Diagnosis method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a diagnosis method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring historical driving data of a target vehicle; acquiring historical diagnosis data of a first vehicle part of the target vehicle; according to the historical diagnosis data and the historical driving data, the reference diagnosis frequency of the first vehicle part in the first time period is determined; the first time period is a preset time period after the current moment; acquiring a target driving route and a target vehicle load of the target vehicle in the first time period; determining a target driving road type and a target driving weather type of the target driving route in the first time period; according to the target vehicle load, the target driving road type and the target driving weather type, the reference diagnosis frequency is adjusted, and the target diagnosis frequency of the first vehicle part is obtained; and diagnosing the first vehicle part according to the target diagnosis frequency to obtain diagnosis information of the first vehicle part. By adopting the embodiment of the invention, the diagnosis efficiency can be improved when the vehicle is diagnosed.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicles, and in particular, to a diagnostic method, device, electronic device, and storage medium. Background Art

[0002] With the development of technology, vehicles have become common means of transportation. There are more and more vehicle models and types, including traditional fuel vehicles, new energy vehicles, hybrid vehicles, driverless vehicles, and so on. During the use of these vehicles, there are vehicle diagnosis and repair requirements.

[0003] However, traditional diagnostic methods are relatively general and cannot achieve personalized diagnosis for different vehicles. For example, in diagnosis, diagnostic devices often receive diagnostic instructions and read multiple vehicle fault codes. However, for some vehicle components that are not prone to faults, frequent reading of fault codes and related data will result in low overall diagnostic efficiency of the vehicle. Summary of the Invention

[0004] To solve the above problems, embodiments of the present invention provide a diagnostic method, device, electronic device, and storage medium, which can improve the diagnostic efficiency when diagnosing a vehicle.

[0005] In a first aspect, an embodiment of the present invention provides a diagnostic method, including:

[0006] Obtaining historical driving data of a target vehicle;

[0007] Obtaining historical diagnostic data of a first vehicle component of the target vehicle;

[0008] Determining a reference diagnostic frequency of the first vehicle component within a first time period according to the historical diagnostic data and the historical driving data; the first time period is a preset time period after the current moment;

[0009] Obtaining a target driving route and a target vehicle load of the target vehicle within the first time period;

[0010] Determining a target driving road type and a target driving weather type of the target driving route within the first time period;

[0011] Adjusting the reference diagnostic frequency according to the target vehicle load, the target driving road type, and the target driving weather type to obtain a target diagnostic frequency of the first vehicle component;

[0012] Diagnosing the first vehicle component according to the target diagnostic frequency to obtain diagnostic information of the first vehicle component.

[0013] In a second aspect, an embodiment of the present invention provides a diagnostic device, which includes an acquisition unit and a processing unit;

[0014] The obtaining unit is configured to obtain historical driving data of a target vehicle;

[0015] Obtain historical diagnostic data of a first vehicle component of the target vehicle;

[0016] The processing unit is configured to determine a reference diagnostic frequency of the first vehicle component within a first time period according to the historical diagnostic data and the historical driving data; the first time period is a preset time period after the current moment;

[0017] Obtain a target driving route and a target vehicle load of the target vehicle within the first time period;

[0018] Determine a target driving road type and a target driving weather type of the target driving route within the first time period;

[0019] Adjust the reference diagnostic frequency according to the target vehicle load, the target driving road type and the target driving weather type to obtain a target diagnostic frequency of the first vehicle component;

[0020] Diagnose the first vehicle component according to the target diagnostic frequency to obtain diagnostic information of the first vehicle component.

[0021] In a third aspect, an embodiment of the present invention provides an electronic device, the electronic device includes a processor and a memory, the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory so that the electronic device executes the method as described in the first aspect.

[0022] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method as described in the first aspect.

[0023] In a fifth aspect, an embodiment of the present application provides a computer program product, the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer is operable to cause the computer to execute the method as described in the first aspect.

[0024] Implementing the embodiments of the present application has the following beneficial effects:

[0025] In the embodiment of the present application, first obtain the historical driving data of the target vehicle and the historical diagnostic data of the first vehicle component of the target vehicle. Then, according to the historical diagnostic data and the historical driving data, determine the reference diagnostic frequency of the first vehicle component within the first time period, where the first time period is a preset time period after the current moment. Then, obtain the target driving route and the target vehicle load of the target vehicle within the first time period, and determine the target driving road type and the target driving weather type of the target driving route within the first time period. Next, adjust the reference diagnostic frequency according to the target vehicle load, the target driving road type, and the target driving weather type to obtain the target diagnostic frequency of the first vehicle component. Finally, diagnose the first vehicle component according to the target diagnostic frequency to obtain the diagnostic information of the first vehicle component. Thus, by determining the reference diagnostic frequency of the first vehicle component within the first time period through the historical diagnostic data and the historical driving data, and adjusting the reference diagnostic frequency according to the target vehicle load, the target driving road type, and the target driving weather type to obtain the target diagnostic frequency of the first vehicle component, and diagnosing the first vehicle component according to the target diagnostic frequency, the diagnostic efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the background art, the following will describe the drawings required to be used in the embodiments of the present invention or the background art. Obviously, the drawings in the following description are some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0027] Figure 1 is a schematic diagram of the architecture of a diagnostic system provided by an embodiment of the present application;

[0028] Figure 2 is a flowchart of a diagnostic method provided by an embodiment of the present application;

[0029] Figure 3 is a schematic diagram of the sequence of diagnoses provided by an embodiment of the present application;

[0030] Figure 4 is a schematic diagram of the fluctuating data of the number of diagnostic requirements provided by an embodiment of the present application;

[0031] Figure 5 is a schematic diagram of the diagnostic serial number tags provided by an embodiment of the present application;

[0032] Figure 6 is a schematic diagram of a maintenance resource scheduling method provided by an embodiment of the present application;

[0033] Figure 7 is a schematic diagram of the structure of a diagnostic device provided by an embodiment of the present application;

[0034] Figure 8 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. Specific implementation manners

[0035] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0036] The terms "first", "second", "third", "fourth", etc. in the specification and claims of the present application and the accompanying drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or modules is not limited to the listed steps or modules, but optionally further includes steps or modules not listed, or optionally further includes other steps or modules inherent to these processes, methods, products, or devices.

[0037] Referring to "embodiments" herein means that specific features, results, or characteristics described in connection with the embodiments can be included in at least one embodiment of the present application. The phrase appears in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art will explicitly and implicitly understand that the embodiments described herein can be combined with other embodiments.

[0038] Traditional vehicle diagnosis generally follows a fault troubleshooting process from simple to complex and from external to internal. A vehicle can usually be divided into multiple subsystems such as an engine system, an electrical system, a braking system, etc. Traditional diagnostic methods generally divide diagnostic work according to these systems and check each system one by one. First, an appearance inspection is carried out to determine whether there are obvious damages, leaks, etc. on the vehicle. Then, basic function tests are carried out, such as starting the vehicle, operating various control buttons, etc., to observe the running condition of the vehicle. Then, detection equipment is used to detect the systems or components that may have faults, gradually narrowing down the fault range. This general troubleshooting process is applicable to the fault diagnosis of vehicles of various brands and models, but it will also lead to low diagnostic efficiency.

[0039] To this end, the embodiments of the present application provide a diagnostic method. In the embodiments of the present application, the diagnostic device diagnoses different vehicle modules in both cases of simultaneous diagnosis at the same time and batch-by-batch and frequency-by-frequency diagnosis, specifically depending on factors such as vehicle design, the functions of the diagnostic device, and diagnostic strategies.

[0040] Exemplarily, modern vehicles usually adopt a distributed control system, and each module is connected through bus technologies such as Controller Area Network. In this architecture, the diagnostic device can utilize the multi-master communication characteristics of the bus to send diagnostic requests to multiple modules simultaneously. Each module will respond simultaneously after receiving the request, enabling the diagnostic device to obtain information of different modules at the same time and achieve simultaneous diagnosis of multiple modules. When the vehicle undergoes a comprehensive physical examination or quickly troubleshoots faults, the diagnostic device will adopt the simultaneous diagnosis method. For example, when the vehicle enters a repair shop for routine maintenance or experiences an unexplained comprehensive fault, the maintenance personnel hope to quickly understand the status of each module of the vehicle. At this time, the diagnostic device will simultaneously send diagnostic instructions to multiple key modules such as the engine control module, transmission control module, anti-lock braking system module, and electronic stability program module to obtain a large amount of diagnostic data at one time, so as to comprehensively evaluate the condition of the vehicle and quickly locate possible problems.

[0041] Exemplarily, different modules of the vehicle have different functions and importance, and the requirements for the timeliness and frequency of diagnosis are also different. For example, core modules such as the engine and transmission are related to the power output and driving safety of the vehicle and require more frequent and detailed diagnosis, while some auxiliary function modules such as the in-vehicle entertainment system have less impact on the driving safety of the vehicle, and the diagnosis frequency can be relatively low. Therefore, the diagnostic device will diagnose different modules batch-by-batch and frequency-by-frequency according to the importance and usage of the modules. The bus bandwidth of the vehicle is limited. If all modules are diagnosed at a high frequency simultaneously, it may lead to an excessive bus load, affecting the normal communication between modules and even causing data transmission errors or losses. To avoid this situation, the diagnostic device will reasonably arrange the diagnostic sequence and frequency, diagnose different modules batch-by-batch, and ensure the stability and reliability of bus communication. In certain specific diagnostic scenarios, in-depth and detailed diagnosis of a certain module or several related modules is required. At this time, the diagnosis of other irrelevant modules will be temporarily stopped, and the focus will be on detecting the specific module. For example, when the engine of the vehicle fails, the maintenance personnel may first focus on detailed diagnosis of the engine control module and its related sensors and actuators, and temporarily suspend the routine diagnosis of other modules to more specifically troubleshoot the cause of the engine failure.

[0042] Moreover, the diagnostic resources or diagnostic computing power of the platform are limited, mainly restricted by factors such as hardware facilities, software algorithms, network conditions, data processing capabilities, and concurrent processing capabilities.

[0043] Exemplarily, the hardware configurations such as the central processing unit, memory, and storage of the server determine the basic processing capabilities of the platform. If the server has a small number of central processing unit cores and a low frequency, the processing efficiency will be low when dealing with a large amount of vehicle diagnostic data and complex algorithm operations. Similarly, insufficient memory will cause the data caching and reading speeds to slow down, and poor storage I / O performance will affect the data storage and retrieval efficiency, all of which will limit the diagnostic computing power of the platform. The performance of devices such as network switches and routers will also affect the diagnostic resources of the platform. If the port bandwidth of the network device is limited and the forwarding capacity is insufficient, network congestion will occur during a large amount of data transmission, resulting in problems such as data transmission delay and packet loss, affecting the timely acquisition of diagnostic data and the accurate sending of instructions, and thus limiting the efficiency and effectiveness of remote diagnosis. The more complex the diagnostic algorithm adopted by the platform, the higher the demand for computing power. Whether the software architecture design of the platform is reasonable will also affect the utilization efficiency of diagnostic resources. The network bandwidth determines the speed and capacity of data transmission. In remote diagnosis, a large amount of diagnostic data needs to be transmitted in real time between the vehicle and the platform. If the network bandwidth is insufficient, the data transmission will become slow, resulting in the platform being unable to obtain the latest status information of the vehicle in a timely manner, affecting the timeliness and accuracy of diagnosis. The stability of the network signal is also crucial for the diagnostic platform. An unstable network may cause problems such as data transmission interruption and large delay fluctuations, making the data received by the platform incomplete or inaccurate, and thus affecting the reliability of the diagnostic results. This situation may be more obvious in some remote areas with poor network signals.

[0044] Exemplarily, as the number of vehicles connected to the platform increases and the amount of data generated by the vehicles continues to grow, the scale of data that the platform needs to process and store will also expand rapidly. A large amount of data requires more computing resources for analysis and processing. If the data processing ability of the platform cannot be correspondingly improved with the increase in the amount of data, problems such as slower processing speed and diagnostic delay will occur. The types and formats of vehicle data are becoming more and more diverse, including sensor data, image data, video data, etc. Different types of data require different processing methods and algorithms, which increases the complexity of data processing and poses higher requirements for the computing resources and storage resources of the platform.

