Vehicle fault judgment method and device, electronic equipment and storage medium

Abstract

The invention discloses a vehicle fault judgment method and device, electronic equipment and a storage medium, and relates to the field of fault judgment, and the method comprises the steps: obtaining the monitoring information of a vehicle remote control function; acquiring current vehicle state data according to the abnormal state of the vehicle remote control function; judging a fault state and positioning a fault source according to the current vehicle state data; acquiring a fault processing strategy according to the judged fault state and the positioned fault source; the method comprises the steps of obtaining a vehicle fault large model and a remote control fault large model; the vehicle fault large model carries out fault information distribution according to current vehicle state data; and the remote control fault large model judges a fault state and locates a fault source according to the distributed fault information. According to the scheme, the two-layer large model is trained to judge the vehicle fault, so that the large model can focus on analysis and judgment of a certain type of information, and the judgment accuracy and efficiency are improved.

Description

Technical Field

[0001] The present application relates to the field of fault determination, and in particular to a vehicle fault determination method, a vehicle fault determination device, an electronic device, a storage medium and a vehicle. Background Art

[0002] With the rapid development of the automotive industry, vehicle remote control technology has gradually become an important function, providing convenient services and better user experience for car owners. However, with the widespread application of vehicle remote control technology, many problems of vehicle remote failure will also be encountered during the use of the car, such as failure to remotely start the vehicle, failure to remotely unlock / lock the doors, failure to remotely raise and lower the windows, failure to remotely open / close the trunk, failure of remote air conditioning control, and many other problems.

[0003] At present, the process of determining the failure of vehicle remote control is cumbersome and inefficient. When a vehicle has a remote control failure problem, the owner first contacts the customer service. The customer service determines the type of problem based on the limited description and then transfers the problem to the second-line operation and maintenance. After the second-line operation and maintenance has conducted a preliminary analysis, if they cannot solve the problem themselves, they will transfer it to the third-line operation and maintenance. The third-line operation and maintenance is responsible for extracting the buried point data to deeply analyze the cause and propose a solution. After that, the work order is returned to the customer service, and finally the customer service feedback is given to the owner.

[0004] The problems reported by customers cannot be accurately identified and classified by the machine system, and a large amount of manpower is still needed to classify, locate and analyze the problems. The process is lengthy and the cost is high, which causes car owners to wait too long and affects the user experience. At the same time, since information may be biased or lost during multiple transmissions, and the problem location capabilities of R&D personnel vary, inaccurate fault diagnosis and resolution may also occur. In addition, even if the fault manifests itself as a failure of the vehicle's remote control, the actual maintenance records show that it is not necessarily caused by the vehicle's remote control-related equipment.

[0005] Therefore, a vehicle fault judgment solution is needed that uses a large model to process and classify vehicle data, environmental data, feedback data, etc., and iteratively trains the large model to improve the accuracy of fault judgment and the efficiency of locking the source of the fault, and reduce the information loss caused by relying on human retelling. Summary of the invention

[0006] The purpose of the present invention is to provide a vehicle fault judgment method, a vehicle fault judgment device, an electronic device, a storage medium and a vehicle, which at least solve the problem of fault type classification, the problem of fault information distribution, the problem of fault source locking, and the problem of model iteration.

[0007] The present invention provides the following scheme:

[0008] According to one aspect of the present invention, a vehicle fault determination method is provided, the vehicle fault determination method comprising:

[0009] Obtain monitoring information of the vehicle's remote control function;

[0010] Collect current vehicle status data based on abnormal status of the vehicle remote control function;

[0011] Determine the fault status and locate the fault source based on the current vehicle status data;

[0012] Obtain the fault handling strategy based on judging the fault status and locating the fault source;

[0013] Among them, a vehicle fault model and a remote control fault model are obtained;

[0014] The vehicle fault big model distributes fault information according to current vehicle status data;

[0015] The remote control fault model determines the fault status and locates the fault source according to the distributed fault information.

[0016] Furthermore, the vehicle fault model includes:

[0017] Get the basic large model;

[0018] Analyze and process vehicle historical data according to the basic large model;

[0019] Adjust the parameters in the training process of the basic large model, process the characteristic data of abnormal and normal states of vehicle functions according to the monitoring information of vehicle historical data, and obtain the vehicle fault large model;

[0020] Among them, corresponding to the characteristic data of the vehicle function, a fault type library is set;

[0021] The fault information of the current vehicle status data is processed according to the fault type library, and the fault information is distributed according to the fault type in the fault type library.

[0022] Furthermore, the remote control fault model includes:

[0023] Get the basic large model;

[0024] Analyze and process vehicle historical data according to the basic large model;

[0025] Adjusting the parameters in the training process of the basic large model, processing the characteristic data of the abnormal state and normal state of the vehicle remote control function based on the monitoring information of the vehicle historical data, and obtaining the remote control fault large model;

[0026] Wherein, corresponding to the characteristic data of the vehicle remote control function, a fault mode library is set;

[0027] Processing the vehicle status data of the current vehicle remote control function fault state according to the fault mode library, and locating the fault source according to the fault state information in the fault mode library;

[0028] Among them, the fault mode library includes, corresponding to the fault state of the vehicle remote control function, setting the fault source location information;

[0029] Among them, one fault state locates one or more fault sources, or one or more fault states locate one fault source.

