 determines the vehicle speed, the direction of change in the vehicle speed, the vehicle speed. The analysis result information is generated with the amount of change in the condition attribute as the condition attribute and the brake degree as the determination attribute.

  And the influence estimation part 105 produces | generates driving condition information using the determination attribute of analysis result information. Since the processing after the generation of the traveling state information is as shown in the first or second embodiment, the description thereof is omitted.

  The above procedure will be described using a specific example.

FIG. 28 shows the change over time in the vehicle speed described in the behavior history information.
In the example of FIG. 28, the slowest speed range is classified as “E”, and the fastest speed range is classified as “A”.
FIG. 29 shows the result of category classification in which the changes over time in the vehicle speed shown in FIG. 28 are represented by symbols “A” to “E”.
FIG. 30 shows travel information in which the category classification result shown in FIG. 29 is combined with the category classification result of the change direction of the vehicle speed and the change amount of the vehicle speed. As described above, the change direction of the vehicle speed is represented by any one of “U”, “D”, and “K”. Further, the amount of change in the vehicle speed is represented by one of “L”, “S”, and “N”.
FIG. 31 shows analysis result information.
In the example of FIG. 31, the vehicle speed, change direction, and change amount of the travel information of FIG. 30 are represented as condition attributes, and the item “brake degree” indicated in the behavior history information is represented as a decision attribute. Moreover, in the example of FIG. 31, each line is described in order of vehicle speed “A” to “E”. In the case of the example in FIG. 31, the influence estimation unit 105 determines that a sudden brake has occurred, for example, when the brake degrees are “2: bellow average” and “1: poor”.
The influence estimation unit 105 counts the number of occurrences of the brake degrees “2: bellow average” and “1: poor” in the analysis result information in FIG. 31, and obtains the value of the sudden brake frequency in the traveling state information (FIG. 15). .

*** Explanation of the effect of the embodiment ***
According to this embodiment, the amount of information can be reduced by symbolizing behavior history information. Therefore, diagnosis can be performed with a small calculation load and storage capacity.

As mentioned above, although embodiment of this invention was described, you may implement in combination of 2 or more among these embodiment.
Alternatively, one of these embodiments may be partially implemented.
Alternatively, two or more of these embodiments may be partially combined.
In addition, this invention is not limited to these embodiment, A various change is possible as needed.

*** Explanation of hardware configuration ***
Finally, a supplementary description of the hardware configuration of the server device 100 and the in-vehicle device 300 will be given.

Each of the processor 911 and the processor 931 is an IC (Integrated Circuit) that performs processing.
The processor 911 and the processor 931 are a CPU (Central Processing Unit), a DSP (Digital Signal Processor), and the like, respectively.
The main storage device 912 and the main storage device 932 are each a RAM (Random Access Memory).
The auxiliary storage device 913 and the auxiliary storage device 933 are a ROM (Read Only Memory), a flash memory, an HDD (Hard Disk Drive), and the like, respectively.
Each of the communication device 914 and the communication device 934 is an electronic circuit that executes data communication processing.
Each of the communication device 914 and the communication device 934 is, for example, a communication chip or a NIC (Network Interface Card).

Each of the auxiliary storage device 913 and the auxiliary storage device 933 also stores an OS (Operating System).
Each of the processor 911 and the processor 931 executes at least a part of the OS.
The processor 911 executes a program that realizes the functions of the information acquisition unit 101, the diagnostic model generation unit 103, the influence estimation unit 105, the diagnostic unit 106, and the diagnostic model transmission unit 107 while executing at least a part of the OS.
When the processor 911 executes the OS, task management, memory management, file management, communication control, and the like are performed.
In addition, the processor 931 executes at least a part of the OS while the communication unit 301, the diagnosis notification display unit 302, the behavior history information generation unit 304, the sensor information collection unit 305, the vehicle control unit 306, the influence estimation unit 309, and the diagnosis unit. A program for realizing the function 310 is executed.
When the processor 931 executes the OS, task management, memory management, file management, communication control, and the like are performed.

In addition, at least one of information, data, a signal value, and a variable value indicating processing results of the information acquisition unit 101, the diagnosis model generation unit 103, the influence estimation unit 105, the diagnosis unit 106, and the diagnosis model transmission unit 107 is stored in the main memory. The data is stored in at least one of the device 912, the auxiliary storage device 913, the register in the processor 911, and the cache memory.
The programs for realizing the functions of the information acquisition unit 101, the diagnostic model generation unit 103, the influence estimation unit 105, the diagnostic unit 106, and the diagnostic model transmission unit 107 are a magnetic disk, a flexible disk, an optical disk, a compact disk, and a Blu-ray (registered trademark). ) It may be stored in a portable recording medium such as a disk or DVD. A portable recording medium in which programs for realizing the functions of the information acquisition unit 101, the diagnostic model generation unit 103, the influence estimation unit 105, the diagnostic unit 106, and the diagnostic model transmission unit 107 are stored may be distributed commercially. .

