Oil diagnosis device, oil diagnosis method, and storage medium

Abstract

The present disclosure provides an oil diagnosis device, an oil diagnosis method, and a storage medium. The oil diagnosis device includes a generation section configured to generate a statistical causal search model showing correlations between a plurality of kinds of driving information by using first data, the first data being various kinds of driving information acquired in advance from sensors connected to an in-vehicle unit mounted on a vehicle; an acquisition section configured to acquire second data, the second data being driving information acquired from sensors mounted on the vehicle and provided independently of the in-vehicle unit; an estimation section configured to estimate the driving information corresponding to the second data by using the statistical causal search model; and a derivation section configured to derive a precursor accumulation amount of the vehicle from the estimated driving information.

Description

Technical Field

[0001] This invention relates to an oil diagnostic device, an oil diagnostic method, and a storage medium for diagnosing driving conditions. Background Technology

[0002] Japanese Unexamined Patent Application Publication No. 2019-14437 (JP 2019-14437 A) discloses a diagnostic system that acquires driving information related to vehicle driving operations from an on-board unit and diagnoses driving skills by using the driving information. Summary of the Invention

[0003] True onboard units are expensive, and therefore cheaper recording devices (data recorders) can be installed to record vehicle driving information. However, the driving information that can be obtained from cheaper recording devices is limited. Therefore, diagnostic systems compatible with onboard units cannot always perform diagnostics using driving information obtained from cheaper recording devices.

[0004] The purpose of this invention is to provide an oil diagnostic device, an oil diagnostic method, and a storage medium, wherein the diagnostic system compatible with an on-board unit can perform diagnostics using driving information obtained from an inexpensive recording device.

[0005] The oil diagnostic device according to the first scheme includes: a generation unit configured to generate a statistical causal search model showing the correlation between multiple types of driving information by using first data, the first data being various types of driving information pre-acquired from sensors connected to an on-board unit installed on the vehicle; an acquisition unit configured to acquire second data, the second data being driving information acquired from sensors installed on the vehicle and set independently of the on-board unit; an estimation unit configured to estimate the driving information corresponding to the second data by using the statistical causal search model; and a derivation unit configured to derive the amount of precursor accumulation of the vehicle from the estimated driving information.

[0006] According to the first scheme, the oil diagnostic device diagnoses the oil using second data, which is driving information acquired from sensors installed on the vehicle and independent of the onboard unit. When diagnosing the oil, the device generates a statistical causal search model showing the correlations between multiple types of driving information using the first data. It then estimates the driving information corresponding to the second data using the statistical causal search model and derives the pre-accumulated quantity of the first data, which is the driving information pre-acquired from sensors installed on the onboard unit. That is, the oil diagnostic device diagnoses the oil based on driving information acquired from sensors retrofitted to the vehicle, utilizing driving information pre-acquired from sensors connected to the onboard unit. Therefore, a diagnostic system compatible with the onboard unit can perform diagnostics using measurement information acquired from inexpensive measuring devices.

[0007] In the oil diagnostic device according to the first scheme, the deduction unit may be configured to deduce the pre-accumulation amount by using a trained model, the trained model being machine learning that uses the first data to experience the relationship between the driving information and the pre-accumulation amount.

[0008] According to the oil diagnostic device of the first scheme, the oil can be diagnosed using the first data obtained from the vehicle unit.

[0009] In the fuel diagnostic device according to the first scheme, the estimation unit may be configured to estimate driving information including at least one of the average value of fuel consumption, the integral value of engine speed, and the maximum value of the engine speed.

[0010] According to the oil diagnostic device of the first scheme, the amount of pre-accumulated material can be deduced by elucidating the relationship.

[0011] The oil diagnostic method according to the second scheme includes: generating a statistical causal search model that shows the correlation between multiple types of driving information by using first data, the first data being various types of driving information pre-acquired from sensors connected to an on-board unit installed on the vehicle; acquiring second data, the second data being driving information acquired from sensors installed on the vehicle and set independently of the on-board unit; estimating the driving information corresponding to the second data by using the statistical causal search model; and deriving the pre-mass accumulation of the vehicle from the estimated driving information.

