Vehicle fault collecting and processing system and method based on large model

Abstract

The invention provides a vehicle fault collecting and processing system and method based on a large model, and belongs to the technical field of intelligent vehicle fault management. The system comprises a vehicle-mounted electronic controller used for collecting fault information of a to-be-detected vehicle; the information is transmitted to the cloud server through the first communication module; the cloud server is used for training the basic large model based on the fault information of the to-be-detected vehicle; reason reasoning is carried out on the received fault information of the to-be-detected vehicle through the trained basic large model, and a fault processing scheme of the to-be-detected vehicle is generated; the vehicle-mounted electronic controller is used for controlling the to-be-detected vehicle to perform corresponding control operation based on the received fault processing scheme; and the vehicle production system is used for generating a fault tracing result by using a data analysis technology based on the obtained vehicle fault information, the vehicle model information and the fault data. The problems that the fault vehicle problem processing speed is low, data mining of a whole vehicle factory is not thorough, and problem tracing is difficult are solved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent automobile fault management, and in particular to a vehicle fault collection and processing system and method based on a large model. Background Art

[0002] There are three main ways to collect vehicle fault information for mainstream models on the market: Method 1: Obtain through the on-board diagnostic system (OBD): Modern vehicles are generally equipped with an on-board diagnostic system (OBD), which monitors the operating status of various vehicle systems in real time through the electronic control unit (ECU) inside the vehicle, such as the engine, transmission, brake system, emission system, etc. When an abnormality is detected, the OBD will generate a fault code (DTC) and light up the fault indicator light on the dashboard to inform the driver that there is a problem.

[0003] Method 2: Using Internet of Vehicles technology, the vehicle operation data and fault information are transmitted to the manufacturer or service provider's cloud server in real time through the vehicle's built-in communication module (such as 4G / 5G, GPS, etc.). Remotely monitor and diagnose vehicle status and collect vehicle fault data in real time without the need for car owners to manually report problems.

[0004] Method three: Feedback from car owners or through after-sales channels.

[0005] The vehicle manufacturers can deal with vehicle failures in the following ways: the manufacturer or service provider can remotely diagnose the vehicle through the cloud platform, manually summarize and analyze the cause of the failure, and provide repair suggestions or software updates (OTA). Maintenance personnel will repair the vehicle based on the fault diagnosis results and solve the problem by replacing the faulty parts or repairing the damaged parts.

[0006] However, the use of the above three methods will cause the current vehicle manufacturers' fault collection and processing solutions to have the following problems: (1) Inconsistent fault collection methods: Most of them still follow the traditional on-board diagnostic system (OBD) method, reading fault codes offline, and the data cannot be directly uploaded to the cloud database.

[0007] (2) Slow response time for problem handling: When a vehicle failure occurs, the owner needs to transfer the vehicle to a repair station, where maintenance personnel will inspect and analyze the vehicle. The entire process takes a long time and provides a poor customer experience. (3) Human experience factors have a great influence: Due to the different technical reserves of different maintenance personnel, the same fault problem is handled in different ways and the maintenance results are different. This may lead to incomplete maintenance, continuous problems, and even affect the driving safety of the driver. (4) Fault data mining is not in-depth enough: Maintenance personnel may miss uploading data, and vehicle manufacturers often only maintain data at the stage of data storage, retrieval, and forming an experience database. Because fault analysis is a time-consuming and labor-intensive task, many vehicle manufacturers have not formed a systematic data analysis and traceability system, and are unable to identify the cause of the problem from the source, and thus are unable to prevent the recurrence of the problem from the root.

[0008] The above problems need to be solved urgently. Summary of the invention

[0009] The purpose of the present invention is to overcome at least one technical problem existing in the prior art and to provide a vehicle fault collection and processing system and method based on a large model.

