A vehicle fault troubleshooting method and related equipment based on AI diagnostic model

Abstract

The present invention provides a vehicle fault troubleshooting method and related equipment based on an AI diagnostic model, and relates to the technical field of vehicle fault troubleshooting. The method includes the steps of: determining all fault causes and arranging each fault cause in order into a first guide troubleshooting table; taking the special maintenance station where the faulty vehicle is first located as the starting maintenance station and adjusting the order of the troubleshooting items in the first guide troubleshooting table according to the troubleshooting items corresponding to the starting maintenance station to obtain a second guide troubleshooting table; controlling the preset AI diagnostic model to obtain the question sequence according to the second guide troubleshooting table so that the AI ​​diagnostic model conducts question-answering interaction with the maintenance personnel according to the question sequence, thereby guiding the maintenance personnel to troubleshoot the corresponding faulty vehicle. The present invention solves the problem of long maintenance cycle and low maintenance efficiency caused by a large number of faulty vehicles queuing together, thereby achieving the effect of shortening the maintenance cycle and improving maintenance efficiency, which is conducive to meeting higher efficiency maintenance requirements.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle fault troubleshooting, and in particular to a vehicle fault troubleshooting method based on an AI diagnostic model and related equipment. Background Art

[0002] With the technological development of fuel vehicles and electric vehicles, more and more vehicles are put into use, which undoubtedly brings new challenges to vehicle maintenance services, especially maintenance services for the taxi industry. Since taxis are used frequently and in large numbers, the number of faulty vehicles is relatively large. At the same time, since the suspension of taxis due to breakdowns directly affects the income of taxi drivers, taxi drivers have relatively higher requirements for maintenance cycles. Therefore, maintenance services for the taxi industry often have higher requirements in terms of maintenance efficiency.

[0003] In this regard, artificial intelligence technology can be used to develop applicable AI diagnostic models to assist maintenance personnel in handling large quantities of faulty vehicles. However, existing AI diagnostic models often only guide maintenance personnel to troubleshoot faulty vehicles in a fixed order of questions. In actual applications, the same vehicle failure may be caused by different causes. If maintenance personnel are guided to troubleshoot each cause one by one in a fixed order of questions, a large number of faulty vehicles will often be concentrated at a certain maintenance station and wait in line, thereby extending the maintenance cycle of the faulty vehicles and failing to meet the requirements of more efficient maintenance.

[0004] There is currently no effective technical solution to the above problems. Summary of the invention

[0005] The purpose of the present invention is to provide a vehicle fault troubleshooting method and related equipment based on an AI diagnostic model, which solves the problem of long maintenance cycle and low maintenance efficiency caused by a large number of faulty vehicles queuing together, thereby achieving the effect of shortening the maintenance cycle and improving maintenance efficiency, which is conducive to meeting more efficient maintenance requirements.

[0006] In a first aspect, the present invention provides a vehicle fault troubleshooting method based on an AI diagnostic model, which is applied to a server of a vehicle fault repair system, wherein the vehicle fault repair system includes a plurality of special repair stations, and the plurality of special repair stations are used to perform different troubleshooting items on the faulty vehicle;

[0007] The vehicle fault troubleshooting method based on the AI ​​diagnostic model includes the following steps:

[0008] S1. According to the fault type of the faulty vehicle, after determining all the fault causes that may cause the corresponding fault from the preset database, each of the fault causes is treated as a separate troubleshooting item and arranged in order into a first guide troubleshooting table;

[0009] S2. After the faulty vehicle enters the special maintenance station for the first time, the special maintenance station where the faulty vehicle is located for the first time is used as the starting maintenance station, and the order of the troubleshooting items in the first guidance troubleshooting table is adjusted according to the troubleshooting items corresponding to the starting maintenance station so that the troubleshooting item ranked first can be checked at the starting maintenance station, and the adjusted first guidance troubleshooting table is used as the second guidance troubleshooting table associated with the faulty vehicle;

[0010] S3. Control the preset AI diagnostic model to obtain a question sequence according to the second guided troubleshooting table so that the AI ​​diagnostic model can perform question-answering interaction with the maintenance personnel according to the question sequence, thereby guiding the maintenance personnel to troubleshoot the corresponding faulty vehicle.

[0011] The present invention provides a vehicle fault troubleshooting method based on an AI diagnostic model, which dynamically adjusts the questioning order of the AI ​​diagnostic model according to the special maintenance station that the faulty vehicle enters, breaks away from the fixed mode of the traditional fixed questioning order, and avoids a large number of faulty vehicles being concentrated in a certain special maintenance station to queue up and wait, thereby achieving the effect of shortening the maintenance cycle and improving maintenance efficiency.

[0012] Furthermore, the specific steps in step S2 include:

[0013] S21. When adjusting the order of the check items in the first guide check table according to the check items corresponding to the starting maintenance station, execute:

[0014] S211. According to the inspection items of each of the special maintenance stations, all the inspection items that can be handled by each of the special maintenance stations are selected from all the inspection items and used as the inspection group corresponding to each of the special maintenance stations;

[0015] S212. Adjust the order of the check items in the first boot check table based on the check group.

[0016] Through intelligent troubleshooting sequence adjustment, the efficiency problem of traditional fixed-sequence troubleshooting methods in practical applications is effectively solved, providing the vehicle maintenance industry with a more efficient and flexible troubleshooting method.

[0017] Furthermore, the specific steps in step S212 include:

[0018] S2121. Multiple faulty vehicles with the same fault type are regarded as faulty vehicles in the same batch; the total number of faulty vehicles in the same batch is the same as the total number of special maintenance stations, and each faulty vehicle in the same batch uses each special maintenance station as the starting maintenance station;

[0019] S2122. Adjust the first guide troubleshooting table corresponding to each faulty vehicle of the same batch so that all the troubleshooting groups in the same sequence in the second guide troubleshooting table are different.

[0020] By dynamically adjusting the troubleshooting order, balanced utilization of resources is achieved. At the same time, through a carefully designed troubleshooting table adjustment mechanism, the advantages of parallel processing are fully utilized, greatly improving maintenance efficiency.

[0021] Furthermore, the specific steps in step S3 include:

[0022] S3A1. Get the number of faulty vehicles to be checked at each of the special maintenance stations; the number of faulty vehicles to be checked refers to the number of faulty vehicles waiting for the corresponding special maintenance stations to perform troubleshooting;

[0023] S3A2. According to the number of faulty vehicles to be checked at each of the special maintenance stations, adjust the order of the second guide investigation group in the unfinished investigation table to update the second guide investigation table;

[0024] S3A3. Update the question sequence according to the updated second guidance checklist.

[0025] Dynamically adjust the inspection order, and adjust the order of the inspection groups that have not completed the inspection according to the number of faulty vehicles to be inspected. This can give priority to the maintenance stations with fewer vehicles to be inspected, avoiding the situation where some stations are idle while other stations are overloaded.

[0026] Furthermore, the specific steps in step S3A2 include:

[0027] S3A21. Arrange the unfinished inspection groups in the second guided inspection table in ascending order according to the number of faulty vehicles to be inspected at the corresponding special maintenance stations to update the second guided inspection table.

[0028] Furthermore, the specific steps in step S3 include:

[0029] S3B1. Obtain the average man-hours required for each of the inspection groups to be performed on the corresponding special maintenance stations and serve as the special man-hours corresponding to each of the inspection groups;

[0030] S3B2. Count the remaining special working hours of all the investigation groups that have not completed the investigation in the second guided investigation table corresponding to the same batch of faulty vehicles and use them as the current remaining working hours corresponding to the same batch of faulty vehicles; the same batch of faulty vehicles consists of multiple faulty vehicles with the same fault type, and the total number of faulty vehicles in the same batch is the same as the total number of special maintenance stations, and each of the faulty vehicles in the same batch uses each of the special maintenance stations as the starting maintenance station;

[0031] S3B3. Compare the current remaining working hours corresponding to each of the same batch of faulty vehicles, and when the current remaining working hours corresponding to any of the same batch of faulty vehicles are different from the current remaining working hours corresponding to another of the same batch of faulty vehicles, adjust the order of the unfinished inspection groups in the second guide inspection table corresponding to the same batch of faulty vehicles with the largest current remaining working hours to update the second guide inspection table corresponding to the same batch of faulty vehicles with the largest current remaining working hours;

[0032] S3B4. Update the questioning sequence corresponding to the faulty vehicle of the same batch with the largest current remaining working hours according to the updated second guided troubleshooting table.