[0012] In the oil diagnostic method according to the second scheme, oil is diagnosed using second data, which is driving information acquired from sensors installed on the vehicle and independent of the on-board unit. When diagnosing oil in the oil diagnostic method, a statistical causal search model showing the correlation between multiple types of driving information is generated using first data. The driving information corresponding to the second data is estimated using the statistical causal search model, and the pre-accumulated quantity is derived. The first data is driving information acquired in advance from sensors installed on the on-board unit. That is, according to the oil diagnostic method, oil is diagnosed based on driving information acquired from sensors modified to the vehicle, utilizing driving information acquired in advance from sensors connected to the on-board unit. Therefore, a diagnostic system compatible with the on-board unit can perform diagnosis using measurement information acquired from inexpensive measuring devices.

[0013] According to the storage medium of the third scheme, a computer is enabled to execute an oil diagnostic procedure, the process comprising: generating a statistical causal search model showing the correlation between multiple types of driving information using first data, the first data being various types of driving information pre-acquired from sensors connected to an on-board unit installed on the vehicle; acquiring second data, the second data being driving information acquired from sensors installed on the vehicle and set independently of the on-board unit; estimating the driving information corresponding to the second data using the statistical causal search model; and deriving the pre-mass accumulation of the vehicle from the estimated driving information.

[0014] The computer executing the oil diagnostic procedure according to the third scheme diagnoses the oil using second data, which is driving information acquired from sensors installed on the vehicle and independent of the onboard unit. When diagnosing the oil, the computer generates a statistical causal search model showing the correlation between multiple types of driving information using first data, estimates the driving information corresponding to the second data using the statistical causal search model, and derives the pre-accumulated quantity of the first data, which is driving information pre-acquired from sensors installed on the onboard unit. That is, the computer diagnoses the oil based on driving information acquired from sensors retrofitted to the vehicle, utilizing driving information pre-acquired from sensors connected to the onboard unit. Therefore, a diagnostic system compatible with the onboard unit can perform diagnostics using measurement information acquired from inexpensive measuring devices.

[0015] According to the present invention, a diagnostic system compatible with an on-board unit can perform diagnostics using driving information obtained from an inexpensive recording device. Attached Figure Description

[0016] The features, advantages, and technical and industrial significance of exemplary embodiments of the invention will be described below with reference to the accompanying drawings, wherein like reference numerals denote like elements, and wherein:

[0017] Figure 1 A diagram illustrating a schematic configuration of an oil diagnostic system according to an embodiment;

[0018] Figure 2 A block diagram illustrating the hardware configuration of a vehicle according to an embodiment;

[0019] Figure 3 A block diagram illustrating the functional configuration of the vehicle-mounted unit according to an embodiment;

[0020] Figure 4 A block diagram illustrating the hardware configuration of the measuring device according to an embodiment;

[0021] Figure 5 A block diagram illustrating the functional configuration of the measuring device according to an embodiment;

[0022] Figure 6 A block diagram illustrating the hardware configuration of a central server according to an embodiment;

[0023] Figure 7 A schematic diagram illustrating an example of a statistical causal search model according to an embodiment;

[0024] Figure 8 A block diagram illustrating the functional configuration of the central server according to an embodiment;

[0025] Figure 9 A data flow diagram illustrating an example of the data flow of the processing to be implemented in the central server according to an embodiment;

[0026] Figure 10 A flowchart illustrating the process of oil diagnostics to be implemented in the central server according to an embodiment;

[0027] Figure 11 A flowchart illustrating the process of generation to be implemented in the central server according to an embodiment; and

[0028] Figure 12 A flowchart illustrating the process of machine learning processing to be implemented in the central server according to an embodiment. Detailed Implementation

[0029] An oil diagnostic system incorporating the oil diagnostic device of the present invention will be described. The oil diagnostic system diagnoses the amount of precursors (accumulated substances) accumulated in the engine by using data related to driving operations acquired from sensors on a measuring device installed on the vehicle but not connected to the vehicle. In the present invention, when diagnostics are performed using data related to driving operations acquired from sensors on a measuring device, data related to driving operations acquired from sensors on an onboard unit connected to the vehicle is utilized.