[0030] Furthermore, the vehicle history data includes: vehicle operation status data and vehicle environment status data;

[0031] Data corresponding to the state of the vehicle's environment marking the data of the vehicle's running state, or data corresponding to the state of the vehicle's running state marking the data of the vehicle's environment state;

[0032] Expand the data of the fault mode library based on the data of the marked vehicle status;

[0033] The data of the extended fault mode library includes data of extended fault state location, data of fault source and data of fault state location fault source.

[0034] Furthermore, the vehicle history data also includes: maintenance processing data;

[0035] The maintenance processing data includes data of successful maintenance processing and data of failed maintenance processing;

[0036] The maintenance processing failure data includes data on failure of maintenance processing of a vehicle remote control function;

[0037] Based on the data of the failure of the remote control function of the maintenance processing vehicle, it is determined whether the fault source has failed to be located according to the fault status information in the fault mode library;

[0038] If it fails, the remote control fault model is iterated according to the data of the failure of the remote control function of the maintenance processing vehicle.

[0039] Furthermore, the vehicle history data also includes: maintenance processing data;

[0040] The maintenance processing data includes data of successful maintenance processing and data of failed maintenance processing;

[0041] The maintenance processing failure data includes data of failure in maintenance processing of abnormal vehicle function status;

[0042] Based on the data of failure in repairing and processing the abnormal state of vehicle functions, it is determined whether the distribution of fault information according to the fault type in the fault type library fails;

[0043] If it fails, then the vehicle fault model is iterated based on the data of the failure of the maintenance process to handle the abnormal state of the vehicle function.

[0044] Furthermore, the data iteration includes:

[0045] According to the data of the failed maintenance process, determining whether the fault source has failed to be located according to the fault state information in the fault mode library;

[0046] If,failed, then determine whether the fault information distribution according to the fault type in the fault type library fails;

[0047] If it fails, after iterating the vehicle fault model according to the data of the failure of the maintenance process to handle the abnormal state of the vehicle function, the fault information is distributed according to the fault type in the fault type library;

[0048] If,distributed to the remote control fault large model, it is determined whether the fault source has failed to be located according to the fault status information in the fault mode library;

[0049] If it fails, the remote control fault model is iterated according to the data of the failure of the remote control function of the maintenance processing vehicle.

[0050] According to two aspects of the present invention, there is provided a vehicle fault determination device, the vehicle fault determination device comprising:

[0051] An information acquisition module, used to acquire monitoring information of a vehicle remote control function;

[0052] A status information module is used to collect current vehicle status data according to the abnormal status of the vehicle remote control function;

[0053] A fault judgment module is used to judge the fault status and locate the fault source according to the current vehicle status data;

[0054] The fault handling module is used to determine the fault status and locate the fault source and obtain the fault handling strategy;

[0055] A model acquisition module is used to acquire a vehicle fault model and a remote control fault model;

[0056] An information distribution module, used for the vehicle fault model to distribute fault information according to current vehicle status data;

[0057] The fault location module is used for the remote control fault model to determine the fault state and locate the fault source according to the distributed fault information.

[0058] According to three aspects of the present invention, there is provided an electronic device, comprising: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus;

[0059] A computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the vehicle fault determination method.

[0060] According to four aspects of the present invention, a computer-readable storage medium is provided, comprising: a computer program executable by an electronic device is stored therein, and when the computer program runs on the electronic device, the electronic device executes the steps of the vehicle fault determination method.

[0061] According to five aspects of the present invention, there is provided a vehicle, comprising:

[0062] An electronic device, used to implement the steps of the vehicle fault determination method;

[0063] A processor, the processor runs a program, and when the program runs, the steps of the vehicle fault determination method are executed from the data output by the electronic device;

[0064] The storage medium is used to store a program, and when the program is running, the steps of the vehicle fault determination method are executed for the data output from the electronic device.

[0065] Through the above scheme, the following beneficial technical effects are obtained:

[0066] This application judges vehicle faults by training a two-layer large model, so that the large model can focus on analyzing and judging certain types of information respectively, thereby improving the accuracy and efficiency of judgment.

[0067] This application iterates the model through feedback information, so that the model is imported with real experience information, further improving the effectiveness of model training.

[0068] The present application configures multiple subordinate models under one model, so that the fault judgment information is classified into different subordinate models, and the models jointly process the same monitoring information, thereby expanding the scope of fault judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0069] Figure 1 It is a flow chart of a vehicle fault determination method provided by one or more embodiments of the present invention.

