Automobile intelligent diagnosis method and system and electronic equipment

Abstract

The invention discloses an automobile intelligent diagnosis method and system and electronic equipment, and belongs to the technical field of automobiles. The method comprises the steps that fault information of a target automobile is acquired; the fault information is input into an automatic diagnosis system for fault diagnosis, a first fault reason of the target vehicle is output, and the automatic diagnosis system comprises a plurality of fault diagnosis modules; according to the fault feature description information of the target vehicle, a second fault reason of the target vehicle is output through an intelligent diagnosis large model, and the intelligent diagnosis large model is constructed based on historical maintenance big data and a decision tree algorithm; on the basis that the first fault reason is different from the second fault reason, determining one of the first fault reason and the second fault reason as a final fault reason through a big data decision model; according to the fault maintenance knowledge base, a maintenance scheme matched with the final fault reason is obtained, the fault reason of the target vehicle can be rapidly positioned, and an accurate and professional maintenance method is given.

Description

Technical Field

[0001] The present application belongs to the field of automobile technology, and specifically relates to an automobile intelligent diagnosis method, an automobile intelligent diagnosis system and an electronic device. Background Art

[0002] With the rapid development of the automobile industry and the continuous increase in the number of cars in use, vehicle failures have become an increasingly difficult problem for OEMs. Today, automobile fault diagnosis mainly relies on traditional diagnostic equipment, which can only output a large amount of raw data or codes, requiring technicians to have high professional qualities and rich experience to accurately interpret them. This undoubtedly increases the complexity and uncertainty of diagnosis. In addition, the professionalism of after-sales personnel is limited and their maintenance experience is insufficient, resulting in the inability to quickly locate the cause of the fault and provide accurate and professional maintenance solutions during after-sales maintenance. Summary of the invention

[0003] The purpose of the embodiments of the present application is to provide an intelligent automobile diagnosis method, system and electronic equipment to solve the technical problem that after-sales personnel are unable to quickly locate the cause of the fault and provide accurate and professional repair solutions during after-sales maintenance.

[0004] In order to solve the above technical problems, this application is implemented as follows: In a first aspect, an embodiment of the present application provides an automobile intelligent diagnosis method, the method comprising: Obtain the fault information of the target vehicle, including the fault code and fault snapshot information; Inputting the fault information into an automatic diagnosis system for fault diagnosis and outputting a first fault cause of the target vehicle, wherein the automatic diagnosis system includes a plurality of fault diagnosis modules; According to the fault feature description information of the target vehicle, the second fault cause of the target vehicle is output through the intelligent diagnosis big model, wherein the intelligent diagnosis big model is constructed based on historical maintenance big data and decision tree algorithm; In the case where the first fault cause is different from the second fault cause, determining one of the first fault cause and the second fault cause as the final fault cause through the big data decision model; According to the fault repair knowledge base, obtain the repair plan that matches the final fault cause.

[0005] Optionally, the steps of inputting the fault information into the automatic diagnosis system for fault diagnosis and outputting the first fault cause of the target vehicle specifically include: in response to the fault code, triggering the automatic diagnosis system to enter the analysis state; based on the preset fault-free information, simulating the fault-free operation state of the target vehicle through the automatic diagnosis system; in response to the fault snapshot information, determining the diagnosis information through multiple fault diagnosis modules; and determining the first fault cause based on the diagnosis information.

[0006] Optionally, based on the fact that the first fault cause is different from the second fault cause, the step of determining one of the first fault cause and the second fault cause as the final fault cause through the big data decision model specifically includes: performing probability analysis on the first fault cause and the second fault cause through the big data decision model based on historical maintenance big data, and generating probability analysis results; performing expert decision on the first fault cause and the second fault cause based on the expert system in the big data decision model, and generating expert decision results; and determining one of the first fault cause and the second fault cause as the final fault cause based on the probability analysis results and the expert decision results.

[0007] Optionally, based on the expert system in the big data decision model, an expert decision is made on the first fault cause and the second fault cause, and the step of outputting the expert decision result specifically includes: based on the expert knowledge base and reasoning algorithm in the expert system, reasoning analysis is performed on the first fault cause and the second fault cause to obtain the expert decision result.

[0008] Optionally, after the step of performing reasoning analysis on the first fault cause and the second fault cause based on the expert knowledge base and reasoning algorithm in the expert system to obtain the expert decision result, it also includes: generating expert maintenance suggestions matching the expert decision result based on the expert knowledge base.