[0030] Overall configuration

[0031] like Figure 1 As shown, the oil diagnostic system 10 according to an embodiment of the present invention includes a plurality of vehicles 12 and a central server 40 serving as an oil diagnostic device. The vehicles 12 include vehicle 12A and vehicle 12B, vehicle 12A including an on-board unit 20, and vehicle 12B including a measuring device 30. The on-board unit 20 and the measuring device 30 are connected to the central server 40 via a network N.

[0032] Although Figure 1 The illustration shows two vehicles 12, including an onboard unit 20 or a measuring device 30, for a central server 40, but the number of vehicles 12, onboard units 20, and measuring devices 30 is not limited to these numbers.

[0033] The on-board unit 20 acquires driving information related to the operation of the vehicle 12 and sends the driving information to the central server 40.

[0034] The measuring device 30 acquires the measured driving information and sends it to the central server 40. The types of sensors connected to the measuring device 30 are limited compared to the on-board unit 20 installed on vehicle 12A. The sensors connected to the measuring device 30 acquire data with lower accuracy than those connected to the on-board unit 20. Therefore, the measuring device 30 is sold at a lower price than the on-board unit 20 and is installed on vehicle 12B.

[0035] The central server 40 is installed, for example, at the manufacturer of vehicle 12 or at a car dealership affiliated with the manufacturer.

[0036] In the following text, the driving information acquired from the vehicle unit 20 will be referred to as "driving information," while the driving information acquired from the measuring device 30 will be referred to as "measurement information." For example, in this embodiment, the driving information includes vehicle speed, acceleration, yaw rate, steering angle, accelerator input, brake pedal force, engine speed during stroke, fuel consumption, and distance traveled, while the measurement information includes positioning information and acceleration. Examples of driving information as "first data" and measurement information as "second data" are provided.

[0037] vehicle

[0038] like Figure 2 As shown, the vehicle 12A according to this embodiment includes an on-board unit 20, a plurality of electronic control units (ECUs) 22 and a plurality of on-board devices 24.

[0039] The vehicle unit 20 includes a central processing unit (CPU) 20A, a read-only memory (ROM) 20B, a random access memory (RAM) 20C, a vehicle communication interface (I / F) 20D, and a wireless communication I / F 20E. The CPU 20A, ROM 20B, RAM 20C, vehicle communication I / F 20D, and wireless communication I / F 20E are connected to enable communication between them via an internal bus 20G.

[0040] CPU 20A is a central processing unit that executes various programs and controls various units. That is, CPU 20A reads programs from ROM 20B and uses RAM 20C as its working area to execute programs.

[0041] ROM 20B stores various programs and data. In this embodiment, ROM 20B stores a collection program 100, which collects driving information related to the status and control of vehicle 12A from ECU 22. As the collection program 100 is executed, the on-board unit 20 performs the process of sending the driving information to the central server 40. ROM 20B also stores historical information 110 as backup data for the driving information. RAM 20C serves as a temporary storage area for programs or data.

[0042] The vehicle communication I / F 20D is an interface for connecting to each ECU 22. For this interface, a communication standard based on the Controller Area Network (CAN) protocol is used. The vehicle communication I / F 20D connects to the external bus 20F.

[0043] Wireless communication I / F 20E is a wireless communication module used for communicating with the central server 40. For example, communication standards such as 5G, LTE, or Wi-Fi (registered trademark) are used for this wireless communication module. Wireless communication I / F 20E is connected to network N.

[0044] ECU 22 includes at least the advanced driver assistance system (ADAS) ECU 22A, steering ECU 22B, braking ECU 22C, and engine ECU 22D.

[0045] The ADAS-ECU 22A controls the advanced driver assistance system in a comprehensive manner. The vehicle speed sensor 24A, yaw rate sensor 24B, and external sensors 24C, which constitute the onboard unit 24, are connected to the ADAS-ECU 22A. The external sensors 24C are a group of sensors used to detect the surrounding environment of the vehicle 12A. For example, the external sensors 24C include a camera that captures images of the area surrounding the vehicle 12A, a millimeter-wave radar that transmits probe waves and receives reflected waves, and a laser imaging, detection, and ranging (LiDAR) sensor that scans the area in front of the vehicle 12A.

[0046] The steering ECU 22B controls the power steering. The steering angle sensor 24D, which constitutes the on-board unit 24, is connected to the steering ECU 22B. The steering angle sensor 24D detects the steering angle of the steering wheel.