[0033] Furthermore, the specific steps in step S3B3 include:

[0034] S3B31. Advance the order of the inspection group in the second guided inspection table corresponding to the same batch of faulty vehicles with the largest current remaining working hours and which has not completed the inspection and has the shortest remaining special working hours.

[0035] In a second aspect, the present invention provides a vehicle fault troubleshooting device based on an AI diagnostic model, which is applied to a server of a vehicle fault repair system, wherein the vehicle fault repair system includes a plurality of special repair stations, and the plurality of special repair stations are used to perform different troubleshooting items on the faulty vehicle;

[0036] The vehicle fault troubleshooting device based on the AI ​​diagnostic model includes:

[0037] A sorting module, configured to determine all possible fault causes that may cause the corresponding fault from a preset database according to the fault type of the faulty vehicle, and then arrange each of the fault causes as a separate troubleshooting item and arrange them in order into a first guided troubleshooting table;

[0038] an adjustment module, for, after the faulty vehicle enters the special maintenance station for the first time, taking the special maintenance station where the faulty vehicle is located for the first time as the starting maintenance station, and adjusting the order of the troubleshooting items in the first guide troubleshooting table according to the troubleshooting items corresponding to the starting maintenance station so that the troubleshooting item ranked first can be checked at the starting maintenance station, and taking the adjusted first guide troubleshooting table as the second guide troubleshooting table associated with the faulty vehicle;

[0039] A control module is used to control the preset AI diagnostic model to obtain a question sequence according to the second guided troubleshooting table so that the AI ​​diagnostic model can interact with the maintenance personnel in question sequence to guide the maintenance personnel to troubleshoot the corresponding faulty vehicle.

[0040] The vehicle fault troubleshooting device based on the AI ​​diagnostic model provided by the present invention effectively solves the problems of inefficiency and waste of resources in traditional methods by dynamically adjusting the troubleshooting order and optimizing resource allocation, and provides a more efficient and accurate fault diagnosis solution for the vehicle maintenance industry, which is conducive to meeting more efficient maintenance requirements.

[0041] In a third aspect, the present invention provides an electronic device comprising a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps of the vehicle fault troubleshooting method based on the AI ​​diagnostic model provided in the first aspect are executed.

[0042] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the vehicle fault troubleshooting method based on the AI ​​diagnostic model provided in the first aspect are performed.

[0043] As can be seen from the above, the vehicle fault troubleshooting method based on the AI ​​diagnostic model provided by the present invention is proposed based on a vehicle fault maintenance system including multiple special maintenance stations, and each special maintenance station finds the cause of the fault by executing different troubleshooting items. Among them, the questioning sequence of the AI ​​diagnostic model is not fixed according to the traditional mode, but the questioning sequence of the AI ​​diagnostic model is dynamically adjusted according to the special maintenance station where the faulty vehicle first enters, thereby avoiding the situation where a large number of faulty vehicles of the same fault type can only enter each special maintenance station in sequence according to a fixed order, resulting in a large number of faulty vehicles being concentrated in a certain special maintenance station waiting, so as to make more reasonable use of each special maintenance station, achieve the effect of shortening the maintenance cycle and improving the maintenance efficiency, and thus meet the maintenance requirements of higher efficiency.

[0044] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flow chart of a vehicle fault troubleshooting method based on an AI diagnostic model provided in an embodiment of the present invention.

[0046] Figure 2 A schematic diagram of an embodiment of the present invention after adjusting the first guidance investigation table based on the investigation group.

[0047] Figure 3 A schematic diagram of an embodiment of the present invention after adjusting the first guide troubleshooting table corresponding to each faulty vehicle of the same batch.

[0048] Figure 4 It is a schematic diagram of an embodiment of the present invention after adjusting the second guidance troubleshooting table according to the number of faulty vehicles to be checked at each special maintenance station.

[0049] Figure 5 A schematic diagram of an embodiment of the present invention after adjusting the second guidance check list corresponding to the same batch fault vehicle with the largest remaining working hours.

[0050] Figure 6 A schematic diagram of the structure of a vehicle fault troubleshooting device based on an AI diagnostic model provided in an embodiment of the present invention.

[0051] Figure 7 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention.

[0052] Description of labels:

[0053] 100, sorting module; 200, adjustment module; 300, control module; 13, electronic device; 1301, processor; 1302, memory; 1303, communication bus. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0055] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0056] Reference Figure 1 , the present invention provides a vehicle fault troubleshooting method based on an AI diagnostic model, which is applied to a server of a vehicle fault maintenance system, wherein the vehicle fault maintenance system includes a plurality of special maintenance stations, and the plurality of special maintenance stations are used to perform different troubleshooting items on the faulty vehicle;

[0057] The vehicle fault troubleshooting method based on the AI ​​diagnostic model includes the following steps:

[0058] S1. According to the fault type of the faulty vehicle, after determining all the possible causes of the corresponding fault from the preset database, each cause of the fault is treated as a separate troubleshooting item and arranged in order into a first guide troubleshooting table;

[0059] S2. After the faulty vehicle enters the special maintenance station for the first time, the special maintenance station where the faulty vehicle is located for the first time is used as the starting maintenance station, and the order of the troubleshooting items in the first guide troubleshooting table is adjusted according to the troubleshooting items corresponding to the starting maintenance station so that the troubleshooting items ranked first can be checked at the starting maintenance station, and the adjusted first guide troubleshooting table is used as the second guide troubleshooting table associated with the faulty vehicle;

[0060] S3. Control the preset AI diagnostic model to obtain a question sequence according to the second guided troubleshooting table so that the AI ​​diagnostic model can perform question-answering interaction with the maintenance personnel according to the question sequence, thereby guiding the maintenance personnel to troubleshoot the corresponding faulty vehicle.

[0061] In actual application, for a vehicle with the same fault, there is often more than one cause of the fault. For example, if the steering wheel is not straight, the cause may be a misaligned steering rod or worn tires; if the fuel consumption is abnormally high, the cause may be a dirty throttle, old spark plugs, or severe carbon deposits; if the window cannot be raised or lowered, the cause may be a damaged window lift motor, poor contact of the electronic control harness, motor overheat protection, or excessive resistance of the glass guide groove.

[0062] Taking into account that different fault types have multiple different fault causes, and different equipment and facilities are often required to troubleshoot different fault causes, taking the fault type of a misaligned steering wheel as an example, a lift is not required to check whether the steering rod is out of adjustment, but a lift is required to check whether the tire is worn. Therefore, in order to improve maintenance efficiency, the vehicle fault maintenance system based on this embodiment includes multiple special maintenance stations, each of which is equipped with different equipment to perform different troubleshooting items on the faulty vehicle. For example, the first special maintenance station is equipped with a special tool box, spare parts storage rack, trench, etc., which are mainly used to troubleshoot visible surface faults; and the second special maintenance station is equipped with a lift, tire changer, etc., which are mainly used to troubleshoot chassis and tire faults.

[0063] When arranging special maintenance stations, the fault type can be considered. For example, for a fault of misaligned steering wheel, two special maintenance stations can be arranged, one for checking the steering rod and the other for checking the tire. This arrangement of special maintenance stations is particularly suitable for the taxi industry. On the one hand, because there are a large number of taxis and a large number of faulty vehicles with the same fault type, arranging special maintenance stations according to the fault type is more conducive to meeting the large-scale maintenance needs of the taxi industry; on the other hand, because the specifications of taxis put into use in the same batch of the taxi industry are generally the same, when the same fault occurs in the batch of taxis, the cause of the fault is rarely special, so the special maintenance stations have sufficient ability to troubleshoot the fault.

[0064] It should be noted that when considering the arrangement of special maintenance stations from the perspective of fault types, the fault types are not limited to the failure of specific components, but can also be more general universal faults. For example, if there is an abnormal fault in the vehicle, the causes of the fault include engine failure, transmission system failure and electronic system failure. Therefore, three special maintenance stations can be arranged to check the engine, transmission system and electronic system respectively.

[0065] Based on the above-mentioned vehicle fault maintenance system, if the traditional mode of fixed questioning sequence is adopted, it will inevitably lead to a large number of faulty vehicles being concentrated in a certain maintenance station and waiting in line. In this case, the maintenance cycle of faulty vehicles that subsequently enter the maintenance system is significantly extended, and it is impossible to meet the requirements of efficient maintenance. For example, in the maintenance center of a large taxi company, suppose there are 100 faulty vehicles that need to be repaired, of which 30% are related to the engine, 25% are related to the transmission system, 20% are related to the electronic system, and the rest involve other systems. If the AI ​​diagnostic model asks questions in a fixed order, it may cause the engine maintenance station to be overcrowded, while other stations are relatively idle, resulting in uneven resource allocation and overall inefficiency.