[0009] Optionally, the step of determining, based on the probability analysis results and the expert decision results, one of the first fault cause and the second fault cause as the final fault cause specifically includes: performing preliminary weight allocation on the probability analysis results and the expert decision results to generate preliminary weight allocation results; and determining, based on the preliminary weight allocation results, one of the first fault cause and the second fault cause as the final fault cause.

[0010] Optionally, based on the fault feature description information of the target vehicle, the second fault cause of the target vehicle is output through the intelligent diagnosis big model, wherein, after the step of constructing the intelligent diagnosis big model based on historical maintenance big data and decision tree algorithm, the following steps are included: determining whether the first fault cause is the same as the second fault cause; based on the situation that the first fault cause is the same as the second fault cause, inputting the first fault cause or the second fault cause into the fault maintenance knowledge base, and obtaining a maintenance plan that matches the first fault cause or the second fault cause.

[0011] Optionally, after the step of obtaining a maintenance solution matching the final fault cause according to the fault maintenance knowledge base, the following steps are included: obtaining after-sales feedback information of the target vehicle and updating the intelligent diagnosis big model.

[0012] In a second aspect, an embodiment of the present application provides an automobile intelligent diagnosis system, which diagnoses automobile faults according to the automobile intelligent diagnosis method of the first aspect, including: An information acquisition module is used to acquire fault information of a target vehicle, the fault information including fault code and fault snapshot information; An automatic diagnosis system module, inputting fault information into the automatic diagnosis system for fault diagnosis, and outputting a first fault cause of the target vehicle, wherein the automatic diagnosis system includes a plurality of fault diagnosis modules; An intelligent diagnosis big model module is used to output the second fault cause of the target vehicle through the intelligent diagnosis big model according to the fault feature description information of the target vehicle, wherein the intelligent diagnosis big model is constructed based on historical maintenance big data and decision tree algorithm; A big data decision model module, used for determining, by means of a big data decision model, one of the first fault cause and the second fault cause as a final fault cause when the first fault cause is different from the second fault cause; The fault repair knowledge base module is used to obtain a repair method that matches the cause of the fault based on the fault repair knowledge base.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor, wherein the program or instruction, when executed by the processor, implements the intelligent automobile diagnosis method of the first aspect.

[0014] In an embodiment of the present application, firstly, the fault information of the target vehicle is obtained, the fault information includes a fault code and a fault snapshot information, the fault information is input into the automatic diagnosis system for fault diagnosis, and the first fault cause of the target vehicle is output, wherein the automatic diagnosis system includes a plurality of fault diagnosis modules; then, according to the fault feature description information of the target vehicle, the second fault cause of the target vehicle is output through the intelligent diagnosis big model, wherein the intelligent diagnosis big model is constructed based on historical maintenance big data and a decision tree algorithm; based on the fact that the first fault cause is different from the second fault cause, one of the first fault cause and the second fault cause is determined as the final fault cause through the big data decision model; then, according to the fault maintenance knowledge base, a maintenance plan matching the final fault cause is obtained; that is, the fault diagnosis of the target vehicle is performed through the automatic diagnosis system and the intelligent diagnosis big model, and the fault cause can be accurately located. When the fault causes obtained by the two are different, the final fault cause can be determined through the big data decision module, thereby improving the diagnostic accuracy of the fault cause. Through the fault maintenance knowledge base, a maintenance plan matching the fault cause can be obtained, thereby solving the technical problem that after-sales personnel cannot quickly locate the fault cause and provide accurate and professional maintenance plans during after-sales maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flowchart of an automobile intelligent diagnosis method provided by some embodiments of the present application.

[0016] Figure 2 It is a logical schematic diagram of an automobile intelligent diagnosis method provided by some embodiments of the present application.

[0017] Figure 3 is a schematic diagram of an automatic diagnosis system provided by some embodiments of the present application.

[0018] Figure 4 is a schematic diagram of another automatic diagnosis system provided by some embodiments of the present application.

[0019] Figure 5 It is a structural schematic diagram of an automobile intelligent diagnosis system provided by some embodiments of the present application.

[0020] Figure 6 It is a structural schematic diagram of an electronic device provided in some embodiments of the present application. DETAILED DESCRIPTION

[0021] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0022] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here. In addition, the "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally represents that the objects associated with each other are in an "or" relationship.

[0023] The automobile intelligent diagnosis method provided by the embodiment of the present application is described in detail below through specific embodiments and their application scenarios in conjunction with the accompanying drawings.