[0047] The brake ECU 22C controls the braking system of the vehicle 12A. The brake actuator 24E, which constitutes the on-board unit 24, is connected to the brake ECU 22C.

[0048] The engine ECU 22D controls the engine of vehicle 12A. The throttle actuator 24F and sensor 24G constituting the on-board unit 24 are connected to the engine ECU 22D. The sensor 24G includes an oil temperature sensor for measuring the oil temperature of the engine oil, an oil pressure sensor for measuring the oil pressure of the engine oil, and a rotation sensor for detecting the engine speed.

[0049] According to this embodiment, the vehicle speed sensor 24A, yaw rate sensor 24B, external sensor 24C, steering angle sensor 24D, brake actuator 24E, throttle actuator 24F, and sensor 24G are examples of "sensors connected to the vehicle unit".

[0050] like Figure 3 As shown, in the vehicle unit 20 according to this embodiment, the CPU 20A serves as a collection unit 200 and an output unit 210 by executing the collection program 100.

[0051] The collection unit 200 has the function of acquiring driving information related to the status of the on-board unit 24 and the driving of the vehicle 12A obtained from the on-board unit 24, which is related to the vehicle 12A's status. The driving information may include images of the external area of ​​the vehicle 12A captured by a camera used as an external sensor 24C.

[0052] The output unit 210 has the function of outputting the driving information collected by the collection unit 200 to the central server 40.

[0053] Measuring device

[0054] like Figure 4As shown, the measuring device 30 includes a CPU 30A, ROM 30B, RAM 30C, storage unit 30D, communication I / F 30E, sensor 30F, and Global Positioning System (GPS) device 30G. The CPU 30A, ROM 30B, RAM 30C, storage unit 30D, communication I / F 30E, sensor 30F, and GPS device 30G are connected to enable communication between them via an internal bus 30H. The functions of the CPU 30A, ROM 30B, RAM 30C, and communication I / F 30E are the same as those of the CPU 20A, ROM 20B, RAM 20C, and wireless communication I / F 20E of the vehicle-mounted unit 20 described above.

[0055] The storage unit 30D, used as memory, is a hard disk drive (HDD) or a solid-state drive (SSD), and stores various programs and measurement information related to driving of the vehicle 12 obtained from the sensor 30F and the GPS device 30G. In this embodiment, the storage unit 30D stores the collection program 120. The ROM 30B can store the collection program 120.

[0056] Sensor 30F includes an acceleration sensor that detects acceleration on a measuring device 30 mounted on the vehicle, and an angular velocity sensor that detects angular velocity in the yaw direction.

[0057] The GPS device 30G detects its position by receiving positioning information from multiple GPS satellites obtained by measuring the position of a measuring device 30 installed on the vehicle 12B. The GPS device 30G includes an antenna (not shown) for receiving positioning information from GPS satellites.

[0058] The collection program 120, used as a program, performs the process of acquiring positioning information, acceleration, and angular velocity as measurement information and sending the measurement information to the central server 40.

[0059] The sensor 30F and GPS device 30G according to this embodiment are examples of "sensors installed on a vehicle and set up independently of the vehicle unit". The phrase "set up independently" means that the sensor is installed on the vehicle 12 and connected to a measuring device 30 that is different from the vehicle unit 20.

[0060] like Figure 5 As shown, in the measuring device 30 according to this embodiment, the CPU 30A serves as a collection unit 300 and an output unit 310 by executing the collection program 120.

[0061] The collection unit 300 collects the positioning information of the measuring device 30 installed on the vehicle 12B from the GPS device 30G and collects the acceleration and angular velocity of the vehicle 12B as measurement information from the sensor 30F.

[0062] The output unit 310 has the function of outputting the measurement information collected by the collection unit 300 to the central server 40.

[0063] Central server

[0064] like Figure 6 As shown, the central server 40 includes a CPU 40A, ROM 40B, RAM 40C, storage unit 40D, and communication I / F 40E. The CPU 40A, ROM 40B, RAM 40C, storage unit 40D, and communication I / F 40E are connected to enable communication between them via an internal bus 40F. The functions of the CPU 40A, ROM 40B, RAM 40C, and communication I / F 40E are the same as those of the CPU 20A, ROM 20B, RAM 20C, and wireless communication I / F 20E of the vehicle unit 20 described above. The communication I / F 40E can perform wired communication.