[0066] Furthermore, this fixed-order troubleshooting method not only increases the maintenance time of a single vehicle, but may also lead to a waste of maintenance resources. For example, some simple faults may be ranked after complex faults, delaying the opportunity for quick repair. Since the troubleshooting order cannot be dynamically adjusted according to the actual workstation situation, some professional maintenance personnel may be idle for a long time while other personnel are overloaded. This unbalanced resource allocation directly affects the operating efficiency of the entire maintenance system.

[0067] In contrast, the method provided in this embodiment first determines all possible fault causes from a preset database according to the fault type of the faulty vehicle, and compiles each fault cause as a separate troubleshooting item into a first guided troubleshooting table. This step lays the foundation for subsequent dynamic adjustments. The database can contain various vehicle models, fault types and their corresponding possible causes to ensure comprehensiveness and accuracy.

[0068] Then, when the faulty vehicle enters the special maintenance station for the first time, the station is set as the starting maintenance station. According to the characteristics of the starting maintenance station, the order of the troubleshooting items in the first guide troubleshooting table is adjusted to generate the second guide troubleshooting table. This step ensures that the troubleshooting process can fully utilize the resources of the current station and avoid unnecessary station transfers. For example, if the starting station is the engine maintenance station, then the troubleshooting items related to the engine will be adjusted to the front.

[0069] Finally, the AI ​​diagnostic model generates a question sequence based on the second guided troubleshooting table to guide the maintenance personnel to troubleshoot. This step combined with the previous steps allows the maintenance personnel to directly transfer the faulty vehicle to an idle special maintenance station after receiving it. Then the AI ​​diagnostic model automatically adjusts the question sequence to guide the maintenance personnel to troubleshoot related troubleshooting items at the current special maintenance station. This dynamically adjusted question sequence can better adapt to the actual maintenance environment and improve troubleshooting efficiency.

[0070] In practical applications, this method can significantly improve maintenance efficiency. For example, in a large maintenance center with 10 specialized maintenance stations, assuming that each vehicle has an average of 20 possible causes of failure, by dynamically adjusting the troubleshooting sequence, the average maintenance time can be shortened from the original 4 hours to 2.5 hours, improving efficiency by about 37.5%.

[0071] Specifically, in the maintenance center of a large taxi company, there are 10 special maintenance stations, including engine stations, transmission stations, electronic system stations, suspension system stations, etc. The maintenance center is equipped with a vehicle troubleshooting system based on an AI diagnostic model, which runs on the center's server.

[0072] When a taxi with a breakdown enters the maintenance center, the system first retrieves all possible causes of the breakdown from the preset database according to the type of breakdown of the vehicle (for example, "engine cannot start"). These causes may include low battery, starter motor failure, fuel system problems, etc. The system treats these possible causes as separate troubleshooting items and arranges them into the first guided troubleshooting table in a certain logical order (such as from simple to complex).

[0073] Assuming that the taxi is directed to the electronic system station (as the starting maintenance station), the system will adjust the order of the check items in the first guided checklist according to the characteristics of the electronic system station. For example, the check items related to the electronic system (such as checking the battery power) are adjusted to the front of the table to form the second guided checklist. This ensures that the maintenance personnel first conduct checks related to the current station, improving efficiency.

[0074] Next, the AI ​​diagnostic model generates a sequence of questions based on the second guided troubleshooting table. For example, it may first ask the maintenance technician: "Please check whether the circuit connection of the starter motor is normal." The maintenance technician answers after checking. If the circuit connection is normal, the AI ​​diagnostic model will continue to the next question, such as "Please check the vehicle battery voltage, what is the value?". In this way, the AI ​​diagnostic model guides the maintenance technician to step by step check and finally determine whether the cause of the fault is insufficient battery power. If the result is no, the second guided troubleshooting table associated with the faulty vehicle can also guide the maintenance technician to move the faulty vehicle to the engine station and further use the AI ​​diagnostic model to troubleshoot the starter motor fault. In this way, the faulty vehicle is orderly controlled to be moved to each station in turn until the cause of the fault is determined.

[0075] In another embodiment, consider a maintenance center that specializes in repairing electric vehicles. The center has five special maintenance stations, one for the battery system, one for the motor system, one for the charging system, one for the vehicle electronic system, and one for the chassis system. When an electric vehicle reports a "sharp drop in mileage" fault, the system retrieves possible causes from the database, such as battery capacity attenuation, motor efficiency reduction, insufficient tire pressure, etc., to form a first guided troubleshooting table.

[0076] If the vehicle is first directed to the battery system station, the system will adjust the battery-related troubleshooting items (such as checking the battery capacity) to the top of the second guided troubleshooting table. The AI ​​diagnostic model will then generate a sequence of questions based on this table, such as "Please check the operating status of the battery management system", "Please perform a battery capacity test, what is the result?", etc., to guide the maintenance personnel to conduct targeted inspections.

[0077] Compared with the traditional fixed-order AI diagnostic model, this method significantly improves maintenance efficiency. In the traditional method, even if the faulty vehicle is already at the electronic system station, the AI ​​diagnostic model may still guide the maintenance personnel to check the mechanical parts first according to the preset order, resulting in time waste and unnecessary station transfers. This method ensures the matching of the maintenance operation with the current station by dynamically adjusting the troubleshooting order, reducing the number of station transfers and improving overall efficiency.

[0078] For example, in the case of the taxi maintenance center mentioned above, after adopting this method, the average maintenance time per vehicle was shortened from the original 4 hours to 2.5 hours, and the efficiency was improved by 37.5%. This not only shortened the maintenance cycle of a single vehicle, but also increased the throughput of the entire maintenance center and reduced the waiting time of faulty vehicles.

[0079] In addition, this method improves the accuracy of maintenance. By considering the characteristics of the starting maintenance station, the system can more accurately guide the maintenance personnel to perform relevant inspections, reducing the possibility of misdiagnosis. In the case of an electric vehicle maintenance center, this method increased the accuracy of fault diagnosis from the original 85% to 95%, greatly reducing the number of repeated inspections and repairs.

[0080] The present invention first realizes the dynamic adjustment of the troubleshooting order, rather than simply following a preset order. This flexibility enables the maintenance process to better adapt to actual conditions and improve efficiency. Secondly, the present invention introduces the concept of a starting maintenance station, taking the station characteristics into consideration, which is missing in the prior art. This innovation greatly reduces unnecessary station transfers and saves time and human resources. Finally, the present invention combines an AI diagnostic model with a dynamically adjusted troubleshooting table to achieve smarter and more accurate fault diagnosis, which is unattainable with traditional fixed-order diagnostic models.

[0081] In general, the vehicle fault troubleshooting method based on the AI ​​diagnostic model proposed in the present invention effectively solves the problems of inefficiency and waste of resources in traditional methods by dynamically adjusting the troubleshooting order and optimizing resource allocation, and provides a more efficient and accurate fault diagnosis solution for the vehicle maintenance industry, which is conducive to meeting more efficient maintenance requirements.

[0082] In some embodiments, the specific steps in step S2 include:

[0083] S21. When adjusting the order of the check items in the first guide check list according to the check items corresponding to the starting maintenance station, execute:

[0084] S211. According to the inspection items of each special maintenance station, all inspection items that can be handled by each special maintenance station are selected from all inspection items and used as the inspection group corresponding to each special maintenance station;

[0085] S212. Adjust the order of the check items in the first boot check table based on the check group.

[0086] In this embodiment, first, according to the troubleshooting items of each special maintenance station, the troubleshooting items that each special maintenance station can handle are screened from all the troubleshooting items to form a corresponding troubleshooting group. This step helps to clarify the capacity range of each maintenance station and avoids the situation where the order of all the troubleshooting items that a special maintenance station can handle is too scattered, resulting in the repeated transfer of the faulty vehicle to various stations. Secondly, based on the formed troubleshooting group, the order of the troubleshooting items in the first guide troubleshooting table is adjusted. This step ensures that the adjusted order matches the capacity of each maintenance station and improves the troubleshooting efficiency.

