Vehicle collaborative diagnosis method and device, diagnosis equipment and storage medium

Abstract

The embodiment of the invention discloses a vehicle collaborative diagnosis method and device, diagnosis equipment and a storage medium, the method is applied to a vehicle diagnosis service platform, and the method comprises the following steps: obtaining first vehicle diagnosis data of a first vehicle; the first vehicle diagnosis data comprises a fault parameter, a data processing capability parameter and first position information; determining a first fault type and a first fault level of the first vehicle according to the fault parameters; determining m second vehicles associated with the first vehicle according to the first fault type, the first fault level, the data processing capability parameter and the first position information; the distance between the m second vehicles and the first vehicle is smaller than a target threshold value; acquiring second vehicle diagnosis data of each second vehicle in m second vehicles; the m second vehicle diagnosis data are used for reflecting the running state information of the m second vehicles; the first vehicle is diagnosed according to the m second vehicle diagnosis data, and a diagnosis result is obtained; and returning the diagnosis result to the first vehicle.

Description

Technical Field

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

[0002] With the rapid development of industries such as logistics transportation, public transportation, and shared cars, the management and maintenance of large-scale vehicle fleets have become an important issue, and the reliability and safety of vehicles are crucial for the normal operation of these industries. Vehicle failures often occur. When diagnosing large-scale vehicle fleets such as logistics transportation, public transportation, and shared cars, the traditional diagnosis method is single-vehicle diagnosis.

[0003] However, traditional single-vehicle diagnosis only relies on the information of a single vehicle, making it difficult to accurately determine the cause of the failure, and the diagnostic accuracy rate is low.

[0004] Therefore, there is an urgent need for a vehicle collaborative diagnosis method that can improve the diagnostic accuracy rate through vehicle collaboration when a vehicle fails. Summary of the Invention

[0005] To solve the above problems, embodiments of the present invention provide a vehicle collaborative diagnosis method, apparatus, diagnostic device, and storage medium, which can improve the diagnostic accuracy rate through vehicle collaboration when a vehicle fails.

[0006] In a first aspect, an embodiment of the present invention provides a vehicle collaborative diagnosis method applied to a vehicle diagnostic service platform. The method includes:

[0007] Obtain first vehicle diagnostic data of a first vehicle; the first vehicle diagnostic data includes a fault parameter, a data processing capability parameter, and first location information;

[0008] Determine a first fault type and a first fault level of the first vehicle according to the fault parameter; the first fault level is used to reflect the complexity of the first fault type;

[0009] Determine m second vehicles associated with the first vehicle according to the first fault type, the first fault level, the data processing capability parameter, and the first location information; the distance between the m second vehicles and the first vehicle is less than a target threshold; m is a natural number;

[0010] Obtain second vehicle diagnostic data of each of the m second vehicles to obtain m second vehicle diagnostic data; the m second vehicle diagnostic data is used to reflect the operating state information of the m second vehicles;

[0011] Diagnose the first vehicle according to the m second vehicle diagnostic data to obtain a diagnostic result;

[0012] Return the diagnostic result to the first vehicle.

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

[0014] The acquisition unit is configured to acquire first vehicle diagnostic data of a first vehicle; the first vehicle diagnostic data includes a fault parameter, a data processing capability parameter, and a first location information;

[0015] The processing unit is configured to determine a first fault type and a first fault level of the first vehicle according to the fault parameter; the first fault level is used to reflect the complexity of the first fault type;

[0016] Determine m second vehicles associated with the first vehicle according to the first fault type, the first fault level, the data processing capability parameter, and the first location information; the distance between the m second vehicles and the first vehicle is less than a target threshold; m is a natural number;

[0017] Acquire second vehicle diagnostic data of each of the m second vehicles to obtain m second vehicle diagnostic data; the m second vehicle diagnostic data is used to reflect the operating state information of the m second vehicles;

[0018] Diagnose the first vehicle according to the m second vehicle diagnostic data to obtain a diagnostic result;

[0019] Return the diagnostic result to the first vehicle.

[0020] In a third aspect, an embodiment of the present invention provides a diagnostic device, which 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 diagnostic device executes the method as described in the first aspect.

[0021] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the method as described in the first aspect.

[0022] In a fifth aspect, an embodiment of the present application provides a computer program product, which 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.

[0023] Implementing the embodiments of the present application has the following beneficial effects:

[0024] In an embodiment of the present application, first, obtain the first vehicle diagnosis data of the first vehicle, where the first vehicle diagnosis data includes a fault parameter, a data processing capability parameter, and a first location information. Then, according to the fault parameter, determine the first fault type and the first fault level of the first vehicle; the first fault level is used to reflect the complexity of the first fault type, and according to the first fault type, the first fault level, the data processing capability parameter, and the first location information, determine m second vehicles associated with the first vehicle, where the distance between the m second vehicles and the first vehicle is less than a target threshold, and m is a natural number. Then, obtain the second vehicle diagnosis data of each of the m second vehicles to obtain m second vehicle diagnosis data, where the m second vehicle diagnosis data is used to reflect the operating state information of the m second vehicles. Diagnose the first vehicle according to the m second vehicle diagnosis data to obtain a diagnosis result, and return the diagnosis result to the first vehicle. Thus, by determining the first fault type and the first fault level of the first vehicle, and according to the first fault type, the first fault level, the data processing capability parameter, and the first location information, determining m second vehicles associated with the first vehicle, and diagnosing the first vehicle according to the m second vehicle diagnosis data to obtain a diagnosis result, when a vehicle breaks down, collaborative diagnosis by vehicles can improve the diagnosis accuracy rate. Description of the Drawings

[0025] 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.

[0026] Figure 1 It is a schematic diagram of the architecture of a vehicle collaborative diagnosis system provided by an embodiment of the present application;

[0027] Figure 2 It is a flowchart of a vehicle collaborative diagnosis method provided by an embodiment of the present application;

[0028] Figure 3 It is an application scenario diagram of a vehicle collaborative diagnosis method based on a common vehicle provided by an embodiment of the present application;

[0029] Figure 4 It is an application scenario diagram of a vehicle collaborative diagnosis method based on a large-scale fleet provided by an embodiment of the present application;

[0030] Figure 5 It is an application scenario diagram of a vehicle maintenance method provided by an embodiment of the present application;

[0031] Figure 6 It is a flowchart of a judgment method based on vehicle collaborative diagnosis provided by an embodiment of the present application;

[0032] Figure 7 It is a schematic structural diagram of a vehicle collaborative diagnosis device provided by an embodiment of the present application;

[0033] Figure 8 It is a schematic structural diagram of a diagnostic device provided by an embodiment of the present application. Detailed implementation manners

[0034] 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 of the present application without creative efforts shall fall within the protection scope of the present application.

[0035] 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.

[0036] Referring to "embodiment" herein means that a specific feature, result, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears in various places in the specification and 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.

[0037] The vehicle collaborative diagnosis method provided by the embodiment of the present application is applied to a vehicle diagnosis service platform. Refer to Figure 1 , Figure 1 It is a schematic architecture diagram of a vehicle collaborative diagnosis system provided by an embodiment of the present application. As shown in Figure 1As shown in the figure, the vehicle collaborative diagnosis system includes a vehicle diagnosis service platform and a diagnosis device. Among them, the diagnosis device is a terminal tool that directly interacts with the vehicle to obtain data. The diagnosis device can be an on-vehicle diagnostic instrument, which can read the vehicle's fault codes and real-time operation data, such as engine speed and water temperature, and can also detect the working status of sensors and actuators to provide data for vehicle diagnosis. The vehicle diagnosis service platform is a comprehensive platform that integrates data collection, analysis, diagnosis, and repair guidance, and can perform in-depth processing, analysis, and integration of these data. After the diagnosis device collects data from the vehicle, it will transmit the data to the vehicle diagnosis service platform through wired or wireless means. After the platform receives the data, it will perform analysis and processing, and then feedback the analysis results and diagnosis instructions to the diagnosis device to guide subsequent detection operations, such as prompting the diagnosis device to further detect specific components. In the working process of this platform, the first vehicle collects its own vehicle data in real time through devices such as on-vehicle sensors and diagnostic systems, including fault parameters, data processing ability parameters, location information, vehicle characteristics, and operation parameters, and uploads these data to the vehicle diagnosis service platform. After the platform receives the data of the first vehicle, it determines its first fault type and first fault level based on the fault parameters. Subsequently, the platform screens out m second vehicles associated with the first vehicle from many vehicles according to the first fault type, first fault level, data processing ability parameters, and first location information. These second vehicles also transmit information such as vehicle diagnosis data, vehicle characteristics, and operation parameters to the platform through their own data collection devices. After the platform obtains the relevant data of the m second vehicles, it conducts multi-dimensional analysis and comparison of the data of the first vehicle and the m second vehicles. For example, it compares the first vehicle characteristics with the m second vehicle characteristics to obtain the vehicle characteristic similarity, compares the first vehicle operation parameters with the m second vehicle operation parameters to obtain the vehicle operation parameter similarity, determines the second fault type and second fault level of the m second vehicles according to their diagnosis data, and compares them with the fault type and level of the first vehicle. Through these analyses, the platform finally determines the target fault type and target fault level of the first vehicle, forms a diagnosis result, and determines the vehicle repair time limit index based on the diagnosis result. Combining the energy consumption information of the first vehicle, it provides a repair plan for the user, including determining multiple repair points, selecting a target repair point, and planning a repair path.