[0065] The storage unit 40D, used as a memory, is a hard disk drive (HDD) or a solid-state drive (SSD), and stores various programs and data. In this embodiment, the storage unit 40D stores the oil diagnostic program 130, the driving information database (DB) 140, the search model 150, the derivation model 160, and the learning data 170. The ROM 40B can store the oil diagnostic program 130, the driving information database (DB) 140, the search model 150, the derivation model 160, and the learning data 170.

[0066] The oil diagnostic program 130, used as a program, controls the central server 40. As the oil diagnostic program 130 is executed, the central server 40 performs a process including an oil diagnostic process for diagnosing the amount of accumulated substances in the pre-existing condition of the vehicle 12.

[0067] The driving information DB 140 stores driving information received from the vehicle unit 20 and measurement information received from the measuring device 30.

[0068] Search model 150 illustrates the correlation between driving-related data generated using driving information obtained from the vehicle unit 20. Specifically, search model 150 is a model that estimates the correlation between data in association with the data included in the driving information by using a statistical causal search (LiNGAM, Linear Non-Gaussian Acyclic Model) for the correlation between data.

[0069] For example, such as Figure 7As shown, search model 150 illustrates the correlations between data included in driving information, such as vehicle speed, engine speed, integral value of engine speed, fuel consumption, and driving distance, and is able to estimate each data point from the correlations between the data. For example, according to search model 150, engine speed, fuel consumption, and driving distance can be estimated from vehicle speed, and integral value of engine speed and fuel consumption can be estimated from engine speed. According to search model 150, fuel consumption and driving distance can be estimated from integral value of engine speed, and driving distance can be estimated from fuel consumption.

[0070] That is, by inputting the vehicle speed into the search model 150, the engine speed, the integral value of the engine speed, the fuel consumption, and the driving distance can be estimated.

[0071] The derivation model 160 is as follows: a trained model that derives the engine's pre-accumulation amount through machine learning of the relationship between driving information and pre-accumulation amount in the learning data 170 (described later). According to this embodiment, the derivation model 160 outputs the corresponding pre-accumulation amount by inputting the maximum engine speed, the integral value of the engine speed, and the fuel consumption.

[0072] Learning data 170 is the data used to train and derive model 160. Learning data 170 consists of the following: pre-stored driving information, including the maximum engine speed, the integral value of engine speed, and fuel consumption, as input data, and the pre-accumulated amount of driving information as teaching data.

[0073] like Figure 8 As shown, in the central server 40 of this embodiment, the CPU 40A is used as an acquisition unit 400, a storage unit 410, an estimation unit 420, a derivation unit 430, an output unit 440, a generation unit 450, and a learning unit 460 by executing the oil diagnostic program 130.

[0074] The acquisition unit 400 has the function of acquiring driving information and measurement information from the vehicle-mounted unit 20 of vehicle 12A and the measuring device 30 of vehicle 12B. The acquisition unit 400 acquires driving information and measurement information transmitted from the vehicle-mounted unit 20 and the measuring device 30 at any time.

[0075] The storage unit 410 stores the search model 150 and the derivation model 160 generated by using driving information obtained from the vehicle unit 20.

[0076] The estimation unit 420 estimates driving information for the vehicle 12 corresponding to data related to the measurement information using the search model 150. Specifically, the estimation unit 420 estimates the vehicle speed of the vehicle 12 from the positioning information, acceleration, and angular velocity included in the measurement information, and estimates driving information corresponding to the vehicle speed using the search model 150. For example, the estimation unit 420 estimates engine speed, the integral value of engine speed, and fuel consumption as driving information.

[0077] The derivation unit 430 derives the amount of pre-accumulation from the estimated driving information using the derivation model 160. For example, according to this embodiment, the derivation unit 430 derives the amount of pre-accumulation from the estimated maximum engine speed, the integral value of engine speed, and the average value of fuel consumption using the derivation model 160.