[0070] Figure 2 It is a structural diagram of a vehicle fault determination device provided by one or more embodiments of the present invention.

[0071] Figure 3A schematic diagram of model training and fault handling according to a specific embodiment of the present invention.

[0072] Figure 4 A schematic diagram of fault sorting and problem location for a vehicle window that cannot be opened remotely in a specific embodiment of the present invention.

[0073] Figure 5 A schematic diagram of fault sorting and problem location when a car cannot be remotely started normally according to a specific embodiment of the present invention.

[0074] Figure 6 A schematic diagram of fault sorting and problem location when a trunk cannot be opened remotely normally according to a specific embodiment of the present invention.

[0075] Figure 7 A block diagram of an electronic device structure of a vehicle fault determination method provided by one or more embodiments of the present invention. DETAILED DESCRIPTION

[0076] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0077] Figure 1 It is a flow chart of a vehicle fault determination method provided by one or more embodiments of the present invention.

[0078] like Figure 1 The vehicle fault determination method shown includes:

[0079] Step S1, obtaining monitoring information of a vehicle remote control function;

[0080] Step S2, collecting current vehicle status data according to the abnormal state of the vehicle remote control function;

[0081] Step S3, judging the fault status and locating the fault source according to the current vehicle status data;

[0082] Step S4, obtaining a fault handling strategy based on determining the fault state and locating the fault source;

[0083] Step S5, obtaining a vehicle fault model and a remote control fault model;

[0084] Step S6, the vehicle fault model distributes fault information according to the current vehicle status data;

[0085] Step S7: The remote control fault model determines the fault status and locates the fault source according to the distributed fault information.

[0086] Specifically, in this embodiment, two models, the vehicle fault big model and the remote control fault big model, are used to judge and locate the abnormal state of the vehicle remote control function. The fault information is first distributed through the vehicle fault big model, wherein the remote control fault big model judges the fault state and locates the fault source according to the distributed fault information. The vehicle fault big model is a big model of the upper level relative to the remote control fault big model, and is used to analyze the type of fault. The remote control fault big model is a big model of the lower level relative to the vehicle fault big model, and is used to locate the fault state and fault source of the remote control fault.

[0087] It is possible that the abnormal state of the vehicle remote control function is not caused by the modules, lines, software, etc. related to the vehicle remote control function, but may be caused by other types of faults. At least the vehicle fault model needs to analyze whether there are other functional abnormalities in addition to the abnormality of the vehicle remote control function. When only the vehicle remote control function is abnormal, it can be determined that the current fault information is only distributed to the remote control fault model. When there are other functional abnormalities stored, it is necessary to further analyze according to the correlation between multiple functional abnormal states. For example, if the vehicle remote control function is abnormal at the same time as the power supply function is abnormal, it is not ruled out that the vehicle remote control function is abnormal due to the power supply function abnormality. In this case, the fault information can be distributed to the power supply fault model first, and the fault state of the power supply fault model is judged and the fault source is located, and then the fault information is distributed to the remote control fault model. For another example, if the Tbox function is abnormal at the same time as the vehicle remote control function, it is not ruled out that the Tbox function is abnormal due to the vehicle remote control function abnormality. In this case, the fault information can be distributed to the remote control fault model first, and the fault state of the remote control fault model is judged and the fault source is located, and then the fault information is distributed to the Tbox fault model.

[0088] Fault information includes collected vehicle status information, vehicle environment information, maintenance record information, etc., which are used to analyze the abnormality of the current vehicle remote control function. Fault information can be multi-mode information, which is unified and integrated into a data format that can be input by the large model.

[0089] In this embodiment, the vehicle fault model includes:

[0090] Get the basic large model;

[0091] Analyze and process vehicle historical data based on the basic large model;

[0092] Adjust the parameters in the training process of the basic large model, monitor the historical data of the vehicle, process the characteristic data of the abnormal and normal states of the vehicle functions, and obtain the large model of vehicle faults;

[0093] Among them, corresponding to the characteristic data of the vehicle function, a fault type library is set;

[0094] The fault information of the current vehicle status data is processed according to the fault type library, and the fault information is distributed according to the fault type in the fault type library.

[0095] Specifically, a large model is initially established and trained based on the historical data of the vehicle, wherein the characteristic data of the abnormal state and normal state of the vehicle function are used as the initial input data. Through the characteristic data of the abnormal state and normal state of the vehicle function, a fault type library is set, that is, the faults are divided into multiple types.

[0096] When real-time data is input into the model, the vehicle fault model analyzes and processes the data based on the fault type library to obtain the classification results of the fault types, which are used to guide the next level, such as the data analysis and processing of the remote control fault model.

[0097] It is not ruled out that the vehicle fault model selects multiple fault types based on the current data, and then further analyzes the mutual influence relationship according to the vehicle functions involved in the fault type until the result corresponding to the remote control fault is output, and the fault information is distributed to the remote control fault model.

