WO2021023097A1 - 一种汽车维修方法、装置及其系统 - Google Patents

一种汽车维修方法、装置及其系统 Download PDF

Info

Publication number
WO2021023097A1
WO2021023097A1 PCT/CN2020/106053 CN2020106053W WO2021023097A1 WO 2021023097 A1 WO2021023097 A1 WO 2021023097A1 CN 2020106053 W CN2020106053 W CN 2020106053W WO 2021023097 A1 WO2021023097 A1 WO 2021023097A1
Authority
WO
WIPO (PCT)
Prior art keywords
fault
car
maintenance
vehicle
data
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2020/106053
Other languages
English (en)
French (fr)
Inventor
张良
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Autel Intelligent Technology Corp Ltd
Original Assignee
Autel Intelligent Technology Corp Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Autel Intelligent Technology Corp Ltd filed Critical Autel Intelligent Technology Corp Ltd
Publication of WO2021023097A1 publication Critical patent/WO2021023097A1/zh
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
    • G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
    • G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B23/00—Testing or monitoring of control systems or parts thereof
    • G05B23/02—Electric testing or monitoring
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B2219/00—Program-control systems
    • G05B2219/20—Pc systems
    • G05B2219/24—Pc safety
    • G05B2219/24065—Real time diagnostics

Definitions

  • This application relates to the technical field of automobiles and software, in particular to an automobile maintenance method, device and system.
  • the fault inspection of the car is mainly based on the maintenance experience and level of the maintenance personnel.
  • the maintenance personnel perform the fault inspection on the car, they use the maintenance experience to judge the failure symptoms of the car and determine the fault point of the car through continuous testing. More time is spent, maintenance efficiency is low, and if the maintenance personnel are inexperienced or do not understand the car model, the failure point of the car cannot be accurately judged, and the failure solution cannot be obtained, and the maintenance effect is poor.
  • the embodiments of the present invention aim to provide an automobile maintenance method, device and system, which can improve maintenance efficiency.
  • a technical solution adopted in the embodiment of the present invention is to provide a vehicle maintenance method, including:
  • the relevant data including vehicle data and fault data of the vehicle to be repaired;
  • the vehicle data and the fault data of the vehicle to be repaired are input into the vehicle maintenance model to obtain a fault solution for the vehicle to be repaired.
  • the vehicle maintenance model is obtained through training based on sample data
  • sample data includes at least one of the following:
  • Car repair case samples car fault code samples, car system and component information samples, car diagnostic data stream samples, car failure symptoms and causes samples, and car basic information samples.
  • the obtaining the vehicle maintenance model corresponding to the vehicle to be repaired includes:
  • the car data includes at least one of the brand, model, and model year of the car to be repaired.
  • vehicle maintenance models corresponding to different vehicle data are obtained based on different neural network algorithm training.
  • the number of fault solutions is at least two, and the method further includes:
  • a target failure solution is selected from the at least two failure solutions.
  • the number of fault solutions is at least two, and the method further includes:
  • the preset output sequence is determined by the vehicle maintenance model according to the degree of correlation between the at least two fault solutions and the fault data of the vehicle to be repaired.
  • the method further includes:
  • the method further includes:
  • the preset car repair case template also includes at least one of the following modules:
  • Basic vehicle information module applicable model module, fault phenomenon module, existing fault code module, fault point module, maintenance process module, case author module, manufacturer-related information module.
  • the fault data includes at least one of a fault code, a fault diagnosis data stream, and a fault symptom;
  • the fault symptom is input by the user, and the fault code and the fault diagnosis data stream are obtained from the vehicle to be repaired.
  • the method further includes:
  • the vehicle maintenance model is optimized according to the hyperparameters.
  • the method further includes:
  • the vehicle maintenance model is optimized according to the feedback result.
  • an automobile maintenance device including:
  • An acquisition module the acquisition module is used to acquire relevant data of the car to be repaired, the relevant data including car data and fault data of the car to be repaired;
  • An input module which is used to input the car data and the fault data of the vehicle to be repaired into the vehicle repair model to obtain a fault solution for the vehicle to be repaired.
  • the vehicle maintenance model is obtained through training based on sample data
  • sample data includes at least one of the following:
  • Car repair case samples car fault code samples, car system and component information samples, car diagnostic data stream samples, car failure symptoms and causes samples, and car basic information samples.
  • the acquisition module is specifically configured to:
  • the car data includes at least one of the brand, model, and model year of the car to be repaired.
  • vehicle maintenance models corresponding to different vehicle data are obtained based on different neural network algorithm training.
  • the number of the failure solutions is at least two, and the obtaining module is further configured to:
  • a target failure solution is selected from the at least two failure solutions.
  • the number of fault solutions is at least two, and the device further includes:
  • a providing module configured to provide the user with the at least two failure solutions according to a preset output sequence of the automobile maintenance model
  • the preset output sequence is determined by the vehicle maintenance model according to the degree of correlation between the at least two fault solutions and the fault data of the vehicle to be repaired.
  • the input module is also used for:
  • the failure points associated with the failure solution, the repair process, and the manufacturer of the car to be repaired are obtained At least one of the materials.
  • the device further includes:
  • a filling module which is used to fill the fault solution into the solution module of the preset automobile maintenance case template to display it to the user;
  • the preset car repair case template also includes at least one of the following modules:
  • Basic vehicle information module applicable model module, fault phenomenon module, existing fault code module, fault point module, maintenance process module, case author module, manufacturer-related information module.
  • the fault data includes at least one of a fault code, a fault diagnosis data stream, and a fault symptom;
  • the fault symptom is input by the user, and the fault code and the fault diagnosis data stream are obtained from the vehicle to be repaired.
  • the acquisition module is also used for:
  • the vehicle maintenance model is optimized according to the hyperparameters.
  • the acquisition module is also used for:
  • the vehicle maintenance model is optimized according to the feedback result.
  • an automobile maintenance system including:
  • a model training and calculation unit is respectively communicatively connected with the interaction unit, the data storage unit and the result display unit;
  • model training and operation unit includes:
  • At least one processor and
  • the device can be used to perform one of the above-mentioned car repair methods.
  • another technical solution adopted by the embodiments of the present invention is to provide a non-volatile computer-readable storage medium, the non-volatile computer-readable storage medium stores computer executable instructions, so The computer-executable instructions are used to make the automobile maintenance system execute the above-mentioned automobile maintenance method.
  • the beneficial effect of the embodiment of the present invention is that, different from the prior art, the embodiment of the present invention provides an automobile maintenance method, device and system.
  • the automobile maintenance method after obtaining the automobile data and fault data of the automobile to be repaired , Obtain the car repair model corresponding to the car to be repaired, and get the fault solution for the car to be repaired by inputting the car data and fault data into the car repair model.
  • the maintenance personnel can directly repair the car according to the fault solution. It is necessary to determine the point of failure through continuous testing, which greatly shortens the maintenance time and improves the maintenance efficiency.
  • the failure solution obtained through the vehicle maintenance model does not need to be based on the maintenance experience and level of the maintenance personnel, and can avoid the lack of experience of the maintenance personnel. The resulting poor maintenance effect.
  • Figure 1 is a schematic structural diagram of an automobile maintenance system provided by an embodiment of the present invention.
  • FIG. 2 is a schematic flowchart of an automobile maintenance method provided by an embodiment of the present invention.
  • FIG. 3 is a schematic flowchart of an automobile maintenance method provided by another embodiment of the present invention.
  • FIG. 4 is a schematic flowchart of an automobile maintenance method according to another embodiment of the present invention.
  • FIG. 5 is a schematic flowchart of an automobile maintenance method according to still another embodiment of the present invention.
  • Figure 6 is a schematic structural diagram of an application scenario provided by an embodiment of the present invention.
  • Fig. 7 is a schematic diagram of an automobile maintenance scheme output by the application scenario shown in Fig. 6;
  • FIG. 8 is a schematic diagram of another vehicle maintenance solution output by the application scenario shown in FIG. 6;
  • Figure 9 is a schematic structural diagram of an automobile maintenance device provided by an embodiment of the present invention.
  • FIG. 10 is a schematic structural diagram of an automobile maintenance device provided by another embodiment of the present invention.
  • FIG. 11 is a schematic structural diagram of an automobile maintenance device provided by another embodiment of the present invention.
  • FIG. 12 is a schematic diagram of the hardware structure of a model training and calculation unit provided by an embodiment of the present invention.
  • the invention provides an automobile maintenance method and device.
  • the method and device are applied to an automobile maintenance system, so that the automobile maintenance system can output a fault solution according to the automobile data and fault data of the automobile to be repaired.
  • the maintenance personnel use the car maintenance system, they can input the car data and fault data of the car to be repaired into the car maintenance system to obtain the fault solution.
  • the maintenance personnel can judge and test based on the fault symptoms to determine the fault point, which greatly reduces Maintenance time, improve maintenance efficiency, and can avoid the poor maintenance effect caused by the lack of experience of maintenance personnel.
  • FIG. 1 is an automobile maintenance system provided by an embodiment of the present invention.
  • the automobile maintenance system includes: an interactive unit 100, a data storage unit 200, a model training and calculation unit 300, and a result display unit 400, a model training and calculation unit 300 is respectively communicatively connected with the interaction unit 100, the data storage unit 200, and the result display unit 400.
  • the interaction unit 100 is used for information interaction with users.
  • the users can be front-end maintenance personnel or back-end technicians.
  • the user When the user is a front-end maintenance person, the user can interactively feed back results, maintenance plan selection conditions, and related data of the vehicle to be repaired to the automobile maintenance system through the interactive unit 100.
  • the feedback result is the user's feedback on the feasibility of the fault solution output by the automobile maintenance system.
  • the selection condition of the maintenance plan is the personalized demand condition set by the user, which is used to limit the fault solution output of the automobile maintenance system. Through the selection condition of the maintenance plan, the automobile maintenance system can output a fault solution that meets the user's individual needs.
  • the selection conditions of the maintenance plan include but are not limited to: acceptable price range, accessory brand preferences, acceptable duration range, etc.
  • the relevant data of the car to be repaired includes the car data and fault data of the car to be repaired.
  • Automobile data is data that characterizes the basic information of the automobile to be repaired, including but not limited to: brand, model, and year model.
  • the fault data is the data that characterizes the fault condition of the vehicle to be repaired, including but not limited to: fault code, fault diagnosis data stream, and fault symptoms.
  • the user When the user is a back-end technician, the user can interact with the vehicle maintenance system through the interaction unit 100 with configuration information, and the configuration information includes hyperparameters.
  • hyperparameters are used to configure the neural network framework, including but not limited to: the number of hidden layers, the number of neurons in each layer, the learning rate, the weight attenuation, and the number of iterations.
  • the interaction unit 100 includes a communication interface, which can be connected to a car fault diagnosis instrument, so that the interaction unit 100 can obtain at least one of a fault code, a fault diagnosis data stream, and vehicle data from the vehicle to be repaired through the automobile fault diagnosis instrument Kind.
  • the interaction unit 100 also includes physical input components such as a keyboard or a touch screen, and feedback results, maintenance plan selection conditions, fault symptoms, and configuration information can be input into the automobile maintenance system through physical input components such as the keyboard or touch screen.
  • physical input components such as a keyboard or a touch screen
  • car data can also be input into the car maintenance system through physical input components such as a keyboard or a touch screen.
  • the data storage unit 200 is used to store sample data.
  • the sample data is used to train the automobile maintenance model, and the sample data includes at least one of the following: automobile maintenance case samples, automobile fault code samples, automobile system and component information samples, automobile diagnosis data stream samples, automobile fault symptoms and causes samples, and Samples of basic car information, etc.
  • the auto repair case sample includes a number of auto repair cases, which are collected through a preset auto repair case template.
  • the preset car repair case template includes the solution module, as well as the basic vehicle information module, applicable vehicle model module, fault phenomenon module, existing fault code module, fault point module, repair process module, case author module and manufacturer-related information module. At least one module.
  • the solution module is used to collect fault solutions in automobile maintenance cases;
  • the basic vehicle information module is used to collect vehicle information in automobile maintenance cases.
  • the vehicle information includes brand, model, year, VIN code, mileage, and engine model. , Gearbox, model code, chassis number, etc.;
  • applicable vehicle model module is used to collect applicable vehicle models in auto repair cases;
  • fault phenomenon module is used to collect fault symptoms in auto repair cases;
  • existing fault code modules are used to collect auto repair cases The fault code in the case;
  • the fault point module is used to collect suspicious points in the car repair case;
  • the repair process module is used to collect the repair steps in the car repair case;
  • the case author module is used to collect the author information of the car repair case; manufacturer-related
  • the data module is used to collect the original related data of the car involved in the car repair case, including circuit diagrams, specification parameters, component disassembly methods, disassembly and assembly man-hour costs, etc.
  • car maintenance case samples are classified and stored level by level according to car brand, model, and year model.