[0078] The output unit 440 outputs the derivation results from the derivation unit 430. In order to output the derivation results, the output unit 440 can send the derivation results to the vehicle unit 20, the measuring device 30, etc., or display the derivation results on a monitor (not shown) set in the central server 40.

[0079] The generation unit 450 generates a search model by using driving information pre-acquired from the vehicle unit 20 and stored in the driving information DB140. For example, the generation unit 450 estimates the correlation between data by analyzing data such as engine speed, integral value of engine speed, and fuel consumption related to driving information, and generates a search model that can estimate the value of one data point corresponding to another data point.

[0080] The learning unit 460 generates a derivation model, which is a trained model that undergoes machine learning to derive prior quality accumulation, by using driving information pre-acquired from the vehicle unit 20 and stored in the driving information DB140. Specifically, the learning unit 460 generates the derivation model by performing supervised learning, in which the driving information acquired from the vehicle 12 is the input data and the prior quality accumulation corresponding to the driving information is the teaching data.

[0081] Before describing the operation of the oil diagnostic system 10, refer to Figure 9 Describes the data flow in the central server 40, which is used as an oil diagnostic device. Figure 9 A data flow diagram illustrating an example of data flow in central server 40.

[0082] For example, such as Figure 9 As shown, the generation unit 450 generates a search model 150 by using driving information stored in the driving information DB 140, and outputs the search model 150 to the estimation unit 420.

[0083] The learning unit 460 generates a derivation model that has undergone learning corresponding to the pre-accumulated amount of driving information by using learning data 170 including driving information and pre-accumulated amount of driving information, and outputs the derivation model to the derivation unit 430.

[0084] The acquisition unit 400 acquires measurement information from the measuring device 30 and inputs the acquired measurement information to the estimation unit 420. The estimation unit 420 estimates the maximum engine speed, the integral value of engine speed, and the average value of fuel consumption as driving information corresponding to the data related to the measurement information by using the search model 150, and inputs the estimated driving information to the derivation unit 430. The derivation unit 430 derives the pre-accumulation amount from the estimated driving information by using the derivation model 160 generated by the learning unit 460, and outputs the pre-accumulation amount as a diagnostic result.

[0085] Control process

[0086] Reference Figure 10 The flowchart describes the processing flow to be performed by the oil diagnostic system 10 of this embodiment. Each process in the central server 40 is executed by the CPU 40A of the central server 40, which serves as an acquisition unit 400, a storage unit 410, an estimation unit 420, a derivation unit 430, an output unit 440, a generation unit 450, and a learning unit 460. For example, when an instruction to perform oil diagnostics is input, the process is executed... Figure 10 The oil diagnostic treatment shown.

[0087] In step S100, CPU 40A acquires the stored search model 150 and the stored derivation model 160.

[0088] In step S101, the CPU 40A acquires measurement information from the measuring device 30.

[0089] In step S102, the CPU 40A estimates the maximum value of engine speed, the integral value of engine speed, and the average value of fuel consumption from the measurement information using the search model 150 as driving information.

[0090] In step S103, CPU 40A derives the premass accumulation amount from the estimated maximum value of engine speed, the estimated integral value of engine speed, and the estimated average value of fuel consumption using the derivation model 160.

[0091] In step S104, CPU 40A outputs the derived pre-mass accumulation amount.

[0092] In step S105, CPU 40A determines whether to terminate the oil diagnostic process. If the determination to terminate the oil diagnostic process is made (step S105: Yes), the oil diagnostic process is terminated. If the determination not to terminate the oil diagnostic process is made (step S105: No), CPU 40A proceeds to step S101 to obtain measurement information.

[0093] Next, we will refer to Figure 11 The flowchart describes the process to be executed by the oil diagnostic system 10 of this embodiment to generate a search model 150 using driving information previously acquired from the vehicle unit 20. For example, when an instruction is input to execute the process for generating the search model 150, the process is executed. Figure 11 The processing shown.

[0094] In step S200, CPU 40A acquires driving information stored by pre-acquiring it from vehicle unit 20.

[0095] In step S201, CPU 40A generates search model 150 by using the acquired driving information.

[0096] In step S202, CPU 40A determines whether to terminate the process for generating search model 150. If the determination to terminate the process for generating search model 150 is made (step S202: Yes), the process proceeds to step S203. If the determination not to terminate the process for generating search model 150 is made (step S202: No), CPU 40A proceeds to step S200 to obtain driving information.