[0098] In this embodiment, the remote control fault model includes:

[0099] Get the basic large model;

[0100] Analyze and process vehicle historical data based on the basic large model;

[0101] Adjust the parameters in the basic large model training process, process the characteristic data of abnormal and normal states of the vehicle remote control function based on the monitoring information of the vehicle historical data, and obtain the remote control fault large model;

[0102] Wherein, corresponding to the characteristic data of the vehicle remote control function, a fault mode library is set;

[0103] Processing the vehicle status data of the current vehicle remote control function fault state according to the fault mode library, and locating the fault source according to the fault state information in the fault mode library;

[0104] Among them, the fault mode library includes, corresponding to the fault state of the vehicle remote control function, setting the fault source location information;

[0105] Among them, one fault state locates one or more fault sources, or one or more fault states locate one fault source.

[0106] Specifically, when the vehicle remote control function is abnormal, a fault state may be caused by multiple fault sources independently or together, or one fault source may cause multiple fault states. Based on the historical data of the vehicle, a large model is initially established and trained to analyze the fault state and fault source, and establish a fault mode library.

[0107] When real-time data (such as fault information distributed by the vehicle fault big model) is input into the model, the remote control fault big model analyzes and processes the data based on the fault mode library to obtain the classification results of fault source location, which is used to guide maintenance, self-diagnosis and other fault handling strategies.

[0108] In this embodiment, the vehicle history data includes: vehicle operation status data and vehicle environment status data;

[0109] Data corresponding to the state of the vehicle's environment marking the data of the vehicle's running state, or data corresponding to the state of the vehicle's running state marking the data of the vehicle's environment state;

[0110] Expand the data of the fault mode library based on the data of the marked vehicle status;

[0111] The data of the extended fault mode library includes data of extended fault state location, data of fault source, and data of fault state location fault source.

[0112] Specifically, it is possible that the fault state of the vehicle during driving disappears after it is sent to the maintenance department. That is, the state data of some vehicle operations can be affected by the environmental state of the vehicle. For example, the owner drives in an extreme temperature environment, causing the performance of some vehicle components to decline or even fail. The historical data includes information on the impact of the vehicle's environmental state on the vehicle's operating state. Based on this, the data corresponding to the vehicle's environmental state can be marked with the data of the vehicle's operating state, or the data corresponding to the vehicle's operating state can be marked with the data of the vehicle's environmental state, forming the correlation relationship data between the vehicle's operating state and the vehicle's environmental state, and expanding the data of the fault mode library. For example, it is determined whether the current vehicle environment has the possibility of causing abnormal operation of some vehicle components. If so, leaving the environmental state can be used as part of the fault handling strategy. At the same time, sensitive components that are easily affected are used as fault sources for later enhanced maintenance processing, such as increasing heat insulation, heat dissipation, and sealing.

[0113] In this embodiment, the vehicle history data also includes: maintenance processing data;

[0114] The maintenance processing data includes the data of successful maintenance processing and the data of failed maintenance processing;

[0115] The data of maintenance processing failure includes the data of maintenance processing failure of vehicle remote control function;

[0116] Based on the data of the failure of the remote control function of the maintenance processing vehicle, it is determined whether the fault source has failed to be located according to the fault status information in the fault mode library;

[0117] If,failure, then the remote control fault model is iterated based on the data of the failure of the remote control function of the maintenance processing vehicle.

[0118] Specifically, although the fault source is located based on the big model, it does not rule out the possibility of fault location failure, that is, according to the fault source provided by the big model, the data of the failure of the remote control function of the vehicle is repaired. The maintenance department may adopt the strategy of abandoning the repair, or adopt other strategies to restore the remote control function of the vehicle. The remote control fault big model is iterated based on the data of the failure of the remote control function of the vehicle to repair and process, and the judgment accuracy of the remote control fault big model is enhanced.

[0119] In this embodiment, the vehicle history data also includes: maintenance processing data;

[0120] The maintenance processing data includes the data of successful maintenance processing and the data of failed maintenance processing;

[0121] The data of failed maintenance processing includes data of failed maintenance processing of abnormal vehicle function status;

[0122] Based on the data of failure in repairing and processing the abnormal state of vehicle functions, it is determined whether the distribution of fault information according to the fault type in the fault type library fails;

[0123] If ,failure, then the vehicle fault model is iterated based on the data of ,failure of repair processing of the abnormal vehicle function state.

[0124] Specifically, although the fault source is located based on the big model, it does not rule out the possibility of failure in fault type analysis, that is, according to the fault classification provided by the big model, the maintenance and processing of the abnormal state of the vehicle function fails. The maintenance department may adopt the strategy of abandoning maintenance, or adopt other strategies to restore the abnormal function, such as the maintenance department believes that the fault is handled according to the type of non-remote control fault.

[0125] The vehicle fault model is iterated based on the data of failed maintenance and treatment of vehicle function abnormalities to enhance the judgment accuracy of the vehicle fault model.