[0045] Exemplarily, the number of concurrent diagnostic tasks that the platform can handle simultaneously is limited. When a large number of vehicles request diagnostic services at the same time, if the concurrent processing ability of the platform is insufficient, some requests will not be able to be responded to in a timely manner, resulting in a decrease in diagnostic efficiency. When multiple diagnostic tasks are executed concurrently, there will be competition for server resources, network resources, etc. If the platform does not have an effective resource scheduling and management mechanism, it may lead to unbalanced resource allocation, where some tasks occupy too many resources while other tasks cannot proceed normally due to insufficient resources, affecting the overall diagnostic effect.

[0046] Refer to Figure 1 , Figure 1 which is a schematic architecture diagram of a diagnostic system provided by an embodiment of the present application. As Figure 1 shown, the diagnostic system includes a target vehicle, a diagnostic device, and a diagnostic platform. The diagnostic device collects data from the target vehicle and transmits the collected data to the diagnostic platform, and the diagnostic platform is used to analyze and diagnose the collected data. Specifically, remote diagnosis is usually jointly completed by the diagnostic platform and the diagnostic device. The diagnostic device is responsible for directly connecting and communicating with the vehicle's electronic control unit to collect real-time operating data of the vehicle, such as engine speed, vehicle speed, water temperature, fault codes, and other information. After collecting the data, the diagnostic device will send the data to the diagnostic platform through a built-in communication module, such as 4G, 5G, or Bluetooth. The diagnostic device can receive instructions from the diagnostic platform and perform specific operations or tests on the vehicle according to the instructions. For example, the diagnostic platform can remotely control the diagnostic device to perform an activation test on a certain electronic component of the vehicle, or require the diagnostic device to re-read the fault codes of a specific system, etc. The diagnostic device needs to accurately execute these instructions and feedback the execution results to the diagnostic platform. The diagnostic platform has a powerful network communication function and can receive vehicle data sent by the diagnostic device. After receiving the data, the platform will parse, store, and analyze these data, and use various algorithms and models to convert the original data into meaningful information, such as determining whether the vehicle has a fault, the possible causes and locations of the fault, etc. The diagnostic platform can display the operating status and relevant data of the vehicle in real time. When abnormal data or fault codes are found in the vehicle, the platform can perform a preliminary diagnosis on the vehicle according to preset rules and knowledge bases and give diagnostic suggestions.

[0047] In addition, maintenance personnel can send various instructions to the diagnostic device through the diagnostic platform, such as reading data, clearing fault codes, performing function tests, etc. At the same time, the diagnostic platform can also coordinate the communication between multiple diagnostic devices and vehicles. For scenarios such as fleet management, it can uniformly manage and schedule the remote diagnosis work of vehicles. The platform can store the received vehicle data for a long time and establish a diagnostic database for the vehicle. These data can be used for vehicle maintenance history query, fault trend analysis, vehicle performance evaluation, etc., providing strong data support for the subsequent maintenance and management of the vehicle.

[0048] Refer to Figure 2 , Figure 2 which is a flowchart of a diagnostic method provided by an embodiment of the present application. As Figure 2 shown, the diagnostic method provided by an embodiment of the present application includes but is not limited to the following steps:

[0049] Step S101: Obtain the historical driving data of the target vehicle;

[0050] Step S102: Obtain the historical diagnostic data of the first vehicle component of the target vehicle;

[0051] Step S103: Determine the reference diagnostic frequency of the first vehicle component within the first time period according to the historical diagnostic data and the historical driving data; the first time period is a preset time period after the current moment;

[0052] Step S104: Obtain the target driving route and the target vehicle load of the target vehicle within the first time period;

[0053] Step S105: Determine the target driving road type and the target driving weather type of the target driving route within the first time period;

[0054] Step S106: Adjust the reference diagnostic frequency according to the target vehicle load, the target driving road type and the target driving weather type to obtain the target diagnostic frequency of the first vehicle component;

[0055] Step S107: Diagnose the first vehicle component according to the target diagnostic frequency to obtain the diagnostic information of the first vehicle component.

[0056] In a possible embodiment, the historical driving data of the target vehicle includes at least one of the following: driving mileage, driving speed, driving time distribution, and driving road conditions. The historical driving data is used to reflect the driving habits of the target vehicle. By quantifying the historical driving mileage, the usage intensity of the vehicle can be intuitively understood. For example, for a vehicle with a long-term high driving mileage, components such as the engine, transmission, and tires are usually more severely worn, the probability of failure increases accordingly, and the diagnosis frequency may be higher. Taking a taxi as an example, compared with an ordinary household car, its annual driving mileage is high and the component wear is fast, so more time is required to check for potential faults during diagnosis. By quantifying the driving speed data, the speed range in which the vehicle often travels can be analyzed. If the vehicle often travels at a high speed, higher performance requirements are imposed on components such as the engine and braking system, and problems such as engine overheating and accelerated brake pad wear are likely to occur. For example, for a sports car that often travels at a high speed, the diagnosis of its braking system needs to focus on the thickness of the brake pads and the flatness of the brake discs, because frequent braking during high-speed driving will cause these components to wear faster and the diagnosis frequency will also increase. By clarifying the driving duration of the vehicle at different time periods, the usage scenario of the vehicle can be judged. If the vehicle travels mostly during the morning and evening rush hours, frequent starting and stopping will cause additional wear to components such as the starter, clutch (manual transmission), and torque converter (automatic transmission). When diagnosing a city commuting vehicle, these components need to be inspected emphatically, and the diagnosis frequency will increase compared with a vehicle with a good driving environment and few starting and stopping times. By quantifying the road condition information, such as dividing it into types such as congestion, smoothness, and rugged mountain roads. In a congested road condition, the engine of the vehicle is prone to carbon deposition and the transmission shifts frequently. During diagnosis, it is necessary to check the engine intake and exhaust systems, as well as the transmission oil quality and shifting logic, which increases the diagnosis time. For a vehicle traveling on a rugged mountain road, the suspension system and chassis components bear greater pressure. During diagnosis, it is necessary to carefully check whether these components are loose or deformed, and the diagnosis process is more complex and the frequency is higher.

[0057] In a possible embodiment, the historical diagnostic data of the target vehicle includes at least one of the following: failure frequency, repair duration, failure correlation, diagnostic equipment usage frequency, and the historical diagnostic data of the first vehicle component is obtained from the historical diagnostic data of the target vehicle. For the historical diagnostic data of the target vehicle, by counting the number of occurrences of various types of failures, the high-incidence points of failures of different vehicle components can be identified. For example, if the engine fault code P0300 of a certain vehicle model frequently appears in the historical diagnostic data, it indicates that there may be a design defect or vulnerability problem in the engine ignition system of this vehicle model, and it needs to be focused on during subsequent diagnosis, and the diagnostic frequency may also increase. Quantifying the time consumed for each fault repair can understand the repair complexity of different faults, which helps to more accurately estimate the required diagnostic frequency for this diagnosis based on the fault type and the previous repair duration. Analyze the correlation relationship between different fault codes to determine whether there is a fault chain reaction. For example, when the engine coolant temperature sensor fault code and the thermostat fault code frequently appear simultaneously, it indicates that there may be an associated fault between the two, and during diagnosis, it is necessary to check the working status of the relevant circuits, sensors, and thermostat simultaneously, increasing the diagnostic frequency.

[0058] In a possible embodiment, the first vehicle component can be any one of the engine, transmission, drive shaft, shock absorber, brake disc, battery, spark plug, and filter, or any vehicle component in the powertrain system, chassis system, body system, and electrical system. Among them, the chassis system includes the suspension system, braking system, and steering system, the body system includes the body control module and the airbag system, and the electrical system includes the battery and charging system and the entire vehicle circuit.

[0059] In a possible embodiment, in the current diagnosis of the target vehicle, the diagnostic result is related to the current driving path and driving environment of the vehicle. In different driving paths or driving environments, different vehicle components are focused on for diagnosis to improve the diagnostic accuracy. The target driving road types include urban roads, highways, rural roads, and mountain roads.

[0060] Exemplarily, in urban congestion conditions, vehicles start and stop frequently, and the load of power systems such as engines and transmissions changes greatly, making it easy to have problems such as overheating and increased wear. At the same time, frequent use of brakes also subjects the braking system to greater pressure, which may lead to accelerated wear of brake pads and increased temperature of brake fluid. In addition, there are many traffic lights and intersections on urban roads, and vehicles need to turn frequently, increasing the usage frequency of the steering system, which may have problems such as steering assist failure and loose steering ball joints. When a vehicle is driving on a highway at a high speed, the engine needs to run at a high speed for a long time, which requires high power output and heat dissipation system of the engine, and may have problems such as insufficient engine power and too high coolant temperature. When driving at a high speed, the vehicle's suspension system needs to bear greater impact force, posing a greater test to components such as shock absorbers and springs, and may have faults such as abnormal suspension noise and deteriorated shock absorption effect. Moreover, the rotation speed and load of the tires are also very large when driving at a high speed, making it easy to have situations such as abnormal tire pressure, uneven tire wear, and even tire blowout. Rural roads usually have poor road conditions, the road surface is uneven, and there are many potholes and bumps. When a vehicle is driving on such a road, chassis components such as half shafts, drive shafts, and swing arms are easily subjected to greater impact force, which may result in problems such as chassis scraping, component deformation or damage. At the same time, the rural road environment with large dust may also cause the air filter to be blocked, affecting the intake air volume of the engine and thus affecting the performance of the engine. When driving on mountain roads, vehicles need to climb and descend frequently. When climbing, the engine needs to output greater power, which easily causes engine overheating and excessive load on the power system. When descending, brakes need to be used frequently to control the vehicle speed, increasing the burden on the braking system, and serious problems such as brake failure may occur. In addition, there are many curves on mountain roads, which also require high requirements for the vehicle's steering system and suspension system, and it is easy to have situations such as insensitive steering and excessive vehicle body roll.

[0061] Correspondingly, when driving on urban roads, focus on checking the oil temperature of the engine and transmission, the water temperature, and determine whether there is overheating. Check the thickness of the brake pads, the wear condition of the brake discs, as well as the level and quality of the brake fluid. Check whether the connections of the components of the steering system are loose and whether the power steering is normal. When driving on highways, focus on checking whether the power output of the engine is normal and whether the cooling system is working well. Check the air pressure, wear degree, and whether there are damages on the surface of the tires. Check the shock absorption effect of the suspension system and determine whether the shock absorbers are leaking oil and whether the springs are deformed. When driving on rural roads, first check whether the chassis components are scratched, deformed, or damaged, including the half shafts, drive shafts, swing arms, chassis armor, etc. Clean the air filter and check its filtering effect. Check the vehicle's suspension system and determine whether there are loose components or abnormal noises. When driving on mountain roads, focus on checking the engine and the braking system. Determine whether the engine coolant is sufficient and whether there is leakage. Check the wear condition of the brake discs and brake pads and test whether the braking performance is good. Check the components of the steering system and the suspension system to ensure that the steering and suspension functions of the vehicle are normal after driving on curves.

[0062] In a possible embodiment, in the current diagnosis of the target vehicle, the diagnosis result is related to the current driving weather condition, path, and environment of the vehicle. In different weather conditions and corresponding driving paths and environments, different vehicle components need to be focused on for diagnosis to improve the diagnosis accuracy. The target driving weather types include high-temperature weather, low-temperature weather, rainy days, snowy days, and sandy weather.