[0038] Refer to Figure 2 , Figure 2 is a flowchart of a vehicle collaborative diagnosis method provided by an embodiment of the present application. As Figure 2 shown, the vehicle collaborative diagnosis method provided by an embodiment of the present application includes but is not limited to the following steps:

[0039] Step S101: Obtain the first vehicle diagnosis data of the first vehicle;

[0040] Among them, the first vehicle diagnostic data includes fault parameters, data processing capability parameters, and first location information;

[0041] Step S102: Determine the first fault type and the first fault level of the first vehicle according to the fault parameters;

[0042] Among them, the first fault level is used to reflect the complexity of the first fault type;

[0043] Step S103: Determine m second vehicles associated with the first vehicle according to the first fault type, the first fault level, the data processing capability parameters, and the first location information;

[0044] Among them, the distance between the m second vehicles and the first vehicle is less than the target threshold; m is a natural number;

[0045] Step S104: Obtain the second vehicle diagnostic data of each of the m second vehicles to obtain m second vehicle diagnostic data;

[0046] Among them, the m second vehicle diagnostic data is used to reflect the operating status information of the m second vehicles;

[0047] Step S105: Diagnose the first vehicle according to the m second vehicle diagnostic data to obtain a diagnostic result;

[0048] Step S106: Return the diagnostic result to the first vehicle.

[0049] In a possible embodiment, to obtain the first vehicle diagnostic data of the first vehicle, first, the vehicle diagnostic service platform connects to the diagnostic device of the first vehicle, communicates with the electronic control unit (ECU) of the vehicle through a standard communication protocol, and reads various fault parameters from the ECU. The fault parameters include information such as fault codes, the time when the fault occurred, and the frequency of the fault occurrence. Then, collect the data processing capability parameters of the vehicle, such as indicators of the operating speed of the central processing unit (CPU) of the in-vehicle computer, the memory capacity, and the data transmission rate. These parameters can be obtained through the vehicle's system information query or specialized test tools. And obtain the accurate location information of the first vehicle through the vehicle's positioning system, including data such as longitude, latitude, and altitude, and update the location information in real time.

[0050] In a possible embodiment, according to the fault parameters, determine the first fault type and the first fault level of the first vehicle. Compare the read fault code with a preset fault code manual to identify the fault type of the first vehicle. For example, if the fault code P0101 indicates a fault in the air flow sensor, then the first fault type is a fault related to the air flow sensor. And based on factors such as the severity of the fault, the impact on vehicle performance, and the complexity of repair, divide the fault level. For example, if the fault causes the vehicle to be unable to drive normally, such as the engine not starting, it can be determined as a high-level fault. If it only affects the comfort of the vehicle, such as poor air conditioning cooling effect, it is determined as a low-level fault.

[0051] In a possible embodiment, according to the first fault type, the first fault level, the data processing capacity parameter, and the first location information, determine m second vehicles associated with the first vehicle. Obtain a preset vehicle database, which contains a large amount of information about vehicles, such as vehicle models, fault history records, location information, etc. According to the first location information, screen out the vehicles in the database whose distance from the first vehicle is less than the target threshold as candidate second vehicles. The target threshold can be set according to the actual situation, for example, set to 10 kilometers. For the candidate second vehicles, according to their historical fault records, find the vehicles with the same or similar fault type as the first fault type. For the judgment of similar fault types, it can be comprehensively analyzed based on the occurrence location of the fault, the fault phenomenon, etc. According to the first fault level and the data processing capacity parameter of the first vehicle, if the first fault level is high, it means that the current fault situation of the first vehicle is more complex and more second vehicles are needed for collaborative diagnosis. If the data processing capacity of the first vehicle is limited, then fewer second vehicles are needed for collaborative diagnosis. This step aims to balance various judgment indicators to determine m second vehicles to ensure effective collaborative diagnosis. Determine a priority rule according to the first fault type and the first fault level. The priority rule can be distance priority or fault similarity priority, etc. Further, according to the priority rule, determine m second vehicles from the selected candidate second vehicles.

[0052] In a possible embodiment, obtain the second vehicle diagnostic data of each of the m second vehicles to get m second vehicle diagnostic data. Establish communication connections with the m second vehicles respectively. Also, through a diagnostic device or other data collection methods, obtain the diagnostic data of each second vehicle. Among them, the second vehicle diagnostic data includes but is not limited to the real-time operating parameters of the vehicle, such as engine speed, vehicle speed, fuel consumption, etc., as well as fault codes, sensor data, such as temperature sensor and pressure sensor data, and information such as the historical repair records of the vehicle.

[0053] In a possible embodiment, the first vehicle is diagnosed based on m pieces of second vehicle diagnostic data to obtain a diagnostic result. The m pieces of second vehicle diagnostic data and the first vehicle diagnostic data are comprehensively analyzed. For example, the fault codes of the first vehicle and the second vehicle are compared, and the frequency and combination of the fault codes are analyzed to determine whether there are common problems. At the same time, in combination with the operating parameters of the vehicle, the possible impact of the fault on the vehicle performance is analyzed.

[0054] In a possible embodiment, the diagnostic result is returned to the first vehicle, and the diagnostic result is sent back to the display screen or in-vehicle information system of the first vehicle through wireless communication technology. The diagnostic result includes forms such as text descriptions and charts, which is convenient for the driver or maintenance personnel to understand the fault situation and handling suggestions.

[0055] In the embodiments of the present application, the fault parameters, data processing capability parameters, and location information of the vehicle are comprehensively obtained. The fault parameters help to quickly locate the fault type, the data processing capability parameters provide a basis for determining a suitable collaborative diagnosis scheme, and the location information facilitates screening for nearby associated vehicles to improve the diagnosis efficiency. Multiple factors are comprehensively considered to screen for associated vehicles to ensure that the selected second vehicle has similarity with the first vehicle in terms of the fault type. The detailed diagnostic data of multiple second vehicles are obtained, enriching the source of diagnostic information. By comparing and analyzing the data of different vehicles, the common and individual characteristics of the faults can be found, providing more reference basis for more accurately diagnosing the faults of the first vehicle. By comprehensively analyzing the data of multiple vehicles, the root causes of the faults can be deeply explored, improving the accuracy and reliability of the diagnosis. Compared with the diagnosis of a single vehicle, the collaborative diagnosis of multiple vehicles can consider various factors more comprehensively, avoiding misdiagnosis and missed diagnosis.

[0056] Optionally, in step S103, determining m second vehicles associated with the first vehicle according to the first fault type, the first fault level, the data processing capability parameters, and the first location information may include the following steps:

[0057] Step S201: Obtain the vehicle road parameters of the first vehicle;

[0058] Step S202: Determine the collaborative diagnosis accuracy rate according to the vehicle road parameters, the first fault type, and the first fault level; the collaborative diagnosis accuracy rate is used to reflect the accuracy rate when diagnosing the first vehicle through the vehicle diagnostic data of multiple vehicles;

[0059] Step S203: Determine the vehicle diagnosis timeliness index of the first vehicle according to the first fault type and the first fault level; the vehicle diagnosis timeliness index is used to reflect the diagnosis efficiency required by the first vehicle;

[0060] Step S204: Determine the target quantity according to the collaborative diagnosis accuracy rate, the vehicle diagnosis timeliness index, and the data processing capability parameters;

[0061] Step S205: Determine n associated vehicles of the first vehicle according to the first position information; n is a natural number;

[0062] Step S206: Determine the association priority of each associated vehicle among the n associated vehicles to obtain n association priorities;

[0063] Step S207: Screen the n associated vehicles according to the target quantity and the n association priorities to obtain m second vehicles.

[0064] In a possible embodiment, obtain the vehicle road parameters of the first vehicle. The vehicle road parameters may be road type, road surface condition, slope, curve radius, traffic flow, traffic density, pedestrian density, traffic signal, etc. The vehicle road parameters further include meteorological parameters and surrounding object parameters. Among them, the meteorological parameters may be temperature, humidity, wind speed and direction, and precipitation condition, and the surrounding object parameters may be obstacle distance, speed and driving direction of surrounding vehicles, and position of roadside facilities.