  • car brand, model, and year model For example: set up a primary database of several brands, the primary database of each brand includes secondary databases of several vehicle models, and the secondary database of each vehicle model includes secondary databases of several model years.
  • the automobile fault code sample includes the corresponding relationship between the automobile fault code and the cause of the fault.
  • the automobile fault code sample is classified and stored step by step according to the automobile brand, model, and model year.
  • the car system and component information sample includes the damage probability of each component in the car system.
  • the car system and component information sample is classified and stored level by level according to the car brand, model, and year.
  • the car diagnostic data stream sample includes the corresponding relationship between the car diagnostic data stream and the cause of the failure.
  • the car diagnostic data stream sample is classified and stored level by level according to the car brand, model, and model year.
  • Samples of car failure symptoms and causes include the corresponding relationship between car failure symptoms and failure causes.
  • the car failure symptoms and cause samples are classified and stored level by level according to car brand, model, and model year.
  • the basic car information sample includes basic car information such as brand, model, and model year.
  • the car repair model can be trained through car repair case samples, the car repair model can also be trained through car repair case samples, car fault code samples, and the car repair model Samples of symptoms and causes, as well as samples of car system and component information, train the car repair model.
  • Various combinations of sample data can achieve the training of the car repair model, which will not be repeated here.
  • the model training and computing unit 300 is used to train the vehicle maintenance model, which can extract sample data from the data storage unit 200 to train the vehicle maintenance model according to the configuration information obtained by the interaction unit 100.
  • the model training and computing unit 300 configures the neural network framework according to the configuration information, and extracts samples from the data storage unit 200 according to the neural network framework Data, the sample data is trained through the preset neural network algorithm, and the vehicle maintenance model is obtained.
  • the model training and calculation unit 300 can also obtain a fault solution through the calculation of the vehicle maintenance model, and output the obtained fault solution to the maintenance personnel, so that the maintenance personnel can repair the vehicle to be repaired according to the failure solution, and improve the maintenance personnel’s Maintenance efficiency.
  • model training and computing unit 300 inputs the relevant data of the vehicle to be repaired acquired by the interaction unit 100 into the vehicle maintenance model corresponding to the vehicle to be repaired for calculation to obtain a fault solution for the vehicle to be repaired.
  • the model training and computing unit 300 can selectively output a fault solution that meets the user's personalized needs according to the maintenance plan selection conditions obtained by the interaction unit 100.
  • the maintenance personnel after the maintenance personnel repair the vehicle to be repaired according to the fault solution, they can also feed back the feasibility of the fault solution to the model training and computing unit 300 through the interaction unit 100, so that the model training and computing unit 300 can According to the feedback results, the vehicle maintenance model is optimized.
  • the model training and operation unit 300 can be implemented by a processor and a memory storing codes, and the processor calls the codes in the memory to realize the functions of model training and operation.
  • the result display unit 400 is used to display the fault solution output by the model training and computing unit 300 to the user.
  • the fault solution can be displayed in the form of a preset car repair case template.
  • the result display unit 400 may be a display screen, or an external electronic device provided with a display screen, such as a computer, a tablet computer, or a smart phone.
  • FIG. 2 is a schematic flowchart of an automobile maintenance method provided by an embodiment of the present invention.
  • the automobile maintenance method is applied to the above-mentioned automobile maintenance system and is executed by the above-mentioned model training and calculation unit 300 for improving maintenance. Maintenance efficiency of personnel.
  • the vehicle maintenance method includes:
  • the relevant data includes car data and fault data of the car to be repaired.
  • the car data includes at least one of the brand, model, and model year of the car to be repaired, and the car data may be input by the user or obtained from the car to be repaired.
  • the fault data includes at least one of a fault code, a fault diagnosis data stream, and a fault symptom, where the fault symptom is input by the user, and the fault code and the fault diagnosis data stream are obtained from the vehicle to be repaired.
  • the vehicle data, the fault code, and the fault diagnosis data stream can be obtained from the vehicle to be repaired through the vehicle fault diagnosis instrument.
  • the above-mentioned vehicle maintenance model is a neural network model trained on the basis of sample data, and the fault solution can be obtained through calculation of the vehicle maintenance model.
  • the sample data includes at least one of automobile maintenance case samples, automobile fault code samples, automobile system and component information samples, automobile diagnosis data stream samples, automobile fault symptoms and causes samples, and automobile basic information samples.
  • the sample data includes car repair case samples; for example, the sample data includes car repair case samples, car failure code samples; for example, sample data includes car repair case samples, car failure symptoms and causes samples, and car system and component information samples;
  • the sample data includes car repair case samples, car fault code samples, car system and component information samples, car diagnostic data stream samples, car failure symptoms and causes samples, and car basic information samples.
  • the auto repair case sample includes a number of auto repair cases, which are collected through a preset auto repair case template.
  • the preset car repair case template includes the solution module, as well as the basic vehicle information module, applicable vehicle model module, fault phenomenon module, existing fault code module, fault point module, repair process module, case author module and manufacturer-related information module. At least one module.
  • the preset car repair case template includes solution module, basic vehicle information module, applicable model module, fault phenomenon module, existing fault code module, fault point module, repair process module, case author module, and manufacturer-related information module;
  • the preset car repair case template includes a solution module, a repair process module, and a failure phenomenon module; for example, the preset car repair case template includes a solution module, a basic vehicle information module, an existing fault code module, and a manufacturer-related information module.
  • the solution module is used to collect fault solutions in automobile maintenance cases;
  • the basic vehicle information module is used to collect vehicle information in automobile maintenance cases.
  • the vehicle information includes brand, model, year, VIN code, mileage, and engine model. , Gearbox, model code, chassis number, etc.;
  • applicable vehicle model module is used to collect applicable vehicle models in auto repair cases;
  • fault phenomenon module is used to collect fault symptoms in auto repair cases;
  • existing fault code modules are used to collect auto repair cases The fault code in the case;
  • the fault point module is used to collect suspicious points in the car repair case;
  • the repair process module is used to collect the repair steps in the car repair case;
  • the case author module is used to collect the author information of the car repair case; manufacturer-related
  • the data module is used to collect the original related data of the car involved in the car repair case, including circuit diagrams, specification parameters, component disassembly methods, disassembly and assembly man-hour costs, etc.
  • This sample car maintenance case is classified and stored level by level according to car brand, model, and model year.
  • the automobile fault code sample includes the corresponding relationship between the automobile fault code and the cause of the fault.
  • the automobile fault code sample is classified and stored step by step according to the automobile brand, model, and model year.
  • the car system and component information sample includes the damage probability of each component in the car system.
  • the car system and component information sample is classified and stored level by level according to the car brand, model, and year.
  • the car diagnostic data stream sample includes the corresponding relationship between the car diagnostic data stream and the cause of the failure.
  • the car diagnostic data stream sample is classified and stored level by level according to the car brand, model, and model year.
  • Samples of car failure symptoms and causes include the corresponding relationship between car failure symptoms and failure causes.
  • the car failure symptoms and cause samples are classified and stored level by level according to car brand, model, and model year.
  • the basic car information sample includes basic car information such as brand, model, and model year.
  • configuration information is obtained to configure a neural network framework, and then sample data is extracted according to the neural network framework, and then the sample data is trained through a preset neural network algorithm to obtain an automobile maintenance model.
  • the configuration information includes hyperparameters, which are used to configure the neural network framework, including but not limited to: the number of hidden layers, the number of neurons in each layer, the learning rate, the weight attenuation, and the number of iterations.
  • the extracted sample data includes features such as car brand, model, model year, fault code, fault diagnosis data stream, fault symptoms, and fault solutions, so that the trained car repair model can be classified according to brand, model, and model year.
  • the vehicle maintenance model corresponding to the vehicle data can be obtained according to the acquired vehicle data of the vehicle to be repaired.
  • the car repair model corresponding to the brand is obtained according to the brand of the car to be repaired; when the car data is the brand and model of the car, the car repair model corresponding to the brand and model is obtained according to the brand and model of the car to be repaired Car repair model.
  • the car maintenance models corresponding to different car data are obtained based on different neural network algorithm training.
  • the car repair model is trained on the characteristics of the car brand, model, model year, fault code, fault diagnosis data stream, fault symptoms, fault solutions, etc.
  • the car repair model Car data and fault data are feature-matched, and the fault solution corresponding to the qualified vehicle maintenance model is determined as the fault solution of the vehicle to be repaired.
  • the number of the obtained failure solutions for the vehicle to be repaired may be one or at least two.
  • the fault solution can be directly output to the maintenance personnel.
  • one fault solution can be selected and output to the maintenance personnel, or all the failure solutions can be output to the maintenance personnel.
  • the car maintenance method also includes:
  • S150 Select a target failure solution from the at least two failure solutions according to the maintenance solution selection condition.
  • the maintenance plan selection condition is the personalized demand condition set by the user, which is used to limit the output of the fault solution, and the maintenance plan selection condition can output the fault solution that meets the individual needs of the car owner.
  • the selection conditions of the maintenance plan include but are not limited to: acceptable price range, accessory brand preferences, acceptable duration range, etc.
  • the selection condition of the maintenance plan input by the user includes the acceptable price range of 500-800
  • the repair price of the fault solution A is 600
  • the fault solution B If the repair price is 1000, then the fault solution A meets the maintenance plan selection conditions entered by the user, and the fault solution A is output to the maintenance personnel.
  • step S140 can be performed simultaneously with any of steps S110-S130, or can be performed after step S130, which is not specifically limited herein.
  • This vehicle maintenance method also includes:
  • S240 Provide the user with the at least two fault solutions according to the preset output sequence of the automobile maintenance model.
  • the preset output sequence is determined by the vehicle maintenance model according to the degree of correlation between the at least two fault solutions and the fault data of the vehicle to be repaired.
  • the fault solution A is based on the feature of the tire pressure warning indicator light after tire replacement
  • the fault solution B is based on the characteristics of the warning indicator light, and the correlation degree between the fault solution A and the fault data of the vehicle to be repaired is greater than the correlation degree between the fault solution B and the fault data of the vehicle to be repaired, therefore, First output the fault solution A and then output the fault solution B, that is, the fault solution A is ranked first, and the fault solution B is ranked second.
  • the vehicle repair model after entering the vehicle data and fault data of the vehicle to be repaired into the vehicle repair model, it is also possible to obtain the fault points associated with the fault solution, the repair process, and the manufacturer-related information of the vehicle to be repaired At least one of the above, so that the maintenance personnel can perform quick maintenance according to the failure solution and the failure point associated with the failure solution, the maintenance process or the manufacturer-related information.
  • the manufacturer-related information is the original factory-related information of the car to be repaired, including circuit diagrams, specifications, parts assembly and disassembly methods, and assembly and assembly man-hour costs.
  • the output of at least two fault solutions can also be determined according to the failure probability of the fault points associated with the at least two fault solutions order.
  • the vehicle maintenance method when outputting the obtained fault solution to the maintenance personnel, in order to facilitate the display and facilitate the maintenance personnel to quickly extract useful information, please refer to FIG. 5, the vehicle maintenance method further includes:
  • S340 Fill the fault solution into the solution module of the preset automobile maintenance case template to display it to the user.
  • the vehicle maintenance model can also be optimized.
  • the hyperparameters set by the user are obtained, and the automobile maintenance model is optimized according to the hyperparameters.
  • the vehicle maintenance model can be optimized by changing the hyperparameter settings.
  • the feedback result is the user's feedback on the feasibility of the fault solution output by the automobile maintenance system.
  • the fault solution, car data and fault data are integrated into a new car repair case, which is input into the car repair case sample to train the new car failure model and realize the continuous optimization of the car failure model.
  • the maintenance personnel will feedback the problem online, so that the technical personnel can optimize the vehicle maintenance model according to the problem feedback by the maintenance personnel.
  • the heuristic rule configuration module sends the configuration information to the neural network model, and the neural network model configures the neural network framework according to the configuration information , And extract sample data according to the configured neural network framework, and train the sample data through the preset neural network algorithm to obtain the vehicle maintenance model.
  • the heuristic rule configuration module of the automobile maintenance system can also be used to inspire the front-end user to input the selection conditions of the maintenance plan, or the heuristic rule configuration module can also be set at the front end or the back end to provide different user interfaces to the front end Maintenance personnel or back-end technicians.