[0063] Exemplarily, when the engine operates in a high-temperature environment, the difficulty of heat dissipation increases, and overheating is likely to occur, leading to a decrease in power and poor acceleration. At the same time, high temperature will reduce the viscosity of the engine oil and its lubrication performance, exacerbating component wear. The usage frequency and load of the air-conditioning system increase, and problems such as poor cooling effect and air-conditioning compressor failure may occur. The tire pressure will increase due to thermal expansion and contraction, increasing the risk of tire blowout. The tire rubber will also age and wear faster due to high temperature. At low temperatures, the performance of the battery will decline, and the starting current will be insufficient, resulting in difficult vehicle starting. The coolant in the cooling system may freeze, damaging components such as the engine block. Rubber components such as tires, windshield wipers, and sealing rubber strips will become hard and brittle, with reduced elasticity, and are prone to cracks and damage. Rain will reduce the friction between the brake pads and the brake discs, extending the braking distance. At the same time, the braking system may get water in, resulting in a decline in the performance of the brake fluid and triggering braking failures. The vehicle's electrical equipment gets damp, and faults such as short circuits and electric leakage may occur, affecting the normal operation of the vehicle's electronic system, such as the engine not starting and the dashboard warning lights turning on. The chassis is easily eroded by mud and water, accelerating the rust of the chassis components. When driving in snow, the vehicle's steering and suspension systems need to withstand greater lateral forces and impacts, and problems such as insensitive steering and loose or damaged suspension components are likely to occur. Tire wear will be exacerbated due to the special road conditions of driving in snow, and the heating system is used frequently. In sandy and windy weather, a large amount of dust is likely to enter the air filter, causing blockage, affecting the engine's air intake volume, reducing the engine power, increasing fuel consumption. The dust may enter the air-conditioning system, damaging the air-conditioning filter element and the blower, and affecting the air quality inside the vehicle and the air-conditioning performance.

[0064] Correspondingly, when driving in high-temperature weather, check the liquid level and temperature of the engine coolant to ensure the normal operation of the cooling system, detect the oil level and quality, and replace it if necessary. Check the air-conditioning cooling effect, the working condition of the compressor, and the refrigerant pressure, measure the tire pressure, and check the tire surface for cracks and abnormal wear. When driving in low-temperature weather, detect the battery voltage and starting current, check whether the starter works normally, check whether the coolant has frozen and whether the liquid level is normal, and detect whether rubber components such as tires and windshield wipers have cracks and become hard. When driving in rainy weather, check the wear conditions of the brake pads and brake discs, determine whether the brake fluid has got water in and whether the braking performance is good, check whether each electrical equipment of the vehicle is damp, and whether there are electric leakage and short-circuit phenomena in the circuits. Check whether the chassis components are rusted and damaged and whether the chassis armor is intact. When driving in snowy weather, check whether components such as the steering ball joint and the suspension arm are loose and whether the shock absorber works normally. Determine whether there is snow or ice in the tire tread and whether the wear is abnormal. Check the tire pressure, check the heating effect, the working condition of the blower, and whether the air duct is unobstructed. When driving in sandy and windy weather, check whether there is dust accumulation in the air intake pipe of the air filter and whether the air-conditioning blower and air duct are blocked by dust.

[0065] In the embodiments of the present application, diagnosing the first vehicle component according to the target diagnosis frequency of the first vehicle component can reasonably arrange the diagnostic tasks and allocate the diagnostic resources, avoid resource idleness or over-allocation, and thus improve the overall diagnostic efficiency.

[0066] Optionally, step S103 of determining the reference diagnosis frequency of the first vehicle component within the first time period according to the historical diagnosis data and the historical driving data may include the following steps:

[0067] Step S201: Determine the initial diagnosis frequency of the first vehicle component within the first time period according to the vehicle type of the target vehicle;

[0068] Step S202: Determine the failure frequency and failure level of the first vehicle component according to the historical diagnosis data;

[0069] Step S203: Predict the first failure probability of the first vehicle component within the first time period according to the failure frequency and the failure level;

[0070] Step S204: Determine the driving feature vector of the target vehicle according to the historical driving data; the driving feature vector is used to reflect at least one of the following vehicle driving features of the target vehicle: historical driving years, historical driving mileage, historical driving speed, historical vehicle load, historical driving road type, historical driving weather type;

[0071] Step S205: Predict the second failure probability of the first vehicle component within the first time period according to the driving feature vector;

[0072] Step S206: Determine the frequency adjustment value according to the first failure probability, the second failure probability, and a preset first mapping relationship; the first mapping relationship is used to reflect the mapping relationship between the first failure probability, the second failure probability, and the frequency adjustment value;

[0073] Step S207: Adjust the initial diagnosis frequency of the first vehicle component according to the frequency adjustment value to obtain the reference diagnosis frequency.

[0074] In a possible embodiment, different vehicle types correspond to different initial diagnosis frequencies, and different values of the initial diagnosis frequency can be preset according to different vehicle components.

[0075] For example, for components directly related to driving safety, such as the braking system and steering system, a higher diagnosis frequency is usually required. Generally, basic diagnosis can be performed every time the vehicle is started, and real-time or high-frequency monitoring can be performed during driving, such as a status check every second or every few seconds, to ensure that it is always in a safe working state. For complex electronic components such as engine control units and transmission control modules, due to their complex functions and high integration, the possibility of failure is relatively large, and once a failure occurs, it may cause serious consequences. The diagnosis frequency can be determined according to their working hours or mileage, such as a more comprehensive diagnosis every 1,000 kilometers or every 50 hours of work. For consumable parts such as tires, brake pads, and wipers, the degree of wear is closely related to the frequency of use and the environment. The corresponding diagnosis frequency can be formulated according to the intensity of vehicle use and the expected driving conditions. For example, when driving on normal urban roads, tires and brake pads can be checked every 2-3 months. If driving on uneven roads, it is set to be checked once a month.

[0076] In a possible embodiment, the frequency adjustment value is determined based on historical driving data. If the vehicle often travels on rugged mountain roads or muddy roads, the chassis, suspension system and other components are subject to greater impact and wear, and the diagnosis frequency needs to be increased, and may need to be checked once every 500-1000 kilometers. For vehicles that mainly travel on flat highways, the diagnosis frequency of these components can be relatively reduced, and they can be checked once every 2000-3000 kilometers. In high temperature, high humidity or high cold areas, the battery, air conditioning system, cooling system and other components of the vehicle will be greatly affected. For example, in high temperature areas, the battery is prone to aging and the air conditioning system is heavily loaded. It may be necessary to check the battery status once a month and conduct a comprehensive diagnosis of the air conditioning system once a quarter. In cold areas, the antifreeze of the cooling system needs to be checked more frequently, and the liquid level and freezing point may be checked once every half a month or a month. For vehicles with high usage intensity, such as taxis and logistics vehicles, the diagnosis frequency of various components is much higher than that of private cars. The engine, gearbox and other components of a taxi may need a routine inspection every day or every 500 kilometers. Logistics vehicles may need a comprehensive diagnosis every 1000-2000 kilometers depending on the transportation mission.

[0077] In a possible embodiment, the frequency adjustment value is determined based on historical diagnostic data. By analyzing the historical failure data of vehicle components, it is possible to understand which components are prone to failure and the patterns of failure occurrence. For components that fail frequently, the diagnostic frequency is appropriately increased. For example, the oxygen sensor of a certain model often fails after 2-3 years of use. For vehicles of this model that have been used for more than 2 years, the oxygen sensor can be tested every six months.

[0078] In a possible embodiment, historical diagnostic data of a first vehicle component is collected from data sources such as the vehicle's maintenance records and diagnostic reports, including information such as the time of each fault occurrence and the fault description. A target time interval is determined, such as one year or one month. The number of faults of the first vehicle component occurring within this time interval is counted, and the fault frequency is obtained by dividing the number of faults by the length of the time interval. The faults are classified according to factors such as the impact of the fault on the normal operation of the vehicle, the repair cost, and the safety risk. For example, they can be classified into minor faults, such as the dashboard indicator light flashing occasionally without affecting the basic driving of the vehicle; moderate faults, such as partial failure of a certain function but the vehicle can still continue to drive; and severe faults, such as causing the vehicle to fail to start or posing a serious threat to driving safety. A fault probability prediction model is established using a statistical model or a machine learning model. Different weights are assigned to different fault levels. For example, the weight of a severe fault can be set to 0.8, the weight of a moderate fault can be set to 0.5, and the weight of a minor fault can be set to 0.2. The frequencies of faults at different levels are multiplied by the corresponding weights and then summed to obtain the comprehensive fault frequency. The length of the first time period is substituted into the prediction model, and combined with the comprehensive fault frequency, the first fault probability of the first vehicle component within the first time period is calculated.

[0079] In a possible embodiment, historical driving data of a target vehicle is collected from data sources such as the vehicle's driving recorder, positioning system, and in-vehicle sensors. According to the historical driving data, features such as historical driving years, historical driving mileage, historical driving speed, historical vehicle load, historical driving road type, and historical driving weather type are extracted. For continuous features, such as historical driving mileage and historical driving speed, statistical quantities such as their average values, maximum values, and minimum values can be calculated. For discrete features, such as historical driving road type and historical driving weather type, the occurrence frequencies of different types can be counted. The extracted driving features are arranged in a certain order to form a driving feature vector. For example, the driving feature vector can be expressed as: [historical driving years, average historical driving mileage, maximum historical driving speed, proportion of heavy loads, proportion of driving on urban roads, proportion of driving in rainy weather]. A fault probability prediction model based on the driving feature vector is established. The historical driving data and the corresponding fault conditions of the first vehicle component are used as training data and divided according to a preset ratio. The training set is used to train the prediction model, and the parameters of the model are adjusted to enable it to accurately predict the fault probability. The driving feature vector of the target vehicle within the first time period is input into the trained prediction model to obtain the second fault probability of the first vehicle component within the first time period.

[0080] In the embodiments of the present application, the driving characteristics of different vehicles may vary greatly. Through prediction based on the driving feature vector, personalized fault probability prediction can be provided for each vehicle, thereby formulating a more targeted diagnostic strategy.

[0081] Optionally, in step S106, according to the target vehicle load, the target driving road type, and the target driving weather type, adjusting the reference diagnosis frequency to obtain the target diagnosis frequency of the first vehicle component may include the following steps:

[0082] Step S301: Determine the first loss impact factor of the target vehicle load on the first vehicle component according to a preset first impact relationship; the first impact relationship is used to reflect the loss caused by the vehicle load of the target vehicle to the first vehicle component;

[0083] Step S302: Determine the second loss impact factor of the target driving road type on the first vehicle component according to a preset second impact relationship; the second impact relationship is used to reflect the loss caused by the driving road type of the target vehicle to the first vehicle component;

[0084] Step S303: Determine the third loss impact factor of the target driving weather type on the first vehicle component according to a preset third impact relationship; the third impact relationship is used to reflect the loss caused by the driving weather type of the target vehicle to the first vehicle component;

[0085] Step S304: Determine the target driving mileage and target driving time of the target vehicle within the first time period according to the target driving route;

[0086] Step S305: Determine the first weight, the second weight, and the third weight of the first vehicle component according to the target driving mileage and the target driving time; the first weight corresponds to the first loss impact factor, the second weight corresponds to the second loss impact factor, and the third weight corresponds to the third loss impact factor;

[0087] Step S306: Determine the target adjustment value according to the first weight, the second weight, and the third weight, and the first loss impact factor, the second loss impact factor, and the third loss impact factor;

[0088] Step S307: Adjust the reference diagnosis frequency according to the target adjustment value to obtain the target diagnosis frequency.