[0024] It is worth noting that the intelligent automobile fault diagnosis method disclosed in this application has the function of quickly locating the cause of the fault and providing accurate repair plans when a vehicle fault occurs, so that after-sales personnel can efficiently perform vehicle inspection and repair, thereby improving repair efficiency and accuracy.

[0025] like Figure 1 and Figure 2 As shown, the main flow chart and logic chart of some embodiments of the automobile intelligent diagnosis method provided by the embodiments of the present application include the following steps S101 to S105, wherein: S101, acquiring fault information of a target vehicle, where the fault information includes a fault code and fault snapshot information.

[0026] In some embodiments of the present application, the automatic diagnosis system may be arranged on a diagnostic instrument, and connected to the target vehicle through an on-board diagnostic system (OBD) to read fault information, including fault codes and fault snapshot information. The automatic diagnosis system may also be deployed in the cloud, and the fault information of the target vehicle may be uploaded to the cloud through a telematics box (TBOX), and the automatic diagnosis system deployed in the diagnostic instrument or the cloud may analyze the fault information.

[0027] In this embodiment, fault information of the target vehicle is acquired, the fault information including fault code and fault snapshot information, which is used by the automatic diagnosis system to perform fault diagnosis and output the first fault cause of the target vehicle.

[0028] It is worth mentioning that the fault code is a specific code automatically generated by the built-in OBD system of the target vehicle when an abnormality or potential problem is detected. The fault snapshot information includes the Controller Area Network (CAN) bus data within a preset time period when the vehicle records the fault, and the ambient temperature, humidity, positioning and other information identified by the vehicle. This information is saved in the form of snapshots to help the automatic diagnosis system to diagnose the fault. In some vehicle models, it is also necessary to collect information from the on-board information system (i.e., the car computer), such as ambient temperature, humidity, positioning and other information. The information collected by the car computer is not included in the CAN bus data and can be used to supplement the fault snapshot information.

[0029] S102, inputting fault information into an automatic diagnosis system for fault diagnosis, and outputting a first fault cause of the target vehicle, wherein the automatic diagnosis system includes a plurality of fault diagnosis modules.

[0030] In some embodiments of the present application, the fault information includes a fault code and a fault snapshot information, and in response to the fault code, the automatic diagnosis system is triggered to enter an analysis state; according to the preset fault-free information, the fault-free running state of the target vehicle is simulated through the automatic diagnosis system; In this embodiment, the automatic diagnosis system triggers the analysis state after receiving the fault code; according to the preset fault-free information, the automatic diagnosis system simulates the fault-free running state of the target vehicle, so that the automatic diagnosis system can analyze the collected fault snapshot information in a normal time sequence; In some embodiments of the present application, the automatic diagnosis system responds to the fault snapshot information, and the diagnosis information can be determined through multiple fault diagnosis modules in the automatic diagnosis system, and the first fault cause can be determined by locating and analyzing the diagnosis information.

[0031] In this embodiment, the automatic diagnosis system includes multiple fault diagnosis modules, and each fault diagnosis module can coordinately operate after the non-fault data is imported. By performing logical judgment on the fault snapshot information imported in time sequence, the fault diagnosis module related to the fault cause will trigger a key signal (the diagnostic information includes the triggered key signal and the triggered key signal time) during the logical judgment process; when the automatic diagnosis system receives the diagnostic information, it can locate and analyze the diagnostic information, thereby determining the first fault cause of the target vehicle; See also Figure 3 , Figure 3 A schematic diagram of an automatic diagnosis system provided in an embodiment of the present application can be used for fault diagnosis of new energy vehicles. The fault diagnosis modules of the automatic diagnosis system mainly include VCU fault diagnosis module, DCDC fault diagnosis module, MCU fault diagnosis module, BMS fault diagnosis module, TBOX fault diagnosis module, IVI fault diagnosis module, ACM fault diagnosis module, AFS fault diagnosis module, AVM fault diagnosis module, BCM fault diagnosis module, BLEM fault diagnosis module, EPS fault diagnosis module, FSCM fault diagnosis module, GW fault diagnosis module, IC fault diagnosis module, IPB fault diagnosis module, IPM fault diagnosis module, MRR fault diagnosis module, PACM fault diagnosis module, PAM fault diagnosis module, PEPS fault diagnosis module, PSDMR fault diagnosis module, RBU fault diagnosis module, RTM fault diagnosis module, SCU fault diagnosis module, SRR fault diagnosis module, SRS fault diagnosis module.