[0065] In a possible embodiment, determine the collaborative diagnosis accuracy rate according to the vehicle road parameters, the first fault type and the first fault level. Obtain historical vehicle diagnosis data, including collaborative diagnosis results under different road parameters such as road slope, congestion degree, road surface condition, etc., fault types and fault levels. Train these historical data through a machine learning algorithm to establish an association model between road parameters, fault types, fault levels and collaborative diagnosis accuracy rate. Input the vehicle road parameters, the first fault type and the first fault level of the current first vehicle into the trained association model, and the model outputs the corresponding collaborative diagnosis accuracy rate according to the input information.

[0066] In a possible embodiment, determine the vehicle diagnosis timeliness index of the first vehicle according to the first fault type and the first fault level. Determine the corresponding diagnosis timeliness index according to different fault types and fault levels. For example, for a low-level simple fault, such as a lighting fault, it is determined that the diagnosis is completed within 10 minutes. For a high-level complex fault, such as a serious engine fault, the diagnosis time can be determined to be 30 minutes. Or, determine the diagnosis timeliness index of different fault types according to the driving state of the first vehicle. For example, if the first vehicle is in an idle state, the diagnosis time can be 30 minutes. If the first vehicle is in a driving state and the first fault type has a high degree of relevance to the current driving state, then the first vehicle requires a higher diagnosis efficiency. According to the first fault type and the first fault level of the first vehicle, find the corresponding diagnosis timeliness requirement from the timeliness standard and use it as the vehicle diagnosis timeliness index of the first vehicle.

[0067] In a possible embodiment, a target quantity is determined according to the collaborative diagnosis accuracy rate, the vehicle diagnosis timeliness index, and the data processing capacity parameter, and a comprehensive evaluation function is established. The collaborative diagnosis accuracy rate, the vehicle diagnosis timeliness index, and the data processing capacity parameter are used as input variables. Among them, the evaluation function can be expressed as: F = a * collaborative diagnosis accuracy rate + b * vehicle diagnosis timeliness index + c * data processing capacity parameter, where F is the evaluation function, and a, b, and c are the weights of each parameter respectively. Simulation calculations are carried out for different numbers of associated vehicles, and the corresponding collaborative diagnosis accuracy rate, vehicle diagnosis timeliness index, and data processing capacity parameter under each quantity are substituted into the evaluation function to obtain the corresponding evaluation value. The number of associated vehicles corresponding to the maximum evaluation value is selected as the target quantity.

[0068] In a possible embodiment, n associated vehicles of the first vehicle are determined according to the first position information. In the vehicle database, all vehicles within the target range from the first vehicle are screened out as candidate associated vehicles. The candidate associated vehicles are further screened according to factors such as the type of the vehicle and whether it has the ability to share diagnostic data. For example, only vehicles of the same type as the first vehicle and with data communication functions are selected as associated vehicles, and finally n associated vehicles are determined.

[0069] In a possible embodiment, the association priority of each of the n associated vehicles is determined to obtain n association priorities. The fault similarity between the associated vehicle and the first vehicle is analyzed, that is, whether the associated vehicle has had the same or similar fault experience as the first vehicle. The higher the similarity, the higher the priority. For a specific vehicle fault type, such as abnormal engine noise, the closer the distance between the associated vehicle and the first vehicle, the higher the reference priority.

[0070] In a possible embodiment, according to the target quantity and the n association priorities, the n associated vehicles are screened to obtain m second vehicles. The n associated vehicles are sorted in descending order of association priority, and the first target quantity of associated vehicles after sorting are selected as the m second vehicles.

[0071] In the embodiments of the present application, the collaborative diagnosis accuracy rate is determined based on vehicle road parameters, the first type of fault, and the first fault level, which can more accurately estimate the effect of multi-vehicle collaborative diagnosis. Different road conditions may affect vehicle faults. Considering these factors can make the diagnosis more in line with the actual situation, thereby improving the accuracy of the diagnosis. The vehicle diagnosis timeliness index is determined according to the first type of fault and the first fault level, ensuring that the diagnosis time can be reasonably arranged under different fault conditions, improving the diagnosis efficiency, and avoiding the problems of excessive time consumption for simple faults or insufficient diagnosis time for complex faults. The target quantity is determined by comprehensively considering the collaborative diagnosis accuracy rate, the vehicle diagnosis timeliness index, and the data processing capacity parameter. It is possible to reasonably select the number of associated vehicles participating in collaborative diagnosis on the premise of ensuring the diagnosis quality and efficiency, avoiding waste or shortage of resources. The association priority of the associated vehicles is determined and screened, so that the finally selected m second vehicles are the most effective in assisting the first vehicle in diagnosis. Vehicles with high fault similarity and short distance are preferentially selected to improve the effect of collaborative diagnosis.

[0072] Optionally, step S204 of determining the target quantity according to the collaborative diagnosis accuracy rate, the vehicle diagnosis timeliness index, and the data processing capacity parameter may include the following steps:

[0073] Step S301: Determine a reference quantity according to the collaborative diagnosis accuracy rate and a preset first mapping relationship; the first mapping relationship is used to reflect the mapping relationship between the collaborative diagnosis accuracy rate and the reference quantity;

[0074] Step S302: Determine the reference data processing volume corresponding to the reference quantity;

[0075] Step S303: Obtain the diagnosis duration of the first vehicle;

[0076] Step S304: Determine the data processing duration according to the data processing capacity parameter, the reference data processing volume, and the diagnosis duration;

[0077] Step S305: Determine the target quantity according to the reference quantity, the vehicle diagnosis timeliness index, and the data processing duration.

[0078] In a possible embodiment, to determine the reference quantity according to the collaborative diagnosis accuracy rate and the preset first mapping relationship, first, a first mapping relationship table or function model is established through historical collaborative diagnosis case data. The mapping relationship table includes the optimal reference quantity corresponding to different collaborative diagnosis accuracy rates. When the collaborative diagnosis accuracy rate of the current first vehicle is obtained, look up and match in the established first mapping relationship. If a mapping relationship table is used, the reference quantity closest to the current accuracy rate can be found by methods such as linear interpolation. If it is a function model, directly substitute the collaborative diagnosis accuracy rate into the function to calculate the reference quantity.

[0079] In a possible embodiment, the reference data processing amount corresponding to the reference quantity is determined. For each reference quantity, the corresponding reference data processing amount is pre-statistically calculated or computed. Then, the diagnosis duration of the first vehicle is obtained, the diagnosis duration information is extracted from the diagnosis record or relevant log of the first vehicle, and the data processing duration is determined based on the data processing capacity parameter, the reference data processing amount, and the diagnosis duration. The data processing capacity parameter of the first vehicle can be the data processing speed, that is, the amount of data that can be processed per unit time. Then, the target quantity is determined based on the reference quantity, the vehicle diagnosis timeliness index, and the data processing duration. According to the vehicle diagnosis timeliness index, it is determined how long it is necessary to complete the diagnosis of the first vehicle. An evaluation function is established, comprehensively considering the reference quantity, the vehicle diagnosis timeliness index, and the data processing duration. For example, when the data processing duration exceeds the vehicle diagnosis timeliness index, the reference quantity is appropriately reduced, and the data processing duration is recalculated until the timeliness requirement is met. On the contrary, on the premise of meeting the timeliness requirement, the reference quantity can be appropriately increased to improve the accuracy of collaborative diagnosis. Through continuous adjustment and optimization, the target quantity that can not only meet the diagnosis timeliness requirement but also ensure a certain collaborative diagnosis effect is finally determined.

[0080] In the embodiments of the present application, determining the reference quantity through the preset first mapping relationship can quickly find a suitable range of the number of collaborative diagnosis vehicles with the help of historical experience, improving the diagnosis efficiency. Determining the reference data processing amount corresponding to the reference quantity and combining the data processing capacity parameter and the diagnosis duration to determine the data processing duration can determine the data processing requirements and capabilities in the current situation, avoiding diagnosis delays or failures caused by excessive data volume or insufficient processing capacity. Determining the target quantity according to the vehicle diagnosis timeliness index enables the entire diagnosis process to be completed within the specified time, meeting the time requirements of the actual application scenario, improving the timeliness and practicality of the diagnosis. Considering multiple factors comprehensively to determine the target quantity avoids blindly increasing or decreasing the number of vehicles participating in collaborative diagnosis, thereby realizing the optimal allocation of resources, reducing costs and resource consumption on the premise of ensuring the diagnosis quality.