[0126] In this embodiment, data iteration includes:

[0127] Based on the data of failed maintenance processing, determine whether the fault source has failed to be located according to the fault status information in the fault mode library;

[0128] If,failed, then determine whether the fault information distribution according to the fault type in the fault type library fails;

[0129] If,failed, then after iterating the vehicle fault model based on the data of the failure of the maintenance process to handle the abnormal state of the vehicle function, the fault information is distributed according to the fault type in the fault type library;

[0130] If,distributed to the remote control fault large model, it is determined whether the fault source has failed to be located according to the fault status information in the fault mode library;

[0131] If,failure, then the remote control fault model is iterated based on the data of the failure of the remote control function of the maintenance processing vehicle.

[0132] Specifically, it is possible that the maintenance department has disputes over the data output by the large model, and both the fault type and fault location may be questioned in the maintenance department. The fault source can be located according to the fault status information in the fault mode library to determine whether it has failed. If it fails, it may be caused by the failure to determine the fault type. Then, the fault information distribution is further performed according to the fault type in the fault type library to determine whether it has failed. If it fails, it is iterated from the vehicle fault large model based on the data of the failure of the maintenance and processing vehicle function abnormal state, so that it can cope with the judgment of the current vehicle fault type, and then the result data of the fault type and the fault information distribution are generated based on the iterated vehicle fault large model; based on the new fault type classification, if it is a remote control fault type, the fault information is distributed to the remote control fault large model. If the new fault classification result is a remote control fault, the remote control fault large model is run according to the new fault information distribution. If the fault source still fails to be located, the remote control fault large model is iterated according to the data of the failure of the maintenance and processing vehicle remote control function. During this period, the model iteration process is equivalent to updating historical data.

[0133] Figure 2 It is a structural diagram of a vehicle fault determination device provided by one or more embodiments of the present invention.

[0134] like Figure 2 The vehicle fault determination device shown includes: an information acquisition module, a state information module, a fault determination module, a fault processing module, a model acquisition module, an information distribution module, and a fault location module;

[0135] An information acquisition module, used to acquire monitoring information of a vehicle remote control function;

[0136] A status information module is used to collect current vehicle status data according to the abnormal status of the vehicle remote control function;

[0137] A fault judgment module is used to judge the fault status and locate the fault source according to the current vehicle status data;

[0138] The fault handling module is used to determine the fault status and locate the fault source and obtain the fault handling strategy;

[0139] A model acquisition module is used to acquire a vehicle fault model and a remote control fault model;

[0140] Information distribution module, used for the vehicle fault model to distribute fault information according to the current vehicle status data;

[0141] The fault location module is used to remotely control the fault model to determine the fault status and locate the fault source according to the distributed fault information.

[0142] It is worth noting that although the present system only discloses an information acquisition module, a status information module, a fault judgment module, a fault processing module, a model acquisition module, an information distribution module, and a fault location module, it does not mean that the present device is limited to the above-mentioned basic functional modules. Rather, what the present invention wants to express is that, based on the above-mentioned basic functional modules, those skilled in the art can arbitrarily add one or more functional modules in combination with the prior art to form an infinite number of embodiments or technical solutions. In other words, the present system is open rather than closed. Just because the present embodiment only discloses individual basic functional modules, it cannot be considered that the scope of protection of the claims of the present invention is limited to the above-mentioned basic functional modules.

[0143] Through the above scheme, the following beneficial technical effects are obtained:

[0144] This application judges vehicle faults by training a two-layer large model, so that the large model can focus on analyzing and judging certain types of information respectively, thereby improving the accuracy and efficiency of judgment.

[0145] This application iterates the model through feedback information, so that the model is imported with real experience information, further improving the effectiveness of model training.

[0146] The present application configures multiple subordinate models under one model, so that the fault judgment information is classified into different subordinate models, and the models jointly process the same monitoring information, thereby expanding the scope of fault judgment.

[0147] Figure 3 A schematic diagram of model training and fault handling according to a specific embodiment of the present invention.

[0148] Figure 4 A schematic diagram of fault sorting and problem location for a vehicle window that cannot be opened remotely in a specific embodiment of the present invention.

[0149] Figure 5A schematic diagram of fault sorting and problem location when a car cannot be remotely started normally according to a specific embodiment of the present invention.

[0150] Figure 6 A schematic diagram of fault sorting and problem location when a trunk cannot be opened remotely normally according to a specific embodiment of the present invention.

[0151] In a specific embodiment, Figure 3 The model training and fault handling shown include:

[0152] 1. Data acquisition system: By installing various sensors at key parts of the vehicle, the vehicle's operating data can be obtained in real time, such as engine speed, vehicle speed, battery power, door switch status, etc. At the same time, the vehicle-mounted communication equipment is used to collect relevant information on the network connection, including signal strength, delay time, data packet loss rate, etc.; detailed information on control commands can also be obtained, such as the sending time, content, and reception confirmation status of the commands.