[0089] In a possible embodiment, when determining the loss impact factor, first determine the impact degree of each factor on vehicle components. For example, when the vehicle load is heavy, it has a greater impact on the tires, suspension system, and braking system. For instance, the tires will experience accelerated wear and large air pressure changes due to heavy loads. The components such as springs and shock absorbers in the suspension system will bear increased pressure and are prone to deformation and damage. The braking system requires greater braking force, and the brake pads and brake discs will experience increased wear. When the type of driving road is a rough mountain road, the suspension system, chassis, and steering system of the vehicle will be subject to greater impacts. Frequent bumps and steering operations make the suspension components prone to loosening and damage, the chassis may be scratched and deformed, and the components such as ball joints and tie rods in the steering system will experience accelerated wear. When the type of driving road is an urban flat road, generally the wear of vehicle components is relatively uniform and small, but due to frequent starts and stops, the engine, transmission, and braking system are used more frequently, and the wear conditions of these components need to be concerned about. When the type of driving road is a highway, the vehicle travels at high speed for a long time, and components such as the engine, tires, and bearings are in a high-load operating state. The engine continuously outputs power and is prone to problems such as overheating and oil consumption. The tires rotate at high speed, the temperature rises, and the risks of wear and blowout increase. The bearings will also bear greater pressure due to high-speed rotation and may experience problems such as wear and abnormal noise. When the type of driving weather is high-temperature weather, it is difficult for the engine to dissipate heat, the viscosity of the engine oil decreases, affecting lubrication, which may lead to a decrease in power. The air-conditioning system has a large load and is prone to failures. The tire pressure increases, and the rubber aging accelerates. When the type of driving weather is low-temperature weather, the performance of the battery decreases, starting is difficult, the coolant in the cooling system may freeze, and rubber components become hard and brittle, such as the tire grip decreasing and the elasticity of the windshield wiper blades decreasing. When the type of driving weather is rainy, the friction force of the braking system decreases, the braking distance extends, and it is prone to water ingress and cause failures. The electrical system gets damp and may short-circuit and leak electricity. The chassis is eroded by mud and water, accelerating rusting. When the type of driving weather is snowy, the steering and suspension systems bear greater lateral forces and impacts, the tire grip is poor, and the wear is abnormal. The heating system is used frequently, and if it fails, it will affect the visibility and driving comfort.

[0090] In a possible embodiment, according to the influence degrees of the above factors on different vehicle components, a quantitative influence relationship is established for each factor and vehicle component. For example, a scoring system can be adopted, with 1 - 5 points representing the high and low influence degrees, 5 points being the highest influence degree, and 1 point being the lowest influence degree. According to the scoring results, the first loss influence factor, the second loss influence factor, and the third loss influence factor are determined. The first weight, the second weight, and the third weight of the first vehicle component are determined according to the target driving mileage and the target driving time. The longer the target driving mileage and the target driving time are, the greater the first weight, the second weight, and the third weight are. Add the influence factors of the expected vehicle load, driving road type, and driving weather type on each vehicle component within the first time period to obtain the comprehensive influence score of the first vehicle component. Establish a corresponding relationship between the comprehensive influence score and the diagnostic frequency adjustment coefficient. For example, when the comprehensive influence score is between 3 - 5 points, the diagnostic frequency remains unchanged at the reference diagnostic frequency; when it is between 6 - 8 points, the reference diagnostic frequency is increased by 20%; when it is between 9 - 12 points, the reference diagnostic frequency is increased by 50%; when it is above 12 points, the reference diagnostic frequency is increased by 100%. The target adjustment value can be obtained by multiplying the diagnostic frequency adjustment coefficient and the reference diagnostic frequency, and then the target diagnostic frequency of the first vehicle component can be calculated. For example, if the expected comprehensive influence score of the engine within the first time period is 9 points, and the original basic diagnostic frequency is to check once every 5000 kilometers or every 3 months, then the adjusted target diagnostic frequency is to check once every 3000 kilometers or every 2 months.

[0091] In a possible embodiment, if the target driving route reflects that the target driving mileage of the target vehicle is 0, then the reference diagnostic frequency can be used as the target diagnostic frequency.

[0092] In the embodiments of the present application, according to various situations of the target vehicle in the future time period, the reference diagnostic frequency of the vehicle component is reasonably adjusted to obtain the target diagnostic frequency, so as to improve the pertinence and accuracy of vehicle diagnosis and ensure the safe operation of the vehicle.

[0093] Optionally, the target vehicle includes n vehicle components, where the first vehicle component is any one of the n vehicle components, and n is a positive integer; Step S107, diagnosing the first vehicle component according to the target diagnostic frequency to obtain the diagnostic information of the first vehicle component, which may include the following steps:

[0094] Step S401: Determine the target diagnostic server corresponding to the target vehicle;

[0095] Step S402: Obtain the current computing power of the target diagnostic server;

[0096] Step S403: Obtain the diagnostic sequence of the n vehicle components;

[0097] Step S404: Determine the target diagnosis time period of the first vehicle component within the first time period according to the current computing power, diagnosis sequence, and target diagnosis frequency.

[0098] Step S405: Obtain the auxiliary diagnosis data of the first vehicle component according to the target vehicle load, target driving road type, and target driving weather type; the auxiliary diagnosis data includes environmental auxiliary diagnosis data obtained from the external environment of the target vehicle and component auxiliary diagnosis data obtained from the associated vehicle components of the first vehicle component among the n vehicle components, and is used for auxiliary diagnosis of the first vehicle component.

[0099] Step S406: Diagnose the first vehicle component according to the target diagnosis time period, auxiliary diagnosis data, and fault code of the first vehicle component to obtain diagnosis information.

[0100] In a possible embodiment, when diagnosing a target vehicle, local diagnosis can be used, or a diagnosis server can be connected. When performing vehicle diagnosis, the computing and processing capabilities of the local diagnosis device itself determine its diagnosis speed and efficiency. In the case of local operation, it is not directly affected by the server computing power, but in actual application scenarios, there are still some situations where the diagnosis process is indirectly affected by the server computing power.

[0101] Exemplarily, the diagnostic device equipped on the vehicle usually has certain diagnostic programs and algorithms, as well as corresponding computing resources. For some basic and common vehicle fault diagnoses, these local resources are sufficient to complete the tasks. For example, detecting the engine fault code of the vehicle, reading some basic sensor data, etc. The diagnostic device can directly send instructions to the vehicle's electronic control unit and receive feedback locally, and then analyze and judge according to the built-in rules and algorithms to obtain the diagnostic result. The whole process does not require data interaction with the server and is not affected by the server computing power. The diagnostic device may store the offline data of the vehicle, including the technical parameters of the vehicle, common fault modes, etc. When performing diagnosis, the device can directly call the locally stored data for comparison and analysis. For example, the diagnostic device pre-stores the ranges of various sensor data when a certain vehicle model is running normally. When diagnosing this vehicle model, the real-time obtained sensor data can be compared with the standard data stored locally to determine whether the vehicle is abnormal. This process also does not need to rely on the server computing power.

[0102] Exemplarily, if it is necessary to upload the diagnostic data of a vehicle to a server for further analysis or perform remote diagnosis, the computing power of the server will affect the diagnosis. For example, when encountering a complex fault and the local diagnostic device cannot accurately determine the problem, a large amount of vehicle operation data needs to be uploaded to the server, and the server uses more powerful computing power and more complex algorithms for in-depth analysis. At this time, the computing power of the server will affect the speed and accuracy of the diagnosis. Functions such as software updates of the diagnostic device, obtaining the latest vehicle technical information, and obtaining online diagnostic support all rely on the server. If the server computing power is insufficient, it may lead to a slower software update speed and an inability to obtain the latest vehicle data in a timely manner, thereby affecting the diagnostic ability of the diagnostic device for new vehicle models or new fault modes. For example, when an automobile manufacturer launches a new vehicle model or makes a major upgrade to the vehicle system, the diagnostic device needs to download new diagnostic programs and data files from the server for adaptation. If the server computing power is limited, the download and update process may experience lags or even failures, thus affecting the diagnostic work of the relevant vehicles. Some advanced diagnostic systems use big data analysis technology to comprehensively analyze the diagnostic data of a large number of vehicles to achieve fault prediction and preventive maintenance. In this case, the server needs to process and analyze a huge amount of data. If the server computing power is insufficient, it will not be able to perform data analysis and mining in a timely and accurate manner, thereby affecting the ability to predict vehicle faults and unable to provide effective preventive maintenance suggestions to users.

[0103] In a possible embodiment, the target diagnostic server corresponding to the target vehicle is determined based on factors such as server performance, vehicle location, network conditions, data security and compliance. Evaluating the central processing unit processing power, memory size, and storage performance of the server are key factors. For vehicle diagnostic tasks that require a large amount of data processing and complex algorithm operations, such as the battery health status assessment of new energy vehicles, the server needs to have powerful computing capabilities to quickly process data to ensure the timely output of diagnostic results. Evaluate the concurrent processing ability of the server. If a large number of vehicles make diagnostic requests simultaneously, the concurrent processing ability of the server is crucial. For example, during peak traffic hours, a large number of vehicles may upload data simultaneously for real-time road condition diagnosis, etc. A server with high concurrent processing ability can ensure that there will be no data congestion or response delay, and ensure that each vehicle's diagnostic request can be processed in a timely manner. Preferentially select a server that is close. Generally speaking, selecting a server that is close to the physical location of the vehicle can reduce the latency of data transmission. For example, in a city, a taxi or online car-hailing platform will allocate vehicles to the nearest regional server according to the urban area where the vehicle is located, so that the real-time data of the vehicle can be quickly transmitted to the server for diagnosis, improving the real-time nature of the diagnosis. Combine with the characteristics of the regional network. The network infrastructure and network congestion conditions are different in different regions. For example, in some cities with well-developed network construction, the requirements for server selection may be relatively low, but in some remote areas with poor network conditions, it is necessary to select a server with good network coverage and strong signal to ensure stable data transmission. Detect the network bandwidth. The network bandwidth between the vehicle and the server determines the speed of data transmission. Before remote diagnosis, the available bandwidth in the current network environment of the vehicle can be detected through a network detection tool. For example, for the diagnosis of intelligent vehicles that need to transmit high-definition videos or a large amount of sensor data, sufficient bandwidth is required to ensure the fast transmission of data and avoid data stuttering or loss. Evaluate the network stability. The stability of the network directly affects the continuity and accuracy of the diagnosis. The network stability can be evaluated by monitoring indicators such as packet loss rate and delay jitter. For example, in places with unstable network signals such as mountainous areas, it is necessary to select a server that can adapt to the unstable network environment and has a data caching and retransmission mechanism to ensure the smooth progress of the diagnostic process.

[0104] In a possible embodiment, the current computing power of the server can be quantified into a variety of specific indicators, which can reflect the server's ability to process data and execute computing tasks from different perspectives, including: processor-related indicators, memory-related indicators, storage-related indicators, and comprehensive indicators. Among them, processor-related indicators include clock frequency, number of cores and threads, and floating-point operations per second. Memory-related indicators include memory capacity and memory bandwidth. Storage-related indicators include storage capacity and storage I / O performance. Comprehensive indicators include benchmark test scores and data processing capabilities.

[0105] In a possible embodiment, the diagnostic sequence of n vehicle components is obtained. There may not necessarily be a diagnostic sequence relationship between every two of the n vehicle components. Refer to Figure 3 , Figure 3 which is a schematic diagram of the diagnostic sequence provided by an embodiment of the present application. As Figure 3 shown, for vehicle components A to I, there are diagnostic sequence relationships between vehicle component A and vehicle component C, between vehicle component B and vehicle component D, between vehicle component E and vehicle component F, between vehicle component G and vehicle component H, and among vehicle components C, D, and E. There is no diagnostic sequence relationship between vehicle component I and other vehicle components.

[0106] In a possible embodiment, different target driving road types and target driving weather types will have different impacts on vehicle components. Therefore, it is necessary to determine the auxiliary diagnostic data required for the corresponding target vehicle components according to the specific situation.

[0107] Exemplarily, when the target driving road type is an urban road, for a traffic-congested section, the vehicle starts and stops frequently, and components such as the engine, transmission, and braking system have a relatively high working load. It is necessary to focus on obtaining data such as the engine's idle speed, coolant temperature, oil pressure, the transmission's oil temperature, shift time, and sense of jerk, as well as the brake pad thickness, brake fluid level, and temperature of the braking system, to ensure that these components can work properly under frequent operations. For a flat highway section, the vehicle travels at a relatively high speed, and there are relatively high requirements for the tires, suspension system, steering system, and power system. At this time, it is necessary to obtain data such as the tire pressure, temperature, and wear condition, the shock absorber working state and spring stiffness of the suspension system, the steering force and steering angle sensor data of the steering system, as well as the engine speed, torque, and fuel consumption rate, to ensure the stability and safety of the vehicle during high-speed driving.