  • the heuristic rule configuration module can implement the function of the module by the processor running code, and it can be configured in the front-end device or the back-end device, or in the automobile maintenance system of the embodiment of the present application.
  • the front-end maintenance personnel repair Toyota RAV4 they connect Toyota RAV4 to the car repair system through the car fault diagnosis instrument.
  • the car fault diagnosis instrument can obtain relevant data of Toyota RAV4 through user input and/or from Toyota RAV4.
  • the automobile fault diagnosis instrument outputs to the neural network model of the automobile maintenance system that the brand of Toyota RAV4 is Toyota, the model is RAV4, and the fault codes are C2123/23 and C2123/24 (the fault code is obtained from Toyota RAV4)
  • the neural network model performs feature matching according to the brand and car model to obtain the car maintenance model corresponding to Toyota RAV4, and input Toyota, RAV4, C2123/23 and C2123/24 into the obtained car maintenance model corresponding to Toyota RAV4.
  • the car repair model performs calculations based on the brand, model and fault code, and outputs the fault solutions corresponding to Toyota, RAV4, C2123/23 and C2123/24, including replacement of tire pressure sensors, replacement of tire pressure controllers, and repair of tire pressure control circuits, etc.
  • the maintenance personnel can use the maintenance program selection criteria as the input parameter before the neural network model calculation One is input to the neural network model, or, when the neural network model is calculated, the maintenance plan selection conditions are entered according to the prompts, and the neural network model screens out the fault solution according to the acceptable price range of 100-200 to replace the tire pressure sensor.
  • the replacement tire pressure sensor into the solution module of the preset car repair case template, fill Toyota and RAV4 into the basic vehicle information module of the preset car repair case template, and fill C2123/23 and C2123/24 into the preset
  • the car maintenance plan shown in Figure 7 is displayed to the maintenance personnel.
  • the maintenance process can also be displayed in the car maintenance plan, which can be used as a secondary display page. When the maintenance personnel need to further check, it will be displayed to the maintenance personnel.
  • the vehicle maintenance plan can also include manufacturer-related materials such as circuit diagrams, specifications, and component disassembly methods related to Toyota RAV4 for the maintenance personnel to perform Refer to the car repair plan; if the repairer does not input the repair plan selection conditions into the neural network model of the car repair system, the neural network model will first output the tire pressure sensor replacement plan according to the preset output order of the car repair model, and then output the replacement The tire pressure controller plan, and then output the tire pressure control circuit repair plan; the maintenance personnel repair the Toyota RAV4 according to the car repair plan displayed by the car repair system. If the repair is successful, it will feed back to the car repair system that it is feasible.
  • manufacturer-related materials such as circuit diagrams, specifications, and component disassembly methods related to Toyota RAV4 for the maintenance personnel to perform Refer to the car repair plan; if the repairer does not input the repair plan selection conditions into the neural network model of the car repair system, the neural network model will first output the tire pressure sensor replacement plan according to the preset output order of the car repair model, and
  • the car repairs The system enters the car maintenance plan as a new case into the car maintenance case sample; if the maintenance is unsuccessful, feedback to the car maintenance system is not feasible, and feedback problems to the car maintenance system, so that the technicians can address the problems reported by the maintenance personnel optimize;
  • the neural network model When the automobile fault diagnosis instrument outputs to the neural network model of the automobile maintenance system, the brand of Toyota RAV4 is Toyota, the model is RAV4, and the fault symptom is the tire pressure warning indicator light after replacing the tire (the fault symptom is input by the maintenance personnel through the automobile fault diagnosis instrument ), the neural network model performs feature matching according to the brand and car model to obtain the car repair model corresponding to Toyota RAV4, and enter the car repair model corresponding to Toyota RAV4 with Toyota, RAV4 and the tire pressure warning indicator after replacing tires.
  • the car repair model performs calculations based on the brand, model and fault symptoms, and outputs the fault solutions corresponding to Toyota, RAV4, and tire pressure warning indicator lights after tire replacement include replacement of tire pressure sensor, replacement of tire pressure controller, and repair Tire pressure control circuit, etc.
  • the selection condition is the acceptable price range of 100-200, that is, the maintenance personnel can change the maintenance plan before the neural network model is calculated
  • the selection condition is input to the neural network model as one of the input parameters, or, when the neural network model is calculated, the maintenance plan selection conditions are entered according to the prompts, and the neural network model screens out the fault solutions according to the acceptable price range 100-200.
  • the tire pressure sensor Replace the tire pressure sensor, and fill the replacement tire pressure sensor into the solution module of the preset car repair case template, fill Toyota and RAV4 into the basic vehicle information module of the preset car repair case template, and replace the tire pressure after the tire
  • the warning indicator When the warning indicator is on, fill in the fault phenomenon module of the preset car repair case template, and the car repair plan shown in Figure 8 is displayed to the maintenance personnel.
  • the repair process can also be displayed in the car repair plan, which can be used as a second
  • the level display page is displayed to the maintenance personnel when the maintenance personnel need to view it further.
  • the car maintenance plan can also include manufacturer-related materials such as circuit diagrams, specification parameters, and component disassembly methods related to Toyota RAV4.
  • the maintenance personnel make reference when implementing the vehicle maintenance program; if the maintenance personnel does not input the maintenance program selection conditions into the neural network model of the vehicle maintenance system, the neural network model first outputs the replacement tire pressure sensor program according to the preset output order of the vehicle maintenance model , And then output the plan to replace the tire pressure controller, and then output the plan to repair the tire pressure control circuit; the maintenance personnel repair the Toyota RAV4 according to the car repair plan displayed by the car repair system, and if the repair is successful, it is possible to feedback to the car repair system.
  • the auto repair system enters the auto repair plan as a new case into the auto repair case sample; if the repair is unsuccessful, it is not feasible to feed back to the auto repair system, and feedback the problem to the auto repair system so that the technicians can focus on the repair Optimize the problems feedback from personnel.
  • a failure solution for the car to be repaired is obtained, so that the maintenance personnel can directly repair the car according to the failure solution without the need
  • the failure solution obtained through the vehicle maintenance model does not need to be based on the maintenance experience and level of the maintenance personnel, which can avoid the lack of experience of the maintenance personnel.
  • the maintenance effect is poor.
  • FIG. 9 is a schematic structural diagram of an automobile maintenance device provided by an embodiment of the present invention.
  • the automobile maintenance device is applied to the above-mentioned automobile maintenance system, and the functions of each module of the automobile maintenance device are trained and calculated by the above-mentioned model
  • the unit 300 is executed to improve the maintenance efficiency of maintenance personnel.
  • module used in the embodiments of the present invention is a combination of software and/or hardware that can implement predetermined functions.
  • devices described in the following embodiments can be implemented by software, implementation by hardware or a combination of software and hardware is also possible.
  • the automobile maintenance device includes:
  • An obtaining module 500 which is used to obtain relevant data of the car to be repaired, the relevant data including car data and fault data of the car to be repaired;
  • the input module 600 is configured to input the vehicle data and the fault data of the vehicle to be repaired into the vehicle repair model to obtain a fault solution for the vehicle to be repaired.
  • the vehicle maintenance model is obtained through training based on sample data
  • sample data includes at least one of the following:
  • Car repair case samples car fault code samples, car system and component information samples, car diagnostic data stream samples, car failure symptoms and causes samples, and car basic information samples.
  • the acquiring module 500 is specifically configured to:
  • the car data includes at least one of the brand, model, and model year of the car to be repaired.
  • vehicle maintenance models corresponding to different vehicle data are obtained based on different neural network algorithm training.
  • the number of fault solutions is at least two, and the obtaining module 500 is further configured to:
  • a target failure solution is selected from the at least two failure solutions.
  • the number of the fault solutions is at least two, and the device further includes:
  • a providing module 700 which is configured to provide the user with the at least two fault solutions according to the preset output sequence of the automobile maintenance model
  • the preset output sequence is determined by the vehicle maintenance model according to the degree of correlation between the at least two fault solutions and the fault data of the vehicle to be repaired.
  • the input module 600 is also used to:
  • the failure points associated with the failure solution, the repair process, and the manufacturer of the car to be repaired are obtained At least one of the materials.
  • the device further includes:
  • a filling module 800 which is used to fill the fault solution into the solution module of the preset automobile maintenance case template to display it to the user;
  • the preset car repair case template also includes at least one of the following modules:
  • Basic vehicle information module applicable model module, fault phenomenon module, existing fault code module, fault point module, maintenance process module, case author module, manufacturer-related information module.
  • the fault data includes at least one of a fault code, a fault diagnosis data stream, and a fault symptom;
  • the fault symptom is input by the user, and the fault code and the fault diagnosis data stream are obtained from the vehicle to be repaired.
  • the acquiring module 500 is further used for:
  • the vehicle maintenance model is optimized according to the hyperparameters.
  • the acquiring module 500 is further used for:
  • the vehicle maintenance model is optimized according to the feedback result.
  • the content of the device embodiment can be quoted from the method embodiment on the premise that the content does not conflict with each other, which will not be repeated here.
  • the above-mentioned acquisition module 500, input module 600, provision module 700, and filling module 800 may be processing chips of the model training and computing unit 300.
  • a failure solution for the car to be repaired is obtained, so that the maintenance personnel can directly repair the car according to the failure solution without the need
  • the failure solution obtained through the vehicle maintenance model does not need to be based on the maintenance experience and level of the maintenance personnel, which can avoid the lack of experience of the maintenance personnel.
  • the maintenance effect is poor.
  • FIG. 12 is a schematic diagram of the hardware structure of a model training and calculation unit provided by an embodiment of the present invention, including:
  • processors 310 and memory 320 are taken as an example in FIG. 12.
  • the processor 310 and the memory 320 may be connected through a bus or in other ways. In FIG. 12, the connection through a bus is taken as an example.
  • the memory 320 can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, as corresponding to an automobile maintenance method in the above-mentioned embodiment of the present invention.
  • the program instructions of and a module corresponding to an automobile maintenance device for example, the acquisition module 500, the input module 600, the provision module 700, and the filling module 800, etc.
  • the processor 310 executes various functional applications and data processing of an automobile maintenance method by running non-volatile software programs, instructions, and modules stored in the memory 320, that is, implements an automobile maintenance method in the above method embodiment.
  • the memory 320 may include a program storage area and a data storage area.
  • the program storage area may store an operating system and an application program required by at least one function; the data storage area may store data created according to the use of an automobile maintenance device.
  • the storage data area also stores preset data, including preset output sequences and the like.
  • the memory 320 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.
  • the memory 320 may optionally include memories remotely provided with respect to the processor 310, and these remote memories may be connected to the processor 310 through a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
  • the program instructions and one or more modules are stored in the memory 320, and when executed by the one or more processors 310, each step of an automobile maintenance method in any of the foregoing method embodiments is executed, or , To realize the functions of each module of an automobile maintenance device in any of the above-mentioned device embodiments.
  • the above-mentioned product can execute the method provided in the above-mentioned embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.
  • the above-mentioned product can execute the method provided in the above-mentioned embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method.
  • the embodiment of the present invention also provides a non-volatile computer-readable storage medium, the computer-readable storage medium stores computer-executable instructions, the computer-executable instructions are executed by one or more processors, for example, FIG. 12
  • a processor 310 in any of the foregoing method embodiments may enable a computer to execute each step of an automobile maintenance method in any of the foregoing method embodiments, or realize the functions of various modules of an automobile repair device in any of the foregoing device embodiments.
  • the embodiment of the present invention also provides a computer program product, the computer program product includes a computer program stored on a non-volatile computer-readable storage medium, the computer program includes program instructions, when the program instructions are Or multiple processors, such as a processor 310 in FIG. 12, can cause a computer to execute each step of an automobile maintenance method in any of the foregoing method embodiments, or implement an automobile in any of the foregoing device embodiments. Repair the functions of the various modules of the device.
  • the device embodiments described above are merely illustrative.
  • the modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in One place, or it can be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
  • each embodiment can be implemented by software plus a general hardware platform, and of course, it can also be implemented by hardware.
  • Those of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by computer programs instructing relevant hardware.
  • the programs can be stored in a computer readable storage medium, and the program is executed At the time, it may include the flow of the implementation method of each method as described above.
  • the storage medium may be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM).

