Automobile fault diagnosis method, device and equipment and storage medium

Abstract

The invention provides an automobile fault diagnosis method and device, equipment and a storage medium. The method comprises the following steps: receiving an automobile fault question of a user account; generating a questionnaire with a predefined format; matching the questionnaire task to one or more expert accounts according to the automobile fault questions; sending a link of the questionnaire to one or more expert accounts; receiving answers for the questionnaire submitted by one or more expert accounts, wherein the answers comprise fault elements, fault related features, one or more fault causes and probabilities thereof, and solutions; generating a fault probability analysis result according to the fault reasons and the probabilities thereof provided by the one or more expert accounts respectively; generating a fault knowledge tree according to the fault probability analysis result, the fault elements, the fault related characteristics and the solutions; and sending the fault knowledge tree to the user account. According to the invention, a user can solve the fault problem conveniently, and potential safety hazards are eliminated.

Description

Technical Field

[0001] The embodiments of the present invention generally relate to the technical field of automobile fault diagnosis, and more specifically, to an automobile fault diagnosis method, device, equipment and storage medium. Background Art

[0002] With the popularity of cars, the number of cars in the market is gradually increasing. A car consists of a large number of parts and is a complex mechanical system. If one or some of the parts fail, it will cause driving danger. Due to the diversity and complexity of vehicle parts, it is difficult to find the root cause of the problem immediately when a vehicle fails. Summary of the invention

[0003] In order to solve the above-mentioned problems in the prior art, in a first aspect, an embodiment of the present invention provides a method for diagnosing automobile faults, the method comprising: receiving an automobile fault question from a user account, wherein the automobile fault question includes a fault-related vehicle model, faulty equipment and a fault description; generating a questionnaire with a predefined format according to the automobile fault question; matching the questionnaire task to one or more expert accounts according to the vehicle model, faulty equipment and fault description in the automobile fault question; sending a link to the questionnaire to the one or more expert accounts; receiving answers to the questionnaire submitted by the one or more expert accounts, the answers including a fault component, fault-related features, one or more fault causes and their probabilities, and a solution; generating a fault probability analysis result according to the fault causes and their probabilities respectively provided by the one or more expert accounts; generating a fault knowledge tree according to the fault probability analysis result and the fault component, the fault-related features and the solution; and sending the fault knowledge tree to the user account.

[0004] In some embodiments, generating a fault probability analysis result based on the fault causes and probabilities thereof respectively provided by the one or more expert accounts includes: performing a weighted average on the fault causes and probabilities thereof provided by the one or more expert accounts to obtain the fault probability analysis result.

[0005] In some implementations, expert accounts of different levels have different weights.

[0006] In some embodiments, the method further includes: receiving and storing configuration information input by an administrator account, the configuration information including one or more of vehicle type, equipment category and model, sensor acquisition characteristics, fault category, related component information, and component association relationship.

[0007] In some embodiments, matching the questionnaire task to one or more expert accounts based on the vehicle model, faulty equipment and fault description in the vehicle fault question includes: matching the vehicle model, faulty equipment and fault description in the vehicle fault question with the configuration information to determine the one or more matching expert accounts.

[0008] In some implementations, the method further includes: storing the fault knowledge tree in a fault knowledge base.

[0009] In some embodiments, the method further includes: after receiving a car fault question from a user account, searching a stored fault knowledge base for a fault knowledge tree that matches the car fault question based on the car model, faulty equipment and fault description in the car fault question; and sending the matching fault knowledge tree to the user account.

[0010] In a second aspect, an embodiment of the present invention proposes an automobile fault diagnosis device, the device comprising: a question receiving module, configured to receive automobile fault questions from a user account, wherein the automobile fault questions include a fault-related vehicle model, faulty equipment and fault description; a questionnaire generating module, configured to generate a questionnaire with a predefined format according to the automobile fault question; an expert matching module, configured to match the questionnaire task to one or more expert accounts according to the vehicle model, faulty equipment and fault description in the automobile fault question; a questionnaire sending module, configured to send a link to the questionnaire to the one or more expert accounts; an answer receiving module, configured to receive answers to the questionnaire submitted by the one or more expert accounts, the answers including a fault element, fault-related features, one or more fault causes and their probabilities, and a solution; a probability analysis module, configured to generate a fault probability analysis result according to the fault causes and their probabilities respectively provided by the one or more expert accounts; a fault knowledge tree generating module, configured to generate a fault knowledge tree according to the fault probability analysis result and the fault element, the fault-related features and the solution; a fault knowledge tree sending module, configured to send the fault knowledge tree to the user account.