[0010] On the one hand, an embodiment of the present invention provides a vehicle fault collection and processing system based on a large model, the system comprising: a cloud server, a first communication module, a vehicle to be detected, a second communication module and a vehicle production system, the first communication module is integrated in the vehicle to be detected, the cloud server is bidirectionally electrically connected to the vehicle to be detected through the first communication module, the second communication module is integrated in the vehicle generation system, and the vehicle production system is electrically connected to the cloud server through the second communication module; the vehicle to be detected is integrated with an on-board electronic controller for collecting fault information of the vehicle to be detected; the first communication module is used to transmit the fault information of the vehicle to be detected to the cloud server; the cloud server is integrated with a large model server The large model server is integrated with a model training module for training a basic large model based on the fault information of the vehicle to be detected; the large model server is used to perform cause inference on the received fault information of the vehicle to be detected through the trained basic large model, and generate a fault handling plan for the vehicle to be detected; the first communication module is also used to send the fault handling plan to the on-board electronic controller in the vehicle to be detected; the on-board electronic controller is also used to control the vehicle to be detected to perform fault reminders, self-service fault resolution and / or autonomous safety control operations based on the received fault handling plan; the vehicle production system is used to generate fault tracing results based on the acquired vehicle fault information, vehicle model information and fault data using data analysis technology.

[0011] Furthermore, the on-board electronic controller is used to collect and monitor fault information of various systems of the vehicle to be tested in real time through at least one sensor and a communication network; the sensor includes one or a combination of a temperature sensor, a pressure sensor, a position sensor and a speed sensor; the system includes one or a combination of the engine system, transmission system and brake system of the vehicle to be tested.

[0012] Furthermore, a storage module is integrated in the vehicle-mounted electronic controller for storing fault information collected by the vehicle-mounted electronic controller; the fault information includes one or a combination of fault codes, vehicle operating status data, sensor data and maintenance records.

[0013] Furthermore, the cloud server is also used to learn and identify specific failure modes based on the failure information of the vehicle to be detected, and the specific failure modes include conventional failure modes and failures related to environmental conditions.

[0014] Furthermore, the cloud server is also used to generate fault prediction information based on the fault information of the vehicle to be detected through the pre-learned and stored fault association relationship in the trained basic large model.

[0015] Furthermore, the large model server is integrated in the vehicle to be detected, and is used to perform cause inference on the received fault information of the vehicle to be detected through the trained basic large model, and generate a fault handling solution for the vehicle to be detected.

[0016] Furthermore, the large model server is used to generate at least one cause of the fault based on the received fault information combined with external environment information through the trained basic large model; based on the cause of the fault, generate at least one corresponding fault handling solution according to historical handling cases.

[0017] Furthermore, the on-board controller is also used to: perform fault reminder operations based on the fault handling plan, including pushing fault information and warning information to the driver through the vehicle dashboard; perform self-service fault resolution operations based on the fault handling plan, including automatically executing corresponding troubleshooting procedures based on the fault handling plan; perform autonomous safety control operations based on the fault handling plan, including automatically controlling the vehicle's driving status based on the fault handling plan.

[0018] Furthermore, the vehicle production system is also used to: obtain fault data through real-time monitoring of the on-board electronic controller, user feedback and / or maintenance records, the fault data including one or a combination of fault occurrence time, fault nature and fault frequency; and optimize the vehicle design and production process based on the fault tracing results.

[0019] In a second aspect, an embodiment of the present invention provides a vehicle fault collection and processing method based on a large model, characterized in that the method is applied to the above-mentioned vehicle fault collection and processing system based on a large model, and the method includes: collecting the fault information of the vehicle to be detected through the on-board electronic controller integrated in the vehicle to be detected; transmitting the fault information of the vehicle to be detected to the cloud server through the first communication module; on the cloud server side, cyclically training the basic large model deployed in the cloud server based on the fault information of the vehicle to be detected; the cloud server performs cause inference on the received fault information of the vehicle to be detected through the trained basic large model, and generates a fault handling plan for the vehicle to be detected; the fault handling plan is sent to the on-board electronic controller in the vehicle to be detected through the first communication module; the on-board electronic controller performs fault reminder, self-service fault resolution and / or autonomous safety control operation based on the received fault handling plan; the vehicle production system generates fault tracing results based on the acquired vehicle fault information, vehicle model information and fault data using data analysis technology.

[0020] In a third aspect, an embodiment of the present invention further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program implements the above-mentioned large model-based vehicle fault collection and processing method when executed by the processor.

[0021] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium, which, when the instructions in the storage medium are executed by a processor of an electronic device, enables the electronic device to execute the above-mentioned large model-based vehicle fault collection and processing method.