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Automation & Control Theory (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)

Abstract

本发明实施例涉及汽车和软件技术领域，公开了一种汽车维修方法、装置及其系统。其中，汽车维修方法包括：获取待维修汽车的相关数据，所述相关数据包括所述待维修汽车的汽车数据和故障数据；获取所述待维修汽车对应的汽车维修模型；将所述待维修汽车的所述汽车数据和所述故障数据输入至所述汽车维修模型，以得到针对所述待维修汽车的故障解决方案。通过上述方式，本发明实施例能够提高维修效率，减少因维修人员经验不足而造成的维修效果差的情况。

Description

一种汽车维修方法、装置及其系统
本申请要求于2019年8月2日提交中国专利局、申请号为201910712507.2、申请名称为“一种汽车维修方法、装置及其系统”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及汽车和软件技术领域，特别是涉及一种汽车维修方法、装置及其系统。
背景技术
随着汽车产业的不断发展，汽车保有量不断增加，汽车已经成为人们日常生活中不可或缺的一部分。在汽车行驶过程中，汽车的任意部件出现故障都会导致事故的发生，危害人们的人身安全，因此，为了保证汽车行驶的安全性，需要定期对汽车进行故障检查。
目前，主要通过维修人员的维修经验和维修水平对汽车进行故障检查，维修人员对汽车进行故障检查时，凭借维修经验对汽车的故障症状进行判断，并通过不断测试来确定汽车的故障点，需要花费较多的时间，维修效率较低，且若维修人员经验不足或对汽车型号不了解，则无法准确判断出汽车的故障点，进而无法得到故障解决方案，维修效果差。
发明内容
本发明实施例旨在提供一种汽车维修方法、装置及其系统，能够提高维修效率。
为解决上述技术问题，本发明实施例采用的一个技术方案是：提供一种汽车维修方法，包括：
获取待维修汽车的相关数据，所述相关数据包括所述待维修汽车的汽车数据和故障数据；
获取所述待维修汽车对应的汽车维修模型；
将所述待维修汽车的所述汽车数据和所述故障数据输入至所述汽车维修模型，以得到针对所述待维修汽车的故障解决方案。
可选地，所述汽车维修模型是根据样本数据训练得到的；
其中，所述样本数据包括以下至少一种：
汽车维修案例样本、汽车故障代码样本、汽车系统和部件信息样本、汽车诊断数据流样本、汽车故障症状及原因样本、汽车基本信息样本。
可选地，所述获取所述待维修汽车对应的汽车维修模型，包括：
根据所述待维修汽车的汽车数据，获取与所述汽车数据对应的汽车维修模型；
其中，所述汽车数据包括所述待维修汽车的品牌、车型和年款中的至少一种。
可选地，不同汽车数据对应的汽车维修模型是基于不同的神经网络算法训练得到的。
可选地，所述故障解决方案的数量为至少两个，所述方法还包括：
获取用户输入的维修方案选择条件；
根据所述维修方案选择条件，从所述至少两个故障解决方案中选取出目标故障解决方案。
可选地，所述故障解决方案的数量为至少两个，所述方法还包括：
按照所述汽车维修模型的预设输出顺序向用户提供所述至少两个故障解决方案；
其中，所述预设输出顺序是所述汽车维修模型根据所述至少两个故障解决方案与所述待维修汽车的所述故障数据的相关程度确定的。
可选地，所述将所述待维修汽车的所述汽车数据和所述故障数据输入至所述汽车维修模型之后，所述方法还包括：
得到与所述故障解决方案相关联的故障点、维修过程和所述待维修汽车的厂商相关资料中的至少一种。
可选地，所述方法还包括：
将所述故障解决方案填入预设汽车维修案例模板的解决方案模块中，以向用户进行显示；
其中，所述预设汽车维修案例模板还包括以下至少一个模块：
基本车辆信息模块、适用车型模块、故障现象模块、存在的故障码模块、故障点模块、维修过程模块、案例作者模块、厂商相关资料模块。
可选地，所述故障数据包括故障代码、故障诊断数据流、故障症状中的至少一个；
其中，所述故障症状是用户输入的，所述故障代码和所述故障诊断数据流是从所述待维修汽车中获取的。
可选地，，所述方法还包括：
获取用户设置的超参数；
根据所述超参数优化所述汽车维修模型。
可选地，所述方法还包括：
获取用户针对所述故障解决方案的反馈结果；
根据所述反馈结果优化所述汽车维修模型。
为解决上述技术问题，本发明实施例采用的另一个技术方案是：提供一种汽车维修装置，包括：
获取模块，所述获取模块用于获取待维修汽车的相关数据，所述相关数据包括所述待维修汽车的汽车数据和故障数据；以及
用于获取所述待维修汽车对应的汽车维修模型；
输入模块，所述输入模块用于将所述待维修汽车的所述汽车数据和所述故障数据输入至所述汽车维修模型，以得到针对所述待维修汽车的故障解决方案。
可选地，所述汽车维修模型是根据样本数据训练得到的；
其中，所述样本数据包括以下至少一种：
汽车维修案例样本、汽车故障代码样本、汽车系统和部件信息样本、汽车诊断数据流样本、汽车故障症状及原因样本、汽车基本信息样本。
可选地，所述获取模块具体用于：
根据所述待维修汽车的汽车数据，获取与所述汽车数据对应的汽车维修模型；
其中，所述汽车数据包括所述待维修汽车的品牌、车型和年款中的至少一种。
可选地，不同汽车数据对应的汽车维修模型是基于不同的神经网络算法训练得到的。
可选地，所述故障解决方案的数量为至少两个，所述获取模块还用于：
获取用户输入的维修方案选择条件；
根据所述维修方案选择条件，从所述至少两个故障解决方案中选取出目标故障解决方案。
可选地，所述故障解决方案的数量为至少两个，所述装置还包括：
提供模块，所述提供模块用于按照所述汽车维修模型的预设输出顺序向用户提供所述至少两个故障解决方案；
其中，所述预设输出顺序是所述汽车维修模型根据所述至少两个故障解决方案与所述待维修汽车的所述故障数据的相关程度确定的。
可选地，所述输入模块还用于：
在将所述待维修汽车的所述汽车数据和所述故障数据输入至所述汽车维修模型之后，得到与所述故障解决方案相关联的故障点、维修过程和所述待维修汽车的厂商相关资料中的至少一种。
可选地，所述装置还包括：
填写模块，所述填写模块用于将所述故障解决方案填入预设汽车维修案例模板的解决方案模块中，以向用户进行显示；
其中，所述预设汽车维修案例模板还包括以下至少一个模块：
基本车辆信息模块、适用车型模块、故障现象模块、存在的故障码模块、故障点模块、维修过程模块、案例作者模块、厂商相关资料模块。
可选地，所述故障数据包括故障代码、故障诊断数据流、故障症状中的至少一个；
其中，所述故障症状是用户输入的，所述故障代码和所述故障诊断数据流是从所述待维修汽车中获取的。
可选地，所述获取模块还用于：
获取用户设置的超参数；
根据所述超参数优化所述汽车维修模型。
可选地，所述获取模块还用于：
获取用户针对所述故障解决方案的反馈结果；
根据所述反馈结果优化所述汽车维修模型。
为解决上述技术问题，本发明实施例采用的另一个技术方案是：提供一种汽车维修系统，包括：
交互单元；
数据存储单元；
结果显示单元；以及
模型训练及运算单元，所述模型训练及运算单元分别与所述交互单元、所述数据存储单元以及所述结果显示单元通信连接；
其中，所述模型训练及运算单元包括：
至少一个处理器，以及
与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够用于执行以上所述的一种汽车维修方法。
为解决上述技术问题，本发明实施例采用的另一个技术方案是：提供一种非易失性计算机可读存储介质，所述非易失性计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使汽车维修系统执行以上所述的一种汽车维修方法。
本发明实施例的有益效果是：区别于现有技术的情况下，本发明实施例提供一种汽车维修方法、装置及系统，在汽车维修方法中，获取待维修汽车的汽车数据和故障数据后，获取待维修汽车对应的汽车维修模型，通过将汽车数据和故障数据输入汽车维修模型，得到针对待维修汽车的故障解决方案，此时，维修人员能够直接根据故障解决方案对汽车进行维修，不需要通过不断测试来确定故障点，极大地缩短了维修时间，提高维修效率，并且通过汽车维修模型得到的故障解决方案不需要依据维修人员的维修经验和维修水平，能够避免因维修人员经验不足而造成的维修效果差的情况。
附图说明
一个或多个实施例通过与之对应的附图中的图片进行示例性说明，这些示例性说明并不构成对实施例的限定，附图中具有相同参考数字标号的元件表示为类似的元件，除非有特别申明，附图中的图不构成比例限制。
图1是本发明实施例提供的一种汽车维修系统的结构示意图；
图2是本发明实施例提供的一种汽车维修方法的流程示意图；
图3是本发明另一实施例提供的一种汽车维修方法的流程示意图；
图4是本发明又一实施例提供的一种汽车维修方法的流程示意图；
图5是本发明再一实施例提供的一种汽车维修方法的流程示意图；
图6是本发明实施例提供的一种应用场景的结构示意图；
图7是图6所示的应用场景输出的一种汽车维修方案的示意图；
图8是图6所示的应用场景输出的另一种汽车维修方案的示意图；
图9是本发明实施例提供的一种汽车维修装置的结构示意图；
图10是本发明另一实施例提供的一种汽车维修装置的结构示意图；
图11是本发明又一实施例提供的一种汽车维修装置的结构示意图；
图12是本发明实施例提供的一种模型训练及运算单元的硬件结构示意图。
具体实施方式
为使本发明实施例的目的、技术方案和优点更加清楚，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整的描述，显然，所描述的实施例是本发明一部分实施例，而不是全部的实施例。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
需要说明的是，当元件被表述“固定于”另一个元件，它可以直接在另一个元件上、或者其间可以存在一个或多个居中的元件。当一个元件被表述“连接”另一个元件，它可以是直接连接到另一个元件、或者其间可以存在一个或多个居中的元件。本说明书所使用的术语“垂直的”、“水平的”、“左”、“右”以及类似的表述只是为了说明的目的。
此外，下面所描述的本发明各个实施例中所涉及到的技术特征只要彼此之间未构成冲突就可以相互组合。
本发明提供了一种汽车维修方法及装置，该方法及装置应用于汽车维修系统，从而使得该汽车维修系统能够根据待维修汽车的汽车数据和故障数据输出故障解决方案。当维修人员使用汽车维修系统时，将待维修汽车的汽车数据和故障数据输入汽车维修系统，即可获得故障解决方案，无需维修人员依据故障症状进行判断、测试来确定故障点，极大地缩短了维修时间，提高维修效率，并且能够避免因维修人员经验不足而造成的维修效果差的情况。
下面，将通过具体实施例对本发明进行阐述。
请参阅图1，是本发明实施例提供的一种汽车维修系统，该汽车维修系统包括：交互单元100、数据存储单元200、模型训练及运算单元300以及结果显示单元400，模型训练及运算单元300分别与交互单元100、数据存储单元200以及结果显示单元400通信连接。
交互单元100用于与用户进行信息交互。
其中，用户可以为前端维修人员，也可以为后端技术人员。
当用户为前端维修人员时，用户可以通过交互单元100向汽车维修系统交互反馈结果、维修方案选择条件以及待维修汽车的相关数据。
其中，反馈结果为用户针对汽车维修系统输出的故障解决方案的可行性进行的反馈。
维修方案选择条件则为用户设置的个性化需求条件，用于限制汽车维修系统输出的故障解决方案，通过维修方案选择条件能够使汽车维修系统输出满足用户个性化需求的故障解决方案。该维修方案选择条件包括但不限于：可接受价格范围、配件品牌喜好、可接受时长范围等。
待维修汽车的相关数据则包括待维修汽车的汽车数据和故障数据。
汽车数据为表征待维修汽车基本信息的数据，包括但不限于：品牌、车型和年款等。
故障数据则为表征待维修汽车故障情况的数据，包括但不限于：故障代码、故障诊断数据流和故障症状等。
当用户为后端技术人员时，用户可以通过交互单元100向汽车维修系统交互配置信息，该配置信息包括超参数。
其中，超参数用于配置神经网络框架，包括但不限于：隐藏层的层数、每层神经元的个数、学习率、权值衰减和迭代次数等。
该交互单元100包括通信接口，该通信接口能够与汽车故障诊断仪连接，以使交互单元100能够通过汽车故障诊断仪从待维修汽车中获取故障代码、故障诊断数据流以及汽车数据中的至少一种。
该交互单元100还包括键盘或者触控屏幕等物理输入部件，反馈结果、维修方案选择条件、故障症状以及配置信息能够通过键盘或者触控屏幕等物理输入部件输入汽车维修系统。
在一些实施例中，汽车数据也能够通过键盘或者触控屏幕等物理输入部件输入汽车维修系统。
数据存储单元200用于存储样本数据。
其中，样本数据用于训练汽车维修模型，该样本数据包括以下至少一种：汽车维修案例样本、汽车故障代码样本、汽车系统和部件信息样本、汽车诊断数据流样本、汽车故障症状及原因样本以及汽车基本信息样本等。
其中，汽车维修案例样本包括数量若干的汽车维修案例，该汽车维修案例通过预设汽车维修案例模板进行收集。
该预设汽车维修案例模板包括解决方案模块，以及基本车辆信息模块、适用车型模块、故障现象模块、存在的故障码模块、故障点模块、维修过程模块、案例作者模块以及厂商相关资料模块中的至少一个模块。