[0108] Exemplarily, when the target driving road type is a rural road, for a bumpy dirt road, the road surface is uneven, and the vehicle's suspension system, chassis components, and tires are easily impacted and worn. It is necessary to collect data such as the shock absorber stroke and damping force of the suspension system, the connection tightness and deformation of the chassis components, as well as the tread depth and damage of the tires, to promptly discover potential problems and avoid component damage caused by long-term jolting. For a muddy road, the wheels are prone to slipping, and there are relatively high requirements for the vehicle's drive system, braking system, and tire grip. It is necessary to obtain data such as the torque distribution of the drive system, the working state of the anti-skid control system, the braking distance and braking stability of the braking system, as well as the adhesion between the tires and the ground, in order to judge the performance and safety of the vehicle when driving on a muddy road.

[0109] Exemplarily, when the target driving road type is a mountain road, for the uphill section, the engine needs to output a relatively large power, which requires a relatively high power system. At the same time, the vehicle's center of gravity moves backward, which also has a certain impact on the suspension system and the braking system. It is necessary to monitor data such as the engine's power, speed, and water temperature, the compression amount of the rear suspension and the spring stress of the suspension system, and the braking efficiency reserve of the braking system to ensure sufficient power during the climbing process and the normal operation of the suspension and braking systems. For the downhill section, the vehicle mainly relies on the braking system to control the speed, which is likely to cause overheating and increased wear of the brake pads. Therefore, it is necessary to focus on obtaining data such as the temperature of the brake pads, the temperature and pressure of the brake fluid of the braking system, and the working state data of the auxiliary braking system, such as engine braking and retarder, to prevent the braking system from failing due to overheating.

[0110] Exemplarily, when the target driving weather type is sunny, direct sunlight may cause the temperature inside the vehicle to rise, affecting the heat dissipation and performance of electronic devices. It is necessary to monitor data such as the working temperature of in-vehicle electronic devices, such as the navigation system and in-vehicle computer, and the rotation speed of the cooling fan to ensure its stable operation in a high-temperature environment. In addition, during normal driving, it is also necessary to pay attention to the tire pressure and temperature because the tire pressure will increase slightly with the increase in temperature, to prevent tire blowout caused by too high pressure.

[0111] When the target driving weather type is rainy, the road surface is slippery, the tire grip decreases, and the vehicle's braking distance increases. At the same time, rainwater may affect the insulation performance of the vehicle's electrical system. It is necessary to collect data such as the drainage performance of the tires, the contact area between the tire tread and the ground, the braking distance of the braking system, the water content of the brake fluid, and the insulation resistance of the electrical system to ensure braking safety and the normal operation of the electrical system when the vehicle is driving on a slippery road surface.

[0112] Exemplarily, when the target driving weather type is snowy, in addition to the similar tire and braking system problems as in rainy days, low temperature will also affect the vehicle's power system, battery, and antifreeze. It is necessary to monitor data such as the cold start performance of the engine, the viscosity of the engine oil, the voltage and capacity of the battery, and the freezing point and liquid level of the antifreeze to ensure that the vehicle can start smoothly and drive normally in a low-temperature environment. In addition, it is also necessary to pay attention to the working condition of the defrosting and defogging systems of the vehicle, collect data of relevant sensors and actuators, and ensure good visibility for the driver.

[0113] Exemplarily, when the target driving weather type is foggy, the visibility is low. It is necessary to obtain data such as the brightness of the light bulbs of the lighting system, the working state of the fog lights, and the relevant data of the light control module to ensure that the vehicle can provide sufficient lighting and signal indication in foggy weather, improving driving safety. At the same time, due to the high air humidity in foggy weather, it is also necessary to obtain the moisture-proof situation of the electrical system to prevent faults such as short circuits caused by moisture.

[0114] Optionally, in step S404, according to the current computing power, the diagnosis sequence, and the target diagnosis frequency, determining the target diagnosis time period of the first vehicle component in the first time period may include the following steps:

[0115] Step S501: Obtain the historical diagnosis event processing data of the target diagnosis server;

[0116] Step S502: Predict the fluctuation data of the diagnosis demand quantity in the first time period according to the historical diagnosis event processing data;

[0117] Step S503: Determine the fluctuation data of the idle diagnosis computing power in the first time period according to the current computing power and the fluctuation data of the diagnosis demand quantity;

[0118] Step S504: Determine the diagnosis priority of the first vehicle component;

[0119] Step S505: Determine the diagnosis sequence label of the first vehicle component according to the diagnosis priority, the diagnosis sequence, and the target diagnosis frequency;

[0120] Step S506: Determine the target required computing power of the first vehicle component;

[0121] Step S507: Determine the target diagnosis time period of the first vehicle component in the first time period according to the diagnosis sequence label, the target required computing power, and the fluctuation data of the idle diagnosis computing power.

[0122] In a possible embodiment, according to the historical diagnosis event processing data, predicting the fluctuation data of the diagnosis demand quantity in the first time period, collecting the vehicle diagnosis data in the past relatively long period, including information such as the time of each diagnosis, the fault type and occurrence frequency of the vehicle component, etc. These data can be obtained from multiple channels such as the vehicle manufacturer's database, maintenance records, and remote monitoring systems. Sort out and clean the collected data to ensure the accuracy and integrity of the data, and remove duplicate, incorrect, or incomplete data records. Extract the key features related to the diagnosis demand from the historical data, such as the number of diagnoses in different time periods, such as hours, days, weeks, months, etc., the diagnosis situation under different seasons or weather conditions, the diagnosis demand corresponding to different driving mileage intervals, etc. Analyze the correlation between these features and the diagnosis demand, determine which features have a greater impact on the diagnosis demand, and input the relevant feature values of the future time period into the trained prediction model to obtain the prediction result of the diagnosis demand. The diagnosis demand can be predicted at different time granularities as needed, such as the peak and trough of the diagnosis demand per hour, per day, or per week. Specifically, the fluctuation data of the diagnosis demand quantity can refer to Figure 4 , Figure 4 which is a schematic diagram of the fluctuation data of the diagnosis demand quantity provided by an embodiment of the present application.

[0123] Refer toFigure 5 , Figure 5 is a schematic diagram of a diagnostic serial number label provided by an embodiment of the present application. According to the diagnostic priority, the order of diagnosis, and the target diagnostic frequency, the diagnostic serial number label of the first vehicle component is determined. For the first vehicle component, if the diagnostic priority of the first vehicle component is relatively high, there is no order of diagnosis relationship with other vehicle components, and the target diagnostic frequency is relatively high, then there can be multiple diagnostic serial number labels. For example Figure 5 1, 15, and 43 in

[0124] In a possible embodiment, the target diagnostic time period in the future time period can be determined according to the diagnostic computing power of the server, the diagnostic association relationship between vehicle components, and the target diagnostic frequency of vehicle components in the future time period. First, a comprehensive evaluation of the diagnostic computing power of the server is required, including key indicators such as the processing capacity of the central processing unit, the size of the memory, the storage read and write speed, and the network bandwidth, to determine the number and complexity of diagnostic tasks that the server can process per unit time and determine its maximum diagnostic processing capacity. Analyze the diagnostic association relationship between vehicle components and construct an association matrix. If there is a diagnostic association between component 1 and component 2, that is, when diagnosing component 1, the status of component 2 may need to be considered or referred to simultaneously, then mark 1 at the positions of the two components in the matrix, otherwise mark 0. According to the association matrix, through the connected component algorithm in graph theory or other clustering methods, the mutually associated components are divided into different association groups. Components within the same group need to be arranged in adjacent time periods during diagnosis to improve the diagnostic efficiency and accuracy. According to the target diagnostic frequency of each vehicle component, calculate the total amount of diagnostic tasks that the server needs to process in the future time period. According to the available diagnostic computing power of the server and the total amount of diagnostic tasks, allocate corresponding diagnostic resources to each component, and the computing power can be allocated according to the proportion of the diagnostic task volume of each component to the total task volume. According to the computing power allocated to each component and its diagnostic task volume, calculate the time required to complete the diagnosis of each component. Divide the future time period into several time slices, and the length of each time slice is determined according to the computing power of the server and the specific situation of the diagnostic tasks. For components in the same association group, try to make their time slices adjacent or close during time slice allocation to facilitate correlation analysis during the diagnosis process. If the association between some components is very close, they can be arranged to be diagnosed in the same time slice. At the same time, it is necessary to ensure that each component can be diagnosed in a timely manner within the time interval specified by its target diagnostic frequency. Conduct overall optimization and fine-tuning on the initially determined target diagnostic time period to check for problems such as uneven computing power allocation and unreasonable time slice arrangement. For example, if the diagnostic tasks in a certain time slice are too concentrated, resulting in a too high server load, some tasks can be adjusted to other idle time slices. Through continuous optimization and fine-tuning, finally determine the target diagnostic time period of each vehicle component among the vehicle components in the future time period.

[0125] In a possible embodiment, for each vehicle component, the time required to complete the diagnosis is calculated based on the allocated computing power and its diagnostic task volume. For example, the task volume of component A is 1000 data processing units, the time for the server to process a unit of data is 0.01 second, and the computing power allocated to component A can process 100 data processing units per second. Then the diagnostic duration of component A is 0.1 second. For complex components, their diagnostic tasks may include multiple subtasks. The durations of each subtask need to be calculated separately and then summed up to obtain the total diagnostic duration. For example, engine diagnosis may involve the diagnosis of multiple subsystems such as the fuel system and the ignition system. The diagnostic durations of each subsystem are calculated separately and then accumulated. In the order of components, the diagnostic tasks of each component are sequentially allocated to time slices. Starting from the first time slice, try to completely place the component diagnostic task within the time slice. If the diagnostic duration of a component is less than or equal to the remaining duration of the current time slice, the diagnostic task of this component is allocated to the current time slice. If it is greater than the remaining duration of the current time slice, the remaining duration of the current time slice is allocated to this component, and the remaining diagnostic task is allocated to the next time slice. For example, the diagnostic duration of component B is 0.3 second, and the remaining duration of the first time slice is 0.2 second. Then 0.2 second remaining in the first time slice is allocated to component B, and the remaining 0.1 second diagnostic task of component B is allocated to the second time slice.

[0126] In a possible embodiment, based on the constructed diagnostic association matrix, different association groups are identified through depth-first search or breadth-first search algorithms. Starting from a certain node (component) in the matrix, if this node is associated with other nodes, these related nodes are grouped into the same group, and the search continues for the associated nodes of these related nodes until all associated nodes are traversed, forming an association group. For example, starting the search from component C, it is found that component C is associated with component A and component E. Continuing the search, it is found that component E is also associated with component D, and component D is also associated with component B. Then components A, C, B, D, and E form an association group. Repeat the above process for all components that have not been searched until all components are divided into the corresponding association groups.

[0127] In a possible embodiment, for each association group, check whether the group members have been allocated to adjacent or close time slices. If there are components within the same association group scattered in non-adjacent time slices, make adjustments. For example, the association group includes components O, P, and Q. Component O is in time slice 5, component P is in time slice 10, and component Q is in time slice 12. First, try to move components P and Q closer to the time slice where component O is located, and check whether the remaining capacity of time slices 6 - 9 can accommodate some or all of the diagnostic tasks of components P and Q. If the remaining capacity of time slices 6 - 9 is sufficient, adjust component P to time slice 7 and component Q to time slice 8.

[0128] In a possible embodiment, for components that are very closely related, such as components that must be processed simultaneously in the diagnostic logic, for example, certain sensors and control modules of an engine, if they are not in the same time slice, check whether there are mergeable time slices. If there are adjacent time slices and the total remaining capacity can accommodate the diagnostic tasks of these two closely related components, then merge them into one time slice. For example, component K and component L are closely related. Component K is in time slice 15 and component L is in time slice 16. The total remaining capacity of time slices 15 and 16 is 0.5 seconds, and the total diagnostic duration of component K and component L is 0.4 seconds. Then, merge component K and component L into time slice 15 for diagnosis.

[0129] In a possible embodiment, for each component, check whether the time interval specified by the target diagnostic frequency is satisfied in the adjusted time slice allocation. Taking component M as an example, its target diagnostic frequency is once every 10 seconds. If the time interval between two consecutive diagnoses of component M in the currently allocated time slice sequence is greater than 10 seconds, then further adjustment of the time slice allocation is required. It is possible to try to find a suitable position in subsequent time slices to advance the diagnosis of component M, or check whether there is enough remaining capacity in the previous time slice to insert the diagnostic task for component M.