[0022] The beneficial effects of the present invention are: (1) By using a large model to perform root cause analysis on the collected fault information of the vehicle to be tested, multiple causes of the fault can be obtained, so that the cause of the vehicle fault can be quickly located.

[0023] (2) The large model based on the cause of the fault can provide the car owner with a quick and objective solution to the problem through successful handling cases for the cause of the fault in historical data.

[0024] (3) By retrieving data from the cloud processor through the vehicle production system (vehicle manufacturer), fault information and fault data for a certain vehicle model can be collected. The vehicle manufacturer can trace the vehicle model based on the collected historical data, thereby reducing the vehicle maintenance pressure of the vehicle manufacturer and providing the vehicle manufacturer with comprehensive fault cause analysis and quality improvement suggestions. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0026] Figure 1 It is a schematic diagram of the structure of a vehicle fault collection and processing system based on a large model provided in Example 1 of the present invention.

[0027] Figure 2 This is a flow chart of a vehicle fault collection and processing method based on a large model provided in Example 2 of the present invention.

[0028] Figure 3 This is a partial block diagram of an electronic device provided in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0029] It should be mentioned before discussing the exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe the operations as sequential processes, many of the operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of the operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to a method, function, procedure, subroutine, subprogram, etc.

[0030] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0031] The present invention will now be described in detail with reference to the accompanying drawings. This figure is a simplified schematic diagram, which only illustrates the basic structure of the present invention in a schematic manner, and therefore only shows the components related to the present invention.

[0032] Example 1 For ease of understanding, the inventive concept is generally described below before describing the embodiments of the present invention in detail: The present application provides a vehicle fault collection and processing system and method based on a large model. The fault status of the controller and the whole vehicle is collected through the on-board electronic controller; the acquired controller and vehicle fault information is transmitted to the cloud through the wireless communication module on the on-board equipment; the collected fault information and cause analysis of many vehicles are learned through the large model deployed on the cloud; the cause is inferred through the large model, and the fault handling plan for the whole vehicle is decided; the fault handling decision is sent to the corresponding on-board controller through the wireless network, and the vehicle is reminded of faults, self-service fault resolution, and autonomous safety control is performed through the on-board controller; the vehicle manufacturer obtains the fault information of the vehicle model through the background, and uses the fault analysis results to trace the cause of the fault and solve the root problem. The collected fault data is comprehensively analyzed and decided through the background big data model; the problem of slow processing speed of faulty vehicle problems is solved, and the problem of incomplete data mining and difficult problem tracing of vehicle manufacturers is solved.

[0033] The specific implementation is as follows: like Figure 1 As shown, it is a schematic diagram of the structure of a vehicle fault collection and processing system based on a large model provided by the present invention.

[0034] As an example, the system includes: a cloud server 1, a first communication module 210, a vehicle to be detected 2, a second communication module 310 and a vehicle production system 3, wherein the first communication module 210 is integrated in the vehicle to be detected 2, the cloud server 1 is bidirectionally electrically connected to the vehicle to be detected 2 through the first communication module 210, the second communication module 310 is integrated in the vehicle generation system 3, and the vehicle production system 3 is electrically connected to the cloud server 1 through the second communication module 310; the vehicle to be detected 2 is integrated with an on-board electronic controller 220 for collecting fault information of the vehicle to be detected 2; the first communication module 210 is used to transmit the fault information of the vehicle to be detected to the cloud server 1; the cloud server 1 is integrated with a large model server 110, the The large model server 110 is integrated with a model training module 1101, which is used to train the basic large model based on the fault information of the vehicle to be detected; the large model server 110 is used to perform cause inference on the received fault information of the vehicle to be detected through the trained basic large model, and generate a fault handling plan for the vehicle to be detected; the first communication module 210 is also used to send the fault handling plan to the on-board electronic controller 220 in the vehicle to be detected; the on-board electronic controller 220 is also used to control the vehicle to be detected 2 to perform fault reminders, self-service fault resolution and / or autonomous safety control operations based on the received fault handling plan; the vehicle production system 3 is used to generate fault tracing results based on the acquired vehicle fault information, vehicle model information and fault data using data analysis technology.

[0035] In some feasible embodiments, the on-board electronic controller 220 is used to collect and monitor fault information of various systems of the vehicle to be tested in real time through at least one sensor and a communication network; the sensor includes one or a combination of a temperature sensor, a pressure sensor, a position sensor and a speed sensor; the system includes one or a combination of the engine system, transmission system and brake system of the vehicle to be tested.