其中，解决方案模块用于收集汽车维修案例中的故障解决方案；基本车辆信息模块用于收集汽车维修案例中的车辆信息，该车辆信息包括品牌、车型、年款、VIN码、里程、发动机型号、变速箱、车型代码、底盘号等；适用车型 模块用于收集汽车维修案例中的适用车型；故障现象模块用于收集汽车维修案例中的故障症状；存在的故障码模块用于收集汽车维修案例中存在的故障码；故障点模块用于收集汽车维修案例中的故障可疑点；维修过程模块用于收集汽车维修案例中的维修步骤；案例作者模块用于收集汽车维修案例的作者信息；厂商相关资料模块则用于收集汽车维修案例所涉及的汽车的原厂相关资料，包括电路图、规格参数、部件的拆装方法、拆装工时费用等。
在本发明实施例中，汽车维修案例样本按照汽车品牌、车型、年款进行逐级分类存储。比如：设置若干个品牌的初级数据库，每个品牌的初级数据库包括若干个车型的次级数据库，每个车型的次级数据库包括若干个年款的次次级数据库。
汽车故障代码样本包括汽车故障代码与故障原因的对应关系，该汽车故障代码样本按照汽车品牌、车型、年款进行逐级分类存储。
汽车系统和部件信息样本包括汽车系统中各个部件的损坏概率，该汽车系统和部件信息样本按照汽车品牌、车型、年款进行逐级分类存储。
汽车诊断数据流样本包括汽车诊断数据流与故障原因的对应关系，该汽车诊断数据流样本按照汽车品牌、车型、年款进行逐级分类存储。
汽车故障症状及原因样本包括汽车故障症状与故障原因的对应关系该汽车故障症状及原因样本按照汽车品牌、车型、年款进行逐级分类存储。
汽车基本信息样本则包括品牌、车型、年款等汽车基本信息。
可以理解的是，在本发明实施例中，能够通过汽车维修案例样本训练汽车维修模型，也能够通过汽车维修案例样本、汽车故障代码样本训练汽车维修模型，还能够通过汽车维修案例样本、汽车故障症状及原因样本以及汽车系统和部件信息样本训练汽车维修模型，样本数据的多种组合方式均能够实现汽车维修模型的训练，在此不再一一赘述。
模型训练及运算单元300则用于进行汽车维修模型的训练，其能够根据交互单元100获取的配置信息从数据存储单元200中提取样本数据来训练汽车维修模型。
具体地，交互单元100获取配置信息并将配置信息发送至模型训练及运算单元300后，模型训练及运算单元300根据配置信息配置神经网络框架，并依据神经网络框架从数据存储单元200中提取样本数据，通过预设神经网络算法对样本数据进行训练，得到汽车维修模型。
该模型训练及运算单元300还能够通过汽车维修模型运算得到故障解决方案，并将得到的故障解决方案输出给维修人员，以使维修人员能够根据故障解决方案对待维修汽车进行维修，提高维修人员的维修效率。
具体地，模型训练及运算单元300将交互单元100获取的待维修汽车的相关数据输入待维修汽车对应的汽车维修模型中进行运算，得到针对待维修汽车的故障解决方案。
在一些实施例中，当模型训练及运算单元300得到故障解决方案后，能够 根据交互单元100获取的维修方案选择条件选择性输出符合用户个性化需求的故障解决方案。
在一些实施例中，当维修人员根据故障解决方案对待维修汽车进行维修后，还能够通过交互单元100向模型训练及运算单元300反馈故障解决方案的可行性，以使模型训练及运算单元300能够根据反馈结果对汽车维修模型进行优化。
其中，模型训练及运算单元300可由处理器以及存储有代码的存储器实现，处理器调用存储器中的代码以实现模型训练及运算的功能。
结果显示单元400则用于向用户显示模型训练及运算单元300输出的故障解决方案。其中，故障解决方案能够通过预设汽车维修案例模板的形式进行显示。
可以理解的是，结果显示单元400可以为显示屏，也可以为计算机、平板电脑、智能手机等设置有显示屏的外部电子设备。
进一步地，请参阅图2，是本发明实施例提供的一种汽车维修方法的流程示意图，该汽车维修方法应用于上述汽车维修系统，并由上述模型训练及运算单元300执行，用于提高维修人员的维修效率。
具体地，该汽车维修方法包括：
S110：获取待维修汽车的相关数据。
其中，相关数据包括待维修汽车的汽车数据和故障数据。
汽车数据包括待维修汽车的品牌、车型和年款中的至少一种，该汽车数据可以是用户输入的，也可以是从待维修汽车中获取的。
故障数据包括故障代码、故障诊断数据流和故障症状中的至少一个，其中，故障症状是用户输入的，故障代码和故障诊断数据流是从待维修汽车中获取的。
在一些实施例中，能够通过汽车故障诊断仪从待维修汽车中获取汽车数据、故障代码和故障诊断数据流。
S120：获取所述待维修汽车对应的汽车维修模型。
上述汽车维修模型是根据样本数据训练得到的神经网络模型，通过汽车维修模型能够运算得到故障解决方案。
其中，样本数据包括汽车维修案例样本、汽车故障代码样本、汽车系统和部件信息样本、汽车诊断数据流样本、汽车故障症状及原因样本以及汽车基本信息样本中的至少一种。比如，样本数据包括汽车维修案例样本；比如，样本数据包括汽车维修案例样本、汽车故障代码样本；比如，样本数据包括汽车维修案例样本、汽车故障症状及原因样本以及汽车系统和部件信息样本；比如，样本数据包括汽车维修案例样本、汽车故障代码样本、汽车系统和部件信息样本、汽车诊断数据流样本、汽车故障症状及原因样本以及汽车基本信息样本。
其中，汽车维修案例样本包括数量若干的汽车维修案例，该汽车维修案例通过预设汽车维修案例模板进行收集。
该预设汽车维修案例模板包括解决方案模块，以及基本车辆信息模块、适用车型模块、故障现象模块、存在的故障码模块、故障点模块、维修过程模块、案例作者模块以及厂商相关资料模块中的至少一个模块。比如，预设汽车维修案例模板包括解决方案模块、基本车辆信息模块、适用车型模块、故障现象模块、存在的故障码模块、故障点模块、维修过程模块、案例作者模块以及厂商相关资料模块；比如，预设汽车维修案例模板包括解决方案模块、维修过程模块以及故障现象模块；比如，预设汽车维修案例模板包括解决方案模块、基本车辆信息模块、存在的故障码模块以及厂商相关资料模块。
其中，解决方案模块用于收集汽车维修案例中的故障解决方案；基本车辆信息模块用于收集汽车维修案例中的车辆信息，该车辆信息包括品牌、车型、年款、VIN码、里程、发动机型号、变速箱、车型代码、底盘号等；适用车型模块用于收集汽车维修案例中的适用车型；故障现象模块用于收集汽车维修案例中的故障症状；存在的故障码模块用于收集汽车维修案例中存在的故障码；故障点模块用于收集汽车维修案例中的故障可疑点；维修过程模块用于收集汽车维修案例中的维修步骤；案例作者模块用于收集汽车维修案例的作者信息；厂商相关资料模块则用于收集汽车维修案例所涉及的汽车的原厂相关资料，包括电路图、规格参数、部件的拆装方法、拆装工时费用等。
该汽车维修案例样本按照汽车品牌、车型、年款进行逐级分类存储。
汽车故障代码样本包括汽车故障代码与故障原因的对应关系，该汽车故障代码样本按照汽车品牌、车型、年款进行逐级分类存储。
汽车系统和部件信息样本包括汽车系统中各个部件的损坏概率，该汽车系统和部件信息样本按照汽车品牌、车型、年款进行逐级分类存储。
汽车诊断数据流样本包括汽车诊断数据流与故障原因的对应关系，该汽车诊断数据流样本按照汽车品牌、车型、年款进行逐级分类存储。
汽车故障症状及原因样本包括汽车故障症状与故障原因的对应关系该汽车故障症状及原因样本按照汽车品牌、车型、年款进行逐级分类存储。
汽车基本信息样本则包括品牌、车型、年款等汽车基本信息。
可以理解的是，当通过样本数据训练汽车维修模型时，获取配置信息配置神经网络框架，然后依据神经网络框架提取样本数据，然后通过预设神经网络算法对样本数据进行训练，得到汽车维修模型。
其中，配置信息包括超参数，该超参数用于配置神经网络框架，包括但不限于：隐藏层的层数、每层神经元的个数、学习率、权值衰减和迭代次数等。
所提取的样本数据则包括汽车品牌、车型、年款、故障代码、故障诊断数据流、故障症状、故障解决方案等特征，使得训练出的汽车维修模型能够按照品牌、车型以及年款进行分类。
基于此，获取待维修汽车对应的汽车维修模型时，能够根据所获取的待维修汽车的汽车数据，获取与汽车数据对应的汽车维修模型。
比如，当汽车数据为品牌时，则根据待维修汽车的品牌获取该品牌对应的 汽车维修模型；当汽车数据为品牌和车型时，则根据待维修汽车的品牌和车型获取该品牌和车型对应的汽车维修模型。
其中，不同汽车数据对应的汽车维修模型是基于不同的神经网络算法训练得到的。
S130：将所述待维修汽车的所述汽车数据和所述故障数据输入至所述汽车维修模型，以得到针对所述待维修汽车的故障解决方案。
由于汽车维修模型由汽车品牌、车型、年款、故障代码、故障诊断数据流、故障症状、故障解决方案等特征训练得到，因此，将汽车数据和故障数据输入汽车维修模型后，汽车维修模型根据汽车数据和故障数据进行特征匹配，将符合条件的汽车维修模型对应的故障解决方案确定为待维修汽车的故障解决方案。
其中，所得到的待维修汽车的故障解决方案的数量可以为1个，也可以为至少两个。
当所得到的故障解决方案的数量为1个时，能够直接将故障解决方案输出给维修人员。
当所得到的故障解决方案的数量为至少两个时，能够选择1个故障解决方案输出给维修人员，也能够将全部故障解决方案输出给维修人员。
当选择1个故障解决方案输出给维修人员时，为了满足车主的个性化需求，请参阅图3，该汽车维修方法还包括：
S140：获取用户输入的维修方案选择条件；
S150：根据所述维修方案选择条件，从所述至少两个故障解决方案中选取出目标故障解决方案。
其中，维修方案选择条件为用户设置的个性化需求条件，用于限制故障解决方案的输出，通过维修方案选择条件能够输出满足车主个性化需求的故障解决方案。该维修方案选择条件包括但不限于：可接受价格范围、配件品牌喜好、可接受时长范围等。
举例而言，当用户输入的维修方案选择条件包括可接受价格范围500-800时，若得到的故障解决方案A和故障解决方案B中，故障解决方案A的维修价格为600，故障解决方案B的维修价格为1000，则故障解决方案A符合用户输入的维修方案选择条件，将故障解决方案A输出给维修人员。
可以理解的是，在本发明实施例中，步骤S140可以与步骤S110-S130中任意一步同时进行，也可以在步骤S130后执行，在此不做具体限定。
当将全部故障解决方案输出给维修人员时，为了方便维修人员选择，请参阅图4，该汽车维修方法还包括：
S240：按照所述汽车维修模型的预设输出顺序向用户提供所述至少两个故障解决方案。
其中，所述预设输出顺序是所述汽车维修模型根据所述至少两个故障解决方案与所述待维修汽车的所述故障数据的相关程度确定的。
举例而言，当所获取的故障数据包括更换轮胎后胎压警告指示灯亮时，若得到的故障解决方案A和故障解决方案B中，故障解决方案A是根据更换轮胎后胎压警告指示灯亮的特征得出，故障解决方案B是根据警告指示灯亮的特征得出，则故障解决方案A与待维修汽车的故障数据的相关程度大于故障解决方案B与待维修汽车的故障数据的相关程度，因此，先输出故障解决方案A后再输出故障解决方案B，即故障解决方案A排列在第一位，故障解决方案B排列在第二位。
进一步地，在一些实施例中，在将待维修汽车的汽车数据和故障数据输入汽车维修模型之后，还能够得到与故障解决方案相关联的故障点、维修过程和待维修汽车的厂商相关资料中的至少一种，以方便维修人员能够根据故障解决方案以及与故障解决方案相关联的故障点、维修过程或者厂商相关资料进行快速维修。
其中，厂商相关资料为待维修汽车的原厂相关资料，包括电路图、规格参数、部件的拆装方法、拆装工时费用等。
当得到与故障解决方案相关联的故障点后，将全部故障解决方案输出给维修人员时，还能够根据至少两个故障解决方案相关联的故障点的故障概率确定至少两个故障解决方案的输出顺序。
进一步地，在一些实施例中，在将得到的故障解决方案输出给维修人员时，为了方便显示以及方便维修人员快速提取有用信息，请参阅图5，该汽车维修方法还包括：
S340：将所述故障解决方案填入预设汽车维修案例模板的解决方案模块中，以向用户进行显示。
进一步地，为了增加汽车维修模型的准确性，还能够对汽车维修模型进行优化。
具体地，在一些实施例中，对汽车维修模型进行优化时，获取用户设置的超参数，根据超参数优化汽车维修模型。比如，能够通过改变超参数设置优化汽车维修模型。
在另一些实施例中，对汽车维修模型进行优化时，还能够获取用户针对故障解决方案的反馈结果，根据反馈结果优化汽车维修模型。
其中，反馈结果为用户针对汽车维修系统输出的故障解决方案的可行性进行的反馈。
当故障解决方案可行时，将该故障解决方案、汽车数据及故障数据整合成新的汽车维修案例，输入汽车维修案例样本中，以训练新的汽车故障模型，实现汽车故障模型的不断优化。
当故障解决方案不可行时，维修人员在线反馈问题，以使技术人员针对维修人员反馈的问题进行汽车维修模型的优化。
下面结合图6至图8，具体描述本发明实施例中涉及的一种应用场景的实例。
以维修汽车为丰田RAV4，且该待维修汽车的故障症状为更换轮胎后胎压警告指示灯亮为例进行说明。
如图6所示，后端技术人员将配置信息发送至汽车维修系统的启发式规则配置模块后，启发式规则配置模块将配置信息发送至神经网络模型，神经网络模型根据配置信息配置神经网络框架，并依据配置后的神经网络框架提取样本数据，通过预设神经网络算法对样本数据进行训练，得到汽车维修模型。其中，汽车维修系统的启发式规则配置模块还能够用于启发前端用户输入维修方案的选择条件，或者，还可以在前端或后端均设置启发式规则配置模块，以提供不同的用户接口至前端维修人员或后端技术人员。启发式规则配置模块可以由处理器运行代码实现该模块的功能，其可配置在前端设备或后端设备中，或者，配置在本申请实施例的汽车维修系统中。