[0032] See also Figure 4 , Figure 4A schematic diagram of another automatic diagnosis system provided in an embodiment of the present application can be used for fault diagnosis of traditional fuel vehicles. The fault diagnosis modules of the automatic diagnosis system mainly include VCU fault diagnosis module, EMS fault diagnosis module, TCU fault diagnosis module, TBOX fault diagnosis module, IVI fault diagnosis module, FSCM fault diagnosis module, ACM fault diagnosis module, AFS fault diagnosis module, AVM fault diagnosis module, BCM fault diagnosis module, BLEM fault diagnosis module, EPS fault diagnosis module, PAM fault diagnosis module, GW fault diagnosis module, IC fault diagnosis module, IPB fault diagnosis module, IPM fault diagnosis module, MRR fault diagnosis module, PACM fault diagnosis module, SRS fault diagnosis module, PEPS fault diagnosis module, PSDMR fault diagnosis module, RBU fault diagnosis module, RTM fault diagnosis module, SCU fault diagnosis module, and SRR fault diagnosis module.

[0033] S103, outputting a second fault cause of the target vehicle through an intelligent diagnosis big model according to the fault feature description information of the target vehicle, wherein the intelligent diagnosis big model is constructed based on historical maintenance big data and a decision tree algorithm; In some embodiments of the present application, when the fault feature description information of the target vehicle is received, the intelligent diagnosis model will quickly start its built-in decision tree algorithm. The algorithm gradually refines and classifies the fault features through a series of carefully designed logical branches and judgment conditions until the second fault cause is found and output. This process not only relies on the historical maintenance big data learned by the model, but also makes full use of the efficiency and accuracy of the decision tree algorithm, and can efficiently obtain a more accurate fault cause.

[0034] In this embodiment, the intelligent diagnosis big model is based on the construction of a decision tree algorithm and historical maintenance big data. It can be to extract characteristic parameters of fault manifestation characteristics in historical maintenance big data to establish nodes; recursively divide each node to generate child nodes; stop dividing until a stopping condition is met, and mark the node as a leaf node. The leaf node represents the cause of the fault. The stopping condition may be that there are no remaining characteristic parameters that can be used for further division; when the fault feature description information is input, the second fault cause can be located based on the logical judgment of the node.

[0035] It is worth noting that the method of inputting fault feature description information into the intelligent diagnosis big model depends on the application scenario, and usually includes the following methods: after-sales personnel can manually input the observed fault feature description directly into the intelligent diagnosis big model through a keyboard, touch screen or other input device; after-sales personnel can also store the fault feature description information in files, and import these files into the intelligent diagnosis big model by uploading files; after-sales personnel can also describe the fault features through voice and realize text conversion in the intelligent diagnosis big model.

[0036] In some embodiments of the present application, after the automatic diagnosis system outputs the first fault cause of the target vehicle and the intelligent diagnosis model outputs the second fault cause of the target vehicle, there will be a determination process to determine whether the first fault cause is the same as the second fault cause; based on the situation where the first fault cause is the same as the second fault cause, the first fault cause or the second fault cause is input into the fault repair knowledge base to obtain a repair plan that matches the first fault cause or the second fault cause.

[0037] In this embodiment, this judgment process can rely on the cloud for judgment. After the automatic diagnosis system and the intelligent diagnosis model determine the cause of the fault, they will be uploaded to the cloud. Through the judgment program pre-established in the cloud, the two fault causes are compared to determine whether they are consistent. This step is very important for ensuring the accuracy and reliability of the fault cause, which helps us to more effectively determine the cause of the fault and obtain matching maintenance solutions in the fault maintenance knowledge base.

[0038] S104, when the first fault cause is different from the second fault cause, determining one of the first fault cause and the second fault cause as the final fault cause through a big data decision model; In some embodiments of the present application, based on historical maintenance big data, a probability analysis is performed on the first fault cause and the second fault cause through a big data decision model to generate a probability analysis result; In this embodiment, a statistics of the first fault cause and the second fault cause is first performed based on the historical maintenance big data, and then a probability analysis is performed to generate a probability analysis result. This probability analysis result calculates the probability of occurrence of the first fault cause and the second fault cause, and analyzes the more likely fault cause between the first fault cause and the second fault cause.

[0039] In some embodiments of the present application, based on the expert system in the big data decision model, an expert decision is made on the first fault cause and the second fault cause to generate an expert decision result, and the expert decision result is mainly obtained by reasoning and analyzing the first fault cause and the second fault cause through the expert knowledge base and reasoning algorithm in the expert system; based on the expert knowledge base, an expert maintenance suggestion matching the expert decision result is generated.