[0036] In some feasible implementations, the vehicle-mounted electronic controller 220 is integrated with a storage module for storing fault information collected by the vehicle-mounted electronic controller 220; the fault information includes one or a combination of fault codes, vehicle operating status data, sensor data and maintenance records. Specifically, when the vehicle manufacturer defines the functional requirements, it will require the electronic component supplier to develop a diagnostic function. The vehicle-mounted electronic controller 220 (ECU) generally collects and monitors the fault status of each vehicle system in real time through sensors and communication networks. Key systems such as engines, transmissions and brake systems are equipped with a variety of sensors (such as temperature, pressure, position and speed sensors) to convert physical quantities into electrical signals and transmit them to the ECU. When the ECU processes these signals, it first performs signal processing, including filtering and analog-to-digital conversion, and then monitors the status to check whether the data is within the normal range. If an abnormality is found, the ECU will generate a fault code (DTC) to identify a specific fault. Each fault corresponds to a unique DTC, such as P0XXX (power system fault), etc., which is convenient for maintenance personnel to quickly locate the problem. In addition, the ECU stores fault codes and related information (such as occurrence time and environmental conditions) in non-volatile memory to ensure that fault information is saved even if the vehicle is powered off.

[0037] In some feasible implementations, through the first communication module 210 on the vehicle-mounted device, the vehicle can transmit the collected controller and fault information to the cloud server in real time, forming an efficient fault monitoring and management system. Specifically, the process usually relies on 4G or 5G networks, which makes the data transmission faster and more stable. The first communication module 210 is generally deployed in the vehicle's T-BOX (Telematics BOX, telematics processor). The T-BOX is responsible for connecting the various electronic control units (ECUs) of the vehicle and packaging the fault codes, vehicle operating status data, sensor data and maintenance records it monitors into data packets. These data packets are aggregated through the vehicle network (such as the CAN bus) and sent to the cloud server through the wireless communication module. The cloud server is also integrated with a storage module 120 for centrally storing the data received from different vehicles.

[0038] In some feasible implementations, the cloud server 1 is also used to learn and identify specific failure modes based on the failure information of the vehicle to be detected, and the specific failure modes include conventional failure modes and failures related to environmental conditions. Specifically, the process utilizes machine learning and deep learning algorithms to enable the cloud model to process and parse massive amounts of data, which are sorted and used to train the model. Among them, the basic large model is deployed in the cloud server after pre-training. The large model identifies common failure modes and failures related to environmental conditions through multi-level analysis. For example, specific sensors of a certain model of vehicle are prone to failure in high temperature environments, and the model will learn and identify these specific failure modes.

[0039] In some feasible implementations, the cloud server 1 is also used to generate fault prediction information based on the fault information of the vehicle to be detected through the pre-learned and stored fault association relationship in the trained basic large model. Specifically, the large model deployed by the cloud server can also predict potential faults, and provide early warnings based on current vehicle data to help car owners perform preventive maintenance and avoid serious problems. The continuous learning ability of the large model ensures that it always reflects the latest fault trends, and continuously optimizes the accuracy of prediction and diagnosis by continuously training based on the acquired fault information.

[0040] In some feasible implementations, the large model server 110 is integrated in the vehicle to be detected 2, and is used to perform cause reasoning on the received fault information of the vehicle to be detected through the trained basic large model, and generate a fault handling solution for the vehicle to be detected. That is, the large model server 110 can also be integrated in the vehicle to be detected 2, so that in the scenario of wireless communication failure, the large model deployed on the vehicle can also provide the driver with a timely and effective fault handling solution.