当前端维修人员维修丰田RAV4时，将丰田RAV4通过汽车故障诊断仪与汽车维修系统连接，此时，汽车故障诊断仪可以通过用户输入和/或从丰田RAV4中获取，得到丰田RAV4的相关数据，如品牌、车型、故障代码、故障症状等，
当汽车故障诊断仪向汽车维修系统的神经网络模型输出丰田RAV4的品牌为丰田、车型为RAV4、故障代码为C2123/23和C2123/24(该故障代码是从丰田RAV4中获取到的)时，神经网络模型根据品牌和车型进行特征匹配，获取与丰田RAV4对应的汽车维修模型，并将丰田、RAV4、C2123/23和C2123/24输入所获取的与丰田RAV4对应的汽车维修模型中，此时，汽车维修模型根据品牌、车型和故障代码进行运算，输出与丰田、RAV4、C2123/23和C2123/24对应的故障解决方案包括更换胎压传感器、更换胎压控制器和维修胎压控制电路等，此时或此前，若维修人员向汽车维修系统的神经网络模型输入维修方案选择条件为可接受价格范围100-200，即维修人员可以在神经网络模型运算之前，将维修方案选择条件作为输入参数之一输入至神经网络模型，或者，在神经网络模型运算时，根据提示输入维修方案选择条件，则神经网络模型根据可接受价格范围100-200筛选出符合的故障解决方案为更换胎压传感器，并将更换胎压传感器填入预设汽车维修案例模板的解决方案模块中，将丰田和RAV4填入预设汽车维修案例模板的基本车辆信息模块中，将C2123/23和C2123/24填入预设汽车维修案例模板的存在的故障码模块中，得到如图7所示的汽车维修方案显示给维修人员，进一步地，该汽车维修方案中还可以显示维修过程，其可以作为二级显示页面，在维修人员需要进一步查看时，显示给维修人员，进一步地，该汽车维修方案中还可以包括与丰田RAV4相关的电路图、规格参数、部件的拆装方法等厂商相关资料，以供维修人员在执行汽车维修方案时进行参考；若维修人员未向汽车维修系统的神经网络模型输入维修方案选择条件，则神经网络模型按照汽车维修模型的预设输出顺序先输出更换胎压传感器的方案，再输出更换胎压控制器的方案，再输出维修胎压控制电路的方案；维修人员根据汽车维修系统显示的汽车维修方案维修该丰田RAV4，若维修成功，则向汽车维修系统反馈可行，此时，汽车维修系统将该汽车维修方案作为新的 案例输入汽车维修案例样本中；若维修不成功，则向汽车维修系统反馈不可行，并向汽车维修系统反馈问题，以使技术人员能够针对维修人员反馈的问题进行优化；
当汽车故障诊断仪向汽车维修系统的神经网络模型输出丰田RAV4的品牌为丰田、车型为RAV4、故障症状为更换轮胎后胎压警告指示灯亮(该故障症状为维修人员通过汽车故障诊断仪输入的)时，神经网络模型根据品牌和车型进行特征匹配，获取与丰田RAV4对应的汽车维修模型，并将丰田、RAV4和更换轮胎后胎压警告指示灯亮输入所获取的与丰田RAV4对应的汽车维修模型中，此时，汽车维修模型根据品牌、车型和故障症状进行运算，输出与丰田、RAV4和更换轮胎后胎压警告指示灯亮对应的故障解决方案包括更换胎压传感器、更换胎压控制器和维修胎压控制电路等，此时或此前，若维修人员向汽车维修系统的神经网络模型输入维修方案选择条件为可接受价格范围100-200，即维修人员可以在神经网络模型运算之前，将维修方案选择条件作为输入参数之一输入至神经网络模型，或者，在神经网络模型运算时，根据提示输入维修方案选择条件，则神经网络模型根据可接受价格范围100-200筛选出符合的故障解决方案为更换胎压传感器，并将更换胎压传感器填入预设汽车维修案例模板的解决方案模块中，将丰田和RAV4填入预设汽车维修案例模板的基本车辆信息模块中，将更换轮胎后胎压警告指示灯亮填入预设汽车维修案例模板的故障现象模块中，得到如图8所示的汽车维修方案显示给维修人员，进一步地，该汽车维修方案中还可以显示维修过程，其可以作为二级显示页面，在维修人员需要进一步查看时，显示给维修人员，进一步地，该汽车维修方案中还可以包括与丰田RAV4相关的电路图、规格参数、部件的拆装方法等厂商相关资料，以供维修人员在执行汽车维修方案时进行参考；若维修人员未向汽车维修系统的神经网络模型输入维修方案选择条件，则神经网络模型按照汽车维修模型的预设输出顺序先输出更换胎压传感器的方案，再输出更换胎压控制器的方案，再输出维修胎压控制电路的方案；维修人员根据汽车维修系统显示的汽车维修方案维修该丰田RAV4，若维修成功，则向汽车维修系统反馈可行，此时，汽车维修系统将该汽车维修方案作为新的案例输入汽车维修案例样本中；若维修不成功，则向汽车维修系统反馈不可行，并向汽车维修系统反馈问题，以使技术人员能够针对维修人员反馈的问题进行优化。
在本发明实施例中，通过将汽车数据和故障数据输入待维修汽车对应的汽车维修模型，得到针对待维修汽车的故障解决方案，使得维修人员能够直接根据故障解决方案对汽车进行维修，不需要通过不断测试来确定故障点，极大地缩短了维修时间，提高维修效率，并且通过汽车维修模型得到的故障解决方案不需要依据维修人员的维修经验和维修水平，能够避免因维修人员经验不足而造成的维修效果差的情况。
进一步地，请参阅图9，是本发明实施例提供的一种汽车维修装置的结构示意图，该汽车维修装置应用于上述汽车维修系统，并且该汽车维修装置各个 模块的功能由上述模型训练及运算单元300执行，用于提高维修人员的维修效率。
值得注意的是，本发明实施例所使用的术语“模块”为可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置可以以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能被构想的。
具体地，该汽车维修装置包括：
获取模块500，所述获取模块500用于获取待维修汽车的相关数据，所述相关数据包括所述待维修汽车的汽车数据和故障数据；以及
用于获取所述待维修汽车对应的汽车维修模型；
输入模块600，所述输入模块600用于将所述待维修汽车的所述汽车数据和所述故障数据输入至所述汽车维修模型，以得到针对所述待维修汽车的故障解决方案。
在一些实施例中，所述汽车维修模型是根据样本数据训练得到的；
其中，所述样本数据包括以下至少一种：
汽车维修案例样本、汽车故障代码样本、汽车系统和部件信息样本、汽车诊断数据流样本、汽车故障症状及原因样本、汽车基本信息样本。
在一些实施例中，所述获取模块500具体用于：
根据所述待维修汽车的汽车数据，获取与所述汽车数据对应的汽车维修模型；
其中，所述汽车数据包括所述待维修汽车的品牌、车型和年款中的至少一种。
在一些实施例中，不同汽车数据对应的汽车维修模型是基于不同的神经网络算法训练得到的。
在一些实施例中，所述故障解决方案的数量为至少两个，所述获取模块500还用于：
获取用户输入的维修方案选择条件；
根据所述维修方案选择条件，从所述至少两个故障解决方案中选取出目标故障解决方案。
请参阅图10，在一些实施例中，所述故障解决方案的数量为至少两个，所述装置还包括：
提供模块700，所述提供模块700用于按照所述汽车维修模型的预设输出顺序向用户提供所述至少两个故障解决方案；
其中，所述预设输出顺序是所述汽车维修模型根据所述至少两个故障解决方案与所述待维修汽车的所述故障数据的相关程度确定的。
在一些实施例中，所述输入模块600还用于：
在将所述待维修汽车的所述汽车数据和所述故障数据输入至所述汽车维修模型之后，得到与所述故障解决方案相关联的故障点、维修过程和所述待维修汽车的厂商相关资料中的至少一种。
请参阅图11，在一些实施例中，所述装置还包括：
填写模块800，所述填写模块800用于将所述故障解决方案填入预设汽车维修案例模板的解决方案模块中，以向用户进行显示；
其中，所述预设汽车维修案例模板还包括以下至少一个模块：
基本车辆信息模块、适用车型模块、故障现象模块、存在的故障码模块、故障点模块、维修过程模块、案例作者模块、厂商相关资料模块。
在一些实施例中，所述故障数据包括故障代码、故障诊断数据流、故障症状中的至少一个；
其中，所述故障症状是用户输入的，所述故障代码和所述故障诊断数据流是从所述待维修汽车中获取的。
在一些实施例中，所述获取模块500还用于：
获取用户设置的超参数；
根据所述超参数优化所述汽车维修模型。
在一些实施例中，所述获取模块500还用于：
获取用户针对所述故障解决方案的反馈结果；
根据所述反馈结果优化所述汽车维修模型。
由于装置实施例和方法实施例是基于同一构思，在内容不互相冲突的前提下，装置实施例的内容可以引用方法实施例的，在此不再一一赘述。
在其他一些可替代实施例中，上述获取模块500、输入模块600、提供模块700以及填写模块800可以为模型训练及运算单元300的处理芯片。
在本发明实施例中，通过将汽车数据和故障数据输入待维修汽车对应的汽车维修模型，得到针对待维修汽车的故障解决方案，使得维修人员能够直接根据故障解决方案对汽车进行维修，不需要通过不断测试来确定故障点，极大地缩短了维修时间，提高维修效率，并且通过汽车维修模型得到的故障解决方案不需要依据维修人员的维修经验和维修水平，能够避免因维修人员经验不足而造成的维修效果差的情况。
进一步地，请参阅图12，是本发明实施例提供的一种模型训练及运算单元的硬件结构示意图，包括：
一个或多个处理器310以及存储器320。其中，图12中以一个处理器310为例。
处理器310和存储器320可以通过总线或者其他方式连接，图12中以通过总线连接为例。
存储器320作为一种非易失性计算机可读存储介质，可用于存储非易失性软件程序、非易失性计算机可执行程序以及模块，如本发明上述实施例中的一种汽车维修方法对应的程序指令以及一种汽车维修装置对应的模块(例如，获取模块500、输入模块600、提供模块700和填写模块800等)。处理器310通过运行存储在存储器320中的非易失性软件程序、指令以及模块，从而执行一种汽车维修方法的各种功能应用以及数据处理，即实现上述方法实施例中的 一种汽车维修方法以及上述装置实施例的各个模块的功能。
存储器320可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据一种汽车维修装置的使用所创建的数据等。
所述存储数据区还存储有预设的数据，包括预设输出顺序等。
此外，存储器320可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他非易失性固态存储器件。在一些实施例中，存储器320可选包括相对于处理器310远程设置的存储器，这些远程存储器可以通过网络连接至处理器310。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
所述程序指令以及一个或多个模块存储在所述存储器320中，当被所述一个或者多个处理器310执行时，执行上述任意方法实施例中的一种汽车维修方法的各个步骤，或者，实现上述任意装置实施例中的一种汽车维修装置的各个模块的功能。
上述产品可执行本发明上述实施例所提供的方法，具备执行方法相应的功能模块和有益效果。未在本实施例中详尽描述的技术细节，可参见本发明上述实施例所提供的方法。
本发明实施例还提供了一种非易失性计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，该计算机可执行指令被一个或多个处理器执行，例如图12中的一个处理器310，可使得计算机执行上述任意方法实施例中的一种汽车维修方法的各个步骤，或者，实现上述任意装置实施例中的一种汽车维修装置的各个模块的功能。
本发明实施例还提供了一种计算机程序产品，所述计算机程序产品包括存储在非易失性计算机可读存储介质上的计算机程序，所述计算机程序包括程序指令，当所述程序指令被一个或多个处理器执行，例如图12中的一个处理器310，可使得计算机执行上述任意方法实施例中的一种汽车维修方法的各个步骤，或者，实现上述任意装置实施例中的一种汽车维修装置的各个模块的功能。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的模块可以是或者也可以不是物理上分开的，作为模块显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
通过以上的实施例的描述，本领域普通技术人员可以清楚地了解到各实施例可借助软件加通用硬件平台的方式来实现，当然也可以通过硬件。本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程是可以通过计算机程序指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施方法的流程。其中，所述存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)或随机 存储记忆体(RandomAccessMemory,RAM)等。
以上所述仅为本发明的实施例，并非因此限制本发明的专利范围，凡是利用本发明说明书及附图内容所作的等效结构或等效流程变换，或直接或间接运用在其他相关的技术领域，均同理包括在本发明的专利保护范围内。
最后应说明的是：以上实施例仅用以说明本发明的技术方案，而非对其限制；在本发明的思路下，以上实施例或者不同实施例中的技术特征之间也可以进行组合，步骤可以以任意顺序实现，并存在如上所述的本发明的不同方面的许多其它变化，为了简明，它们没有在细节中提供；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本申请各实施例技术方案的范围。