[0087] For details, please refer to the attached Figure 2For example, the fault causes corresponding to a certain fault type determined from the database include: cause a1, cause b1, cause a2, cause b2, cause a3 and cause c1; and the vehicle fault maintenance system includes three special maintenance stations, namely: special maintenance station A, special maintenance station B and special maintenance station C, among which the troubleshooting items that can be processed by the special maintenance station A include cause a1, cause a2 and cause a3, the troubleshooting items that can be processed by the special maintenance station B include cause b1 and cause b2, and the troubleshooting items that can be processed by the special maintenance station C include cause c1.

[0088] If the order of the troubleshooting items in the second guided troubleshooting table is: cause a1, cause b1, cause a2, cause b2, cause a3 and cause c1, the maintenance personnel will be guided to transfer the faulty vehicle repeatedly between the special maintenance station A and the special maintenance station B, which is obviously unreasonable and has low maintenance efficiency.

[0089] In this regard, this embodiment proposes to group all the troubleshooting items that can be checked at the same special maintenance station as a group of troubleshooting groups, and then sort them by troubleshooting group, so as to avoid the troubleshooting items being too scattered and causing the faulty vehicle to be repeatedly transferred to various stations. Specifically, the above troubleshooting items are divided into three troubleshooting groups, namely, troubleshooting group A, troubleshooting group B and troubleshooting group C, wherein troubleshooting group A includes reasons a1, a2 and a3, troubleshooting group B includes reasons b1 and b2, and troubleshooting group C includes reason c1. Further, when sorting by troubleshooting group, the first troubleshooting group is determined according to the starting maintenance station of the faulty vehicle. For example, if the starting maintenance station of the faulty vehicle is special maintenance station B, troubleshooting group B is ranked first; for another example, if the starting maintenance station of the faulty vehicle is special maintenance station C, troubleshooting group C is ranked first, so as to ensure that the first troubleshooting item can be checked at the starting maintenance station.

[0090] Specifically, when a faulty vehicle enters a special maintenance station as the starting maintenance station, the system will first identify the troubleshooting items that this station can handle, and adjust these troubleshooting items to the front of the first guide troubleshooting table. In this way, maintenance personnel can complete all possible troubleshooting items at the current station, avoiding frequent station switching. For example, if a faulty vehicle first enters the electrical system maintenance station, the system will adjust all troubleshooting items related to the electrical system to the front of the troubleshooting table, so that maintenance personnel can complete all electrical system-related inspections at one time.

[0091] This embodiment can significantly improve the efficiency of troubleshooting through this method. Compared with the traditional fixed-sequence troubleshooting method, this method can reduce the number of workstation conversions by about 30%-50%, thereby saving a lot of time and labor costs, and achieving the following advantages:

[0092] 1. Flexibility: The traditional fixed-order troubleshooting method is difficult to adapt to the actual conditions of different maintenance stations, while this method can flexibly adjust the troubleshooting order according to the starting maintenance station to better adapt to the actual maintenance environment.

[0093] 2. Efficiency improvement: By forming an investigation group corresponding to a special maintenance station, this method can maximize the use of the professional capabilities of each maintenance station, reduce unnecessary station conversions, and thus significantly improve the investigation efficiency.

[0094] 3. Intelligence: This method can be seamlessly integrated with the AI ​​diagnostic model, providing a more reasonable sequence of questions for the AI ​​diagnostic model, further improving the effect of human-computer interaction and the accuracy of fault diagnosis.

[0095] 4. Scalability: This method can easily add maintenance stations or troubleshooting items by simply updating the corresponding database, and has good scalability.

[0096] In general, this embodiment effectively solves the efficiency problem of the traditional fixed-order troubleshooting method in practical applications through intelligent troubleshooting sequence adjustment, and provides a more efficient and flexible troubleshooting method for the vehicle maintenance industry.

[0097] It should be noted that this embodiment does not limit the order of each inspection item in each inspection group, but only emphasizes that each inspection item in each inspection group can be inspected at the corresponding special maintenance station.

[0098] In some embodiments, when arranging special maintenance stations, a corresponding QR code (or a barcode) can be set at each special maintenance station for maintenance personnel to scan with a terminal. The QR code is associated with the special maintenance station, and the troubleshooting items of the special maintenance station can be determined through the QR code. At the same time, the special maintenance station where the faulty vehicle is located can also be determined through the QR code; after scanning the QR code, the information of the faulty vehicle (including the fault type) can be reported to the server through the terminal. If the server receives the information of the faulty vehicle for the first time, the special maintenance station where the faulty vehicle is currently located is used as the starting maintenance station; after determining the starting maintenance station of the faulty vehicle, the troubleshooting items corresponding to the starting maintenance station, and the cause of the fault, the server outputs a second guided troubleshooting table to the AI ​​diagnostic model, and finally the maintenance personnel interacts with the AI ​​diagnostic model through the terminal through question and answer.

[0099] It should be noted that the information of the faulty vehicle may also include information such as a license plate, an identification code, a serial number, etc., thereby making it easier for the server to associate the second guidance checklist with the corresponding faulty vehicle.

[0100] In some embodiments, the specific steps in step S212 include:

[0101] S2121. Multiple faulty vehicles with the same fault type are regarded as faulty vehicles in the same batch; the total number of faulty vehicles in the same batch is the same as the total number of special maintenance stations, and each faulty vehicle in the same batch uses each special maintenance station as the starting maintenance station;

[0102] S2122. Adjust the first guide troubleshooting table corresponding to each faulty vehicle of the same batch so that the troubleshooting groups in the same sequence in all the obtained second guide troubleshooting tables are different.

[0103] In this embodiment, multiple faulty vehicles with the same fault type are regarded as faulty vehicles in the same batch, and the number of faulty vehicles in the same batch is equal to the number of special maintenance stations. Each faulty vehicle starts to be checked at a different special maintenance station. In this way, the resources of each special maintenance station can be fully utilized to avoid the situation where some stations are idle while other stations are crowded. By adjusting the first guide troubleshooting table of each faulty vehicle in the same batch, so that the troubleshooting groups with the same sequence in all the second guide troubleshooting tables are different, it is possible to implement different troubleshooting items for faulty vehicles in the same batch at different maintenance stations at the same time. This arrangement can maximize the use of the specific functions of each special maintenance station and improve the overall maintenance efficiency. It realizes the parallel work of multiple special maintenance stations, effectively avoiding the waste of resources and the problem of waiting in line.

[0104] For example, see Attachment Figure 3 , there are 3 special maintenance stations, namely special maintenance station A, special maintenance station B and special maintenance station C; there are 3 faulty vehicles from the same batch, namely faulty vehicle a from the same batch, faulty vehicle b from the same batch and faulty vehicle c from the same batch; the investigation groups include: investigation group A, investigation group B and investigation group C, among which investigation group A conducts investigation at special maintenance station A, investigation group B conducts investigation at special maintenance station B, and investigation group C conducts investigation at special maintenance station C; thus, 3 different second guided investigation tables can be formed:

[0105] Faulty vehicle a from the same batch: investigation group A, investigation group B and investigation group C;

[0106] Faulty vehicle b from the same batch: investigation group B, investigation group C and investigation group A;

[0107] Faulty vehicle c from the same batch: investigation group C, investigation group A and investigation group B.

[0108] When the time required for each troubleshooting group to complete the troubleshooting is the same, all troubleshooting groups in the same sequence in the second-guide troubleshooting table are different, so that after all faulty vehicles in the same batch complete the troubleshooting of one troubleshooting group, they can continue to troubleshoot the next troubleshooting group by exchanging special maintenance stations. This is equivalent to troubleshooting multiple faulty vehicles at the same time, greatly improving maintenance efficiency.

[0109] Specifically, assume that a maintenance center has 5 special maintenance stations, namely, circuit inspection station, engine inspection station, chassis inspection station, body inspection station and comprehensive inspection station. There are 5 electric vehicles of the same model with similar power system failures. Applying the technical solution of this embodiment, these 5 faulty vehicles will be regarded as faulty vehicles from the same batch, recorded as faulty vehicle a from the same batch, faulty vehicle b from the same batch, faulty vehicle c from the same batch, faulty vehicle d from the same batch and faulty vehicle e from the same batch, and the inspection will start from 5 different stations respectively.