[0153] 2. Historical reference data: including historical work order data and historical processing procedures, which are used for knowledge learning of the big model.

[0154] 3. Basic big model: Integrate and learn data based on data collection systems, historical work order data, historical processing flow and other data to generate a general big model; integrate and deeply analyze multi-source heterogeneous data from vehicles, such as buried point data, historical data, real-time sensor data, network status data, etc., to explore the complex relationships and potential patterns between data; through the study of a large number of historical remote control failure cases and normal operation data, the big model identifies the characteristics of various failure modes and normal operation modes, and establishes an effective pattern recognition mechanism.

[0155] 4. Big model for automotive industry faults: Build a big model architecture based on deep learning algorithms, evolving from a basic big model to a big model for automotive industry faults. The training data for the model comes from a large amount of historical vehicle operation and fault data that has been analyzed and processed by the basic big model. These data cover various vehicle models, different usage environments, and multiple fault types. During the training process, by adjusting the parameters of the neural network, the model can learn the characteristic differences between the data in normal operating conditions and fault conditions, and generate a big fault model that is common to the automotive industry (equivalent to a big vehicle fault model). When car owners report a car failure, the big model for automotive industry faults will automatically sort and classify them, and assign tasks to the downstream big model for specific scenarios.

[0156] 5. Remote control fault big model: Deep learning for remote control fault scenarios, building a remote control fault big model. Focusing on the field of vehicle remote control, this big model can accurately and quickly analyze and locate the causes of remote control related failures; when the vehicle fails to remote control, the remote fault big model will receive the fault message notification from the upstream automobile fault big model, and the data acquisition module will quickly transmit the real-time data to the big model. The big model quickly analyzes these data, first preprocessing the data, including cleaning, normalization and other operations, to improve data quality and analysis accuracy. Then, the trained model is used for feature extraction and pattern recognition, and compared with the existing fault mode library to determine the type of failure and possible causes. In order to improve the accuracy of diagnosis, a multimodal data fusion solution is introduced. In addition to the vehicle's own data, a comprehensive analysis is also conducted in combination with the vehicle's geographical location, surrounding environmental information (such as weather conditions, electromagnetic interference, etc.) and the vehicle's historical maintenance records.

[0157] 6. Result output: In terms of result output, the big model gives fault classification and fault location, for example, clearly points out whether it is a network module fault, control unit fault or other specific component problem, and provides corresponding maintenance suggestions. At the same time, the diagnosis results are transmitted to the car owner, OEM and maintenance site in real time so that maintenance personnel can be arranged in time and the required parts can be prepared.

[0158] 7. Iterative optimization: To ensure continuous optimization of the performance of the large model, it is regularly updated and retrained. New fault data and vehicle model information are constantly incorporated to enable it to adapt to the ever-changing vehicle technology and usage environment.

[0159] In another specific embodiment, if the vehicle window shown in Figure 4 cannot be opened normally by remote control, fault sorting and problem location include:

[0160] 1. Problem feedback: The owner found that the car window could not be opened normally through remote control, and reported this problem through the in-car central control evaluation system;

[0161] 2. On-board large model system: The system receives customer feedback and automatically identifies the fault based on the information provided by the customer. After analysis, it is concluded that the problem is a problem in the remote control field, and the problem is then distributed to the remote control fault large model module;

[0162] 3. Remote control fault model: The remote control fault model receives fault problems reported by the upper layer and reads the actual status signals of the vehicle, including TBOX-related signals, mobile phone APP signals, Bluetooth signals, WiFi signals, cloud service signals, and other signals in the vehicle. It automatically analyzes signal faults based on historical experience in handling remote control problems and finds that the wireless video identification (RFID) signal value of the car key is in an abnormal state, while other signals are within the normal signal value range.

[0163] 4. Problem location: According to the above signal identification results, it is located as a wireless radio frequency fault;

[0164] 5. Cause feedback: Based on the identified causes, feedback is given to the OEM, maintenance center and vehicle owner based on maintenance suggestions.

[0165] In another specific embodiment, if the vehicle shown in 5 cannot be remotely started normally, fault sorting and problem location are performed, including:

[0166] 1. Problem feedback: The owner found that the car window could not be opened normally through remote control, and reported this problem through the in-car central control evaluation system;

[0167] 2. On-board large model system: The system receives customer feedback and automatically identifies the fault based on the information provided by the customer. After analysis, it is concluded that the problem is a problem in the remote control field, and the problem is then distributed to the remote control fault large model module;

[0168] 3. Remote control fault model: The remote control fault model receives fault problems reported by the upper layer and reads the actual status signals of the vehicle, including TBOX-related signals, mobile phone APP signals, Bluetooth signals, WiFi signals, cloud service signals, and other signals in the vehicle. It automatically analyzes signal faults based on historical experience in handling remote control problems and finds that the 4G / 5G signal values ​​are in an abnormal state, while other signals are within the normal signal value range.