[0041] In some feasible implementations, the large model server 110 is used to generate at least one cause of the fault through the trained basic large model based on the received fault information combined with the external environment information; and generate at least one corresponding fault handling solution based on the cause of the fault according to the historical handling case. Specifically, the large model can provide scientific and accurate support for the decision-making of the vehicle fault handling solution by reasoning the cause. The large model is based on historical fault data, sensor information and vehicle operation status data, and uses complex algorithms (such as fault root cause analysis methods) to conduct in-depth analysis of the causes behind the fault. These models can identify potential patterns of fault occurrence and evaluate the causal relationship between faults. When a vehicle fails, the model will analyze the collected data in real time, such as fault codes, vehicle operation status and external environment. Through reasoning analysis, the model can quickly generate multiple possible causes of the fault and propose corresponding handling solutions based on previous successful cases. For example, if the engine is detected to be overheated, the model can immediately determine that it may be insufficient coolant or a temperature sensor failure, and provide corresponding solutions. In addition, the model also has learning capabilities, and can optimize its decision-making capabilities as new data is continuously input to ensure the timeliness and adaptability of the handling solution. Through this intelligent decision support, maintenance personnel can quickly identify the fault, improve maintenance efficiency, reduce the impact of the fault on vehicle operations, and thus improve overall safety and reliability.

[0042] In some feasible implementations, the on-board controller 220 is also used to: perform fault reminder operations based on the fault handling scheme, including pushing fault information and warning information to the driver through the vehicle dashboard; perform self-service fault resolution operations based on the fault handling scheme, including automatically executing the corresponding troubleshooting program based on the fault handling scheme; perform autonomous safety control operations based on the fault handling scheme, including automatically controlling the vehicle driving state based on the fault handling scheme. Specifically, sending the fault handling decision to the corresponding on-board electronic controller 220 through the network is one of the important links of the intelligent vehicle fault management system in this embodiment. First, the cloud server 1 will quickly transmit the fault handling decision based on the large model analysis to the on-board electronic controller 220 of a specific vehicle. This process usually relies on a high-speed wireless network, which is transmitted to the T-BOX, and then transmitted to the terminal electronic controller 220 by the T-BOX to ensure the timeliness and accuracy of the information. Once the on-board electronic controller 220 receives the fault handling decision, it can immediately perform a fault reminder and push the fault information and warning to the driver through the dashboard or mobile phone application. This instant feedback mechanism allows the driver to quickly realize the severity of the fault and the necessary measures. Based on the analysis results of the large model, the on-board controller also has a self-service fault resolution function. Based on the decision information received, it automatically performs some simple troubleshooting procedures, such as restarting certain systems or adjusting settings, to solve temporary problems. This active association helps to reduce the burden on drivers and improve driving safety. Through learning from specific application scenarios, the on-board controller can achieve autonomous safety control. For example, when a major fault is detected, it can automatically limit the vehicle's maximum speed or guide the vehicle to stop safely to prevent potential accidents. This collaborative mechanism not only improves the safety performance of the vehicle, but also enhances the user's sense of trust, adding more protection to the smart driving experience.

[0043] In some feasible implementations, the vehicle production system 3 is also used to: obtain fault data through real-time monitoring of the on-board electronic controller, user feedback and / or maintenance records, the fault data including one or a combination of the time of occurrence of the fault, the nature of the fault and the frequency of the fault; optimize the design and production process of the vehicle based on the fault tracing results. Specifically, the vehicle production system 3 can obtain fault information related to the vehicle model through the background system, thereby improving product quality and customer satisfaction. With the improvement of the degree of vehicle intelligence, the collection and analysis of fault information has become more and more efficient. The vehicle manufacturer summarizes the fault data of each vehicle model through on-board real-time monitoring, user feedback and maintenance records. These data can cover the time of occurrence of the fault, the nature of the fault and the frequency, etc., providing a rich basis for subsequent analysis. After collecting enough fault information, the vehicle manufacturer uses data analysis technology to trace the cause of the fault in detail, and the root cause of the fault may appear at the R&D end, the production end or the user end. Based on the characteristics contained in the large model itself, this process involves building a fault model and root cause analysis to help the OEM identify the root cause of the fault, such as design defects, material problems or improper production processes. Through in-depth analysis, the vehicle manufacturer can identify the source of the problem and take targeted solutions. After the root problem is solved, the vehicle production system 3 will further optimize the design and production process to ensure that the failure will not occur again in the future. This dynamic feedback mechanism not only helps to improve vehicle quality and reduce maintenance rates, but also greatly enhances consumers' trust in the brand, thereby promoting sales and market competitiveness.