[0040] In this embodiment, when the first fault cause and the second fault cause are analyzed and decided in depth, the expert knowledge base and reasoning algorithm in the expert system are fully utilized; the expert knowledge base is the basis of the expert system, which stores the rich knowledge and experience of experts from various fields. These knowledge and experience are carefully organized and structured, so as to facilitate efficient retrieval and call of the computer system. When the automatic diagnosis system outputs the first fault cause and the intelligent diagnosis large model outputs the second fault cause, the expert system will first extract the expert opinions and historical cases related to the two fault causes from the expert knowledge base; the reasoning algorithm will perform logical reasoning and comprehensive analysis on the first fault cause and the second fault cause based on the extracted expert knowledge and experience. The reasoning algorithm may include a variety of methods such as rule reasoning, case reasoning, model reasoning, etc. These methods can simulate the thinking process of experts, analyze the fault cause layer by layer, so as to reveal the deep-seated reasons and possible development trends behind the fault. The expert system will generate an expert decision result based on these reasonings, which includes selecting the fault cause that is more in line with the expert knowledge from the first fault cause and the second fault cause, and will also generate expert maintenance suggestions matching the expert decision result based on the expert knowledge base.

[0041] It is worth noting that the decision results of the expert system are not absolute, but are the optimal solutions based on the currently available information and expert knowledge. With the continuous addition of new data and knowledge, the decision results of the expert system may also be adjusted and optimized accordingly.

[0042] In some embodiments of the present application, the big data decision model will make a preliminary weight distribution between the probability analysis results and the expert decision results, and determine one of the first fault cause and the second fault cause as the final fault cause based on the preliminary weight distribution results.

[0043] In this embodiment, the probability analysis results and the expert decision results are fused according to the preliminary weight distribution strategy. This weight distribution strategy may be based on a variety of factors, such as the reliability of data, the authority of expert knowledge, the specificity of the fault phenomenon, etc., and through reasonable weight setting, it is ensured that the two results can be properly reflected in the final decision; in this fusion process, advanced algorithms such as weighted average and Bayesian fusion can be used to quantify the probability analysis results and expert decision results, and calculate their respective contributions to the final decision. Finally, according to this preliminary weight distribution result, one of the first fault cause and the second fault cause is determined as the final fault cause. This method not only improves the accuracy and efficiency of fault diagnosis, but also can adapt to the complexity of different fault scenarios.

[0044] S105: Obtain a maintenance plan that matches the final fault cause according to the fault maintenance knowledge base.

[0045] In this embodiment, a fault repair knowledge base can be established in the cloud, including but not limited to maintenance manuals, repair graphic instructions, tool use instructions, vehicle basic knowledge, etc.; a fault classification system can also be established to classify the fault causes according to equipment type, fault phenomenon, etc., for subsequent rapid retrieval; an efficient retrieval mechanism can also be built to ensure that after-sales personnel can quickly find a repair plan that matches the current fault of the target vehicle by entering the fault cause. By establishing a fault repair knowledge base and designing a reasonable classification system, professional repair plans that match the final fault cause can be quickly and accurately obtained, providing strong support for after-sales personnel to quickly handle faults during the maintenance process.

[0046] In some embodiments of the present application, after obtaining a matching maintenance plan, the maintenance plan may be returned to the diagnostic instrument, or the maintenance plan may be returned to the vehicle information system.

[0047] In this embodiment, when the after-sales personnel diagnose the fault through the diagnostic instrument, after successfully obtaining the maintenance plan that fully matches the vehicle fault through the automobile diagnostic method, not only can this carefully formulated maintenance plan be directly returned to the diagnostic instrument for precise guidance of subsequent troubleshooting and repair work, but also the maintenance plan can be safely returned to the vehicle's own on-board information system (vehicle computer) through a specific data transmission method. In this way, the vehicle's on-board information system (vehicle computer) can receive this targeted maintenance plan in real time, and provide more intuitive and detailed maintenance information to after-sales personnel or car owners based on it. This flexible and diverse maintenance plan transmission method not only greatly improves the efficiency and accuracy of maintenance work, but also brings a more convenient and efficient maintenance service experience to car owners.

[0048] In some embodiments of the present application, it is also necessary to obtain after-sales feedback information provided by after-sales personnel after repairing the target vehicle through the maintenance plan provided by the automobile intelligent system. By inputting the after-sales feedback information into the intelligent diagnosis big model, the intelligent diagnosis big model can be periodically trained to update the intelligent diagnosis big model.