[0130] In a possible embodiment, calculate the total computing power required for the diagnostic tasks allocated in each time slice. For each time slice, traverse all the components allocated in that time slice, and calculate the total computing power required for component diagnosis in that time slice according to the proportion of the computing power allocated to the component and the diagnostic duration in that time slice. Set a computing power load balancing threshold, such as 1.5 times the average computing power load of each time slice, and check whether there is a time slice that exceeds this threshold. If it is found that the computing power load of a certain time slice is too high, such as time slice 20 exceeding the threshold, while the computing power loads of adjacent time slices 19 and 21 are relatively low, then try to adjust the diagnostic tasks of some components in time slice 20 to time slice 19 or 21. Priority is given to adjusting those components that have a relatively high degree of association with the existing components in time slice 19 or 21 to reduce the impact on the adjustment of the association relationship.

[0131] In a possible embodiment, it is checked whether there is excessive fragmentation in the time slice allocation, that is, there are a large number of time slices in which only a small number of diagnostic tasks are allocated, resulting in low utilization efficiency of the time slices. For example, if the remaining capacity in multiple consecutive time slices exceeds 50%, an attempt can be made to re-integrate the component diagnostic tasks within these time slices. The component diagnostic tasks within these time slices are concentrated into fewer time slices to improve the continuity and utilization efficiency of the time slices. For example, if there is a large amount of remaining capacity in time slices 30 - 35, and components N, O, and P are respectively distributed in these time slices and have a low degree of correlation with each other, components N, O, and P can be re-allocated to time slices 30 and 31, making time slices 32 - 35 idle, so as to more reasonably allocate other component diagnostic tasks subsequently.

[0132] In this way, according to the time slices of the first vehicle component, the target diagnostic time period within the first time period can be finally determined.

[0133] Optionally, step S405 of obtaining the auxiliary diagnostic data of the first vehicle component according to the target vehicle load, the target driving road type, and the target driving weather type may include the following steps:

[0134] Step S601: Determine the diagnostic influence coefficients of the first vehicle component with respect to the target vehicle load, the target driving road type, and the target driving weather type respectively, to obtain the first diagnostic influence coefficient, the second diagnostic influence coefficient, and the third diagnostic influence coefficient;

[0135] Step S602: Obtain the environmental auxiliary diagnostic data according to the first diagnostic influence coefficient, the second diagnostic influence coefficient, and the third diagnostic influence coefficient;

[0136] Step S603: Obtain the fault correlation relationships of n vehicle components;

[0137] Step S604: Obtain the component auxiliary diagnostic data according to the fault correlation relationships.

[0138] In a possible embodiment, diagnostic data required for target vehicle components is determined based on the target driving road type and the target driving weather type to improve the diagnostic accuracy. Information on various different target driving road types is collected, such as urban congested roads, urban expressways, rural dirt roads, mountainous steep roads, etc., and the characteristics of each road are recorded in detail, including road conditions such as flatness, slope, etc., and traffic conditions such as traffic flow, driving speed range, etc. Information on different target driving weather types is collected, such as sunny days, rainy days, snowy days, foggy days, windy days, etc., and the environmental parameters of each weather are recorded, such as temperature, humidity, visibility, etc. For each road type, the impact mechanism on each vehicle component is analyzed. For example, the frequent start-stop in urban congested roads will keep the engine idling or running at low speed for a long time, which is likely to cause carbon deposition, and at the same time increase the number of gear shifts of the transmission, exacerbating the wear of the clutch. The bumps on rural roads will have a greater impact on the suspension system and chassis components, easily causing the components to loosen or be damaged. For each weather type, the impact on vehicle components is analyzed. For example, the humid environment on rainy days may affect the insulation performance of the vehicle's electrical system, resulting in short-circuit faults. The low temperature on snowy days will reduce the battery performance, increase the viscosity of the engine oil, and affect the starting and lubrication effects of the engine. Based on the impact analysis of roads and weather on vehicle components, the key vehicle components in different situations are determined. For example, when driving on urban congested roads, the engine, transmission, and braking system are key components. When driving on snowy days, in addition to the engine and transmission, components such as the battery, antifreeze, and tires are also crucial. For each key component, its relevant diagnostic data is clarified. For example, for the engine, it can include rotational speed, load, coolant temperature, oil pressure, exhaust emission parameters, etc. For the tires, it can include air pressure, temperature, wear degree, tread depth, lateral force coefficient, etc. These data can directly or indirectly reflect the working state and health condition of the components.

[0139] In a possible embodiment, according to the characteristics of the diagnostic data and the actual situation of the vehicle, appropriate data acquisition methods and devices are selected. For example, data in electronic control units such as the engine and transmission can be acquired through the vehicle's OBD-II interface, tire pressure and temperature data can be acquired using a tire pressure monitoring system, and the vibration conditions of the suspension system and chassis components can be monitored using vibration sensors. Determine the frequency and timing of data acquisition. For some data with high real-time requirements, such as engine speed and coolant temperature, it can be set to be acquired multiple times per second. For some data that changes relatively slowly, such as tire wear and brake pad thickness, it can be checked and acquired before each drive or regularly. At the same time, consider the data acquisition strategy under different driving conditions. For example, during dynamic processes such as vehicle acceleration, deceleration, and turning, acquire the dynamic response data of relevant components. Preprocess the acquired raw data, including operations such as data cleaning, denoising, and normalization, to improve data quality and reduce the impact of noise and outliers on the diagnostic results. Extract characteristic parameters from the preprocessed data. These characteristic parameters should be able to prominently reflect the working state and fault characteristics of vehicle components. For example, for engine vibration data, characteristic parameters such as vibration frequency, amplitude, and kurtosis can be extracted. For tire pressure data, characteristic parameters such as pressure change rate and average pressure can be calculated.

[0140] In a possible embodiment, the data required for the engine includes operating parameters, emission data, and vibration information. Operating parameters such as speed, load, coolant temperature, oil pressure, fuel injection quantity, and intake air volume can reflect the working state of the engine. Emission data such as the content of components such as carbon monoxide, hydrocarbons, and nitrogen oxides in the exhaust gas can help determine whether combustion is complete and the working conditions of post-treatment devices such as the three-way catalytic converter. Vibration information such as collecting the vibration signal of the engine through a vibration sensor and analyzing characteristics such as vibration frequency and amplitude can detect internal mechanical faults of the engine, such as piston knocking and valve abnormal sounds. The engine operating parameters and emission data can be obtained through the vehicle's OBD interface, which can communicate with the vehicle's electronic control unit to read relevant data. Vibration information needs to be collected by installing vibration sensors at parts such as the engine block.

[0141] In a possible embodiment, the data required for the transmission includes shift information, oil temperature data, and speed signals. The data required for the braking system includes braking pressure, brake pad thickness, and brake disc temperature. The data required for the suspension system includes vehicle body height, shock absorber damping, and suspension component stress.

[0142] In a possible embodiment, there is a close association between vehicle components and the type of driving road and the type of driving weather. Determining these associations and judging whether relevant data is needed for auxiliary diagnosis requires comprehensive consideration of factors such as the characteristics of the components and the impact of different road and weather conditions on the components.

[0143] Exemplarily, when driving on rough mountain roads or steep slopes, the engine needs to output greater torque and power to overcome gravity and resistance, resulting in a significant increase in load and fuel consumption. In urban congested roads, the engine starts and stops frequently, with a long idle time, which easily leads to the formation of carbon deposits. When starting the engine in cold weather, a richer air-fuel mixture and a higher idle speed are required to ensure smooth starting and warm-up. At the same time, the increase in engine oil viscosity will increase the frictional resistance of the engine. In hot weather, it is difficult for the engine to dissipate heat, and overheating is likely to occur, affecting its performance and reliability. When the engine has faults such as insufficient power, abnormal fuel consumption, or overheating, obtaining data on the type of driving road and the type of driving weather helps to more accurately analyze the cause of the fault. For example, if the vehicle often drives on mountain roads and the engine has insufficient power, there may be a problem with the engine's power output components. If the engine frequently overheats in hot weather, in addition to checking the cooling system, the impact of the ambient temperature on engine heat dissipation also needs to be considered.

[0144] Exemplarily, when driving on mountain roads, the transmission needs to shift gears frequently to adapt to different slope and vehicle speed requirements, which increases the wear of the shifting mechanism and the clutch. When driving at high speed on the highway for a long time, the transmission is in a high gear, and the gears and bearings bear a large load. In snowy and icy weather, due to the low adhesion of the road surface, the vehicle is prone to skidding, and the transmission may frequently adjust the transmission ratio to maintain the stability of the vehicle, which will exert great pressure on the electronic control system and hydraulic system of the transmission. When the transmission has faults such as abnormal shifting, jerks, or abnormal noises, understanding the driving road and weather conditions helps to determine the cause of the fault. For example, if the vehicle has difficulty shifting after driving in the mountains, it may be due to wear of the shifting mechanism or contamination of the hydraulic oil. If the transmission fails after snowy and icy weather, it is necessary to consider whether the electronic control system fails due to frequent adjustment.

[0145] Optionally, the diagnostic method provided by the embodiments of the present application further includes:

[0146] Step S701: Determine whether the target vehicle has a vehicle fault according to the diagnostic information of each vehicle component among the n vehicle components;

[0147] Step S702: If the target vehicle has a vehicle fault, determine multiple repair points according to the positioning data of the target vehicle and the type of the vehicle fault;

[0148] Step S703: Obtain the repair resource information of the multiple repair points;

[0149] Step S704: Obtain the target repair resources required for the vehicle fault;

[0150] Step S705: Repair the vehicle fault according to the target repair resources and the repair resource information.

[0151] In a possible embodiment, the maintenance resource information of multiple maintenance points may not match the target maintenance resources required for vehicle faults, and it is necessary to schedule the maintenance resources. According to n diagnostic information, determine whether the target vehicle has a vehicle fault; if the target vehicle has a vehicle fault, determine m maintenance points according to the positioning data of the target vehicle; obtain the maintenance resource information of each of the m maintenance points to obtain m pieces of maintenance resource information; the maintenance resource information includes at least one of the following: the level and quantity of maintenance personnel, the types and quantities of maintenance tools, and the types and quantities of vehicle parts; determine the target maintenance resources required for the vehicle fault; compare the target maintenance resources with the m pieces of maintenance resource information to obtain m comparison results; generate m maintenance resource scheduling plans according to the m comparison results; determine the target cost of each maintenance resource scheduling plan among the m maintenance resource scheduling plans to obtain m target costs; the target cost includes at least one of the following: maintenance cost, journey cost, waiting cost, and scheduling cost; use the maintenance resource scheduling plan corresponding to the minimum value among the m target costs as the target maintenance resource scheduling plan; schedule the maintenance resources according to the target maintenance resource scheduling plan to repair the vehicle fault.

[0152] Refer to Figure 6 , Figure 6 is a schematic diagram of a maintenance resource scheduling method provided by an embodiment of the present application. As Figure 6 shown, if the target maintenance resources required for the vehicle fault include 3 target parts and 1 target maintenance personnel, the maintenance resource information of maintenance point 1 includes 1 target part and 0 target maintenance personnel, the maintenance resource information of maintenance point 2 includes 0 target parts and 1 target maintenance personnel, and the maintenance resource information of maintenance point 3 includes 2 target parts and 0 target maintenance personnel, a maintenance resource scheduling plan can be obtained according to the maintenance resource information of the above three maintenance points. If, according to cost analysis, maintenance point 3 is used as the target maintenance point, then the first maintenance resource is 1 target part, and the second maintenance resource is 1 target maintenance personnel. After scheduling, the maintenance requirements of the target vehicle can be met.