[0097] In step S203, the CPU 40A stores the generated search model 150 in the storage unit 40D and terminates the process for generating the search model 150.

[0098] Next, we will refer to Figure 12 The flowchart description is to be executed by the oil diagnostic system 10 of this embodiment to train the derivation model 160 using driving information pre-acquired from the vehicle unit 20. For example, when an instruction for generating the derivation model 160 is input, the process is executed. Figure 12 The learning process is shown below.

[0099] In step S300, CPU 40A acquires driving information and prior accumulation as learning data.

[0100] In step S301, CPU 40A generates inference model 160 by performing machine learning using the acquired driving information and the acquired prior accumulation.

[0101] In step S302, CPU 40A determines whether to terminate the process for generating the derivation model 160. If the determination to terminate the process for generating the derivation model 160 is made (step S302: Yes), the process proceeds to step S303. If the determination not to terminate the process for generating the derivation model 160 is made (step S302: No), CPU 40A proceeds to step S300 to obtain driving information and pre-accumulation amount.

[0102] In step S303, the CPU 40A stores the generated derivation model 160 in the storage unit 40D and terminates the processing used to generate the derivation model 160.

[0103] According to the above embodiment, a diagnostic system compatible with an on-board unit can perform diagnostics using driving information obtained from an inexpensive recording device.

[0104] Summarize

[0105] The central server 40, used as the oil diagnostic device in this embodiment, diagnoses the oil using second data, which is measurement information acquired from sensors installed on the vehicle and set independently of the on-board unit 20. When diagnosing the oil, the oil diagnostic device generates a statistical causal search model demonstrating the correlation between various types of driving information using first data, which is driving information pre-acquired from sensors installed on the on-board unit 20. It then estimates the driving information corresponding to the second data using the statistical causal search model and derives the pre-accumulated quantity of mass. In other words, the oil diagnostic device diagnoses the oil based on measurement information acquired from the measurement device 30, which has been retrofitted to the vehicle, using driving information pre-acquired from the on-board unit 20. Therefore, the diagnostic system 10, compatible with the on-board unit 20, can perform diagnostics using measurement information acquired from the inexpensive measurement device 30.

[0106] Remark

[0107] In the above embodiments, the central server 40 is used as an oil diagnostic device. However, the present invention is not limited to the above embodiments. The vehicle-mounted unit 20 can also be used as an oil diagnostic device. When the vehicle-mounted unit 20 is used as an oil diagnostic device, the vehicle-mounted unit 20 acquires measurement information related to the measuring device 30 installed on the vehicle 12, and performs oil diagnostic processing by using a pre-stored search model 150 and a derivation model 160.

[0108] In the above embodiments, the amount of pre-accumulation is derived by acquiring measurement information and estimating driving information. However, the present invention is not limited to the above embodiments. The amount of pre-accumulation can be derived by acquiring driving information. For example, when acquiring driving information, the amount of pre-accumulation can be derived by directly inputting the driving information to the derivation unit 430 without the intervention of the estimation unit 420, or a determination can be made as to whether the estimation unit 420 estimates the driving information based on the acquired information.

[0109] In the above embodiments, the maximum engine speed, the integral value of engine speed, and the average value of fuel consumption are used as driving information. However, the present invention is not limited to the above embodiments. At least one of the maximum engine speed, the integral value of engine speed, and the average value of fuel consumption can be used as driving information.

[0110] The derivation unit 430 according to the above embodiment derives the amount of pre-mass accumulation by using the maximum value of engine speed, the integral value of engine speed, and the average value of fuel consumption. However, the present invention is not limited to the above embodiment. For example, the derivation unit 430 can derive the amount of pre-mass accumulation by using vehicle speed, driving distance, type of engine oil, type of engine installed on vehicle 12, or type of vehicle 12.

[0111] The amount of mass accumulation is derived from the derivation unit 430 in the above embodiment. However, the present invention is not limited to the above embodiment. For example, the replacement time of components of vehicle 12 (such as tires and headlights) can be estimated.