[0049] In this embodiment, after-sales feedback information includes information such as the fault phenomenon, whether the system accurately identifies the fault, whether the repair method provided by the system is accurate, and whether the fault is resolved. Collecting after-sales feedback information and periodically training the intelligent diagnosis model can continuously improve the efficiency and accuracy of fault diagnosis and repair.

[0050] In an embodiment of the present application, firstly, the fault information of the target vehicle is obtained, the fault information includes a fault code and a fault snapshot information, the fault information is input into the automatic diagnosis system for fault diagnosis, and the first fault cause of the target vehicle is output, wherein the automatic diagnosis system includes a plurality of fault diagnosis modules; then, according to the fault feature description information of the target vehicle, the second fault cause of the target vehicle is output through the intelligent diagnosis big model, wherein the intelligent diagnosis big model is constructed based on the historical maintenance big data and the decision tree algorithm; based on the fact that the first fault cause is different from the second fault cause, one of the first fault cause and the second fault cause is determined as the final fault cause through the big data decision model; then, according to the fault maintenance knowledge base, a maintenance plan matching the final fault cause is obtained; that is, by performing fault diagnosis on the target vehicle through the automatic diagnosis system and the intelligent diagnosis big model, the fault cause can be accurately located, and when the fault causes obtained by the two are different, the final fault cause can be determined through the big data decision module, thereby improving the diagnostic accuracy of the fault cause, and through the fault maintenance knowledge base, a maintenance plan matching the fault cause can be obtained, which solves the technical problem that after-sales personnel cannot quickly locate the fault cause and provide accurate and professional maintenance plans during after-sales maintenance, and provides strong support for the rapid handling of faults by after-sales personnel during the maintenance process.

[0051] It should be noted that the execution subject of the automobile intelligent diagnosis system provided in the embodiment of the present application can be the automobile intelligent diagnosis system, or a control module in the system for executing and loading the automobile intelligent diagnosis method. In the embodiment of the present application, the automobile intelligent diagnosis method provided in the embodiment of the present application is explained by taking the automobile intelligent diagnosis system executing the automobile intelligent diagnosis method as an example.

[0052] The automobile diagnostic system in the embodiment of the present application may be a system, or a component, integrated circuit, or chip in a terminal. The system may be a mobile electronic device or a non-mobile electronic device. For example, the mobile electronic device may be an in-vehicle electronic device, a wearable device, etc., and the non-mobile electronic device may be a server, a network attached storage (NAS), a personal computer (PC), etc., which is not specifically limited in the embodiment of the present application.

[0053] The automobile intelligent diagnosis system provided in the embodiment of the present application can achieve Figure 1 To avoid repetition, the various processes implemented in the method embodiment will not be described again here.

[0054] See also Figure 5 , Figure 5 FIG. 1 is a schematic diagram of the structure of an automobile diagnostic system provided by an embodiment of the second aspect of the present invention, the system comprising: The information acquisition module 201 is used to acquire the fault information of the target vehicle. The information acquisition module is used to acquire the fault information of the target vehicle. The fault information includes a fault code and a fault snapshot information. In this embodiment, the information acquisition module 201 can obtain fault information from the vehicle side, including fault codes and fault snapshot information, and can also obtain vehicle-computer collection information from the vehicle computer to supplement the fault snapshot information, which is beneficial for obtaining fault information and providing a data basis for the diagnosis of the automatic diagnosis system.

[0055] The automatic diagnosis system module 202 is used to input the fault information into the automatic diagnosis system for fault diagnosis and output the first fault cause of the target vehicle; wherein the automatic diagnosis system includes a plurality of fault diagnosis modules; In this embodiment, fault information is input from the information acquisition module 201, and the automatic diagnosis system module 202 triggers the automatic diagnosis system to enter the analysis state in response to the fault code; based on the preset fault-free information, the fault-free operation state of the target vehicle is simulated through the automatic diagnosis system; in response to the fault snapshot information, the diagnosis information is determined through multiple fault diagnosis modules; based on the diagnosis information, the first fault cause of the target vehicle is determined.

[0056] The intelligent diagnosis big model module 203 is used to output the second fault cause of the target vehicle through the intelligent diagnosis big model according to the fault feature description information of the target vehicle; In this embodiment, the fault feature description information is obtained according to the information acquisition module 201, and the second fault cause of the target vehicle is determined through the logical judgment of the intelligent diagnosis system based on historical big data and decision tree algorithm. It can also perform periodic training according to the input after-sales feedback information to update the intelligent diagnosis model.