[0081] Optionally, step S205 of determining the n associated vehicles of the first vehicle according to the first location information may include the following steps:

[0082] Step S401: Determine the target threshold according to the first fault type and the first fault level;

[0083] Step S402: Determine the target association range according to the first location information and the target threshold;

[0084] Step S403: Obtain k associated vehicles within the target association range according to the first location information; k is a natural number greater than or equal to n;

[0085] Step S404: Obtain the first vehicle feature and the first vehicle operation parameter of the first vehicle;

[0086] Step S405: Obtain the vehicle feature and the vehicle operation parameter of each of the k associated vehicles, and obtain k associated vehicle features and k associated vehicle operation parameters;

[0087] Step S406: Compare the first vehicle feature with the k associated vehicle features to obtain k vehicle feature similarities;

[0088] Step S407: Compare the first vehicle operation parameter with the k associated vehicle operation parameters to obtain k vehicle operation parameter similarities;

[0089] Step S408: Determine n associated vehicles from the k associated vehicles according to the k vehicle feature similarities and the k vehicle operation parameter similarities.

[0090] In a possible embodiment, a target threshold is determined according to the first fault type and the first fault level, a comprehensive evaluation system of the fault type and the fault level is established, and in combination with the historical vehicle maintenance case data, the distance range rule of the associated vehicles to be referred to under different fault types and different fault levels is analyzed. For example, for a serious engine fault, it may be necessary to search for associated vehicles within a larger range because such faults are more complex and require more references of different vehicle conditions, while for some simple component faults, associated vehicles with reference value can be found within a smaller range.

[0091] In a possible embodiment, according to the analysis result, a target threshold corresponding to a combination of different fault types and fault levels is set. After determining the first fault type and the first fault level of the first vehicle, search in the set corresponding relationship to obtain the target threshold required for this diagnosis. Then, determine the target association range according to the first position information and the target threshold. With the first position as the center, determine a circular or polygonal target association range according to the target threshold. If the target threshold is in units of distance, such as 5 kilometers, draw a circle with the position of the first vehicle as the center and 5 kilometers as the radius, and the area within the circle is the target association range. If the target threshold is defined in other ways, such as covering a certain number of administrative regions, the target association range is delimited according to the corresponding rules.

[0092] In a possible embodiment, k associated vehicles within the target association range are obtained according to the first position information. According to the first position information and the target association range, filter in the database to find all vehicles within the target association range, and these vehicles are the candidate associated vehicles. Further filter and confirm the candidate associated vehicles, and exclude some obviously irrelevant vehicles, such as vehicles of different types, vehicles that cannot provide data, etc., and finally determine k associated vehicles.

[0093] In a possible embodiment, the first vehicle features and the first vehicle operation parameters of the first vehicle are obtained. The first vehicle features include static information such as the vehicle brand, model, production year, configuration, etc. The first vehicle operation parameters include dynamic information such as engine speed, vehicle speed, fuel consumption, and data of various sensors. Moreover, the vehicle features and vehicle operation parameters of each of the k associated vehicles are obtained, resulting in k associated vehicle features and k associated vehicle operation parameters. For the k associated vehicles, a communication connection is established with each vehicle respectively. If the vehicle has the vehicle networking function, the vehicle features and operation parameters can be remotely obtained through the network. If it does not have the vehicle networking function, relevant data can be obtained through a portable data acquisition device deployed on the vehicle with the consent of the vehicle owner.

[0094] In a possible embodiment, the first vehicle features are compared with the k associated vehicle features to obtain k vehicle feature similarities. For discrete features such as vehicle brand and model, a rule-based matching method can be adopted. For numerical or quantifiable features such as production year and configuration, corresponding similarity calculation algorithms are used. Each feature of the first vehicle is sequentially calculated with the corresponding features of the k associated vehicles to obtain the feature similarity between each associated vehicle and the first vehicle, and finally k vehicle feature similarity data are formed.

[0095] In a possible embodiment, the first vehicle operation parameters are compared with the k associated vehicle operation parameters to obtain k vehicle operation parameter similarities. For dynamic operation parameters, since the data changes over time, a suitable time window is selected for data sampling and comparison. Similarly, a suitable similarity calculation method is adopted to compare the operation parameters of the first vehicle and each associated vehicle one by one, calculate the operation parameter similarity between each associated vehicle and the first vehicle, and obtain k vehicle operation parameter similarity data.

[0096] In a possible embodiment, n associated vehicles are determined from the k associated vehicles according to the k vehicle feature similarities and the k vehicle operation parameter similarities. The associated vehicles among the k associated vehicles with vehicle feature similarities and vehicle operation parameter similarities higher than a preset similarity threshold are used as the n associated vehicles.

[0097] In the embodiments of the present application, by determining the target threshold according to the fault type and level, and then determining the target association range, it is possible to accurately screen out the vehicle range that may be related to the first vehicle fault, avoid blind search, and improve the efficiency and pertinence of associated vehicle screening. By obtaining the characteristics and operating parameters of the first vehicle and the associated vehicles, and performing multi-dimensional similarity comparison, it is possible to evaluate the similarity between the associated vehicles and the first vehicle from multiple perspectives. By comprehensively considering the similarity of vehicle characteristics and operating parameters to determine the final n associated vehicles, these associated vehicles have a high degree of similarity with the first vehicle in many aspects, and can provide more valuable information during collaborative diagnosis, thereby improving the accuracy of the first vehicle fault diagnosis. During the process of determining the associated vehicles, irrelevant vehicles are gradually screened and excluded, avoiding data collection and analysis of a large number of irrelevant vehicles, effectively optimizing the utilization of resources, and reducing unnecessary computing and communication costs.

[0098] Optionally, step S206 of determining the association priority of each of the n associated vehicles to obtain n association priorities may include the following steps:

[0099] Step S501: Obtain the second position information of each of the n associated vehicles to obtain n pieces of second position information;

[0100] Step S502: Determine n association distances according to the first position information and the n pieces of second position information;

[0101] Step S503: Determine the n vehicle feature similarities corresponding to the n associated vehicles among the k vehicle feature similarities;

[0102] Step S504: Determine the n vehicle operating parameter similarities corresponding to the n associated vehicles among the k vehicle operating parameter similarities;

[0103] Step S505: Determine the target weight group according to the first fault type and the first fault level; the target weight group includes a first weight, a second weight, and a third weight;

[0104] Step S506: Determine n association priorities according to the n association distances, the n vehicle feature similarities, the n vehicle operating parameter similarities, and the target weight group.

[0105] In a possible embodiment, the second position information of each associated vehicle among the n associated vehicles is obtained to obtain n pieces of second position information. Based on the first position information and the n pieces of second position information, n associated distances are determined. The n vehicle feature similarities corresponding to the n associated vehicles among the k vehicle feature similarities are determined, and the n vehicle operation parameter similarities corresponding to the n associated vehicles among the k vehicle operation parameter similarities are determined. A target weight group is determined according to the first fault type and the first fault level. The target weight group includes a first weight, a second weight, and a third weight. A mapping relationship table between the fault type, the fault level, and the weight group is established. In the mapping relationship table, different combinations of the fault type and the fault level correspond to different weight groups. After the first fault type and the first fault level of the first vehicle are determined, a search and match are performed in the mapping relationship table to find the corresponding target weight group. The first weight in the target weight group corresponds to the weight of the associated distance, the second weight corresponds to the weight of the vehicle feature similarity, and the third weight corresponds to the weight of the vehicle operation parameter similarity. Based on the n associated distances, the n vehicle feature similarities, the n vehicle operation parameter similarities, and the target weight group, n associated priorities are determined. After calculating the associated priorities of the n associated vehicles, the calculation results are sorted, and the order of the associated priorities of each associated vehicle is determined from high to low to obtain n associated priorities.

[0106] In the embodiment of the present application, by obtaining the position information of the associated vehicles and calculating the associated distances, and combining the vehicle feature similarities and the operation parameter similarities, the degree of association between the associated vehicles and the first vehicle can be comprehensively evaluated from multiple dimensions such as spatial position, vehicle hardware features, and real-time operation status. Determining the weight group according to the first fault type and the fault level enables highlighting key factors when calculating the associated priorities, more pertinently screening out the associated vehicles that are most helpful for the fault diagnosis of the first vehicle, and avoiding wasting time and computing resources on a large amount of irrelevant or low-degree-of-association vehicle data, thereby improving the diagnosis efficiency. Considering multiple factors comprehensively to determine the associated priorities can ensure that in the collaborative diagnosis process, vehicles that are closely associated with the first vehicle in multiple key aspects are preferentially selected. These vehicles can provide more valuable reference information, contribute to more accurately analyzing the fault cause of the first vehicle, optimizing the diagnosis results, and improving the accuracy and reliability of the diagnosis. By establishing the mapping relationship between the fault type and level and the weight group, the focus of evaluating the associated vehicles can be flexibly adjusted according to different fault situations, enhancing the adaptability of the system to various complex fault scenarios and being able to better meet the diverse vehicle fault diagnosis requirements.