In addition, information, data, and signal values indicating the processing results of the communication unit 301, diagnosis notification display unit 302, behavior history information generation unit 304, sensor information collection unit 305, vehicle control unit 306, influence estimation unit 309, and diagnosis unit 310 And at least one of the variable values is stored in at least one of the main storage device 932, the auxiliary storage device 933, the register in the processor 931, and the cache memory.
A program for realizing the functions of the communication unit 301, the diagnosis notification display unit 302, the behavior history information generation unit 304, the sensor information collection unit 305, the vehicle control unit 306, the influence estimation unit 309, and the diagnosis unit 310 is a magnetic disk, a flexible You may store in portable recording media, such as a disk, an optical disk, a compact disk, a Blu-ray (trademark) disk, and DVD. And the portable which stored the program which realizes the function of communication part 301, diagnostic notice display part 302, behavior history information generation part 304, sensor information collection part 305, vehicle control part 306, influence estimation part 309, and diagnosis part 310 was stored. Recording media may be distributed commercially.

In addition, the “part” of the information acquisition unit 101, the diagnostic model generation unit 103, the influence estimation unit 105, the diagnostic unit 106, and the diagnostic model transmission unit 107 is replaced with “circuit”, “process”, “procedure”, or “processing”. May be.
The server device 100 may be realized by a processing circuit. The processing circuit is, for example, a logic IC (Integrated Circuit), a GA (Gate Array), an ASIC (Application Specific Integrated Circuit), or an FPGA (Field-Programmable Gate Array).

Further, the “unit” of the communication unit 301, the diagnosis notification display unit 302, the behavior history information generation unit 304, the sensor information collection unit 305, the vehicle control unit 306, the influence estimation unit 309, and the diagnosis unit 310 can be referred to as “circuit” Or “procedure” or “processing”.
In-vehicle device 300 may also be realized by a processing circuit.

In this specification, the superordinate concept of the processor and the processing circuit is referred to as “processing circuitry”.
That is, the processor and the processing circuit are specific examples of “processing circuitry”.

  DESCRIPTION OF SYMBOLS 100 Server apparatus, 101 Information acquisition part, 102 Information storage part, 103 Diagnosis model production | generation part, 104 Diagnosis model memory | storage part, 105 Influence estimation part, 106 Diagnosis part, 107 Diagnosis model transmission part, 200 Vehicle, 300 In-vehicle apparatus, 301 Communication , 302 diagnosis notification display unit, 303 element notification information acquisition unit, 304 behavior history information generation unit, 305 sensor information collection unit, 306 vehicle control unit, 307 storage unit, 308 diagnostic model storage unit, 309 influence estimation unit, 310 diagnosis Part, 500 diagnostic system, 911 processor, 912 main storage device, 913 auxiliary storage device, 914 communication device, 931 processor, 932 main storage device, 933 auxiliary storage device, 934 communication device.

Claims (16)