[0011] In a third aspect, an embodiment of the present invention proposes an automobile fault diagnosis device, which includes a memory and a processor, wherein a computer program is stored on the memory, and when the computer program is executed by the processor, the automobile fault diagnosis method described in any of the above embodiments is implemented.

[0012] In a fourth aspect, an embodiment of the present invention provides a storage medium storing computer-readable instructions, which, when executed by a processor, executes the automobile fault diagnosis method described in any of the above embodiments.

[0013] The fault diagnosis method, device, equipment and storage medium proposed in the embodiments of the present invention can help users find and solve problems in the first place, facilitate users to solve fault problems and eliminate potential safety hazards. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The above and other objects, features and advantages of the embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which:

[0015] Figure 1 A flow chart of a method for diagnosing automobile faults according to an embodiment of the present invention is shown;

[0016] Figure 2 A schematic flow chart of multi-account type operations of a method for diagnosing automobile faults according to an embodiment of the present invention is shown;

[0017] Figure 3 A functional structure diagram of an automobile fault diagnosis application according to an embodiment of the present invention is shown;

[0018] Figure 4 An example entity relationship class diagram of an automobile fault diagnosis application according to an embodiment of the present invention is shown;

[0019] Figure 5 A schematic diagram of a problem management interface of an automobile fault diagnosis application according to an embodiment of the present invention is shown;

[0020] Figure 6 A schematic diagram of a question answering interface of an automobile fault diagnosis application according to an embodiment of the present invention is shown;

[0021] Figure 7 A schematic diagram showing an example of a fault knowledge tree according to an embodiment of the present invention.

[0022] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION

[0023] The principle and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way.

[0024] In one aspect, an embodiment of the present invention provides a method for diagnosing a vehicle fault, referring to Figure 1 , which shows a flow chart of a method for diagnosing automobile faults according to an embodiment of the present invention. The method comprises steps S101-S108.

[0025] In step S101, a car failure question from a user account is received, wherein the car failure question includes a car model, a faulty device, and a description of the fault.

[0026] In step S102, a questionnaire with a predefined format is generated according to the automobile failure question.

[0027] In step S103, the questionnaire task is matched to one or more expert accounts according to the vehicle model, faulty equipment and fault description in the automobile fault question. Expert accounts are also referred to as designer accounts in this specification, and the two expressions can be used interchangeably.

[0028] In step S104, a link to the questionnaire is sent to one or more expert accounts.

[0029] In step S105, answers to the questionnaire submitted by one or more expert accounts are received, the answers including the faulty component, fault-related features, one or more fault causes and their probabilities, and solutions.

[0030] In step S106, a fault probability analysis result is generated according to the fault causes and probabilities thereof respectively provided by one or more expert accounts.

[0031] In step S107, a fault knowledge tree is generated according to the fault probability analysis results as well as the faulty components, fault-related features and solutions.

[0032] In step S108, the fault knowledge tree is sent to the user account.

[0033] As an embodiment of the present invention, step S106 may include: performing weighted averaging on the fault causes and their probabilities provided by one or more expert accounts to obtain a fault probability analysis result.

[0034] As an embodiment of the present invention, expert accounts of different levels have different weights. For example, expert accounts can be divided into professional field experts and non-professional field experts, and the expert level can be set according to department or position.

[0035] Optionally, the level of the expert account may vary according to the different types of questions asked. For example, the same expert account may be a professional domain expert when faced with motor failure problems, but may be a non-professional domain expert when faced with non-motor failure problems, and so on.

[0036] As an embodiment of the present invention, the method may further include: receiving and storing configuration information input by an administrator account, the configuration information including one or more of vehicle type, equipment category and model, sensor acquisition characteristics, fault category, related component information, and component association relationship. In this embodiment, the account types involved in the method are divided into three types: user account, administrator account, and expert account (or designer account).

[0037] As an embodiment of the present invention, step S103 may include: matching the vehicle model, faulty equipment and fault description in the automobile fault question with the configuration information to determine one or more matching expert accounts.

[0038] As an implementation manner of the present invention, the method may further include: storing the fault knowledge tree in a fault knowledge base.