Claims (24)

  1. 一种汽车维修方法，其特征在于，包括：
    获取待维修汽车的相关数据，所述相关数据包括所述待维修汽车的汽车数据和故障数据；
    获取所述待维修汽车对应的汽车维修模型；
    将所述待维修汽车的所述汽车数据和所述故障数据输入至所述汽车维修模型，以得到针对所述待维修汽车的故障解决方案。
  2. 根据权利要求1所述的方法，其特征在于，所述汽车维修模型是根据样本数据训练得到的；
    其中，所述样本数据包括以下至少一种：
    汽车维修案例样本、汽车故障代码样本、汽车系统和部件信息样本、汽车诊断数据流样本、汽车故障症状及原因样本、汽车基本信息样本。
  3. 根据权利要求1或2所述的方法，其特征在于，所述获取所述待维修汽车对应的汽车维修模型，包括：
    根据所述待维修汽车的汽车数据，获取与所述汽车数据对应的汽车维修模型；
    其中，所述汽车数据包括所述待维修汽车的品牌、车型和年款中的至少一种。
  4. 根据权利要求3所述的方法，其特征在于，不同汽车数据对应的汽车维修模型是基于不同的神经网络算法训练得到的。
  5. 根据权利要求1至4中任一项所述的方法，其特征在于，所述故障解决方案的数量为至少两个，所述方法还包括：
    获取用户输入的维修方案选择条件；
    根据所述维修方案选择条件，从所述至少两个故障解决方案中选取出目标故障解决方案。
  6. 根据权利要求1至4中任一项所述的方法，其特征在于，所述故障解决方案的数量为至少两个，所述方法还包括：
    按照所述汽车维修模型的预设输出顺序向用户提供所述至少两个故障解决方案；
    其中，所述预设输出顺序是所述汽车维修模型根据所述至少两个故障解决方案与所述待维修汽车的所述故障数据的相关程度确定的。
  7. 根据权利要求1至6中任一项所述的方法，其特征在于，所述将所述待维修汽车的所述汽车数据和所述故障数据输入至所述汽车维修模型之后，所述方法还包括：
    得到与所述故障解决方案相关联的故障点、维修过程和所述待维修汽车的厂商相关资料中的至少一种。
  8. 根据权利要求1至7中任一项所述的方法，其特征在于，所述方法还包括：
    将所述故障解决方案填入预设汽车维修案例模板的解决方案模块中，以向用户进行显示；
    其中，所述预设汽车维修案例模板还包括以下至少一个模块：
    基本车辆信息模块、适用车型模块、故障现象模块、存在的故障码模块、故障点模块、维修过程模块、案例作者模块、厂商相关资料模块。
  9. 根据权利要求1至8中任一项所述的方法，其特征在于，
    所述故障数据包括故障代码、故障诊断数据流、故障症状中的至少一个；
    其中，所述故障症状是用户输入的，所述故障代码和所述故障诊断数据流是从所述待维修汽车中获取的。
  10. 根据权利要求1至9中任一项所述的方法，其特征在于，所述方法还包括：
    获取用户设置的超参数；
    根据所述超参数优化所述汽车维修模型。
  11. 根据权利要求1至10中任一项所述的方法，其特征在于，所述方法还包括：
    获取用户针对所述故障解决方案的反馈结果；
    根据所述反馈结果优化所述汽车维修模型。
  12. 一种汽车维修装置，其特征在于，包括：
    获取模块，所述获取模块用于获取待维修汽车的相关数据，所述相关数据包括所述待维修汽车的汽车数据和故障数据；以及
    用于获取所述待维修汽车对应的汽车维修模型；
    输入模块，所述输入模块用于将所述待维修汽车的所述汽车数据和所述故障数据输入至所述汽车维修模型，以得到针对所述待维修汽车的故障解决方案。
  13. 根据权利要求12所述的装置，其特征在于，所述汽车维修模型是根 据样本数据训练得到的；
    其中，所述样本数据包括以下至少一种：
    汽车维修案例样本、汽车故障代码样本、汽车系统和部件信息样本、汽车诊断数据流样本、汽车故障症状及原因样本、汽车基本信息样本。
  14. 根据权利要求12或13所述的装置，其特征在于，所述获取模块具体用于：
    根据所述待维修汽车的汽车数据，获取与所述汽车数据对应的汽车维修模型；
    其中，所述汽车数据包括所述待维修汽车的品牌、车型和年款中的至少一种。
  15. 根据权利要求14所述的装置，其特征在于，不同汽车数据对应的汽车维修模型是基于不同的神经网络算法训练得到的。
  16. 根据权利要求12至15中任一项所述的装置，其特征在于，所述故障解决方案的数量为至少两个，所述获取模块还用于：
    获取用户输入的维修方案选择条件；
    根据所述维修方案选择条件，从所述至少两个故障解决方案中选取出目标故障解决方案。
  17. 根据权利要求12至15中任一项所述的装置，其特征在于，所述故障解决方案的数量为至少两个，所述装置还包括：
    提供模块，所述提供模块用于按照所述汽车维修模型的预设输出顺序向用户提供所述至少两个故障解决方案；
    其中，所述预设输出顺序是所述汽车维修模型根据所述至少两个故障解决方案与所述待维修汽车的所述故障数据的相关程度确定的。
  18. 根据权利要求12至17中任一项所述的装置，其特征在于，所述输入模块还用于：
    在将所述待维修汽车的所述汽车数据和所述故障数据输入至所述汽车维修模型之后，得到与所述故障解决方案相关联的故障点、维修过程和所述待维修汽车的厂商相关资料中的至少一种。
  19. 根据权利要求12至18中任一项所述的装置，其特征在于，所述装置还包括：
    填写模块，所述填写模块用于将所述故障解决方案填入预设汽车维修案例模板的解决方案模块中，以向用户进行显示；
    其中，所述预设汽车维修案例模板还包括以下至少一个模块：
    基本车辆信息模块、适用车型模块、故障现象模块、存在的故障码模块、故障点模块、维修过程模块、案例作者模块、厂商相关资料模块。
  20. 根据权利要求12至19中任一项所述的装置，其特征在于，
    所述故障数据包括故障代码、故障诊断数据流、故障症状中的至少一个；
    其中，所述故障症状是用户输入的，所述故障代码和所述故障诊断数据流是从所述待维修汽车中获取的。
  21. 根据权利要求12至20中任一项所述的装置，其特征在于，所述获取模块还用于：
    获取用户设置的超参数；
    根据所述超参数优化所述汽车维修模型。
  22. 根据权利要求12至21中任一项所述的装置，其特征在于，所述获取模块还用于：
    获取用户针对所述故障解决方案的反馈结果；
    根据所述反馈结果优化所述汽车维修模型。
  23. 一种汽车维修系统，其特征在于，包括：
    交互单元；
    数据存储单元；
    结果显示单元；以及
    模型训练及运算单元，所述模型训练及运算单元分别与所述交互单元、所述数据存储单元以及所述结果显示单元通信连接；
    其中，所述模型训练及运算单元包括：
    至少一个处理器，以及
    与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够用于执行如权利要求1至11中任一项所述的一种汽车维修方法。
  24. 一种非易失性计算机可读存储介质，其特征在于，所述非易失性计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使汽车维修系统执行如权利要求1至11中任一项所述的一种汽车维修方法。
PCT/CN2020/106053 2019-08-02 2020-07-31 一种汽车维修方法、装置及其系统 Ceased WO2021023097A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910712507.2A CN112306034A (zh) 2019-08-02 2019-08-02 一种汽车维修方法、装置及其系统
CN201910712507.2 2019-08-02

Publications (1)

Publication Number Publication Date
WO2021023097A1 true WO2021023097A1 (zh) 2021-02-11

Family

ID=74486601

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/106053 Ceased WO2021023097A1 (zh) 2019-08-02 2020-07-31 一种汽车维修方法、装置及其系统

Country Status (2)