[0169] 4. Problem location: According to the above signal identification results, the problem is located as weak 4G / 5G signal;

[0170] 5. Cause feedback: Based on the identified causes, feedback is given to the OEM, maintenance center and vehicle owner based on maintenance suggestions.

[0171] In another specific embodiment, if the trunk shown in 6 cannot be opened normally by remote control, fault sorting and problem location include:

[0172] 1. Problem feedback: The owner found that the car window could not be opened normally through remote control, and reported this problem through the in-car central control evaluation system;

[0173] 2. On-board large model system: The system receives customer feedback and automatically identifies the fault based on the information provided by the customer. After analysis, it is concluded that the problem is a problem in the remote control field, and the problem is then distributed to the remote control fault large model module;

[0174] 3. Remote control fault model: The remote control fault model receives fault problems reported by the upper layer and reads the actual status signals of the vehicle, including TBOX-related signals, mobile phone APP signals, Bluetooth signals, WiFi signals, cloud service signals, and other signals in the vehicle. It automatically analyzes signal faults based on historical experience in handling remote control problems and finds that the Bluetooth signal value is in an abnormal state, while other signals are within the normal signal value range.

[0175] 4. Problem location: According to the above signal identification results, it is located as a Bluetooth failure;

[0176] 5. Cause feedback: Based on the identified causes, feedback is given to the OEM, maintenance center and vehicle owner based on maintenance suggestions.

[0177] Figure 7 A block diagram of an electronic device structure of a vehicle fault determination method provided by one or more embodiments of the present invention.

[0178] like Figure 7 As shown, the present application provides an electronic device, including: a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus;

[0179] A computer program is stored in the memory. When the computer program is executed by the processor, the processor executes the steps of a vehicle fault determination method.

[0180] The present application also provides a computer-readable storage medium storing a computer program executable by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of a vehicle fault determination method.

[0181] The present application also provides a vehicle, comprising:

[0182] An electronic device for implementing the steps of a vehicle fault determination method;

[0183] A processor, the processor runs a program, and when the program runs, the steps of the seat belt control method are executed from the data output by the electronic device;

[0184] The storage medium is used to store a program, and when the program is running, the steps of the seat belt control method are executed for the data output from the electronic device.

[0185] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0186] The electronic device includes a hardware layer, an operating system layer running on the hardware layer, and an application layer running on the operating system. The hardware layer includes hardware such as a central processing unit (CPU), a memory management unit (MMU), and a memory. The operating system can be any one or more computer operating systems that implement electronic device control through a process, such as a Linux operating system, a Unix operating system, an Android operating system, an iOS operating system, or a Windows operating system. In addition, in an embodiment of the present invention, the electronic device can be a handheld device such as a smart phone or a tablet computer, or can be an electronic device such as a desktop computer or a portable computer, which is not particularly limited in the embodiment of the present invention.

[0187] The execution subject of the electronic device control in the embodiment of the present invention may be an electronic device, or a functional module in the electronic device that can call and execute a program. The electronic device may obtain the firmware corresponding to the storage medium. The firmware corresponding to the storage medium is provided by the supplier. The firmware corresponding to different storage media may be the same or different, which is not limited here. After the electronic device obtains the firmware corresponding to the storage medium, the firmware corresponding to the storage medium may be written into the storage medium, specifically, the firmware corresponding to the storage medium may be burned into the storage medium. The process of burning the firmware into the storage medium may be implemented using existing technology, which will not be described in detail in the embodiment of the present invention.

[0188] The electronic device may also obtain a reset command corresponding to the storage medium. The reset command corresponding to the storage medium is provided by the supplier. The reset commands corresponding to different storage media may be the same or different, and are not limited here.

[0189] At this time, the storage medium of the electronic device is a storage medium in which the corresponding firmware is written, and the electronic device can respond to the reset command corresponding to the storage medium in the storage medium in which the corresponding firmware is written, so that the electronic device resets the storage medium in which the corresponding firmware is written according to the reset command corresponding to the storage medium. The process of resetting the storage medium according to the reset command can be implemented by the existing technology and will not be described in detail in the embodiments of the present invention.

[0190] For the convenience of description, the above devices are described in terms of functions and are divided into various units and modules. Of course, when implementing the present application, the functions of each unit and module can be implemented in the same or multiple software and / or hardware.

[0191] Those skilled in the art will appreciate that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art in the art to which the present invention belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with the meanings in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined.

[0192] For the method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0193] It can be known from the description of the above implementation modes that those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform. Based on such an understanding, the technical solution of the present application can be essentially or partly contributed to the prior art in the form of a software product, which can be stored in a storage medium such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes several instructions for enabling a computer device (which can be a personal computer, a server or a network device, etc.) to execute the methods described in the various implementation modes of the present application or certain parts of the implementation modes.