[0057] A big data decision module 204, configured to determine, based on the fact that the first fault cause is different from the second fault cause, that one of the first fault cause and the second fault cause is the final fault cause by using a big data decision model; In this embodiment, the first fault cause and the second fault cause are obtained from the automatic diagnosis system module 202 and the intelligent diagnosis big model module 203, and the probability analysis of the first fault cause and the second fault cause is performed through the big data decision model according to the historical maintenance big data, and the probability analysis result is generated. Based on the expert system in the big data decision model, the first fault cause and the second fault cause are expertly decided, and the expert decision result is generated. The expert decision result is mainly obtained by reasoning and analyzing the first fault cause and the second fault cause through the expert knowledge base and the reasoning algorithm in the expert system; based on the expert knowledge base, an expert maintenance suggestion matching the expert decision result is generated. The big data decision model will make a preliminary weight distribution between the probability analysis result and the expert decision result, and according to the preliminary weight distribution result, it is determined that one of the first fault cause and the second fault cause is the final fault cause.

[0058] The fault maintenance knowledge base module 205 is used to obtain a maintenance plan that matches the final fault cause according to the fault maintenance knowledge base; In this embodiment, the fault repair knowledge base module 205 can quickly and accurately obtain a repair plan that matches the final determined fault cause, and provide strong support for after-sales personnel to quickly handle the fault during the repair process.

[0059] In an embodiment of the present application, firstly, the fault information of the target vehicle is obtained, the fault information includes a fault code and a fault snapshot information, the fault information is input into the automatic diagnosis system for fault diagnosis, and the first fault cause of the target vehicle is output, wherein the automatic diagnosis system includes a plurality of fault diagnosis modules; then, according to the fault feature description information of the target vehicle, the second fault cause of the target vehicle is output through the intelligent diagnosis big model, wherein the intelligent diagnosis big model is constructed based on the historical maintenance big data and the decision tree algorithm; based on the fact that the first fault cause is different from the second fault cause, one of the first fault cause and the second fault cause is determined as the final fault cause through the big data decision model; then, according to the fault maintenance knowledge base, a maintenance plan matching the final fault cause is obtained; that is, by performing fault diagnosis on the target vehicle through the automatic diagnosis system and the intelligent diagnosis big model, the fault cause can be accurately located, and when the fault causes obtained by the two are different, the final fault cause can be determined through the big data decision module, thereby improving the diagnostic accuracy of the fault cause, and through the fault maintenance knowledge base, a maintenance plan matching the fault cause can be obtained, which solves the technical problem that after-sales personnel cannot quickly locate the fault cause and provide accurate and professional maintenance plans during after-sales maintenance, and provides strong support for the rapid handling of faults by after-sales personnel during the maintenance process.

[0060] The third aspect of the present application also provides an electronic device, such as Figure 6As shown, the electronic device includes a processor 301, a memory 302, and a program or instruction 303 stored in the memory and executable on the processor. When the program or instruction is executed by the processor, each process of the above-mentioned automobile intelligent diagnosis method embodiment is implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0061] It should be noted that, in this article, the terms "comprise", "include" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise one..." do not exclude the presence of other identical elements in the process, method, article or device including the element. In addition, it should be pointed out that the scope of the methods and devices in the embodiments of the present application is not limited to performing functions in the order shown or discussed, and may also include performing functions in a substantially simultaneous manner or in reverse order according to the functions involved, for example, the described method may be performed in an order different from that described, and various steps may also be added, omitted, or combined. In addition, the features described with reference to certain examples may be combined in other examples.

[0062] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present application, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal (which can be a mobile phone, a computer, a server, an air conditioner, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0063] The embodiments of the present application are described above in conjunction with the accompanying drawings, but the present application is not limited to the above-mentioned specific implementation methods. The above-mentioned specific implementation methods are merely illustrative and not restrictive. Under the guidance of the present application, ordinary technicians in this field can also make many forms without departing from the purpose of the present application and the scope of protection of the claims, all of which are within the protection of the present application.

Claims

1. An intelligent automobile diagnosis method, characterized in that: The method comprises: Acquire fault information of a target vehicle, wherein the fault information includes a fault code and fault snapshot information; Inputting the fault information into an automatic diagnosis system for fault diagnosis, and outputting a first fault cause of the target vehicle, wherein the automatic diagnosis system includes a plurality of fault diagnosis modules; Outputting the second fault cause of the target vehicle through the intelligent diagnosis big model according to the fault feature description information of the target vehicle, wherein the intelligent diagnosis big model is constructed based on historical maintenance big data and a decision tree algorithm; Based on the fact that the first fault cause is different from the second fault cause, determining one of the first fault cause and the second fault cause as the final fault cause through a big data decision model; According to the fault maintenance knowledge base, a maintenance plan matching the final fault cause is obtained.