[0110] The system first generates a first-guide troubleshooting table that contains all possible fault causes, such as battery check, motor check, controller check, wiring check, and on-board charger check. Then, the system adjusts this checklist for each vehicle to form 5 different second-guide troubleshooting tables:

[0111] 1. Faulty vehicle a of the same batch (starting from the circuit inspection station): circuit inspection, controller inspection, battery inspection, motor inspection, and vehicle charger inspection;

[0112] 2. Faulty vehicle B of the same batch (starting from the engine inspection station): motor inspection, battery inspection, circuit inspection, vehicle charger inspection, controller inspection;

[0113] 3. Faulty vehicle c of the same batch (starting from the chassis inspection station): controller inspection, vehicle charger inspection, motor inspection, circuit inspection, battery inspection;

[0114] 4. Faulty vehicles d of the same batch (starting from the body inspection station): vehicle charger inspection, circuit inspection, controller inspection, battery inspection, motor inspection;

[0115] 5. Faulty vehicles from the same batch (starting from the comprehensive inspection station): battery inspection, motor inspection, vehicle charger inspection, controller inspection, and circuit inspection.

[0116] This arrangement ensures that the five special maintenance stations are in parallel working state, avoiding a special maintenance station being idle or a large number of faulty vehicles waiting in line at a special maintenance station, making full use of the resources of all stations and significantly improving the overall maintenance efficiency.

[0117] Compared with the prior art, the traditional method usually adopts a fixed troubleshooting order, which causes multiple faulty vehicles to be jammed in certain workstations while other workstations are idle. This embodiment achieves balanced utilization of resources by dynamically adjusting the troubleshooting order. In addition, the traditional method often ignores the parallel processing potential of faulty vehicles in the same batch, while the present invention fully utilizes the advantages of parallel processing through a carefully designed troubleshooting table adjustment mechanism, greatly improving maintenance efficiency. This innovative method not only solves the problems of resource waste and inefficiency in the prior art, but also provides a more intelligent and flexible troubleshooting solution for the vehicle maintenance industry.

[0118] In some embodiments, the specific steps in step S3 include:

[0119] S3A1. Get the number of faulty vehicles to be checked at each special maintenance station; the number of faulty vehicles to be checked refers to the number of faulty vehicles waiting for the corresponding special maintenance station to perform troubleshooting;

[0120] S3A2. According to the number of faulty vehicles to be checked at each special maintenance station, adjust the order of the unfinished inspection group in the second guide inspection table to update the second guide inspection table;

[0121] S3A3. Update the question sequence according to the updated second guidance checklist.

[0122] This embodiment obtains the number of faulty vehicles to be checked at each special maintenance station in real time, and dynamically adjusts the troubleshooting order to balance the workload of each maintenance station. Specifically: obtain the number of faulty vehicles to be checked, grasp the working status of each special maintenance station in real time, and provide a data basis for subsequent adjustments. Dynamically adjust the troubleshooting order, and adjust the order of the troubleshooting groups that have not completed the troubleshooting according to the number of faulty vehicles to be checked. In this way, maintenance stations with fewer vehicles to be checked can be given priority to avoid the situation where some stations are idle while other stations are overstocked. Update the questioning order, and update the questioning order of the AI ​​diagnostic model according to the adjusted troubleshooting table to ensure that the maintenance personnel perform troubleshooting in the latest optimized order. This method is particularly suitable for maintenance services for large quantities of faulty vehicles.

[0123] In the specific implementation process, the number of faulty vehicles to be checked at each special maintenance station can be obtained in a variety of ways. For example, the number of vehicles to be checked at each maintenance station can be automatically counted through a real-time monitoring system, or the data can be manually entered by staff. The update frequency of the number of faulty vehicles to be checked can be set according to actual needs, such as updating every 5 minutes or immediately after each inspection is completed.

[0124] When adjusting the order of the unfinished inspection groups in the second guided inspection table, multiple strategies can be used. One method is to rearrange the inspection groups in order of the number of faulty vehicles to be inspected from small to large, giving priority to the inspection groups at maintenance stations with fewer vehicles to be inspected. Another method is to set a threshold. When the number of vehicles to be inspected at a maintenance station exceeds the threshold, the priority of the inspection group corresponding to the station is increased. The order can also be adjusted by combining the estimated time of the inspection group, taking into account the number of vehicles to be inspected and the inspection time.

[0125] When updating the question sequence, the AI ​​diagnosis model needs to be able to quickly adapt to the new troubleshooting sequence. A dynamic adjustment algorithm can be designed to enable the AI ​​diagnosis model to automatically generate a new question sequence based on the updated second-guide troubleshooting table. At the same time, in order to ensure the consistency and accuracy of the diagnosis, the completed diagnostic information can be retained when adjusting the question sequence, and only the unfinished part can be adjusted.

[0126] This dynamic adjustment mechanism is combined with the AI ​​diagnostic model and troubleshooting group design in the previous solution to form a complete intelligent troubleshooting system. By adjusting the troubleshooting sequence in real time, the system can better balance the workload of each maintenance station, reduce the situation where some stations are overly busy while others are idle, and thus improve the overall maintenance efficiency. At the same time, since the adjustment of the troubleshooting sequence is based on real-time data, it can better adapt to the actual maintenance situation and reduce waiting time and resource waste during the maintenance process.

[0127] In practical applications, refer to the attached Figure 4 , suppose a maintenance center has 3 special maintenance stations, namely: special maintenance station A, special maintenance station B and special maintenance station C, which are responsible for the inspection of electronic systems, engine systems and chassis systems respectively. In the initial state, the number of faulty vehicles to be inspected in the three stations is special maintenance station A: 5 vehicles, special maintenance station B: 2 vehicles, special maintenance station C: 8 vehicles. After a faulty vehicle completes the inspection of a troubleshooting group, the system automatically obtains the latest number of faulty vehicles to be inspected, and finds that there are 4 special maintenance stations A, 3 special maintenance stations B, and 6 special maintenance stations C. At this time, the system will adjust the order of the inspection groups that have not completed the inspection according to the new data, and adjust the inspection group corresponding to special maintenance station B to a front position, because special maintenance station B currently has the least vehicles to be inspected. At the same time, the AI ​​diagnosis model will update the question sequence according to the adjusted order, and guide the maintenance personnel to prioritize the troubleshooting related to special maintenance station B.

[0128] Through this dynamic adjustment, the solution of the present invention can effectively avoid the situation where some maintenance stations are overstocked while other stations are idle, thereby improving the resource utilization rate of the entire maintenance center. Compared with the traditional fixed troubleshooting sequence, this dynamic adjustment mechanism can more flexibly respond to changes in the actual maintenance process, reduce the waiting time of faulty vehicles at certain stations, and thus significantly shorten the overall maintenance cycle.

[0129] In addition, the solution of the present invention not only optimizes the troubleshooting order by combining real-time data analysis with the AI ​​diagnostic model, but also guides the maintenance personnel to conduct precise troubleshooting through intelligent questions and answers, further improving the accuracy and efficiency of fault diagnosis. This method of combining artificial intelligence with dynamic scheduling represents an innovative application in the field of vehicle fault maintenance, which can significantly improve the quality and efficiency of maintenance services and bring new technological breakthroughs to the vehicle maintenance industry.

[0130] In some embodiments, the specific steps in step S3A2 include:

[0131] S3A21. Arrange the unfinished inspection groups in the second guided inspection table in ascending order according to the number of faulty vehicles to be inspected at the corresponding special maintenance stations to update the second guided inspection table.

[0132] This sorting method of the present embodiment helps to guide the maintenance personnel to transfer the faulty vehicles to the special maintenance stations with fewer faulty vehicles to be checked, thereby balancing the workload of each maintenance station and improving the overall troubleshooting efficiency. The scheme solves the problem of unbalanced loads at special maintenance stations by dynamically adjusting the troubleshooting order. Specifically, it first obtains the number of faulty vehicles to be checked at each special maintenance station, and then, after completing a troubleshooting group, reorders the unfinished troubleshooting groups according to the latest number of faulty vehicles to be checked. This method can respond to the working conditions of the maintenance stations in real time and assign troubleshooting tasks to relatively idle stations in priority, thereby reducing the waiting time of faulty vehicles at certain stations and improving the working efficiency of the entire maintenance system. At the same time, this dynamic adjustment mechanism can also adapt to various changes that may occur during the maintenance process, such as some stations suddenly becoming busy or idle, ensuring the flexibility and adaptability of the troubleshooting process.

[0133] In practical applications, the sorting method of the present invention cooperates with the aforementioned method of dividing the inspection group. The division of the inspection group provides a basis for the task allocation of different special maintenance stations, and the sorting method of the present invention further optimizes the execution order of these tasks. This combination can not only improve the work efficiency of a single maintenance station, but also balance the workload of the entire maintenance system.