An information acquisition unit for acquiring behavior history information indicating a history of behavior of the vehicle while traveling;
An influence estimator that estimates the influence of the vehicle traveling on the vehicle element, which is an element of the vehicle, based on the behavior history of the vehicle during traveling indicated in the behavior history information;
A driving method for diagnosing a state of the vehicle element based on an influence on the vehicle element due to traveling of the vehicle estimated by the influence estimating unit and reducing an influence on the vehicle element due to traveling of the vehicle. An information processing apparatus including a diagnostic unit that notifies a vehicle user. An information acquisition unit for acquiring behavior history information indicating a history of behavior of the vehicle while traveling;
Analyzing the behavior history of the vehicle during travel indicated by the behavior history information to estimate the travel status of the vehicle and the travel environment of the vehicle, and the estimated travel status of the vehicle and the travel environment of the vehicle Based on the above, a diagnosis model obtained by learning the influence of the traveling state of the vehicle and the traveling environment of the vehicle on the vehicle element is used for the influence of the traveling of the vehicle on the vehicle element that is an element of the vehicle. An impact estimator to estimate
An information processing apparatus comprising: a diagnosis unit that diagnoses a state of the vehicle element based on an influence on the vehicle element caused by traveling of the vehicle estimated by the influence estimation unit. In the behavior history information, as a history of behavior during travel of the vehicle, a change with time of the state value of the vehicle is shown,
The influence estimation unit is
From the behavior history information, a statistic per unit time of the vehicle state value is calculated, and using the calculated statistic per unit time of the vehicle state value, the information processing apparatus according to claim 1 or 2 to estimate the impact. In the behavior history information, as a history of behavior during travel of the vehicle, a change with time of the state value of the vehicle is shown,
The influence estimation unit is
The information processing apparatus according to claim 1 or 2 wherein the state value of the vehicle symbolizes, estimates the effect on the vehicle component by the running of the vehicle using a sign of state values shown in the behavior history information . The influence estimation unit is
Examples impact on the vehicle component by the running of the vehicle, the information processing apparatus according to claim 1 or 2 to estimate the change of the physical quantity related to the vehicle component by the running of the vehicle. The diagnostic unit
Using the cumulative value of the change in the physical quantity of the vehicle element obtained before the vehicle travels and the change in the physical quantity of the vehicle element estimated by the influence estimation unit, the state of the vehicle element is determined. The information processing apparatus according to claim 5 for diagnosing. The diagnostic unit
Diagnosing whether the state of the vehicle element is a state that requires at least one of inspection and replacement of the vehicle element,
When the state of the vehicle element is a state where at least one of inspection and replacement of the vehicle element is necessary, the state of the vehicle element is a state where at least one of inspection and replacement of the vehicle element is necessary the information processing apparatus according to claim 1 or 2 notifies the user of the vehicle. The diagnostic unit
Diagnosing whether the state of the vehicle element is a state that requires at least one of inspection and replacement of the vehicle element,
When the state of the vehicle element is not in a state that requires inspection of the vehicle element, at least one of a travel distance and a period until the vehicle element needs to be inspected is predicted, and the predicted inspection of the vehicle element is performed. Informing the user of the vehicle of at least one of the distance traveled and the period until
When the state of the vehicle element is not a state in which the vehicle element needs to be replaced, at least one of a travel distance and a period until the vehicle element needs to be replaced is predicted, and the predicted replacement of the vehicle element is performed. the information processing apparatus according to claim 1 or 2 notifies the user of the vehicle at least one of travel distance and time to is required. The influence estimation unit is
The information processing apparatus according to claim 2 , wherein an influence on the vehicle element due to travel of the vehicle is estimated using a diagnosis model classified according to at least one of a region, a vehicle type, and a vehicle year. The information processing apparatus further includes:
Using behavior history information collected from a plurality of vehicles and indicating the behavior history of each vehicle while traveling, the influence of the vehicle driving situation and the vehicle driving environment on vehicle elements is learned, and The information processing apparatus according to claim 2 , further comprising a model generation unit that generates a diagnostic model capable of estimating an influence on traveling vehicle elements. The information processing apparatus includes:
Mounted on the vehicle,
The influence estimation unit is
The information processing apparatus according to claim 2 , wherein an influence on the vehicle element due to traveling of the vehicle is estimated using the diagnostic model provided from a server apparatus. The information acquisition unit and the influence estimation unit exist in the vehicle,
The information processing apparatus according to claim 1 or 2, wherein the diagnostic unit is outside the vehicle. The computer obtains behavior history information indicating the history of the behavior of the vehicle while driving,
Information processing in which the computer diagnoses a state of a vehicle element, which is an element of the vehicle, based on the behavior history information, and notifies a user of the vehicle of a driving method for reducing an influence on the vehicle element due to traveling of the vehicle Method. The computer obtains behavior history information indicating the history of the behavior of the vehicle while driving,
The computer analyzes the behavior history of the vehicle during travel indicated by the behavior history information to estimate the travel status of the vehicle and the travel environment of the vehicle, and the estimated travel status of the vehicle and the vehicle Based on the vehicle travel environment, the effect of travel of the vehicle on the vehicle element, which is an element of the vehicle, was obtained by learning the effect of the vehicle travel status and the vehicle travel environment on the vehicle element Estimated using a diagnostic model,
An information processing method in which the computer diagnoses the state of the vehicle element based on the estimated influence on the vehicle element by traveling of the vehicle. An information acquisition process for acquiring behavior history information indicating a history of behavior of the vehicle during travel;
A diagnosis process for diagnosing a state of a vehicle element that is an element of the vehicle based on the behavior history information, and notifying a user of the vehicle of a driving method that reduces an influence on the vehicle element by traveling of the vehicle; Information processing program to be executed. An information acquisition process for acquiring behavior history information indicating a history of behavior of the vehicle during travel;
Analyzing the behavior history of the vehicle during travel indicated by the behavior history information to estimate the travel status of the vehicle and the travel environment of the vehicle, and the estimated travel status of the vehicle and the travel environment of the vehicle Based on the above, a diagnosis model obtained by learning the influence of the traveling state of the vehicle and the traveling environment of the vehicle on the vehicle element is used for the influence of the traveling of the vehicle on the vehicle element that is an element of the vehicle. The impact estimation process
An information processing program for causing a computer to execute a diagnosis process for diagnosing a state of the vehicle element based on an influence on the vehicle element due to traveling of the vehicle estimated by the influence estimation process.

Images