[0107] Optionally, for step S207, according to the target quantity and the n associated priorities, the n associated vehicles are screened to obtain m second vehicles. In a possible embodiment, refer to Figure 3 , Figure 3It is an application scenario diagram of a vehicle collaborative diagnosis method based on a general vehicle provided by an embodiment of the present application. When the first vehicle is a general vehicle, there is no fleet binding relationship with surrounding vehicles. Due to the diversity of driving roads, the surrounding vehicles of the first vehicle may have a relatively low density of distribution. Then, the number of associated vehicles within the target association range is small. At this time, vehicles with relatively low vehicle feature similarity and vehicle operation parameter similarity can also be used as the second vehicle, and vehicles outside the target association range are used as other vehicles.

[0108] Optionally, for step S207, according to the target quantity and n association priorities, screen the n associated vehicles to obtain m second vehicles. In a possible embodiment, refer to Figure 4 , Figure 4 It is an application scenario diagram of a vehicle collaborative diagnosis method based on a large-scale fleet provided by an embodiment of the present application. As Figure 4 shown, when the first vehicle belongs to a vehicle in a fleet, then there may be more associated vehicles within the target association range, and the similarity of the vehicle types between the first vehicle and these associated vehicles is relatively high. When the target quantity is small and the association priority is determined according to the association distance, the associated vehicles with a relatively close association distance to the first vehicle can be used as the second vehicle.

[0109] Optionally, in step S105, diagnose the first vehicle according to the diagnostic data of the m second vehicles to obtain a diagnostic result, including:

[0110] Step S601: Determine the second failure type and second failure level of each second vehicle among the m second vehicles according to the diagnostic data of the m second vehicles, to obtain m second failure types and m second failure levels;

[0111] Step S602: Compare the first failure type with the m second failure types to determine m failure type similarities;

[0112] Step S603: Compare the first failure level with the m second failure levels to determine m failure level similarities;

[0113] Step S604: Determine the m association priorities corresponding to the m second vehicles among the n association priorities;

[0114] Step S605: Determine the target failure type and target failure level of the first vehicle according to the m association priorities, m failure type similarities, and m failure level similarities;

[0115] Step S606: Use the target failure type and target failure level as the diagnostic result.

[0116] In a possible embodiment, based on the m pieces of second vehicle diagnostic data, determine the second fault type and the second fault level of each of the m second vehicles, obtaining m second fault types and m second fault levels. For the fault code data, compare it with the standard fault code library to identify the corresponding fault type. For example, if the fault code P0171 indicates a lean fuel system, then the fault type of this second vehicle may be related to fuel supply problems. Determine the fault level based on factors such as the impact of the fault on vehicle performance, repair difficulty, and possible consequences. For example, a fault where the engine cannot start, because it seriously affects the normal use of the vehicle and is complex to repair, can be determined as a high-level fault, while a fault such as a small interior light not working, which has a relatively small impact on the main functions of the vehicle, can be determined as a low-level fault. Finally, obtain m second fault types and m second fault levels.

[0117] In a possible embodiment, compare the first fault type with the m second fault types to determine m fault type similarities, and establish a feature vector library for fault type descriptions. Convert the first fault type and the m second fault types into feature vectors respectively. For example, for the engine fault type, components involved such as fuel injectors, spark plugs, etc., and fault phenomena such as jitter, flameout, etc. can be used as features, and use numerical values to represent the presence or absence or severity of each feature to form a feature vector. Through the similarity calculation method, calculate the feature vector of the first fault type with the feature vectors of the m second fault types in sequence to obtain m numerical values. These numerical values represent the similarities between the first fault type and each second fault type. The closer the numerical value is to 1, the higher the similarity; the closer it is to 0, the lower the similarity.

[0118] In a possible embodiment, compare the first fault level with the m second fault levels to determine m fault level similarities, and define the quantization standard for fault levels. For example, divide the fault levels into levels 1 - 5, where level 1 is the lowest level and level 5 is the highest level. For the first fault level and each second fault level, perform numerical processing according to the quantization standard, and then through difference calculation, obtain the degree of difference between them, and convert the degree of difference into similarity to obtain m fault level similarities. Similarly, the closer the numerical value is to 1, the higher the similarity.

[0119] In a possible embodiment, determine the m associated priorities corresponding to the m second vehicles among the n associated priorities. According to the m associated priorities, the m failure type similarities, and the m failure level similarities, determine the target failure type and the target failure level of the first vehicle. If the failure type similarities of multiple second vehicles with higher associated priorities among the m second vehicles are higher. For example, when the first failure type of the first vehicle is abnormal engine noise, and the second failure type of a second vehicle with a higher associated priority among the m second vehicles is also abnormal engine noise, then the failure type of the first vehicle may not be abnormal engine noise, and this failure may be a misdiagnosis caused by external environmental noise.

[0120] In the embodiments of the present application, by comparing the failure types and failure levels of the m second vehicles, using similarity calculation and comprehensive evaluation, it is possible to find the reference that best matches the failure situation of the first vehicle from multiple similar cases, thereby more accurately determining the target failure type and the target failure level of the first vehicle and reducing the possibility of misdiagnosis. Considering the associated priorities of the m second vehicles, preferentially referring to the failure information of the vehicles closely associated with the first vehicle enables the diagnostic process to more effectively utilize the data of other vehicles, improving the diagnostic efficiency and quality. Considering the failure type similarity, the failure level similarity, and the associated priority comprehensively, analyzing the failure of the first vehicle from multiple dimensions avoids the limitations of single-dimensional judgment and makes the diagnostic result more comprehensive and reliable.

[0121] Optionally, the vehicle collaborative diagnosis method provided in the embodiments of the present application may further include the following steps:

[0122] Step S701: Determine the vehicle repair timeliness index according to the diagnostic result; the vehicle repair timeliness index is used to reflect the repair efficiency required by the first vehicle;

[0123] Step S702: Obtain the energy consumption information of the first vehicle;

[0124] Step S703: Determine multiple repair points according to the vehicle repair timeliness index and the energy consumption information;

[0125] Step S704: Obtain the repair point information of each repair point among the multiple repair points to obtain multiple repair point information;

[0126] Step S705: Determine the repair time and the target repair point of the first vehicle according to the multiple repair point information and the vehicle repair timeliness index;

[0127] Step S706: Determine the repair path according to the first position information and the third position information of the target repair point;

[0128] Step S707: Generate a repair plan for the first vehicle according to the repair time and the repair path.

[0129] In a possible embodiment, according to the diagnosis result, a vehicle repair timeliness index is determined, and a correspondence database of fault types, fault levels, and repair timeliness indexes is established. This database is used to determine the recommended repair duration range corresponding to different fault types and levels. According to the determined target fault type and target fault level of the first vehicle, the corresponding repair timeliness index is queried in the database. Then, the energy consumption information of the first vehicle is obtained, including the energy consumption data of the vehicle over a period of time, such as fuel consumption or power consumption. According to the vehicle repair timeliness index and the energy consumption information, multiple repair points are determined, and a database containing information on numerous repair points is established, including the location of the repair points, repair capabilities such as the fault types and levels that can be repaired, service quality evaluations, etc. According to the vehicle repair timeliness index, the repair points that can complete the repair within the specified time are screened out. Combining the energy consumption information of the first vehicle and the distance factor of the repair points, the repair points that are closer are preferentially selected to reduce the energy consumption of the vehicle during the repair delivery process. After the above screening, multiple qualified repair points are determined. The repair point information of each repair point among the multiple repair points is obtained, resulting in multiple repair point information. For each determined repair point, detailed information is extracted from the repair point database, including the specific address of the repair point, business hours, technical qualifications of the repair team, equipment configuration of the repair equipment, etc. According to the multiple repair point information and the vehicle repair timeliness index, the repair time and target repair point of the first vehicle are determined. Analyze the repair capabilities and service quality information of each repair point, and combine the vehicle repair timeliness index to predict the actual repair time at each repair point. Considering factors such as repair time, repair price, and service quality comprehensively, calculate the comprehensive score of each repair point, select the repair point with the highest comprehensive score as the target repair point, and determine its corresponding repair time. Then, according to the first position information and the third position information of the target repair point, the repair path is determined. Using a map navigation software or an online map service, input the first position information of the first vehicle and the third position information of the target repair point, and calculate the optimal repair path from the current position of the first vehicle to the target repair point according to the traffic conditions, road types, and traffic rules. The route planning result can include detailed route descriptions such as driving directions, intersection turning information, and estimated driving time. Finally, a repair plan for the first vehicle is generated based on the repair time and the repair path.

[0130] In a possible embodiment, refer to Figure 5 , Figure 5 is an application scenario diagram of a vehicle repair method provided by an embodiment of the present application. As Figure 5 shown, five repair points in the figure are determined according to the vehicle repair timeliness index and the energy consumption information. Each repair point meets the vehicle repair timeliness index and the energy consumption information of the first vehicle. Among them, repair point 1 is in the moving direction of the first vehicle, so repair point 1 can be used as the target repair point.