[0134] In order to better illustrate the sorting method of the present invention, some specific parameters and value ranges can be introduced. For example, we can set a threshold value. When the number of faulty vehicles to be checked at a certain special maintenance station exceeds this threshold value, the system will trigger re-sorting. This threshold value can be dynamically adjusted according to the actual situation, such as being set to 1.5 times the average number of faulty vehicles to be checked. In addition, we can also set a weight coefficient for each special maintenance station to reflect its processing capacity or importance, and multiply the number of faulty vehicles to be checked by this weight coefficient when sorting, so as to achieve more flexible task allocation.

[0135] In some embodiments, the specific steps in step S3 include:

[0136] S3B1. Obtain the average working hours required for each investigation group to be carried out on the corresponding special maintenance station and use it as the special working hours corresponding to each investigation group;

[0137] S3B2. Count the remaining special working hours of all the inspection groups that have not completed the inspection in the second guided inspection table corresponding to the same batch of faulty vehicles (the remaining special working hours refer to the time that the inspection group needs to spend to complete the inspection, and the remaining special working hours = the special working hours corresponding to the inspection group - the time spent in the inspection process) and use them as the current remaining working hours corresponding to the same batch of faulty vehicles; the same batch of faulty vehicles consists of multiple faulty vehicles with the same fault type, and the total number of faulty vehicles in the same batch is the same as the total number of special maintenance stations, and each faulty vehicle in the same batch uses each special maintenance station as the starting maintenance station;

[0138] S3B3. Compare the current remaining working hours corresponding to each faulty vehicle of the same batch, and when the current remaining working hours corresponding to any faulty vehicle of the same batch are different from the current remaining working hours corresponding to another faulty vehicle of the same batch, adjust the order of the unfinished inspection group in the second guide inspection table corresponding to the faulty vehicle of the same batch with the largest current remaining working hours to update the second guide inspection table corresponding to the faulty vehicle of the same batch with the largest current remaining working hours;

[0139] S3B4. Update the questioning sequence corresponding to the faulty vehicle of the same batch with the largest remaining working hours according to the updated second guided troubleshooting table.

[0140] In actual application, the time required for each inspection team to complete the inspection is not always the same. For example, it takes 1 hour to inspect an engine fault, while it takes 10 minutes to inspect a tire. This difference in special working hours will directly affect the workload of each special maintenance station, which may cause some stations to be idle while other stations are overloaded. This method is particularly suitable for the maintenance service of small batches of faulty vehicles.

[0141] Reference Figure 5For example, there are 3 special maintenance stations, and there are 3 faulty vehicles from the same batch, namely: faulty vehicle a from the same batch, faulty vehicle b from the same batch, and faulty vehicle c from the same batch.

[0142] The order of the investigation groups in the second guide investigation table corresponding to the faulty vehicle a of the same batch is: investigation group A, investigation group B and investigation group C;

[0143] The order of the investigation groups in the second guide investigation table corresponding to the faulty vehicle b of the same batch is: investigation group B, investigation group C and investigation group A;

[0144] The order of the investigation groups in the second guided investigation table corresponding to the faulty vehicle c in the same batch is: investigation group C, investigation group A and investigation group B.

[0145] Among them, the time required for investigation group A to complete the investigation accounts for 1, the time required for investigation group B to complete the investigation accounts for 3, and the time required for investigation group C to complete the investigation accounts for 1.

[0146] After 2 percentages of time, the situation is as follows:

[0147] The investigation group A in the second guided investigation table corresponding to the faulty vehicle a of the same batch has completed the investigation, but because the faulty vehicle b of the same batch occupies the special maintenance station corresponding to the investigation group B, the investigation group B in the second guided investigation table corresponding to the faulty vehicle a of the same batch is in a waiting state, so the investigation group B in the second guided investigation table corresponding to the faulty vehicle a of the same batch still has 3 proportions of time left. At this time, the order of the investigation groups that have not completed the investigation in the second guided investigation table corresponding to the faulty vehicle a of the same batch is: investigation group B (3 proportions of time left) and investigation group C (1 proportion of time left); the corresponding current remaining working hours are 3+1=4, that is, 4 proportions of time.

[0148] Similarly, the order of the inspection groups that have not completed the inspection in the second guided inspection table corresponding to the faulty vehicle b in the same batch is: inspection group B (1 proportion of time remaining), inspection group C (1 proportion of time remaining) and inspection group A (1 proportion of time remaining); the corresponding current remaining working hours are 1+1+1=3, which is 3 proportions of time.

[0149] Similarly, the investigation groups C and A in the second guided investigation table corresponding to the faulty car c in the same batch have completed the investigation. Similarly, because the faulty car b in the same batch occupies the special maintenance station corresponding to the investigation group B, the investigation group B in the second guided investigation table corresponding to the faulty car c in the same batch enters the waiting investigation state. At this time, the order of the investigation groups that have not completed the investigation in the second guided investigation table corresponding to the faulty car c in the same batch is: Investigation group B (remaining 3 proportions of time); the corresponding current remaining working hours are 3, that is, 3 proportions of time.

[0150] It should be noted that "time proportion" is a dimensionless parameter, while "current remaining working hours", "proportion of time" and "special working hours" are dimensional parameters. "Remaining working hours" and "proportion of time" express specific time in time units. Taking 1 time proportion equal to 5 minutes as an example, the current remaining working hours are 4 time proportions, which is equal to 4*5=20 minutes; similarly, the remaining working hours are 2 time proportions, which is equal to 2*5=10 minutes; similarly, 1 proportion of time is 5 minutes.

[0151] For the faulty vehicle a from the same batch, if the maintenance personnel are guided to conduct the inspection according to the second guided inspection table before the update, the special maintenance station corresponding to the inspection group C is not occupied at this time, but the faulty vehicle a from the same batch still needs to wait for the inspection group B of the faulty vehicle b from the same batch and its own inspection group B to complete the inspection before conducting the inspection of its own inspection group C. Obviously, this may extend the maintenance cycle of the faulty vehicle a from the same batch. At the same time, the special maintenance station corresponding to the inspection group C is idle, while the special maintenance station corresponding to the inspection group B is in a backlog state.

[0152] Therefore, this embodiment adjusts the order of the inspection groups that have not completed the inspection in the second guided inspection table corresponding to the same batch of faulty vehicles with the largest remaining working hours, so as to update the second guided inspection table corresponding to the same batch of faulty vehicles with the largest remaining working hours, thereby updating the question order and guiding the maintenance personnel to use special maintenance stations with lower workload more efficiently, which is conducive to avoiding the problem of uneven load on the station and achieving better resource allocation.

[0153] It should be noted that obtaining special working hours can be achieved in a variety of ways. For example, the historical data statistics method can be used to analyze the actual working time of each inspection group at the corresponding special maintenance station in the past period of time (such as the past 3 months), and calculate the average value as the special working hours. Another method is the expert evaluation method, in which experienced maintenance experts give the estimated working hours of each inspection group based on the complexity and difficulty of the inspection project. The real-time monitoring method can also be used to record the actual time consumed during each inspection process and dynamically update the special working hours.

[0154] In some embodiments, the specific steps in step S3B3 include:

[0155] S3B31. Advance the order of the inspection group that has not completed the inspection and has the shortest remaining special working time in the second guided inspection table corresponding to the same batch of faulty vehicles with the largest current remaining working time.

[0156] In this embodiment, in actual application, the sorting of the inspection groups that have not completed the inspection and have the shortest remaining special working time can be selectively advanced based on the actual usage of each special maintenance workstation, thereby avoiding the problem of these inspection groups with shorter remaining special working time extending their maintenance cycle and causing unbalanced workstation load due to them being sorted behind the inspection groups with longer remaining special working time.

[0157] Specifically, for example, the order of the unfinished inspection groups in the second guided inspection table corresponding to the faulty vehicle a in the same batch is adjusted to: inspection group C and inspection group B.

[0158] After obtaining the remaining special working hours of each inspection group and calculating the current remaining working hours of the same batch of faulty vehicles, this embodiment optimizes the inspection order by advancing the inspection group with the shortest remaining special working hours. This optimization not only takes into account the inspection efficiency of a single faulty vehicle, but also optimizes the efficiency of multi-vehicle collaboration by comparing the remaining working hours of the same batch of faulty vehicles.