[0039] As an embodiment of the present invention, the method may further include: after receiving a car fault question from a user account, searching a stored fault knowledge base for a fault knowledge tree that matches the car fault question based on the car model, fault equipment and fault description in the car fault question; and sending the matching fault knowledge tree to the user account.

[0040] The automobile fault diagnosis method proposed in the present invention can be implemented by application software (or system) written by computer program.

[0041] The system allows users to ask questions about car failures and search for existing problems. After the system gets the questions, it will assign them to relevant designers to answer. This functional module needs to be able to automatically generate a questionnaire template that can be used to guide designers to describe equipment failure knowledge. The questionnaire template can include three parts: failure characterization, failure cause, and failure solution.

[0042] The system administrator enters basic information such as vehicle model, sensor collection characteristics, fault category, and related components. Subsequently, the administrator can generate a questionnaire template for a specific fault and assign it to the expert account that has been entered into the system. All faults are raised for specific vehicle models. This function module needs to provide a new vehicle model, set the vehicle model category, model, component composition, and the relationship between components.

[0043] According to the designer information entered by the system configuration subsystem, the designer who will be conducting the questionnaire task is automatically matched, a question distribution plan is generated, and the question link is sent to the expert account through the system, and the answers are collected on time. The designer automatic matching results can be manually intervened and adjusted.

[0044] The system applies a weighted average algorithm to perform weighted fitting based on the problem descriptions of multiple experts and the probability of failure of each component. The answers of multiple experts are summarized to ultimately obtain the corresponding failure probability parameters of each component of the faulty equipment.

[0045] After obtaining the probability of failure of each part of the vehicle, valid questionnaires are extracted to extract and transform fault knowledge. In addition to extracting and transforming the knowledge structure, it is also necessary to calculate the correlation coefficient (failure probability, etc.) according to the set conversion rules, and then transform it into a fault knowledge tree with quantitative indicators or qualitative grade indicators.

[0046] The following is a description of the operation of the automobile fault diagnosis application by way of example only.

[0047] Figure 2 A schematic flow chart of multi-account type operation of the automobile fault diagnosis method according to an embodiment of the present invention is shown. In the automobile fault diagnosis application, the system may include three types of users: users, administrators, and designers:

[0048] 1) User part: The system allows users to describe the fault content, characteristics, causes, solutions, etc. At the same time, users can input questions about the problems that occur during the operation of the motor. The system will summarize the content based on the questions input by the user, form a question template and provide it to the designer for answer.

[0049] 2) Administrator: The system administrator enters basic information such as equipment, sensor collection characteristics, fault categories, and related components. The administrator can then generate problem templates for specific faults and assign them to the designer accounts that have been entered into the system.

[0050] 3) Designer part: After logging in, the expert can view and answer all questions, find the faulty components and their corresponding probability of failure, and store their answers in the system and summarize them with the answers of other experts.

[0051] First, the system administrator enters basic information such as vehicle model, sensor collection characteristics, and fault category. Subsequently, the administrator can generate a question template for a specific fault and initiate a task plan, which is assigned to the designer account that has been entered into the system. After receiving the task push, the designer can complete the answer within the specified time. Extract valid answers to extract and transform fault knowledge. In addition to extracting and transforming the knowledge structure, it is also necessary to calculate the correlation coefficient (fault probability, etc.) according to the set conversion rules, and then transform it to generate a fault knowledge tree with quantitative indicators or qualitative grade indicators.

[0052] refer to Figure 3, which shows the functional structure diagram of the automobile fault diagnosis application according to the embodiment of the present invention. It includes three parts: system configuration, fault entry, and fault sorting and summarization. The system configuration completes the preparatory work for the system fault entry. The system can generate a fault analysis set for a specific fault, extract and transform the fault knowledge of the fault information input by the user. In addition to extracting and transforming the knowledge structure, it is also necessary to calculate the correlation coefficient according to the set conversion rules, and then transform and generate a fault knowledge tree with quantitative indicators or qualitative grade indicators.

[0053] According to the previous text, the three main entities in the system are users, administrators, and designers. The entity relationship class diagram completed based on the above analysis is as follows Figure 4 shown.

[0054] The system has three different roles, including: user, administrator, and designer. All three can register and log in. Different roles will have different accounts. Their basic information can be added, deleted, modified, and queried, and basic business logic processing can be performed. Optionally, the system's main page can provide the system's usage and precautions to help system users operate the system better and faster.