[0131] In the embodiments of the present application, the maintenance time limit index is determined according to the diagnosis result to ensure that the maintenance work can be completed within a reasonable time, avoiding inconvenience to the vehicle owner caused by too long maintenance time. At the same time, by screening and determining the target maintenance point, a maintenance point with strong maintenance ability and high efficiency is selected to further improve the maintenance efficiency. Considering the energy consumption information, a maintenance point with a relatively short distance is selected to reduce the energy consumption of the vehicle during the repair process and lower the energy cost. At the same time, considering factors such as the maintenance price comprehensively to determine the target maintenance point helps to control the maintenance cost. Screening and evaluating the maintenance points enables the vehicle to obtain the most suitable maintenance service, optimizing the allocation of maintenance resources and improving the utilization efficiency of maintenance resources.

[0132] In a possible embodiment, refer to Figure 6 , Figure 6 which is a flowchart of a judgment method based on vehicle collaborative diagnosis provided by the embodiments of the present application. As shown in Figure 6 , first, the single-vehicle diagnosis accuracy rate is determined. The single-vehicle diagnosis accuracy rate is used to reflect the accuracy rate when diagnosing the first vehicle through its own data. Then, the single-vehicle accuracy rate is compared with the collaborative accuracy rate to obtain a comparison result. According to the comparison result, it is determined whether to perform collaborative diagnosis. When the single-vehicle diagnosis accuracy rate is higher than the collaborative diagnosis accuracy rate or higher than the preset accuracy threshold, it is determined that the first vehicle does not need to perform collaborative diagnosis, and the first fault type and the first fault level are used as the diagnosis result of the first vehicle. For example, when the fault type of the first vehicle is that the headlights are not on, the single-vehicle diagnosis accuracy rate of this fault type is relatively high, so there is no need to perform collaborative diagnosis. When the fault type of the first vehicle is abnormal engine noise, etc., which may be misjudged due to environmental factors and the single-vehicle diagnosis accuracy rate is relatively low, collaborative diagnosis is performed on the first vehicle at this time.

[0133] In a possible embodiment, the vehicle diagnosis data of the target vehicle is obtained. When the vehicle diagnosis data shows that the target function of the target vehicle may be abnormal, the relevant diagnosis data corresponding to the target function of the surrounding vehicles of the same type is obtained. Based on the relevant diagnosis data and the vehicle diagnosis data, collaborative diagnosis is performed on the target vehicle. Further, corresponding measures are taken based on the collaborative diagnosis result. Exemplarily, if a truck's engine has abnormal noise, the system can obtain the engine operation data and environmental information from other trucks on the same route. By comparing and analyzing the relevant diagnosis data and the vehicle diagnosis data, it is determined whether the fault is universal or related to factors such as a specific section or weather conditions. When a bus's braking system has a slight abnormality, it is analyzed in combination with the braking data of surrounding buses under the same road conditions to determine whether immediate maintenance is required or it can continue to run to the next maintenance point for processing.

[0134] In a shared car platform, multiple cars are distributed at different locations. When a vehicle fault is identified, collaborative diagnosis is carried out with the help of the data of surrounding shared cars. For example, when the battery power of a shared car drops abnormally, the battery performance of nearby vehicles under the same usage time and environment is analyzed to determine whether there is a problem with the battery of this vehicle itself or it is affected by external factors such as charging facility failures or high-power consumption driving behaviors in a specific area.

[0135] Furthermore, corresponding measures can be taken based on the collaborative diagnosis results. For example, for shared bicycles, the mechanical components and electronic lock systems of the bicycles are monitored. When the brakes of a bicycle fail, the brake usage and maintenance records of nearby bicycles are obtained to determine whether it is a batch problem, so as to promptly inspect and repair the vehicles of the same batch to ensure the riding safety of users.

[0136] In an urban intelligent transportation network or on a highway, the remote diagnosis of multi-vehicle collaboration can be combined with the data of the traffic management center to support traffic flow optimization and road safety. For example, when electronic system failures frequently occur to multiple vehicles on a certain section, according to the driving states of the vehicles and the road conditions, the traffic management center can adjust the traffic signals in a timely manner based on the diagnostic information to guide other vehicles to avoid this section.

[0137] In summary, in the embodiment of the present application, first, the first vehicle diagnosis data of the first vehicle is obtained, where the first vehicle diagnosis data includes fault parameters, data processing ability parameters, and first location information. Then, according to the fault parameters, the first fault type and the first fault level of the first vehicle are determined; the first fault level is used to reflect the complexity of the first fault type, and according to the first fault type, the first fault level, the data processing ability parameters, and the first location information, m second vehicles associated with the first vehicle are determined, where the distance between the m second vehicles and the first vehicle is less than the target threshold, and m is a natural number. Then, the second vehicle diagnosis data of each of the m second vehicles is obtained to obtain m second vehicle diagnosis data, where the m second vehicle diagnosis data is used to reflect the operating state information of the m second vehicles. The first vehicle is diagnosed according to the m second vehicle diagnosis data to obtain a diagnosis result, and the diagnosis result is returned to the first vehicle. Thus, by determining the first fault type and the first fault level of the first vehicle, and according to the first fault type, the first fault level, the data processing ability parameters, and the first location information, determining m second vehicles associated with the first vehicle, and diagnosing the first vehicle according to the m second vehicle diagnosis data to obtain a diagnosis result, when a vehicle fails, collaborative diagnosis is carried out through the vehicles, which can improve the diagnosis accuracy.

[0138] The method of the embodiment of the present invention is described in detail above. Below, the device of the embodiment of the present invention is provided.

[0139] Refer to Figure 7 , Figure 7 which is a schematic structural diagram of a vehicle collaborative diagnosis device provided by an embodiment of the present application. As Figure 7 shown, the vehicle collaborative diagnosis device 800 includes an acquisition unit 801 and a processing unit 802;

[0140] The acquisition unit 801 is configured to acquire first vehicle diagnosis data of a first vehicle; the first vehicle diagnosis data includes a fault parameter, a data processing capability parameter, and first location information;

[0141] The processing unit 802 is configured to determine a first fault type and a first fault level of the first vehicle according to the fault parameter; the first fault level is used to reflect the complexity of the first fault type;

[0142] Determine m second vehicles associated with the first vehicle according to the first fault type, the first fault level, the data processing capability parameter, and the first location information; the distance between the m second vehicles and the first vehicle is less than a target threshold; m is a natural number;

[0143] Acquire second vehicle diagnosis data of each of the m second vehicles to obtain m second vehicle diagnosis data; the m second vehicle diagnosis data is used to reflect the operating state information of the m second vehicles;

[0144] Diagnose the first vehicle according to the m second vehicle diagnosis data to obtain a diagnosis result;

[0145] Return the diagnosis result to the first vehicle.

[0146] In a possible embodiment, in terms of determining m second vehicles associated with the first vehicle according to the first fault type, the first fault level, the data processing capability parameter, and the first location information, the processing unit 802 is specifically configured to:

[0147] Acquire vehicle road parameters of the first vehicle;

[0148] Determine a collaborative diagnosis accuracy rate according to the vehicle road parameters, the first fault type, and the first fault level; the collaborative diagnosis accuracy rate is used to reflect the accuracy rate when diagnosing the first vehicle through vehicle diagnosis data of multiple vehicles;

[0149] Determine a vehicle diagnosis timeliness index of the first vehicle according to the first fault type and the first fault level; the vehicle diagnosis timeliness index is used to reflect the diagnosis efficiency required by the first vehicle;

[0150] Determine a target number according to the collaborative diagnosis accuracy rate, the vehicle diagnosis timeliness index, and the data processing capability parameter;

[0151] Determine n associated vehicles of the first vehicle according to the first position information; n is a natural number;

[0152] Determine the association priority of each associated vehicle among the n associated vehicles to obtain n association priorities;

[0153] Screen the n associated vehicles according to the target quantity and the n association priorities to obtain m second vehicles.

[0154] In a possible embodiment, in determining the target quantity according to the collaborative diagnosis accuracy rate, the vehicle diagnosis timeliness index, and the data processing capability parameter, the processing unit 802 is specifically configured to:

[0155] Determine a reference quantity according to the collaborative diagnosis accuracy rate and a preset first mapping relationship; the first mapping relationship is used to reflect the mapping relationship between the collaborative diagnosis accuracy rate and the reference quantity;

[0156] Determine the reference data processing volume corresponding to the reference quantity;

[0157] Obtain the diagnosis duration of the first vehicle;

[0158] Determine the data processing duration according to the data processing capability parameter, the reference data processing volume, and the diagnosis duration;

[0159] Determine the target quantity according to the reference quantity, the vehicle diagnosis timeliness index, and the data processing duration.