Country Link
CN (1) CN112306034A (zh)
WO (1) WO2021023097A1 (zh)

Cited By (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113420893A (zh) * 2021-06-25 2021-09-21 深圳市轱辘车联数据技术有限公司 维修案例生成方法、装置、电子设备及存储介质
CN113486179A (zh) * 2021-07-13 2021-10-08 盛景智能科技(嘉兴)有限公司 基于维修工单的产品数据分析方法及系统
CN113485161A (zh) * 2021-07-29 2021-10-08 厦门凤凰创壹软件有限公司 一种可测量诊断三维虚拟仿真汽车故障的智能诊断仪
CN114219108A (zh) * 2021-12-21 2022-03-22 上海集度汽车有限公司 一种车辆诊断方法、系统、终端及存储介质
CN114661030A (zh) * 2022-03-24 2022-06-24 深圳市元征科技股份有限公司 诊断功能配置的方法及装置
CN115049444A (zh) * 2022-08-15 2022-09-13 深圳市星卡软件技术开发有限公司 一种数据处理方法、装置、设备及介质
CN115062976A (zh) * 2022-06-16 2022-09-16 启明信息技术股份有限公司 一种用于多品牌车辆维修零件及工序结构数据处理方法
CN115759079A (zh) * 2022-10-24 2023-03-07 广州视源电子科技股份有限公司 故障设备的维修配件筛选方法、装置及设备
CN115933588A (zh) * 2022-11-08 2023-04-07 开源网安物联网技术(武汉)有限公司 智能网联汽车故障远程综合诊断方法及系统
CN116107286A (zh) * 2022-12-07 2023-05-12 中国第一汽车股份有限公司 一种车辆故障的诊断方法、装置、车辆及存储介质
CN116186270A (zh) * 2023-03-31 2023-05-30 重庆长安汽车股份有限公司 一种车辆故障原因诊断方法、装置、设备及存储介质
CN117057527A (zh) * 2023-06-30 2023-11-14 东风设备制造有限公司 一种汽车制造设备工业物联网智慧运维方法及系统
CN118761759A (zh) * 2024-08-06 2024-10-11 北京步甲科技有限公司 一种获取车辆维修方案的方法和装置
CN119828651A (zh) * 2024-12-25 2025-04-15 深圳市元征科技股份有限公司 智能诊断方法、设备、存储介质及程序产品

Families Citing this family (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113220733A (zh) * 2021-03-24 2021-08-06 深圳市道通科技股份有限公司 故障汽车的维修方案的生成方法、装置及电子设备
CN113989023A (zh) * 2021-10-29 2022-01-28 中国银行股份有限公司 差错交易的处理方法及装置
CN113886712B (zh) * 2021-11-04 2022-05-17 杭州以诺行汽车科技股份有限公司 基于erp的人工智能汽车维修推荐方法、系统和存储介质
CN114265384A (zh) * 2021-11-22 2022-04-01 阿尔特汽车技术股份有限公司 一种车辆故障信息处理方法以及系统
CN114626560A (zh) * 2022-03-25 2022-06-14 深圳市轱辘车联数据技术有限公司 车辆维修案例显示方法、装置、电子设备及存储介质
CN117113095A (zh) * 2023-07-27 2023-11-24 广州汽车集团股份有限公司 诊断方法、装置、电子设备和存储介质
CN117668038A (zh) * 2023-12-11 2024-03-08 深圳富士伟业科技有限公司 一种汽车故障分析方法、系统和装置

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102708454A (zh) * 2012-05-14 2012-10-03 北京奇虎科技有限公司 终端故障解决方案提供方法及装置
CN102708453A (zh) * 2012-05-14 2012-10-03 北京奇虎科技有限公司 提供终端故障解决方案的方法及装置
WO2014144036A1 (en) * 2013-03-15 2014-09-18 Angel Enterprise Systems, Inc. Engine analysis and diagnostic system
US20160267723A1 (en) * 2015-03-11 2016-09-15 GM Global Technology Operations LLC Modifying vehicle fault diagnosis based on statistical analysis of past service inquiries
CN107193929A (zh) * 2017-05-17 2017-09-22 北京品智能量科技有限公司 基于特征提取和相似度计算的车辆故障问答方法及装置
CN108563214A (zh) * 2018-04-25 2018-09-21 深圳市道通科技股份有限公司 车辆诊断方法、装置及设备
CN108780590A (zh) * 2016-01-19 2018-11-09 罗伯特·博世有限公司 用于使用声音来诊断车辆的方法和系统
CN108985279A (zh) * 2018-08-28 2018-12-11 上海仁童电子科技有限公司 多功能车辆总线mvb波形的故障诊断方法及装置
CN109163913A (zh) * 2018-09-30 2019-01-08 深圳市元征科技股份有限公司 一种汽车故障诊断方法及相关设备
CN109785460A (zh) * 2019-01-03 2019-05-21 深圳壹账通智能科技有限公司 车辆故障识别方法、装置、计算机设备和存储介质
CN110288100A (zh) * 2019-06-10 2019-09-27 广州思创科技发展有限公司 一种根据车辆故障自动匹配维修项目方法及系统

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020007237A1 (en) * 2000-06-14 2002-01-17 Phung Tam A. Method and system for the diagnosis of vehicles
CN104460644A (zh) * 2013-09-25 2015-03-25 比亚迪股份有限公司 车辆故障的解决方法和装置
CN105629964A (zh) * 2016-03-30 2016-06-01 航天科技控股集团股份有限公司 车辆故障远程实时诊断方法
CN106055439B (zh) * 2016-05-27 2019-09-27 大连楼兰科技股份有限公司 基于维修决策树/词向量的故障远程诊断系统和方法
CN108983748B (zh) * 2018-06-27 2021-06-11 深圳市轱辘车联数据技术有限公司 一种车辆故障检测方法及终端设备

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102708454A (zh) * 2012-05-14 2012-10-03 北京奇虎科技有限公司 终端故障解决方案提供方法及装置
CN102708453A (zh) * 2012-05-14 2012-10-03 北京奇虎科技有限公司 提供终端故障解决方案的方法及装置
WO2014144036A1 (en) * 2013-03-15 2014-09-18 Angel Enterprise Systems, Inc. Engine analysis and diagnostic system
US20160267723A1 (en) * 2015-03-11 2016-09-15 GM Global Technology Operations LLC Modifying vehicle fault diagnosis based on statistical analysis of past service inquiries
CN108780590A (zh) * 2016-01-19 2018-11-09 罗伯特·博世有限公司 用于使用声音来诊断车辆的方法和系统
CN107193929A (zh) * 2017-05-17 2017-09-22 北京品智能量科技有限公司 基于特征提取和相似度计算的车辆故障问答方法及装置
CN108563214A (zh) * 2018-04-25 2018-09-21 深圳市道通科技股份有限公司 车辆诊断方法、装置及设备
CN108985279A (zh) * 2018-08-28 2018-12-11 上海仁童电子科技有限公司 多功能车辆总线mvb波形的故障诊断方法及装置
CN109163913A (zh) * 2018-09-30 2019-01-08 深圳市元征科技股份有限公司 一种汽车故障诊断方法及相关设备
CN109785460A (zh) * 2019-01-03 2019-05-21 深圳壹账通智能科技有限公司 车辆故障识别方法、装置、计算机设备和存储介质
CN110288100A (zh) * 2019-06-10 2019-09-27 广州思创科技发展有限公司 一种根据车辆故障自动匹配维修项目方法及系统

Cited By (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113420893B (zh) * 2021-06-25 2023-10-31 深圳市轱辘车联数据技术有限公司 维修案例生成方法、装置、电子设备及存储介质
CN113420893A (zh) * 2021-06-25 2021-09-21 深圳市轱辘车联数据技术有限公司 维修案例生成方法、装置、电子设备及存储介质
CN113486179A (zh) * 2021-07-13 2021-10-08 盛景智能科技(嘉兴)有限公司 基于维修工单的产品数据分析方法及系统
CN113485161A (zh) * 2021-07-29 2021-10-08 厦门凤凰创壹软件有限公司 一种可测量诊断三维虚拟仿真汽车故障的智能诊断仪
CN113485161B (zh) * 2021-07-29 2024-06-11 厦门凤凰创壹软件有限公司 一种可测量诊断三维虚拟仿真汽车故障的智能诊断仪
CN114219108A (zh) * 2021-12-21 2022-03-22 上海集度汽车有限公司 一种车辆诊断方法、系统、终端及存储介质
CN114661030A (zh) * 2022-03-24 2022-06-24 深圳市元征科技股份有限公司 诊断功能配置的方法及装置
CN115062976A (zh) * 2022-06-16 2022-09-16 启明信息技术股份有限公司 一种用于多品牌车辆维修零件及工序结构数据处理方法
CN115049444A (zh) * 2022-08-15 2022-09-13 深圳市星卡软件技术开发有限公司 一种数据处理方法、装置、设备及介质
CN115759079A (zh) * 2022-10-24 2023-03-07 广州视源电子科技股份有限公司 故障设备的维修配件筛选方法、装置及设备
CN115933588A (zh) * 2022-11-08 2023-04-07 开源网安物联网技术(武汉)有限公司 智能网联汽车故障远程综合诊断方法及系统
CN116107286A (zh) * 2022-12-07 2023-05-12 中国第一汽车股份有限公司 一种车辆故障的诊断方法、装置、车辆及存储介质
CN116186270A (zh) * 2023-03-31 2023-05-30 重庆长安汽车股份有限公司 一种车辆故障原因诊断方法、装置、设备及存储介质
CN117057527A (zh) * 2023-06-30 2023-11-14 东风设备制造有限公司 一种汽车制造设备工业物联网智慧运维方法及系统
CN117057527B (zh) * 2023-06-30 2024-05-14 东风设备制造有限公司 一种汽车制造设备工业物联网智慧运维方法及系统
CN118761759A (zh) * 2024-08-06 2024-10-11 北京步甲科技有限公司 一种获取车辆维修方案的方法和装置
CN119828651A (zh) * 2024-12-25 2025-04-15 深圳市元征科技股份有限公司 智能诊断方法、设备、存储介质及程序产品

Also Published As

Publication number Publication date
CN112306034A (zh) 2021-02-02

Similar Documents

Publication Publication Date Title
WO2021023097A1 (zh) 一种汽车维修方法、装置及其系统
US8463485B2 (en) Process for service diagnostic and service procedures enhancement
US10360740B2 (en) Methods and systems for diagnosing a vehicle using sound
US12087099B2 (en) Method for establishing communicable connection with tire pressure monitoring system, apparatus thereof and electronic device
US20230386273A1 (en) Predictive vehicle troubleshooting methods and systems
CN110781381B (zh) 基于神经网络的数据验证方法、装置、设备及存储介质
EP4167040A1 (en) Fault model editor and diagnostic tool
CN109976936B (zh) 汽车四轮定位故障的智能诊断分析及维修引导方法及系统
US12073442B2 (en) Systems and methods for automated trade-in with limited human interaction
CN110197538A (zh) 一种车辆诊断方法、装置及电子设备、存储介质
CN108780312B (zh) 用于使用路径追踪针对装配线的根本原因分析的方法和系统
US20210192264A1 (en) Vehicle damage detection method based on image analysis, electronic device and storage medium
US10783792B1 (en) Systems and methods for automated vehicle tracking for readiness with limited human interaction
CN116107286A (zh) 一种车辆故障的诊断方法、装置、车辆及存储介质
CN106647716A (zh) 通用型汽车健康诊断系统及其应用方法
CN117422344A (zh) 车辆功能安全可控性等级评估方法、装置、设备及介质
CN114860281B (zh) 一种电子设备、车辆、车辆升级评估方法、装置及系统
CN117651012B (zh) 一种车辆中央网关测试方法及系统
CN118446027A (zh) 一种车辆性能评估系统、方法、电子设备及介质
CN119087987A (zh) 基于大模型的车机设备诊断方法、系统及存储介质
CN116776990A (zh) 一种面向汽车视镜系统疲劳耐久试验过程的故障诊断方法
CN114283309B (zh) 行车记录仪图像深度学习中超参数的处理方法及相关装置
CN114529901A (zh) 车牌识别方法、车牌识别系统及电子设备
CN119023284B (zh) 车辆功能的检测方法、装置、设备、介质
CN119148653B (zh) 一种汽车电子装配精度提升系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20850982

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20850982

Country of ref document: EP

Kind code of ref document: A1