2. The automobile intelligent diagnosis method according to claim 1, characterized in that: The step of inputting the fault information into an automatic diagnosis system for fault diagnosis and outputting the first fault cause of the target vehicle specifically includes: In response to the fault code, triggering the automatic diagnosis system to enter an analysis state; According to the preset fault-free information, simulating the fault-free running state of the target vehicle through the automatic diagnosis system; In response to the fault snapshot information, determining diagnostic information by the plurality of fault diagnostic modules; A first fault cause is determined according to the diagnostic information.

3. The automobile intelligent diagnosis method according to claim 1, characterized in that: The step of determining one of the first fault cause and the second fault cause as the final fault cause through the big data decision model based on the fact that the first fault cause is different from the second fault cause specifically includes: According to the historical maintenance big data, a probability analysis is performed on the first fault cause and the second fault cause through the big data decision model to generate a probability analysis result; Based on the expert system in the big data decision model, expert decision is made on the first fault cause and the second fault cause to generate an expert decision result; According to the probability analysis result and the expert decision result, one of the first fault cause and the second fault cause is determined as a final fault cause.

4. The automobile intelligent diagnosis method according to claim 3, characterized in that: The step of performing expert decision making on the first fault cause and the second fault cause based on the expert system in the big data decision model and outputting the expert decision result specifically includes: Based on the expert knowledge base and reasoning algorithm in the expert system, the first fault cause and the second fault cause are reasoned and analyzed to obtain an expert decision result.

5. The automobile intelligent diagnosis method according to claim 4, characterized in that: After the step of performing reasoning analysis on the first fault cause and the second fault cause based on the expert knowledge base and reasoning algorithm in the expert system to obtain an expert decision result, the method further includes: Based on the expert knowledge base, an expert maintenance suggestion matching the expert decision result is generated.

6. The automobile intelligent diagnosis method according to claim 3, characterized in that: The step of determining one of the first fault cause and the second fault cause as the final fault cause according to the probability analysis result and the expert decision result specifically includes: Performing preliminary weight distribution on the probability analysis result and the expert decision result to generate a preliminary weight distribution result; According to the preliminary weight distribution result, one of the first fault cause and the second fault cause is determined as a final fault cause.

7. The automobile intelligent diagnosis method according to claim 1, characterized in that: The step of outputting the second fault cause of the target vehicle through the intelligent diagnosis big model according to the fault feature description information of the target vehicle, wherein after the step of constructing the intelligent diagnosis big model based on historical maintenance big data and decision tree algorithm, the step further comprises: Determining whether the first fault cause is the same as the second fault cause; Based on the situation that the first fault cause is the same as the second fault cause, the first fault cause or the second fault cause is input into the fault repair knowledge base to obtain a repair plan matching the first fault cause or the second fault cause.

8. The automobile intelligent diagnosis method according to claim 6, characterized in that: After the step of obtaining a maintenance solution matching the final fault cause according to the fault maintenance knowledge base, the method further comprises: Obtain after-sales feedback information of the target vehicle and update the intelligent diagnosis model.

9. An intelligent automobile diagnostic system, characterized in that: The system comprises: An information acquisition module, used to acquire fault information of a target vehicle, wherein the fault information includes a fault code and a fault snapshot information; an automatic diagnosis system module, inputting the fault information into an automatic diagnosis system for fault diagnosis, and outputting a first fault cause of the target vehicle, wherein the automatic diagnosis system includes a plurality of fault diagnosis modules; An intelligent diagnosis big model module, used for outputting a second fault cause of the target vehicle through the intelligent diagnosis big model according to the fault feature description information of the target vehicle, wherein the intelligent diagnosis big model is constructed based on historical maintenance big data and a decision tree algorithm; A big data decision model module, configured to determine, based on the fact that the first fault cause is different from the second fault cause, that one of the first fault cause and the second fault cause is a final fault cause through a big data decision model; The fault maintenance knowledge base module is used to obtain a maintenance plan that matches the cause of the fault based on the fault maintenance knowledge base.

10. An electronic device, characterized in that: The electronic device includes a processor, a memory, and a program or instruction stored in the memory and executable on the processor. When the program or instruction is executed by the processor, the intelligent automobile diagnosis method as described in any one of claims 1 to 8 is implemented.

Images