[0160] In a possible embodiment, in determining the n associated vehicles of the first vehicle according to the first position information, the processing unit 802 is specifically configured to:

[0161] Determine a target threshold according to the first fault type and the first fault level;

[0162] Determine a target association range according to the first position information and the target threshold;

[0163] Obtain k associated vehicles within the target association range according to the first position information; k is a natural number greater than or equal to n;

[0164] Obtain the first vehicle characteristics and the first vehicle operation parameters of the first vehicle;

[0165] Obtain the vehicle characteristics and the vehicle operation parameters of each of the k associated vehicles to obtain k associated vehicle characteristics and k associated vehicle operation parameters;

[0166] Compare the first vehicle characteristics with the k associated vehicle characteristics to obtain k vehicle characteristic similarities;

[0167] Compare the first vehicle operation parameters with the k associated vehicle operation parameters to obtain k vehicle operation parameter similarities;

[0168] Determine n associated vehicles from k associated vehicles according to k vehicle feature similarities and k vehicle operation parameter similarities.

[0169] In a possible embodiment, in terms of determining the association priorities of each of the n associated vehicles to obtain n association priorities, the processing unit 802 is specifically configured to:

[0170] Obtain the second position information of each of the n associated vehicles to obtain n pieces of second position information;

[0171] Determine n association distances according to the first position information and the n pieces of second position information;

[0172] Determine the n vehicle feature similarities corresponding to the n associated vehicles among the k vehicle feature similarities;

[0173] Determine the n vehicle operation parameter similarities corresponding to the n associated vehicles among the k vehicle operation parameter similarities;

[0174] Determine a target weight group according to the first fault type and the first fault level; the target weight group includes a first weight, a second weight, and a third weight;

[0175] Determine n association priorities according to the n association distances, the n vehicle feature similarities, the n vehicle operation parameter similarities, and the target weight group.

[0176] In a possible embodiment, in terms of diagnosing the first vehicle according to m pieces of second vehicle diagnosis data to obtain a diagnosis result, the processing unit 802 is specifically configured to:

[0177] Determine the second fault type and the second fault level of each of the m second vehicles according to the m pieces of second vehicle diagnosis data to obtain m second fault types and m second fault levels;

[0178] Compare the first fault type with the m second fault types to determine m fault type similarities;

[0179] Compare the first fault level with the m second fault levels to determine m fault level similarities;

[0180] Determine the m association priorities corresponding to the m second vehicles among the n association priorities;

[0181] Determine the target fault type and the target fault level of the first vehicle according to the m association priorities, the m fault type similarities, and the m fault level similarities;

[0182] Use the target fault type and the target fault level as the diagnosis result.

[0183] In a possible embodiment, the processing unit 802 is further configured to:

[0184] Determine a vehicle maintenance timeliness index according to the diagnosis result; the vehicle maintenance timeliness index is used to reflect the maintenance efficiency required by the first vehicle;

[0185] Obtain the energy consumption information of the first vehicle;

[0186] Determine multiple vehicle repair points according to the vehicle maintenance timeliness index and the energy consumption information;

[0187] Obtain the repair point information of each repair point among the multiple repair points to obtain multiple repair point information;

[0188] Determine the repair time and the target repair point of the first vehicle according to the multiple repair point information and the vehicle maintenance timeliness index;

[0189] Determine a repair path according to the first position information and the third position information of the target repair point;

[0190] Generate a repair plan for the first vehicle according to the repair time and the repair path.

[0191] Refer to Figure 8 , Figure 8 is a schematic structural diagram of a diagnostic device provided by an embodiment of the present application. As Figure 8 shown, the diagnostic device 900 includes a transceiver 901, a processor 902, and a memory 903, which are connected through 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 diagnostic device 900 can be the above-mentioned vehicle collaborative diagnostic device 800, and the processor 902 can be the above-mentioned acquisition unit 801 and processing unit 802.

[0192] The processor 902 is configured to read the computer program in the memory 903 and perform the following operations:

[0193] Obtain the first vehicle diagnostic data of the first vehicle; the first vehicle diagnostic data includes a fault parameter, a data processing capability parameter, and first position information;

[0194] Determine the first fault type and the first fault level of the first vehicle according to the fault parameter; the first fault level is used to reflect the complexity of the first fault type;

[0195] Determine m second vehicles associated with the first vehicle according to the first fault type, the first fault level, the data processing capability parameter, and the first position information; the distance between the m second vehicles and the first vehicle is less than a target threshold; m is a natural number;

[0196] Obtain the second vehicle diagnostic data of each of the m second vehicles to obtain m second vehicle diagnostic data; the m second vehicle diagnostic data is used to reflect the operating status information of the m second vehicles;

[0197] Diagnose the first vehicle based on the m second vehicle diagnostic data to obtain a diagnostic result;

[0198] Return the diagnostic result to the first vehicle.

[0199] In a possible embodiment, in determining the m second vehicles associated with the first vehicle according to the first fault type, the first fault level, the data processing capability parameter, and the first location information, the processor 902 is specifically configured to perform the following operations:

[0200] Obtain the vehicle road parameters of the first vehicle;

[0201] Determine the collaborative diagnosis accuracy rate according to the vehicle road parameters, the first fault type, and the first fault level; the collaborative diagnosis accuracy rate is used to reflect the accuracy rate when diagnosing the first vehicle through the vehicle diagnostic data of multiple vehicles;

[0202] Determine the vehicle diagnosis timeliness index of the first vehicle according to the first fault type and the first fault level; the vehicle diagnosis timeliness index is used to reflect the diagnosis efficiency required by the first vehicle;

[0203] Determine the target quantity according to the collaborative diagnosis accuracy rate, the vehicle diagnosis timeliness index, and the data processing capability parameter;

[0204] Determine the n associated vehicles of the first vehicle according to the first location information; n is a natural number;

[0205] Determine the association priority of each associated vehicle among the n associated vehicles to obtain n association priorities;

[0206] Screen the n associated vehicles according to the target quantity and the n association priorities to obtain m second vehicles.

[0207] In a possible embodiment, in determining the target quantity according to the collaborative diagnosis accuracy rate, the vehicle diagnosis timeliness index, and the data processing capability parameter, the processor 902 is specifically configured to perform the following operations:

[0208] Determine a reference quantity according to the collaborative diagnosis accuracy rate and a preset first mapping relationship; the first mapping relationship is used to reflect the mapping relationship between the collaborative diagnosis accuracy rate and the reference quantity;

[0209] Determine the reference data processing amount corresponding to the reference quantity;

[0210] Obtain the diagnosis duration of the first vehicle;

[0211] Determine the data processing duration according to the data processing capability parameter, the reference data processing volume, and the diagnosis duration;

[0212] Determine the target quantity according to the reference quantity, the vehicle diagnosis timeliness index, and the data processing duration.

[0213] In a possible embodiment, in terms of determining n associated vehicles of the first vehicle according to the first position information, the processor 902 is specifically configured to perform the following operations:

[0214] Determine the target threshold according to the first fault type and the first fault level;

[0215] Determine the target associated range according to the first position information and the target threshold;

[0216] Obtain k associated vehicles within the target associated range according to the first position information; k is a natural number greater than or equal to n;

[0217] Obtain the first vehicle feature and the first vehicle operation parameter of the first vehicle;

[0218] Obtain the vehicle feature and the vehicle operation parameter of each of the k associated vehicles, and obtain k associated vehicle features and k associated vehicle operation parameters;

[0219] Compare the first vehicle feature with the k associated vehicle features to obtain k vehicle feature similarities;

[0220] Compare the first vehicle operation parameter with the k associated vehicle operation parameters to obtain k vehicle operation parameter similarities;

[0221] Determine n associated vehicles from the k associated vehicles according to the k vehicle feature similarities and the k vehicle operation parameter similarities.

[0222] In a possible embodiment, in terms of determining the association priority of each of the n associated vehicles to obtain n association priorities, the processor 902 is specifically configured to perform the following operations:

[0223] Obtain the second position information of each of the n associated vehicles to obtain n second position information;

[0224] Determine n associated distances according to the first position information and the n second position information;

[0225] Determine the n vehicle feature similarities corresponding to the n associated vehicles among the k vehicle feature similarities;

[0226] Determine the n vehicle operation parameter similarities corresponding to the n associated vehicles among the k vehicle operation parameter similarities;

[0227] Determine a target weight group according to the first fault type and the first fault level; the target weight group includes a first weight, a second weight, and a third weight;

[0228] Determine n associated priorities according to n associated distances, n vehicle feature similarities, n vehicle operation parameter similarities, and the target weight group.

[0229] In a possible embodiment, in terms of diagnosing the first vehicle based on m pieces of second vehicle diagnosis data to obtain a diagnosis result, the processor 902 is specifically configured to perform the following operations:

[0230] Determine the second fault type and the second fault level of each second vehicle among the m second vehicles according to the m pieces of second vehicle diagnosis data, obtaining m second fault types and m second fault levels;

[0231] Compare the first fault type with the m second fault types to determine m fault type similarities;

[0232] Compare the first fault level with the m second fault levels to determine m fault level similarities;

[0233] Determine the m associated priorities corresponding to the m second vehicles among the n associated priorities;

[0234] Determine the target fault type and the target fault level of the first vehicle according to the m associated priorities, the m fault type similarities, and the m fault level similarities;

[0235] Use the target fault type and the target fault level as the diagnosis result.