[0153] In summary, in the embodiment of the present application, first, obtain the historical driving data of the target vehicle and the historical diagnostic data of the first vehicle component of the target vehicle. Then, according to the historical diagnostic data and the historical driving data, determine the reference diagnostic frequency of the first vehicle component within the first time period, where the first time period is a preset time period after the current moment. Then, obtain the target driving route and the target vehicle load of the target vehicle within the first time period, and determine the target driving road type and the target driving weather type of the target driving route within the first time period. Next, adjust the reference diagnostic frequency according to the target vehicle load, the target driving road type, and the target driving weather type to obtain the target diagnostic frequency of the first vehicle component. Finally, diagnose the first vehicle component according to the target diagnostic frequency to obtain the diagnostic information of the first vehicle component. Thus, by determining the reference diagnostic frequency of the first vehicle component within the first time period based on the historical diagnostic data and the historical driving data, and adjusting the reference diagnostic frequency according to the target vehicle load, the target driving road type, and the target driving weather type to obtain the target diagnostic frequency of the first vehicle component, and diagnosing the first vehicle component according to the target diagnostic frequency, the diagnostic efficiency can be improved.

[0154] The method of the embodiment of the present invention is described in detail above. The device of the embodiment of the present invention is provided below.

[0155] Refer to Figure 7 , Figure 7 which is a schematic structural diagram of a diagnostic device provided by an embodiment of the present application. As Figure 7 shown, the diagnostic device 800 includes an acquisition unit 801 and a processing unit 802;

[0156] The acquisition unit 801 is configured to acquire the historical driving data of the target vehicle;

[0157] Acquire the historical diagnostic data of the first vehicle component of the target vehicle;

[0158] The processing unit 802 is configured to determine the reference diagnostic frequency of the first vehicle component within the first time period according to the historical diagnostic data and the historical driving data; the first time period is a preset time period after the current moment;

[0159] Acquire the target driving route and the target vehicle load of the target vehicle within the first time period;

[0160] Determine the target driving road type and the target driving weather type of the target driving route within the first time period;

[0161] Adjust the reference diagnostic frequency according to the target vehicle load, the target driving road type, and the target driving weather type to obtain the target diagnostic frequency of the first vehicle component;

[0162] Diagnose the first vehicle component according to the target diagnosis frequency to obtain the diagnosis information of the first vehicle component.

[0163] In a possible embodiment, in determining the reference diagnosis frequency of the first vehicle component within the first time period according to the historical diagnosis data and the historical driving data, the processing unit 802 is specifically configured to:

[0164] Determine the initial diagnosis frequency of the first vehicle component within the first time period according to the vehicle type of the target vehicle;

[0165] Determine the failure frequency and failure level of the first vehicle component according to the historical diagnosis data;

[0166] Predict the first failure probability of the first vehicle component within the first time period according to the failure frequency and the failure level;

[0167] Determine the driving characteristic vector of the target vehicle according to the historical driving data; the driving characteristic vector is used to reflect at least one of the following vehicle driving characteristics of the target vehicle: historical driving years, historical driving mileage, historical driving speed, historical vehicle load, historical driving road type, historical driving weather type;

[0168] Predict the second failure probability of the first vehicle component within the first time period according to the driving characteristic vector;

[0169] Determine the frequency adjustment value according to the first failure probability, the second failure probability, and a preset first mapping relationship; the first mapping relationship is used to reflect the mapping relationship between the first failure probability, the second failure probability, and the frequency adjustment value;

[0170] Adjust the initial diagnosis frequency of the first vehicle component according to the frequency adjustment value to obtain the reference diagnosis frequency.

[0171] In a possible embodiment, in adjusting the reference diagnosis frequency according to the target vehicle load, the target driving road type, and the target driving weather type to obtain the target diagnosis frequency of the first vehicle component, the processing unit 802 is specifically configured to:

[0172] Determine the first loss impact factor of the target vehicle load on the first vehicle component according to a preset first impact relationship; the first impact relationship is used to reflect the loss caused by the vehicle load of the target vehicle to the first vehicle component;

[0173] Determine the second loss impact factor of the target driving road type on the first vehicle component according to a preset second impact relationship; the second impact relationship is used to reflect the loss caused by the driving road type of the target vehicle to the first vehicle component;

[0174] Determine the third loss impact factor of the target driving weather type on the first vehicle component according to the preset third impact relationship; the third impact relationship is used to reflect the loss caused by the driving weather type of the target vehicle to the first vehicle component.

[0175] Determine the target driving mileage and target driving time of the target vehicle within the first time period according to the target driving route.

[0176] Determine the first weight, second weight, and third weight of the first vehicle component according to the target driving mileage and target driving time; the first weight corresponds to the first loss impact factor, the second weight corresponds to the second loss impact factor, and the third weight corresponds to the third loss impact factor.

[0177] Determine the target adjustment value according to the first weight, second weight, and third weight, and the first loss impact factor, second loss impact factor, and third loss impact factor.

[0178] Adjust the reference diagnosis frequency according to the target adjustment value to obtain the target diagnosis frequency.

[0179] In a possible embodiment, the target vehicle includes n vehicle components, where the first vehicle component is any one of the n vehicle components, and n is a positive integer; in terms of diagnosing the first vehicle component according to the target diagnosis frequency to obtain the diagnosis information of the first vehicle component, the processing unit 802 is specifically configured to:

[0180] Determine the target diagnosis server corresponding to the target vehicle.

[0181] Obtain the current computing power of the target diagnosis server.

[0182] Obtain the diagnosis order of the n vehicle components.

[0183] Determine the target diagnosis time period of the first vehicle component within the first time period according to the current computing power, diagnosis order, and target diagnosis frequency.

[0184] Obtain the auxiliary diagnosis data of the first vehicle component according to the target vehicle load, target driving road type, and target driving weather type; the auxiliary diagnosis data includes environmental auxiliary diagnosis data obtained from the external environment of the target vehicle and component auxiliary diagnosis data obtained from the associated vehicle components of the first vehicle component among the n vehicle components, and is used for auxiliary diagnosis of the first vehicle component.

[0185] Diagnose the first vehicle component according to the target diagnosis time period, auxiliary diagnosis data, and fault code of the first vehicle component to obtain the diagnosis information.

[0186] In a possible embodiment, when determining the target diagnosis time period of the first vehicle component within the first time period according to the current computing power, diagnosis sequence, and target diagnosis frequency, the processing unit 802 is specifically configured to:

[0187] Obtain the historical diagnosis event processing data of the target diagnosis server;

[0188] Predict the fluctuation data of the number of diagnosis requirements within the first time period based on the historical diagnosis event processing data;

[0189] Determine the fluctuation data of the idle diagnosis computing power within the first time period according to the current computing power and the fluctuation data of the number of diagnosis requirements;

[0190] Determine the diagnosis priority of the first vehicle component;

[0191] Determine the diagnosis serial number label of the first vehicle component according to the diagnosis priority, diagnosis sequence, and target diagnosis frequency;

[0192] Determine the target required computing power of the first vehicle component;

[0193] Determine the target diagnosis time period of the first vehicle component within the first time period according to the diagnosis serial number label, target required computing power, and the fluctuation data of the idle diagnosis computing power.

[0194] In a possible embodiment, when obtaining the auxiliary diagnosis data of the first vehicle component according to the target vehicle load, target driving road type, and target driving weather type, the processing unit 802 is specifically configured to:

[0195] Determine the diagnosis influence coefficients of the first vehicle component with respect to the target vehicle load, target driving road type, and target driving weather type, and obtain the first diagnosis influence coefficient, the second diagnosis influence coefficient, and the third diagnosis influence coefficient;

[0196] Obtain the environmental auxiliary diagnosis data according to the first diagnosis influence coefficient, the second diagnosis influence coefficient, and the third diagnosis influence coefficient;

[0197] Obtain the fault correlation relationships of n vehicle components;

[0198] Obtain the component auxiliary diagnosis data according to the fault correlation relationships.

[0199] In a possible embodiment, the processing unit 802 is further configured to:

[0200] Determine whether the target vehicle has a vehicle fault according to the diagnosis information of each vehicle component among the n vehicle components;

[0201] If the target vehicle has a vehicle fault, determine multiple repair points according to the positioning data of the target vehicle and the fault type of the vehicle fault.

[0202] Obtain the maintenance resource information of multiple maintenance points;

[0203] Obtain the target maintenance resources required for vehicle faults;

[0204] Repair the vehicle fault according to the target maintenance resources and the maintenance resource information.

[0205] Refer to Figure 8 , Figure 8 is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 8 shown, the electronic device 900 includes a transceiver 901, a processor 902, and a memory 903, which are connected by a bus 904. The memory 903 is used to store computer programs and data, and can transmit the data stored in the memory 903 to the processor 902. Among them, the electronic device 900 can be the above-mentioned diagnostic device 800, and the processor 902 can be the above-mentioned acquisition unit 801 and processing unit 802.

[0206] The processor 902 is used to read the computer program in the memory 903 and perform the following operations:

[0207] Obtain the historical driving data of the target vehicle;

[0208] Obtain the historical diagnostic data of the first vehicle component of the target vehicle;

[0209] Determine the reference diagnostic frequency of the first vehicle component within the first time period according to the historical diagnostic data and the historical driving data; the first time period is a preset time period after the current moment;

[0210] Obtain the target driving route and the target vehicle load of the target vehicle within the first time period;

[0211] Determine the target driving road type and the target driving weather type of the target driving route within the first time period;

[0212] Adjust the reference diagnostic frequency according to the target vehicle load, the target driving road type, and the target driving weather type to obtain the target diagnostic frequency of the first vehicle component;

[0213] Diagnose the first vehicle component according to the target diagnostic frequency to obtain the diagnostic information of the first vehicle component.

[0214] In a possible embodiment, in terms of determining the reference diagnostic frequency of the first vehicle component within the first time period according to the historical diagnostic data and the historical driving data, the processor 902 is specifically used to perform the following operations:

[0215] Determine the initial diagnostic frequency of the first vehicle component within the first time period according to the vehicle type of the target vehicle;

[0216] Determine the fault frequency and fault level of the first vehicle component according to the historical diagnostic data;

[0217] Predict the first fault probability of the first vehicle component within the first time period according to the fault frequency and fault level;

[0218] Determine the driving characteristic vector of the target vehicle according to the historical driving data; the driving characteristic vector is used to reflect at least one of the following vehicle driving characteristics of the target vehicle: historical driving years, historical driving mileage, historical driving speed, historical vehicle load, historical driving road type, historical driving weather type;

[0219] Predict the second fault probability of the first vehicle component within the first time period according to the driving characteristic vector;

[0220] Determine the frequency adjustment value according to the first fault probability, the second fault probability, and a preset first mapping relationship; the first mapping relationship is used to reflect the mapping relationship between the first fault probability, the second fault probability, and the frequency adjustment value;

[0221] Adjust the initial diagnostic frequency of the first vehicle component according to the frequency adjustment value to obtain the reference diagnostic frequency.

[0222] In a possible embodiment, when adjusting the reference diagnostic frequency according to the target vehicle load, the target driving road type, and the target driving weather type to obtain the target diagnostic frequency of the first vehicle component, the processor 902 is specifically configured to perform the following operations:

[0223] Determine the first loss influence factor of the target vehicle load on the first vehicle component according to a preset first influence relationship; the first influence relationship is used to reflect the loss caused by the vehicle load of the target vehicle to the first vehicle component;

[0224] Determine the second loss influence factor of the target driving road type on the first vehicle component according to a preset second influence relationship; the second influence relationship is used to reflect the loss caused by the driving road type of the target vehicle to the first vehicle component;

[0225] Determine the third loss influence factor of the target driving weather type on the first vehicle component according to a preset third influence relationship; the third influence relationship is used to reflect the loss caused by the driving weather type of the target vehicle to the first vehicle component;

[0226] Determine the target driving mileage and target driving time of the target vehicle within the first time period according to the target driving route;

[0227] Determine the first weight, the second weight, and the third weight of the first vehicle component according to the target driving mileage and the target driving time; the first weight corresponds to the first loss impact factor, the second weight corresponds to the second loss impact factor, and the third weight corresponds to the third loss impact factor;

[0228] Determine the target adjustment value according to the first weight, the second weight, and the third weight, and the first loss impact factor, the second loss impact factor, and the third loss impact factor;

[0229] Adjust the reference diagnostic frequency according to the target adjustment value to obtain the target diagnostic frequency.