[0044] In the above embodiment, a method for collecting and processing vehicle faults based on a large model is designed: in the process of vehicle fault analysis and processing, a large model is introduced, and by using the learning and training of the large model, the background is equipped with the ability to analyze and process vehicle faults, and the large model is used to provide scientific and accurate support for the decision-making of vehicle fault processing solutions. On the one hand, the cause of vehicle faults can be quickly located, providing car owners with a quick and objective solution to the problem; on the other hand, it reduces the vehicle maintenance pressure of the vehicle manufacturer and provides the vehicle manufacturer with a comprehensive analysis of the cause of the fault and suggestions for quality improvement.

[0045] It is worth mentioning that all modules involved in this embodiment are logical units. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. In addition, in order to highlight the innovative part of the present invention, this embodiment does not introduce units that are not closely related to solving the technical problem proposed by the present invention, but this does not mean that there are no other units in this embodiment.

[0046] Example 2 See also Figure 2, this embodiment provides a flow chart of a vehicle fault collection and processing method based on a large model.

[0047] As an example, the method is applied to the above-mentioned vehicle fault collection and processing system based on a large model, and the method includes: S210: Collecting fault information of the vehicle to be detected through an on-board electronic controller integrated in the vehicle to be detected.

[0048] S220: Transmitting the fault information of the vehicle to the cloud server through the first communication module.

[0049] S230: On the cloud server side, a basic large model deployed in the cloud server is cyclically trained based on the fault information of the vehicle to be detected.

[0050] S240: The cloud server uses the trained basic large model to infer the cause of the received fault information of the vehicle to be detected, and generates a fault handling solution for the vehicle to be detected.

[0051] S250: Send the fault handling solution to the on-board electronic controller in the vehicle to be detected through the first communication module.

[0052] S260: The on-board electronic controller performs fault reminder, self-service fault resolution and / or autonomous safety control operations based on the received fault handling solution.

[0053] S270: The vehicle production system generates a fault tracing result using data analysis technology based on the acquired vehicle fault information, vehicle model information and fault data.

[0054] It is not difficult to find that this embodiment is a method embodiment corresponding to the first embodiment, and this embodiment can be implemented in conjunction with the first embodiment. The relevant technical details mentioned in the first embodiment are still valid in this embodiment, and in order to reduce repetition, they are not repeated here. Accordingly, the relevant technical details mentioned in this embodiment can also be applied in the first embodiment.

[0055] Example 3 See also Figure 3 An embodiment of the present invention further provides an electronic device, comprising: a memory and a processor; the memory stores at least one program instruction; the processor implements the vehicle fault collection and processing method based on a large model provided in Example 2 by loading and executing the at least one program instruction.

[0056] The memory 702 and the processor 701 are connected in a bus manner, and the bus may include any number of interconnected buses and bridges, and the bus connects various circuits of one or more processors 701 and the memory 702 together. The bus can also connect various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface between the bus and the transceiver. The transceiver can be one element or multiple elements, such as multiple receivers and transmitters, providing a unit for communicating with various other devices on a transmission medium. The data processed by the processor 701 is transmitted on a wireless medium via an antenna, and further, the antenna also receives data and transmits the data to the processor 701.

[0057] The processor 701 is responsible for managing the bus and general processing, and can also provide various functions, including timing, peripheral interfaces, voltage regulation, power management and other control functions. The memory 702 can be used to store data used by the processor 701 when performing operations.

[0058] Example 4 The embodiment of the present invention further provides a storage medium, on which a vehicle fault collection and processing method based on a large model is stored, and when the vehicle fault collection and processing program based on a large model is executed, the steps of the vehicle fault collection and processing method based on a large model as described above are implemented. Since the storage medium adopts all the technical solutions of all the above embodiments, it has at least all the beneficial effects brought by the technical solutions of the above embodiments, which will not be repeated here one by one.