[0236] In a possible embodiment, the processor 902 is further configured to perform the following operations:

[0237] Determine a vehicle repair timeliness index according to the diagnosis result; the vehicle repair timeliness index is used to reflect the repair efficiency required by the first vehicle;

[0238] Obtain the energy consumption information of the first vehicle;

[0239] Determine multiple vehicle repair points according to the vehicle repair timeliness index and the energy consumption information;

[0240] Obtain the repair point information of each repair point among the multiple repair points to obtain multiple repair point information;

[0241] Determine the repair time and the target repair point of the first vehicle according to the multiple repair point information and the vehicle repair timeliness index;

[0242] Determine a repair path according to the first position information and the third position information of the target repair point;

[0243] Generate a maintenance plan for the first vehicle based on the maintenance time and maintenance path.

[0244] An embodiment of the present application also provides a computer-readable storage medium storing a computer program, and the computer program is executed by a processor to implement part or all of the steps of any one of the vehicle collaborative diagnosis methods described in the above method embodiments.

[0245] An embodiment of the present application also 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 part or all of the steps of any one of the vehicle collaborative diagnosis methods described in the above method embodiments.

[0246] 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 adopted 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.

[0247] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0248] 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. In actual implementation, there can be other division methods. 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.

[0249] 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 they can be 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.

[0250] In addition, in each embodiment of the present application, each functional module can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module. The above-mentioned integrated module can be implemented in the form of hardware or in the form of a software program module.

[0251] If the above-mentioned 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 such an understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. The 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 each embodiment of the present application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical discs.

[0252] The embodiments of the present application have been introduced in detail above. Specific examples are used in this article to elaborate on the principles and implementation manners of the present application. The descriptions of the above embodiments are only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manners and application scopes. In summary, the content of this specification should not be construed as a limitation to the present application.

Claims

1. A vehicle collaborative diagnosis method, characterized in that: Applied to a vehicle diagnostic service platform, the method comprises: Acquire first vehicle diagnostic data of a first vehicle; the first vehicle diagnostic data includes a fault parameter, a data processing capability parameter, and first location information; determining a first fault type and a first fault level of the first vehicle according to the fault parameter; the first fault level is used to reflect the complexity of the first fault type; According to the first fault type, the first fault level, the data processing capability parameter and the first position information, m second vehicles associated with the first vehicle are determined; the distance between the m second vehicles and the first vehicle is less than a target threshold; m is a natural number; Acquire second vehicle diagnostic data of each of the m second vehicles to obtain m second vehicle diagnostic data; the m second vehicle diagnostic data are used to reflect the operating state information of the m second vehicles; Diagnose the first vehicle according to the m second vehicle diagnostic data to obtain a diagnostic result; The diagnostic result is returned to the first vehicle.

2. The method according to claim 1, characterized in that The determining, according to the first fault type, the first fault level, the data processing capability parameter, and the first location information, m second vehicles associated with the first vehicle comprises: obtaining vehicle road parameters of the first vehicle; determining a collaborative diagnosis accuracy rate according to the vehicle road parameter, the first fault type and the first fault level; the collaborative diagnosis accuracy rate is used to reflect the accuracy rate of diagnosing the first vehicle using vehicle diagnostic data of multiple vehicles; Determining a vehicle diagnosis time efficiency index of the first vehicle according to the first fault type and the first fault level; the vehicle diagnosis time efficiency index is used to reflect the diagnostic efficiency required by the first vehicle; Determining a target quantity according to the collaborative diagnosis accuracy, the vehicle diagnosis timeliness index and the data processing capability parameter; Determine n associated vehicles of the first vehicle according to the first position information, where n is a natural number; Determining an association priority of each of the n associated vehicles to obtain n association priorities; The n associated vehicles are screened according to the target quantity and the n associated priorities to obtain the m second vehicles.

3. The method according to claim 2, characterized in that The determining of the target quantity according to the collaborative diagnosis accuracy, the vehicle diagnosis timeliness index and the data processing capability parameter includes: Determine a reference quantity according to the collaborative diagnosis accuracy and a preset first mapping relationship; the first mapping relationship is used to reflect the mapping relationship between the collaborative diagnosis accuracy and the reference quantity; Determining a reference data processing amount corresponding to the reference quantity; Obtaining a diagnosis duration of the first vehicle; Determining the data processing duration according to the data processing capability parameter, the reference data processing amount and the diagnosis duration; The target quantity is determined according to the reference quantity, the vehicle diagnosis timeliness index and the data processing time.

4. The method according to claim 2, characterized in that The determining n associated vehicles of the first vehicle according to the first position information includes: determining the target threshold value according to the first fault type and the first fault level; determining a target association range according to the first location information and the target threshold; Acquire k associated vehicles within the target associated range according to the first position information; k is a natural number greater than or equal to n; acquiring a first vehicle characteristic and a first vehicle operating parameter of the first vehicle; Acquire vehicle characteristics and vehicle operating parameters of each of the k associated vehicles to obtain k associated vehicle characteristics and k associated vehicle operating parameters; Comparing the first vehicle feature with the k associated vehicle features to obtain k vehicle feature similarities; Comparing the first vehicle operating parameter with the k associated vehicle operating parameters to obtain similarities of the k vehicle operating parameters; The n associated vehicles are determined from the k associated vehicles according to the k vehicle feature similarities and the k vehicle operating parameter similarities.

5. The method according to claim 2, characterized in that The determining the association priority of each of the n associated vehicles to obtain n association priorities includes: Acquire the second position information of each associated vehicle among the n associated vehicles to obtain n second position information; Determining n associated distances according to the first position information and the n second position information; Determining n vehicle feature similarities corresponding to the n associated vehicles among the k vehicle feature similarities; Determining n vehicle operating parameter similarities corresponding to the n associated vehicles among the k vehicle operating parameter similarities; Determine a target weight group according to the first fault type and the first fault level; the target weight group includes a first weight, a second weight and a third weight; The n association priorities are determined according to the n association distances, the n vehicle feature similarities, the n vehicle operating parameter similarities and the target weight group.

6. The method according to any one of claims 1 to 5, characterized in that: The step of diagnosing the first vehicle according to the m second vehicle diagnostic data to obtain a diagnostic result includes: Determine a second fault type and a second fault level of each of the m second vehicles according to the m second vehicle diagnostic data, to obtain m second fault types and m second fault levels; Comparing the first fault type with the m second fault types to determine the similarity of the m fault types; Comparing the first fault level with the m second fault levels to determine the similarity of the m fault levels; Determining m association priorities corresponding to the m second vehicles among the n association priorities; Determining a target fault type and a target fault level of the first vehicle according to the m associated priorities, the m fault type similarities, and the m fault level similarities; The target fault type and the target fault level are used as the diagnosis result.

7. The method according to claim 6, characterized in that The method further comprises: Determining a vehicle maintenance time efficiency index according to the diagnosis result; the vehicle maintenance time efficiency index is used to reflect the maintenance efficiency required for the first vehicle; Acquiring energy consumption information of the first vehicle; Determine a plurality of maintenance points according to the vehicle maintenance timeliness index and the energy consumption information; Acquire maintenance point information of each maintenance point among the multiple maintenance points to obtain multiple maintenance point information; Determining the maintenance time and target maintenance point of the first vehicle according to the plurality of maintenance point information and the vehicle maintenance time efficiency index; determining a maintenance path according to the first location information and the third location information of the target maintenance point; A maintenance plan for the first vehicle is generated according to the maintenance time and the maintenance path.

8. A vehicle collaborative diagnosis device, characterized in that: The device comprises an acquisition unit and a processing unit; The acquisition unit is used to acquire first vehicle diagnostic data of the first vehicle; the first vehicle diagnostic data includes fault parameters, data processing capability parameters and first location information; The processing unit is used to determine a first fault type and a first fault level of the first vehicle according to the fault parameter; The first fault level is used to reflect the complexity of the first fault type; Determine, according to the first fault type, the first fault level, the data processing capability parameter, and the first location information, m second vehicles associated with the first vehicle; the distance between the m second vehicles and the first vehicle is less than a target threshold; m is a natural number; Acquire second vehicle diagnostic data of each of the m second vehicles to obtain m second vehicle diagnostic data; the m second vehicle diagnostic data are used to reflect the operating state information of the m second vehicles; Diagnose the first vehicle according to the m second vehicle diagnostic data to obtain a diagnostic result; The diagnostic result is returned to the first vehicle.

9. A diagnostic device, characterized in that: include: A processor and a memory, wherein 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 diagnostic 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