[0055] refer to Figure 5 , which shows a schematic diagram of the problem management interface of the automobile fault diagnosis application according to an embodiment of the present invention. The system allows the user to describe the fault content, characteristics, causes, solutions, etc. At the same time, the user can input each component module of the motor, the AND or NOR gate and the fault element, and the system will summarize the content based on the fault results input by multiple users to form a complete and targeted problem template.

[0056] The system administrator enters basic information such as equipment, sensor collection characteristics, fault category, and related components. The administrator can then generate a questionnaire template for a specific fault and assign it to the expert account that has been entered into the system.

[0057] The system links the user's question with the administrator's configuration, extracts and transforms knowledge, forms a complete and targeted question template, and distributes the question template to the designer account, and multiple designers answer the question. Figure 6 shown.

[0058] The answers from different roles need to be weighted to obtain the analysis results of the failure probability.

[0059] As an example only, user roles are divided into professional field experts and non-professional field experts (for example, according to user department, position, job, etc.). For example, the role credibility of professional field experts is 70%, and the credibility of non-professional field experts is 30%. This credibility can be obtained by fitting historical fault analysis results and actual fault causes.

[0060] The weighted analysis method according to different roles is shown in Tables 1 and 2 below.

[0061] Table 1. Failure probability weighted table

[0062]

[0063] Table 2. Failure probability analysis table

[0064]

[0065] Each answer will be multiplied by the corresponding coefficient and accumulated. The accumulated result will be divided by the total number as the probability of fault occurrence and used to form the final fault knowledge base. According to the answers of multiple designers to the questions and the probability of failure of each component, weighted fitting is performed, and the answers of multiple experts are summarized to finally obtain the corresponding fault probability parameters of each component of the motor. After obtaining the fault probability, the cause of the fault is attached to the corresponding fault, and the corresponding solution is attached for different fault causes. The fault knowledge tree is as follows: Figure 7 shown.

[0066] This system can help users find and solve problems in the first place, and provide a technical exchange platform for users, administrators, and part designers, making it easier for users to solve fault problems and eliminate potential safety hazards.

[0067] On the other hand, an embodiment of the present invention provides an automobile fault diagnosis device, which includes the following modules:

[0068] A question receiving module configured to receive automobile fault questions from a user account, wherein the automobile fault questions include the relevant vehicle model, faulty equipment and fault description;

[0069] A questionnaire generation module, configured to generate a questionnaire with a predefined format according to automobile fault questions;

[0070] An expert matching module, configured to match the questionnaire task to one or more expert accounts according to the vehicle model, fault device and fault description in the automobile fault question;

[0071] A questionnaire sending module configured with a link for sending a questionnaire to one or more expert accounts;

[0072] An answer receiving module is configured to receive answers to the questionnaire submitted by one or more expert accounts, the answers including faulty components, fault-related features, one or more fault causes and their probabilities, and solutions;

[0073] A probability analysis module configured to generate a failure probability analysis result according to the failure causes and probabilities thereof respectively provided by one or more expert accounts;

[0074] A fault knowledge tree generation module configured to generate a fault knowledge tree according to the fault probability analysis result and the fault component, fault related characteristics and solutions;

[0075] The fault knowledge tree sending module is configured to send the fault knowledge tree to the user account.

[0076] It should be noted that the functions implemented by each module in the automobile fault diagnosis device proposed in the embodiment of the present invention correspond one-to-one to the various steps of the automobile fault diagnosis method described above. For its specific implementation methods, examples and beneficial effects, please refer to the above description of the method.

[0077] On the other hand, an embodiment of the present invention provides an automobile fault diagnosis device, which includes a memory and a processor. The memory stores a computer program, and when the computer program is executed by the processor, the automobile fault diagnosis method described in any of the above embodiments is implemented.

[0078] In yet another aspect, an embodiment of the present invention provides a storage medium storing computer-readable instructions, which, when executed by a processor, executes the automobile fault diagnosis method described in any of the above embodiments.

[0079] The fault diagnosis method, device, equipment and storage medium proposed in the embodiments of the present invention realize a system platform on which users can provide feedback on vehicle fault information, including fault description and related features. After the questions are collected and summarized by the administrator, the designers answer the questions, and the administrator selects valid answers based on different answers and summarizes them. The summarized results can help users lock in the faulty components, and at the same time obtain the causes and consequences of the faults, and give the relevant probabilities. This system can help users find and solve problems in the first place. It provides a platform for technical exchanges for users, administrators, and parts designers, making it convenient for users to solve fault problems and eliminate potential safety hazards.