[0059] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can know all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the scope of protection of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A vehicle fault collection and processing system based on a large model, characterized in that: The system comprises: a cloud server, a first communication module, a vehicle to be detected, a second communication module and a vehicle production system, wherein the first communication module is integrated in the vehicle to be detected, the cloud server is bidirectionally electrically connected to the vehicle to be detected via the first communication module, the second communication module is integrated in the vehicle production system, and the vehicle production system is electrically connected to the cloud server via the second communication module; The vehicle to be detected is integrated with an on-board electronic controller for collecting fault information of the vehicle to be detected; The first communication module is used to transmit the fault information of the vehicle to be detected to the cloud server; The cloud server is integrated with a large model server, and the large model server is integrated with a model training module for training a basic large model based on the fault information of the vehicle to be detected; The large model server is used to perform cause reasoning on the received fault information of the vehicle to be detected by using the trained basic large model, and generate a fault handling solution for the vehicle to be detected; The first communication module is also used to send the fault handling solution to the on-board electronic controller in the vehicle to be detected; The on-board electronic controller is also used to control the vehicle to be detected to perform fault reminder, self-service fault resolution and / or autonomous safety control operations based on the received fault processing solution; The vehicle production system is used to generate fault tracing results based on the acquired vehicle fault information, vehicle model information and fault data using data analysis technology.

2. The vehicle fault collection and processing system based on a large model according to claim 1 is characterized in that: The on-board electronic controller is used to collect and monitor fault information of various systems of the vehicle to be tested in real time through at least one sensor and a communication network; the sensor includes one or a combination of a temperature sensor, a pressure sensor, a position sensor and a speed sensor; the system includes one or a combination of the engine system, the transmission system and the brake system of the vehicle to be tested.

3. The vehicle fault collection and processing system based on a large model according to claim 1 is characterized in that: The on-board electronic controller is integrated with a storage module for storing fault information collected by the on-board electronic controller; The fault information includes one or a combination of fault codes, vehicle operating status data, sensor data and maintenance records.

4. The vehicle fault collection and processing system based on a large model according to claim 1 is characterized in that: The cloud server is also used to learn and identify specific failure modes based on the failure information of the vehicle to be detected, and the specific failure modes include conventional failure modes and failures related to environmental conditions.

5. The vehicle fault collection and processing system based on a large model according to claim 1 is characterized in that: The cloud server is also used to generate fault prediction information based on the fault information of the vehicle to be detected through the pre-learned and stored fault association relationship in the trained basic large model.

6. The vehicle fault collection and processing system based on a large model according to claim 1 is characterized in that: The large model server is integrated in the vehicle to be detected, and is used to perform cause inference on the received fault information of the vehicle to be detected through the trained basic large model, and generate a fault handling solution for the vehicle to be detected.

7. The vehicle fault collection and processing system based on a large model according to claim 1 is characterized in that: The large model server is used to generate at least one cause of the fault based on the received fault information combined with the external environment information through the trained basic large model; Based on the cause of the fault, at least one corresponding fault handling solution is generated according to historical handling cases.

8. The vehicle fault collection and processing system based on a large model according to claim 1 is characterized in that: The vehicle-mounted controller is also used for: Performing fault reminder operations based on the fault handling solution, including pushing fault information and warning information to the driver through the vehicle dashboard; Performing self-service fault resolution operations based on the fault resolution plan, including automatically executing a corresponding fault troubleshooting procedure based on the fault resolution plan; Performing autonomous safety control operations based on the fault handling solution includes automatically controlling the vehicle driving state based on the fault handling solution.

9. The vehicle fault collection and processing system based on a large model according to claim 1 is characterized in that: The vehicle production system is also used for: Acquire fault data through real-time monitoring of the vehicle electronic controller, user feedback and / or maintenance records, wherein the fault data includes one or a combination of fault occurrence time, fault nature and fault frequency; The design and production process of the vehicle is optimized based on the fault tracing results.

10. A vehicle fault collection and processing method based on a large model, characterized in that: The method is applied to the vehicle fault collection and processing system based on a large model as described in any one of claims 1 to 9, and the method comprises: Collecting fault information of the vehicle to be detected by an on-board electronic controller integrated in the vehicle to be detected; Transmitting the fault information of the vehicle to the cloud server through the first communication module; On the cloud server side, a basic large model deployed in the cloud server is cyclically trained based on the fault information of the vehicle to be detected; The cloud server uses the trained basic large model to infer the cause of the fault information of the received vehicle to be detected, and generates a fault handling solution for the vehicle to be detected; Sending the fault handling solution to the on-board electronic controller in the vehicle to be detected through the first communication module; The on-board electronic controller performs fault reminder, self-service fault resolution and / or autonomous safety control operations based on the received fault resolution plan; The vehicle production system generates a fault tracing result using data analysis technology based on the acquired vehicle fault information, vehicle model information and fault data.

Images