[0159] Please refer to Figure 6 , Figure 6 A vehicle fault troubleshooting device based on an AI diagnostic model in some embodiments of the present invention is applied to a server of a vehicle fault maintenance system. The vehicle fault troubleshooting device based on the AI ​​diagnostic model is integrated in a back-end control device in the form of a computer program. The vehicle fault maintenance system includes a plurality of special maintenance stations, and the plurality of special maintenance stations are used to perform different troubleshooting items on a faulty vehicle.

[0160] The vehicle fault troubleshooting device based on the AI ​​diagnostic model includes:

[0161] The sorting module 100 is used to determine all possible fault causes that may cause the corresponding fault from a preset database according to the fault type of the faulty vehicle, and then arrange each fault cause as a separate troubleshooting item in an orderly manner into a first guided troubleshooting table;

[0162] The adjustment module 200 is used for, after the faulty vehicle enters the special maintenance station for the first time, taking the special maintenance station where the faulty vehicle is located for the first time as the starting maintenance station, and adjusting the order of the troubleshooting items in the first guide troubleshooting table according to the troubleshooting items corresponding to the starting maintenance station so that the troubleshooting items ranked first can be checked at the starting maintenance station, and at the same time taking the adjusted first guide troubleshooting table as the second guide troubleshooting table associated with the faulty vehicle;

[0163] The control module 300 is used to control the preset AI diagnostic model to obtain a question sequence according to the second guide troubleshooting table so that the AI ​​diagnostic model can interact with the maintenance personnel in question sequence to guide the maintenance personnel to troubleshoot the corresponding faulty vehicle.

[0164] In some embodiments, the adjustment module 200 is executed when, after the faulty vehicle enters the special maintenance station for the first time, the special maintenance station where the faulty vehicle is first located is used as the starting maintenance station, and the order of the troubleshooting items in the first guided troubleshooting table is adjusted according to the troubleshooting items corresponding to the starting maintenance station:

[0165] S21. When adjusting the order of the check items in the first guide check list according to the check items corresponding to the starting maintenance station, execute:

[0166] S211. According to the inspection items of each special maintenance station, all inspection items that can be handled by each special maintenance station are selected from all inspection items and used as the inspection group corresponding to each special maintenance station;

[0167] S212. Adjust the order of the check items in the first boot check table based on the check group.

[0168] In some embodiments, the adjustment module 200 is used to adjust the order of the check items in the first boot check list based on the check group when performing:

[0169] S2121. Multiple faulty vehicles with the same fault type are regarded as faulty vehicles in the same batch; the total number of faulty vehicles in the same batch is the same as the total number of special maintenance stations, and each faulty vehicle in the same batch uses each special maintenance station as the starting maintenance station;

[0170] S2122. Adjust the first guide troubleshooting table corresponding to each faulty vehicle of the same batch so that the troubleshooting groups in the same sequence in all the obtained second guide troubleshooting tables are different.

[0171] In some embodiments, the control module 300 is used to control the preset AI diagnostic model to obtain the question sequence according to the second guidance checklist when executing:

[0172] S3A1. Get the number of faulty vehicles to be checked at each special maintenance station; the number of faulty vehicles to be checked refers to the number of faulty vehicles waiting for the corresponding special maintenance station to perform troubleshooting;

[0173] S3A2. According to the number of faulty vehicles to be checked at each special maintenance station, adjust the order of the unfinished inspection group in the second guide inspection table to update the second guide inspection table;

[0174] S3A3. Update the question sequence according to the updated second guidance checklist.

[0175] In some embodiments, the control module 300 is used to adjust the order of the unchecked check groups in the second guide check list according to the number of faulty vehicles to be checked at each special maintenance station to update the second guide check list, and executes:

[0176] S3A21. Arrange the unfinished inspection groups in the second guided inspection table in ascending order according to the number of faulty vehicles to be inspected at the corresponding special maintenance stations to update the second guided inspection table.

[0177] In some embodiments, the control module 300 is used to control the preset AI diagnostic model to obtain the question sequence according to the second guidance checklist when executing:

[0178] S3B1. Obtain the average working hours required for each investigation group to be carried out on the corresponding special maintenance station and use it as the special working hours corresponding to each investigation group;

[0179] S3B2. Statistics of the remaining special working hours of all the investigation groups in the second guide investigation table corresponding to the same batch of faulty vehicles that have not been completed and as the current remaining working hours corresponding to the same batch of faulty vehicles; the same batch of faulty vehicles consists of multiple faulty vehicles with the same fault type, and the total number of faulty vehicles in the same batch is the same as the total number of special maintenance stations, and each faulty vehicle in the same batch is respectively used as the starting maintenance station for each special maintenance station;

[0180] S3B3. Compare the current remaining working hours corresponding to each faulty vehicle of the same batch, and when the current remaining working hours corresponding to any faulty vehicle of the same batch are different from the current remaining working hours corresponding to another faulty vehicle of the same batch, adjust the order of the unfinished inspection group in the second guide inspection table corresponding to the faulty vehicle of the same batch with the largest current remaining working hours to update the second guide inspection table corresponding to the faulty vehicle of the same batch with the largest current remaining working hours;

[0181] S3B4. Update the questioning sequence corresponding to the faulty vehicle of the same batch with the largest remaining working hours according to the updated second guided troubleshooting table.

[0182] In some embodiments, the control module 300 is used to compare the current remaining working hours corresponding to each faulty vehicle of the same batch, and when the current remaining working hours corresponding to any faulty vehicle of the same batch is different from the current remaining working hours corresponding to another faulty vehicle of the same batch, the order of the unfinished inspection groups in the second guide inspection table corresponding to the faulty vehicle of the same batch with the largest current remaining working hours is adjusted to update the second guide inspection table corresponding to the faulty vehicle of the same batch with the largest current remaining working hours.

[0183] S3B31. Advance the order of the inspection group that has not completed the inspection and has the shortest remaining special working time in the second guided inspection table corresponding to the same batch of faulty vehicles with the largest current remaining working time.

[0184] Please refer to Figure 7 , Figure 7The present invention provides a structural diagram of an electronic device provided by an embodiment of the present invention. The present invention provides an electronic device 13, including: a processor 1301 and a memory 1302. The processor 1301 and the memory 1302 are interconnected and communicate with each other through a communication bus 1303 and / or other forms of connection mechanisms (not shown). The memory 1302 stores computer-readable instructions executable by the processor 1301. When the electronic device is running, the processor 1301 executes the computer-readable instructions to execute the vehicle fault troubleshooting method based on the AI ​​diagnostic model in any optional implementation of the above embodiment to achieve the following functions: according to the fault type of the faulty vehicle, determine from a preset database the possible causes of the fault. After all the fault causes of the corresponding fault are checked, each fault cause is taken as a separate troubleshooting item and arranged in order into a first guided troubleshooting table; after the faulty vehicle enters the special maintenance station for the first time, the special maintenance station where the faulty vehicle is first located is taken as the starting maintenance station, and the order of the troubleshooting items in the first guided troubleshooting table is adjusted according to the troubleshooting items corresponding to the starting maintenance station so that the troubleshooting item ranked first can be performed at the starting maintenance station, and the adjusted first guided troubleshooting table is used as the second guided troubleshooting table associated with the faulty vehicle; the preset AI diagnostic model is controlled to obtain the question sequence according to the second guided troubleshooting table so that the AI ​​diagnostic model interacts with the maintenance personnel through question-and-answer interaction in the question sequence, thereby guiding the maintenance personnel to troubleshoot the corresponding faulty vehicle.

[0185] An embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the vehicle fault troubleshooting method based on an AI diagnostic model in any optional implementation of the above-mentioned embodiment is executed to achieve the following functions: according to the fault type of the faulty vehicle, after all fault causes that may cause the corresponding fault are determined from a preset database, each fault cause is taken as a separate troubleshooting item and arranged in order into a first guide troubleshooting table; after the faulty vehicle enters a special maintenance station for the first time, the special maintenance station where the faulty vehicle is first located is taken as the starting maintenance station, and the order of the troubleshooting items in the first guide troubleshooting table is adjusted according to the troubleshooting items corresponding to the starting maintenance station so that the troubleshooting item ranked first can be performed at the starting maintenance station, and the adjusted first guide troubleshooting table is used as a second guide troubleshooting table associated with the faulty vehicle; the preset AI diagnostic model is controlled to obtain a question order according to the second guide troubleshooting table so that the AI ​​diagnostic model interacts with the maintenance personnel through question-answering in the question order, thereby guiding the maintenance personnel to troubleshoot the corresponding faulty vehicle.