[0080] For the purpose of illustration, the foregoing description of the embodiments of the present invention has been given, which is not exhaustive nor intended to limit the present invention to the disclosed exact form. It will be appreciated by those skilled in the art that various changes can be made without departing from the scope of the present invention, and that the elements therein can be replaced with equivalents. In addition, without departing from the basic scope of the present invention, many modifications can be made so that specific situations or materials are adapted to the teachings of the present invention. Therefore, the present invention is not intended to be limited to the disclosed specific embodiments as the best mode for realizing the present invention, and the present invention will include all embodiments falling within the scope of the appended claims.

Claims

1. A method for diagnosing automobile faults, characterized in that: The method comprises: receiving a car fault question from a user account, wherein the car fault question includes a car model, a faulty device, and a description of the fault; Generating a questionnaire with a predefined format according to the automobile failure question; Matching the questionnaire task to one or more expert accounts according to the vehicle model, faulty equipment and fault description in the automobile fault question; sending a link to the questionnaire to the one or more expert accounts; receiving answers to the questionnaire submitted by the one or more expert accounts, the answers including faulty components, fault-related features, one or more fault causes and probabilities thereof, and solutions; Generate a failure probability analysis result according to the failure causes and probabilities thereof respectively provided by the one or more expert accounts; Generate a fault knowledge tree according to the fault probability analysis result, the fault component, the fault-related characteristics and the solution; The fault knowledge tree is sent to the user account.

2. The method according to claim 1, characterized in that Generating a failure probability analysis result according to the failure causes and probabilities respectively provided by the one or more expert accounts includes: The fault causes and probabilities thereof provided by the one or more expert accounts are weighted averaged to obtain the fault probability analysis result.

3. The method according to claim 2, characterized in that Expert accounts of different levels have different weights.

4. The method according to any one of claims 1 to 3, characterized in that The method further comprises: Receive and store configuration information input by an administrator account, wherein the configuration information includes one or more of vehicle type, equipment category and model, sensor acquisition characteristics, fault category, related component information, and component association relationship.

5. The method according to claim 4, characterized in that According to the vehicle model, faulty equipment and fault description in the automobile fault question, matching the questionnaire task to one or more expert accounts includes: The vehicle model, faulty equipment and fault description in the automobile fault question are matched with the configuration information to determine the one or more matching expert accounts.

6. The method according to any one of claims 1 to 3, characterized in that The method further comprises: The fault knowledge tree is stored in a fault knowledge base.

7. The method according to claim 6, characterized in that The method further comprises: After receiving the automobile fault question from the user account, searching the stored fault knowledge base for a fault knowledge tree matching the automobile fault question according to the vehicle model, fault device and fault description in the automobile fault question; The matched fault knowledge tree is sent to the user account.

8. An automobile fault diagnosis device, characterized in that: The device comprises: A question receiving module configured to receive a question about a car failure from a user account, wherein the question about the car failure includes a car model, a faulty device, and a description of the fault; A questionnaire generation module, configured to generate a questionnaire with a predefined format according to the automobile fault question; An expert matching module, configured to match the questionnaire task to one or more expert accounts according to the vehicle model, faulty equipment and fault description in the automobile fault question; A questionnaire sending module, configured to send a link of the questionnaire to the one or more expert accounts; an answer receiving module, configured to receive answers to the questionnaire submitted by the one or more expert accounts, the answers including faulty components, fault-related features, one or more fault causes and probabilities thereof, and solutions; A probability analysis module configured to generate a fault probability analysis result according to the fault causes and probabilities thereof respectively provided by the one or more expert accounts; A fault knowledge tree generating module, configured to generate a fault knowledge tree according to the fault probability analysis result, the fault component, the fault-related characteristics and the solution; A fault knowledge tree sending module is configured to send the fault knowledge tree to the user account.

9. An automobile fault diagnosis device, characterized in that: The device comprises a memory and a processor, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the automobile fault diagnosis method according to any one of claims 1 to 7 is implemented.

10. A storage medium, characterized in that: Computer-readable instructions are stored, and when the instructions are executed by a processor, the automobile fault diagnosis method according to any one of claims 1 to 7 is executed.

Images