[0194] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle fault determination method, characterized in that: The vehicle fault determination method comprises: Obtain monitoring information of the vehicle's remote control function; Collect current vehicle status data based on abnormal status of the vehicle remote control function; Determine the fault status and locate the fault source based on the current vehicle status data; Obtain the fault handling strategy based on judging the fault status and locating the fault source; Among them, a vehicle fault model and a remote control fault model are obtained; The vehicle fault big model distributes fault information according to current vehicle status data; The remote control fault model determines the fault status and locates the fault source according to the distributed fault information.

2. The vehicle fault determination method according to claim 1, characterized in that: The vehicle fault model includes: Get the basic large model; Analyze and process vehicle historical data according to the basic large model; Adjust the parameters in the training process of the basic large model, process the characteristic data of abnormal and normal states of vehicle functions according to the monitoring information of vehicle historical data, and obtain the vehicle fault large model; Among them, corresponding to the characteristic data of the vehicle function, a fault type library is set; The fault information of the current vehicle status data is processed according to the fault type library, and the fault information is distributed according to the fault type in the fault type library.

3. The vehicle fault determination method according to claim 2, characterized in that: The remote control fault model includes: Get the basic large model; Analyze and process vehicle historical data according to the basic large model; Adjusting the parameters in the training process of the basic large model, processing the characteristic data of the abnormal state and normal state of the vehicle remote control function based on the monitoring information of the vehicle historical data, and obtaining the remote control fault large model; Wherein, corresponding to the characteristic data of the vehicle remote control function, a fault mode library is set; Processing the vehicle status data of the current vehicle remote control function fault state according to the fault mode library, and locating the fault source according to the fault state information in the fault mode library; Among them, the fault mode library includes, corresponding to the fault state of the vehicle remote control function, setting the fault source location information; Among them, one fault state locates one or more fault sources, or one or more fault states locate one fault source.

4. The vehicle fault determination method according to claim 3, characterized in that: The vehicle history data includes: vehicle operation status data and vehicle environment status data; Data corresponding to the state of the vehicle's environment marking the data of the vehicle's running state, or data corresponding to the state of the vehicle's running state marking the data of the vehicle's environment state; Expand the data of the fault mode library based on the data of the marked vehicle status; The data of the extended fault mode library includes data of extended fault state location, data of fault source and data of fault state location fault source.

5. The vehicle fault determination method according to claim 4, characterized in that: The vehicle history data also includes: maintenance processing data; The maintenance processing data includes data of successful maintenance processing and data of failed maintenance processing; The maintenance processing failure data includes data on failure of maintenance processing of a vehicle remote control function; Based on the data of the failure of the remote control function of the maintenance processing vehicle, it is determined whether the fault source has failed to be located according to the fault status information in the fault mode library; If it fails, the remote control fault model is iterated according to the data of the failure of the remote control function of the maintenance processing vehicle.

6. The vehicle fault determination method according to claim 4, characterized in that: The vehicle history data also includes: maintenance processing data; The maintenance processing data includes data of successful maintenance processing and data of failed maintenance processing; The maintenance processing failure data includes data of failure in maintenance processing of abnormal vehicle function status; Based on the data of failure in repairing and processing the abnormal state of vehicle functions, it is determined whether the distribution of fault information according to the fault type in the fault type library fails; If it fails, then the vehicle fault model is iterated based on the data of the failure of the maintenance process to handle the abnormal state of the vehicle function.

7. The vehicle fault determination method according to claim 5 or 6, characterized in that: The data iteration includes: According to the data of the failed maintenance process, determining whether the fault source has failed to be located according to the fault state information in the fault mode library; If,failed, then determine whether the fault information distribution according to the fault type in the fault type library fails; If it fails, after iterating the vehicle fault model according to the data of the failure of the maintenance process to handle the abnormal state of the vehicle function, the fault information is distributed according to the fault type in the fault type library; If,distributed to the remote control fault large model, it is determined whether the fault source has failed to be located according to the fault status information in the fault mode library; If it fails, the remote control fault model is iterated according to the data of the failure of the remote control function of the maintenance processing vehicle.

8. A vehicle fault determination device, characterized in that: The vehicle fault determination device comprises: An information acquisition module, used to acquire monitoring information of a vehicle remote control function; A status information module is used to collect current vehicle status data according to the abnormal status of the vehicle remote control function; A fault judgment module is used to judge the fault status and locate the fault source according to the current vehicle status data; The fault handling module is used to determine the fault status and locate the fault source and obtain the fault handling strategy; A model acquisition module is used to acquire a vehicle fault model and a remote control fault model; An information distribution module, used for the vehicle fault model to distribute fault information according to current vehicle status data; The fault location module is used for the remote control fault model to determine the fault state and locate the fault source according to the distributed fault information.

9. An electronic device, characterized in that: include: A processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; A computer program is stored in the memory, and when the computer program is executed by the processor, the processor executes the steps of the vehicle fault determination method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: include: It stores a computer program that can be executed by an electronic device. When the computer program runs on the electronic device, the electronic device executes the steps of the vehicle fault determination method described in any one of claims 1 to 7.

Images