[0112] The measuring device 30 according to the above embodiment includes a sensor 30F and a GPS device 30G. However, the present invention is not limited to the above embodiment. Only the sensor 30F or only the GPS device 30G may be installed.

[0113] The measuring device 30 according to the above embodiment measures the position of vehicle 12B via GPS device 30G. However, the present invention is not limited to the above embodiment. For example, the position of vehicle 12B can be measured using communication I / F 30E. For example, when communication I / F 30E is Wi-Fi (registered trademark), the position and speed of vehicle 12B can be estimated by storing the connected access points of Wi-Fi (registered trademark) and the time of connection to the access points.

[0114] Various processors other than the CPU can execute the various processes performed by reading software (programs) by CPU 20A, CPU 30A, and CPU 40A in the above embodiments. Examples of processors in this case include programmable logic devices (PLDs), such as field-programmable gate arrays (FPGAs) whose circuit configuration can be changed after production, and application-specific circuits, such as application-specific integrated circuits (ASICs), which are processors with circuit configurations specifically designed for performing specific processes. Each of the above processes can be executed by one of the various processors, or by a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs or a combination of a CPU and an FPGA). More specifically, the hardware structure of each of the various processors is a circuit that incorporates circuit elements such as semiconductor elements.

[0115] In the above embodiments, each program is pre-stored (pre-installed) in a non-transitory computer-readable recording medium. For example, the collection program 100 in the vehicle unit 20 is pre-stored in ROM 20B, the collection program 120 in the measuring device 30 is pre-stored in storage unit 30D, and the oil diagnostic program 130 in the central server 40 is pre-stored in storage unit 40D. However, the present invention is not limited to this. Each program can be provided by recording on a non-transitory recording medium (such as a compressed optical disc read-only memory (CD-ROM), a digital multifunction optical disc read-only memory (DVD-ROM), or a universal serial bus (USB) memory). Furthermore, programs can be downloaded from external devices via a network.

[0116] The processing flow in the above embodiments is illustrative, and unnecessary steps may be omitted, new steps may be added, or the processing order may be changed without departing from the main idea.

Claims

1. An oil diagnostic device, comprising: The generation unit is configured to generate a statistical causal search model that shows the correlation between multiple types of driving information by using first data, which is various types of driving information acquired in advance from sensors connected to an on-board unit installed on the vehicle. The acquisition unit is configured to acquire second data, which is measurement information acquired from a sensor installed on a different vehicle than the vehicle and connected to a measuring device different from the vehicle-mounted unit. An estimation unit is configured to estimate driving information of the other vehicle corresponding to data related to the measurement information by using the statistical causal search model; as well as The derivation unit is configured to derive the pre-mass accumulation of the other vehicle from the estimated driving information of the other vehicle.

2. The oil diagnostic device according to claim 1, wherein, The derivation unit is configured to derive the pre-accumulation amount by using a trained model, which is a machine learning process that uses the first data to understand the relationship between the vehicle's driving information and the pre-accumulation amount.

3. The oil diagnostic device according to claim 1, wherein, The estimation unit is configured to estimate driving information of the other vehicle, including at least one of the average value of fuel consumption, the integral value of engine speed, and the maximum value of the engine speed.

4. An oil diagnostic method, comprising: A statistical causal search model is generated by using first data, which is various types of driving information obtained in advance from sensors connected to an on-board unit installed on the vehicle. Acquire second data, which is measurement information obtained from a sensor installed on a different vehicle than the vehicle and connected to a measuring device different from the on-board unit; The driving information of the other vehicle corresponding to the data related to the measurement information is estimated by using the statistical causal search model. as well as The pre-mass accumulation of the other vehicle is derived from the estimated driving information of the other vehicle.

5. A storage medium storing an oil diagnostic program that enables a computer to execute processing, the processing comprising: A statistical causal search model is generated by using first data, which is various types of driving information obtained in advance from sensors connected to an on-board unit installed on the vehicle. Acquire second data, which is measurement information obtained from a sensor installed on a different vehicle than the vehicle and connected to a measuring device different from the on-board unit; The driving information of the other vehicle corresponding to the data related to the measurement information is estimated by using the statistical causal search model. as well as The pre-mass accumulation of the other vehicle is derived from the estimated driving information of the other vehicle.

Images