[0186] Among them, the computer-readable storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable red-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.

[0187] In the embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, and the indirect coupling or communication connection of devices or units can be electrical, mechanical or other forms.

[0188] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0189] Furthermore, the functional modules in the various embodiments of the present invention may be integrated together to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

[0190] In this document, relational terms such as first and second, etc. are used merely to distinguish one entity or operation from another entity or operation, but do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0191] The above description is only an embodiment of the present invention and is not intended to limit the protection scope of the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A vehicle fault troubleshooting method based on an AI diagnostic model, applied to a server of a vehicle fault maintenance system, characterized in that: The vehicle fault repair system includes a plurality of special repair stations, and the plurality of special repair stations are used to perform different troubleshooting items on the faulty vehicle; The vehicle fault troubleshooting method based on the AI ​​diagnostic model includes the following steps: S1. According to the fault type of the faulty vehicle, after determining all the fault causes that may cause the corresponding fault from the preset database, each of the fault causes is treated as a separate troubleshooting item and arranged in order into a first guide troubleshooting table; S2. After the faulty vehicle enters the special maintenance station for the first time, the special maintenance station where the faulty vehicle is located for the first time is used as the starting maintenance station, and the order of the troubleshooting items in the first guidance troubleshooting table is adjusted according to the troubleshooting items corresponding to the starting maintenance station so that the troubleshooting item ranked first can be checked at the starting maintenance station, and the adjusted first guidance troubleshooting table is used as the second guidance troubleshooting table associated with the faulty vehicle; S3. Control the preset AI diagnostic model to obtain the question sequence according to the second guide troubleshooting table so that the AI ​​diagnostic model can interact with the maintenance personnel in the question sequence to guide the maintenance personnel to troubleshoot the corresponding faulty vehicle; The specific steps in step S2 include: S21. When adjusting the order of the check items in the first guide check table according to the check items corresponding to the starting maintenance station, execute: S211. According to the inspection items of each of the special maintenance stations, all the inspection items that can be handled by each of the special maintenance stations are selected from all the inspection items and used as the inspection group corresponding to each of the special maintenance stations; S212. Adjust the order of the screening items in the first guide screening table based on the screening group; The specific steps in step S212 include: S2121. Multiple faulty vehicles with the same fault type are regarded as faulty vehicles in the same batch; the total number of faulty vehicles in the same batch is the same as the total number of special maintenance stations, and each faulty vehicle in the same batch uses each special maintenance station as the starting maintenance station; S2122. Adjust the first guide checklist corresponding to each faulty vehicle of the same batch so that all checklist groups in the same sequence in the second guide checklist obtained are different; The specific steps in step S3 include: S3A1. Get the number of faulty vehicles to be checked at each of the special maintenance stations; the number of faulty vehicles to be checked refers to the number of faulty vehicles waiting for the corresponding special maintenance stations to perform troubleshooting; S3A2. According to the number of faulty vehicles to be checked at each of the special maintenance stations, adjust the order of the second guide investigation group in the unfinished investigation table to update the second guide investigation table; S3A3. Update the question sequence according to the updated second guidance checklist.

2. The vehicle fault troubleshooting method based on the AI ​​diagnostic model according to claim 1 is characterized in that: The specific steps in step S3A2 include: S3A21. Arrange the unfinished inspection groups in the second guided inspection table in ascending order according to the number of faulty vehicles to be inspected at the corresponding special maintenance stations to update the second guided inspection table.

3. The vehicle fault troubleshooting method based on the AI ​​diagnostic model according to claim 1 is characterized in that: The specific steps in step S3 include: S3B1. Obtain the average man-hours required for each of the inspection groups to be performed on the corresponding special maintenance stations and serve as the special man-hours corresponding to each of the inspection groups; S3B2. Count the remaining special working hours of all the investigation groups that have not completed the investigation in the second guided investigation table corresponding to the same batch of faulty vehicles and use them as the current remaining working hours corresponding to the same batch of faulty vehicles; the same batch of faulty vehicles consists of multiple faulty vehicles with the same fault type, and the total number of faulty vehicles in the same batch is the same as the total number of special maintenance stations, and each of the faulty vehicles in the same batch uses each of the special maintenance stations as the starting maintenance station; S3B3. Compare the current remaining working hours corresponding to each of the same batch of faulty vehicles, and when the current remaining working hours corresponding to any of the same batch of faulty vehicles are different from the current remaining working hours corresponding to another of the same batch of faulty vehicles, adjust the order of the unfinished inspection groups in the second guide inspection table corresponding to the same batch of faulty vehicles with the largest current remaining working hours to update the second guide inspection table corresponding to the same batch of faulty vehicles with the largest current remaining working hours; S3B4. Update the questioning sequence corresponding to the faulty vehicle of the same batch with the largest current remaining working hours according to the updated second guided troubleshooting table.

4. The vehicle fault troubleshooting method based on the AI ​​diagnostic model according to claim 3 is characterized in that: The specific steps in step S3B3 include: S3B31. Advance the order of the inspection group in the second guided inspection table corresponding to the same batch of faulty vehicles with the largest current remaining working hours and which has not completed the inspection and has the shortest remaining special working hours.

5. A vehicle fault troubleshooting device based on an AI diagnostic model, applied to a server of a vehicle fault repair system, characterized in that: The vehicle fault repair system includes a plurality of special repair stations, and the plurality of special repair stations are used to perform different troubleshooting items on the faulty vehicle; The vehicle fault troubleshooting device based on the AI ​​diagnostic model includes: A sorting module, configured to determine all possible fault causes that may cause the corresponding fault from a preset database according to the fault type of the faulty vehicle, and then arrange each of the fault causes as a separate troubleshooting item and arrange them in order into a first guided troubleshooting table; an adjustment module, for, after the faulty vehicle enters the special maintenance station for the first time, taking the special maintenance station where the faulty vehicle is located for the first time as the starting maintenance station, and adjusting the order of the troubleshooting items in the first guide troubleshooting table according to the troubleshooting items corresponding to the starting maintenance station so that the troubleshooting item ranked first can be checked at the starting maintenance station, and taking the adjusted first guide troubleshooting table as the second guide troubleshooting table associated with the faulty vehicle; a control module, configured to control a preset AI diagnostic model to obtain a question sequence according to the second guide troubleshooting table so that the AI ​​diagnostic model performs question-answering interaction with the maintenance personnel according to the question sequence, thereby guiding the maintenance personnel to troubleshoot the corresponding faulty vehicle; The adjustment module is executed when the faulty vehicle enters the special maintenance station for the first time, takes the special maintenance station where the faulty vehicle is first located as the starting maintenance station, and adjusts the order of the troubleshooting items in the first guided troubleshooting table according to the troubleshooting items corresponding to the starting maintenance station: S21. When adjusting the order of the check items in the first guide check list according to the check items corresponding to the starting maintenance station, execute: S211. According to the inspection items of each special maintenance station, all inspection items that can be handled by each special maintenance station are selected from all inspection items and used as the inspection group corresponding to each special maintenance station; S212. Adjust the order of the check items in the first guide check table based on the check group; The adjustment module is executed when it is used to adjust the order of the check items in the first boot check list based on the check group: S2121. Multiple faulty vehicles with the same fault type are regarded as faulty vehicles in the same batch; the total number of faulty vehicles in the same batch is the same as the total number of special maintenance stations, and each faulty vehicle in the same batch uses each special maintenance station as the starting maintenance station; S2122. Adjust the first guide checklist corresponding to each faulty vehicle of the same batch so that all checklist groups in the same sequence in the obtained second guide checklist are different; The control module is used to control the preset AI diagnosis model to obtain the question sequence according to the second guidance checklist when executing: S3A1. Get the number of faulty vehicles to be checked at each special maintenance station; the number of faulty vehicles to be checked refers to the number of faulty vehicles waiting for the corresponding special maintenance station to perform troubleshooting; S3A2. According to the number of faulty vehicles to be checked at each special maintenance station, adjust the order of the unfinished inspection group in the second guide inspection table to update the second guide inspection table; S3A3. Update the question sequence according to the updated second guidance checklist.

6. An electronic device, characterized in that: It includes a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the vehicle fault troubleshooting method based on the AI ​​diagnostic model as described in any one of claims 1 to 4 are executed.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, the steps of the vehicle fault troubleshooting method based on the AI ​​diagnostic model as described in any one of claims 1 to 4 are performed.

Images