[0230] In a possible embodiment, the target vehicle includes n vehicle components, where the first vehicle component is any one of the n vehicle components, and n is a positive integer; in terms of diagnosing the first vehicle component according to the target diagnostic frequency to obtain the diagnostic information of the first vehicle component, the processor 902 is specifically configured to perform the following operations:

[0231] Determine the target diagnostic server corresponding to the target vehicle;

[0232] Obtain the current computing power of the target diagnostic server;

[0233] Obtain the diagnostic sequence order of the n vehicle components;

[0234] Determine the target diagnostic time period of the first vehicle component within the first time period according to the current computing power, the diagnostic sequence order, and the target diagnostic frequency;

[0235] Obtain the auxiliary diagnostic data of the first vehicle component according to the target vehicle load, the target driving road type, and the target driving weather type; the auxiliary diagnostic data includes environmental auxiliary diagnostic data obtained from the external environment of the target vehicle and component auxiliary diagnostic data obtained from the associated vehicle components of the first vehicle component among the n vehicle components, and is used for auxiliary diagnosis of the first vehicle component;

[0236] Diagnose the first vehicle component according to the target diagnostic time period, the auxiliary diagnostic data, and the fault code of the first vehicle component to obtain the diagnostic information.

[0237] In a possible embodiment, in terms of determining the target diagnostic time period of the first vehicle component within the first time period according to the current computing power, the diagnostic sequence order, and the target diagnostic frequency, the processor 902 is specifically configured to perform the following operations:

[0238] Obtain the historical diagnostic event processing data of the target diagnostic server;

[0239] Predict the diagnostic demand quantity fluctuation data within the first time period according to the historical diagnostic event processing data;

[0240] Determine the idle diagnostic computing power fluctuation data within the first time period according to the current computing power and the diagnostic demand quantity fluctuation data;

[0241] Determine the diagnostic priority of the first vehicle component;

[0242] Determine the diagnostic sequence tag of the first vehicle component according to the diagnostic priority, the diagnostic sequence, and the target diagnostic frequency;

[0243] Determine the target required computing power of the first vehicle component;

[0244] Determine the target diagnostic time period of the first vehicle component within the first time period according to the diagnostic sequence tag, the target required computing power, and the idle diagnostic computing power fluctuation data.

[0245] In a possible embodiment, in terms of obtaining the auxiliary diagnostic data of the first vehicle component according to the target vehicle load, the target driving road type, and the target driving weather type, the processor 902 is specifically configured to perform the following operations:

[0246] Determine the diagnostic influence coefficients of the first vehicle component with respect to the target vehicle load, the target driving road type, and the target driving weather type respectively, to obtain the first diagnostic influence coefficient, the second diagnostic influence coefficient, and the third diagnostic influence coefficient;

[0247] Obtain the environmental auxiliary diagnostic data according to the first diagnostic influence coefficient, the second diagnostic influence coefficient, and the third diagnostic influence coefficient;

[0248] Obtain the fault correlation relationships of n vehicle components;

[0249] Obtain the component auxiliary diagnostic data according to the fault correlation relationships.

[0250] In a possible embodiment, the processor 902 is further configured to perform the following operations:

[0251] Determine whether the target vehicle has a vehicle fault according to the diagnostic information of each vehicle component among the n vehicle components;

[0252] If the target vehicle has a vehicle fault, determine multiple repair points according to the positioning data of the target vehicle and the fault type of the vehicle fault;

[0253] Obtain the repair resource information of the multiple repair points;

[0254] Obtain the target repair resources required for the vehicle fault;

[0255] Repair the vehicle fault according to the target repair resources and the repair resource information.

[0256] An embodiment of the present application further provides a computer-readable storage medium storing a computer program, and the computer program is executed by a processor to implement some or all of the steps of any one of the diagnostic methods described in the foregoing method embodiments.

[0257] An embodiment of the present application further provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute some or all of the steps of any one of the diagnostic methods described in the foregoing method embodiments.

[0258] It should be noted that, for the foregoing method embodiments, for the sake of simple description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present application is not limited by the described action sequence, because according to the present application, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present application.

[0259] In the above embodiments, the descriptions of the various embodiments have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0260] In several embodiments provided by the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division, and there can be other division methods in actual implementation. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed mutual coupling or direct coupling or communication connection can be through some interfaces, and the indirect coupling or communication connection of the device or module can be in an electrical or other form.

[0261] The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical modules, that is, they can be located in one place, or distributed to multiple network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0262] In addition, in each embodiment of the present application, the various functional modules can be integrated into one processing module, or each module exists physically alone, or two or more modules can be integrated into one module. The above integrated modules can be implemented in the form of hardware or in the form of software program modules.

[0263] When the integrated module is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs.

[0264] The embodiments of this application have been introduced in detail above. Specific examples are used in this article to elaborate on the principle and implementation manner of this application. The description of the above embodiments is only used to help understand the method and its core idea of this application; at the same time, for those of ordinary skill in the art, according to the idea of this application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to this application.

Claims

1. A diagnostic method, characterized in that: include: Obtain historical driving data of the target vehicle; Acquiring historical diagnostic data of a first vehicle component of the target vehicle; Determine, based on the historical diagnostic data and the historical driving data, a reference diagnostic frequency of the first vehicle component within a first time period; the first time period is a preset time period after a current moment; Obtaining a target driving route and a target vehicle load of the target vehicle within the first time period; Determine a target driving road type and a target driving weather type for the target driving route within the first time period; adjusting the reference diagnostic frequency according to the target vehicle load, the target driving road type, and the target driving weather type to obtain a target diagnostic frequency of the first vehicle component; The first vehicle component is diagnosed according to the target diagnosis frequency to obtain diagnostic information of the first vehicle component.

2. The method according to claim 1, characterized in that The step of determining a reference diagnosis frequency of the first vehicle component within a first time period according to the historical diagnosis data and the historical driving data includes: determining, according to the vehicle type of the target vehicle, an initial diagnosis frequency of the first vehicle component within the first time period; determining a fault frequency and a fault level of the first vehicle component based on the historical diagnostic data; predicting a first failure probability of the first vehicle component within the first time period according to the failure frequency and the failure level; Determine a driving feature vector of the target vehicle according to the historical driving data; the driving feature vector is used to reflect at least one of the following vehicle driving characteristics of the target vehicle: historical driving years, historical driving mileage, historical driving speed, historical vehicle load, historical driving road type, and historical driving weather type; predicting a second failure probability of the first vehicle component within the first time period according to the driving feature vector; Determine a frequency adjustment value according to the first fault probability and the second fault probability, and a preset first mapping relationship; the first mapping relationship is used to reflect the mapping relationship between the first fault probability, the second fault probability and the frequency adjustment value; The initial diagnostic frequency of the first vehicle component is adjusted according to the frequency adjustment value to obtain the reference diagnostic frequency.

3. The method according to claim 1, characterized in that The step of adjusting the reference diagnostic frequency according to the target vehicle load, the target driving road type, and the target driving weather type to obtain the target diagnostic frequency of the first vehicle component includes: Determine a first loss influence factor of the target vehicle load on the first vehicle component according to a preset first influence relationship; the first influence relationship is used to reflect the loss caused by the vehicle load of the target vehicle to the first vehicle component; Determine a second loss influence factor of the target driving road type on the first vehicle component according to a preset second influence relationship; the second influence relationship is used to reflect the loss caused by the driving road type of the target vehicle to the first vehicle component; Determine, according to a preset third influence relationship, a third loss influence factor of the target driving weather type on the first vehicle component; the third influence relationship is used to reflect the loss caused by the driving weather type of the target vehicle to the first vehicle component; Determining a target driving mileage and a target driving time of the target vehicle within the first time period according to the target driving route; Determine a first weight, a second weight, and a third weight of the first vehicle component according to the target mileage and the target driving time; the first weight corresponds to the first loss impact factor, the second weight corresponds to the second loss impact factor, and the third weight corresponds to the third loss impact factor; Determine a target adjustment value according to the first weight, the second weight, and the third weight, and the first loss impact factor, the second loss impact factor, and the third loss impact factor; The reference diagnostic frequency is adjusted according to the target adjustment value to obtain the target diagnostic frequency.

4. The method according to claim 1, characterized in that The target vehicle includes n vehicle components, wherein the first vehicle component is any one of the n vehicle components, and n is a positive integer; the step of diagnosing the first vehicle component according to the target diagnostic frequency to obtain diagnostic information of the first vehicle component includes: Determining a target diagnostic server corresponding to the target vehicle; Obtaining the current computing power of the target diagnostic server; Obtaining a diagnostic sequence of the n vehicle components; determining a target diagnosis time period for the first vehicle component within the first time period according to the current computing power, the diagnosis sequence, and the target diagnosis frequency; Acquire auxiliary diagnosis data of the first vehicle component according to the target vehicle load, the target driving road type and the target driving weather type; the auxiliary diagnosis data includes environmental auxiliary diagnosis data acquired from the external environment of the target vehicle and component auxiliary diagnosis data acquired from vehicle components associated with the first vehicle component among the n vehicle components, and is used for auxiliary diagnosis of the first vehicle component; The first vehicle component is diagnosed according to the target diagnostic time period, the auxiliary diagnostic data and the fault code of the first vehicle component to obtain the diagnostic information.

5. The method according to claim 4, characterized in that The determining, according to the current computing power, the diagnostic sequence and the target diagnostic frequency, a target diagnostic time period of the first vehicle component within the first time period includes: Acquire historical diagnostic event processing data of the target diagnostic server; Predicting fluctuation data of the number of diagnostic requirements within the first time period based on the historical diagnostic event processing data; Determining idle diagnostic computing power fluctuation data within the first time period according to the current computing power and the diagnostic demand quantity fluctuation data; determining a diagnostic priority for the first vehicle component; determining a diagnostic sequence number label for the first vehicle component according to the diagnostic priority, the diagnostic sequence, and the target diagnostic frequency; determining a target required computing power of the first vehicle component; A target diagnostic time period for the first vehicle component within the first time period is determined according to the diagnostic sequence number tag, the target required computing power, and the idle diagnostic computing power fluctuation data.

6. The method according to claim 4, characterized in that The step of acquiring the auxiliary diagnosis data of the first vehicle component according to the target vehicle load, the target driving road type, and the target driving weather type includes: Determine the diagnostic influence coefficients of the first vehicle component and the target vehicle load, the target driving road type, and the target driving weather type, respectively, to obtain a first diagnostic influence coefficient, a second diagnostic influence coefficient, and a third diagnostic influence coefficient; acquiring the environment-aided diagnosis data according to the first diagnosis influence coefficient, the second diagnosis influence coefficient, and the third diagnosis influence coefficient; Obtaining the fault association relationship of the n vehicle components; The component auxiliary diagnosis data is obtained according to the fault association relationship.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: determining whether the target vehicle has a vehicle fault according to the diagnostic information of each of the n vehicle components; If the target vehicle has the vehicle fault, determining a plurality of maintenance points according to the positioning data of the target vehicle and the fault type of the vehicle fault; Acquire maintenance resource information of the plurality of maintenance points; Obtaining target maintenance resources required for the vehicle failure; The vehicle fault is repaired according to the target maintenance resource and the maintenance resource information.

8. A diagnostic device, characterized in that: The device comprises an acquisition unit and a processing unit; The acquisition unit is used to acquire historical driving data of the target vehicle; Acquiring historical diagnostic data of a first vehicle component of the target vehicle; The processing unit is used to determine a reference diagnosis frequency of the first vehicle component within a first time period according to the historical diagnosis data and the historical driving data; the first time period is a preset time period after a current moment; Obtaining a target driving route and a target vehicle load of the target vehicle within the first time period; Determine a target driving road type and a target driving weather type for the target driving route within the first time period; adjusting the reference diagnostic frequency according to the target vehicle load, the target driving road type, and the target driving weather type to obtain a target diagnostic frequency of the first vehicle component; The first vehicle component is diagnosed according to the target diagnosis frequency to obtain diagnostic information of the first vehicle component.

9. An electronic device, characterized in that: include: A processor and a memory, the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 7.

Images