Remote diagnosis method and system of vehicle, storage medium and electronic equipment

Abstract

The invention is suitable for the technical field of vehicle diagnosis, and provides a remote diagnosis method and system of a vehicle, a storage medium and electronic equipment. The remote diagnosis method of the vehicle comprises the steps of obtaining vehicle bus data of the vehicle; based on a target prediction model obtained through pre-training, the adaptation probability of the vehicle bus data and the multiple alternative bus configuration files is determined, the target prediction model is obtained by training an initial neural network model based on multiple pieces of historical vehicle diagnosis data, and each piece of historical vehicle diagnosis data comprises the historical vehicle bus data and the multiple alternative bus configuration files; the bus configuration file is matched with the historical vehicle bus data; determining a target configuration file adapted to the vehicle bus data in the plurality of alternative bus configuration files according to the adaptation probability of the vehicle bus data and the plurality of alternative bus configuration files; and performing remote diagnosis on the vehicle according to the target configuration file. The technical problem that an existing vehicle remote diagnosis method is inaccurate in configuration file adaptation is solved.

Description

Technical Field

[0001] The present application belongs to the field of vehicle diagnosis technology, and more specifically, to a vehicle remote diagnosis method, system, storage medium and electronic device. Background Art

[0002] In the field of vehicle remote diagnosis, the existing remote diagnosis system receives the diagnostic data sent by the diagnostic equipment through the customer service end (i.e., the Busi ness end, the B end), and transmits it transparently to the customer service end (i.e., the Consumer end, the C end). The customer service end then interacts with the vehicle and transmits the collected diagnostic data back to the customer service end to realize remote diagnosis.

[0003] However, existing vehicle remote diagnosis methods have the problem of inaccurate configuration file adaptation, which affects the accuracy and efficiency of vehicle remote diagnosis. Summary of the invention

[0004] The purpose of the embodiments of the present application is to provide a vehicle remote diagnosis method, system, storage medium and electronic device, aiming to solve the technical problem of inaccurate configuration file adaptation in existing vehicle remote diagnosis methods.

[0005] To achieve the above object, according to a first aspect of the present application, a remote diagnosis method for a vehicle is provided, the method comprising:

[0006] Obtain vehicle bus data of the vehicle;

[0007] Based on a pre-trained target prediction model, determining the adaptation probability of the vehicle bus data and a plurality of candidate bus configuration files, wherein the target prediction model is obtained by training an initial neural network model based on a plurality of historical vehicle diagnostic data, each of the historical vehicle diagnostic data comprising: historical vehicle bus data, and a bus configuration file adapted to the historical vehicle bus data;

[0008] Determining a target configuration file adapted to the vehicle bus data from among the plurality of candidate bus configuration files according to the adaptation probabilities of the vehicle bus data and the plurality of candidate bus configuration files;

[0009] Remote diagnosis is performed on the vehicle according to the target profile.

[0010] Optionally, in a possible implementation manner of the first aspect, acquiring vehicle bus data of the vehicle includes:

[0011] Acquiring vehicle bus data of the vehicle collected by the first client, wherein the first client communicates and / or exchanges data with the vehicle through any type of bus after successfully shaking hands with the vehicle;

[0012] The vehicle bus data includes at least one of the following: a pin voltage value of an on-board self-diagnostic system, a bus pin, a bus baud rate, a bus broadcast identifier, and a pin voltage value of an activation pin of an Internet Protocol-based diagnostic communication DO IP interface.

[0013] Optionally, in a possible implementation manner of the first aspect, determining a target profile adapted to the vehicle bus data from among a plurality of candidate bus profiles according to the adaptation probabilities of the vehicle bus data and a plurality of candidate bus profiles includes:

[0014] sorting the plurality of candidate bus configuration files according to the matching probabilities between the vehicle bus data and the plurality of candidate bus configuration files to obtain a sorting result;

[0015] According to the ranking result, selecting a candidate bus configuration file with the highest adaptation probability from the plurality of candidate bus configuration files;

[0016] If the adaptation probability of the candidate bus profile with the highest adaptation probability is greater than the probability threshold, the candidate bus profile with the highest adaptation probability is used as the target profile.

[0017] Optionally, in a possible implementation manner of the first aspect, the method further includes:

[0018] If the adaptation probability of the candidate bus configuration file with the highest adaptation probability is less than or equal to the probability threshold, obtaining the bus pin and bus baud rate in the vehicle bus data;

[0019] The target configuration file is generated according to the bus pin and the bus baud rate in the vehicle bus data.

[0020] Optionally, in a possible implementation manner of the first aspect, performing remote diagnosis on the vehicle according to the target configuration file includes:

[0021] The target configuration file is sent to a first client and a second client so as to perform remote diagnosis on the vehicle through the first client and the second client, wherein the second client is communicatively connected to a vehicle diagnostic device through any type of bus.

[0022] Optionally, in a possible implementation manner of the first aspect, before determining the adaptation probability of the vehicle bus data and a plurality of candidate bus configuration files based on the pre-trained target prediction model, the method further includes:

[0023] The vehicle bus data is preprocessed, wherein the preprocessing includes at least one of the following: encoding conversion processing, vector conversion processing, and numerical scaling processing.

[0024] Optionally, in a possible implementation manner of the first aspect, before acquiring vehicle bus data of the vehicle, the method further includes:

[0025] Acquire a plurality of the historical vehicle diagnostic data stored in the historical diagnostic log data, wherein the diagnostic result of each of the historical vehicle diagnostic data is a successful diagnosis;

[0026] Extracting the historical vehicle bus data and a bus configuration file adapted to the historical vehicle bus data from each of the historical vehicle diagnostic data;

[0027] The target prediction model is obtained by training the initial neural network model based on the historical vehicle bus data respectively extracted from the plurality of historical vehicle diagnostic data and a bus configuration file adapted to the historical vehicle bus data.

[0028] According to a second aspect of the present application, a vehicle remote diagnosis system is provided, the system comprising:

[0029] A first client, used to obtain vehicle bus data of a vehicle;

[0030] The vehicle remote diagnosis server determines the adaptation probability between the vehicle bus data and a plurality of candidate bus configuration files based on a pre-trained target prediction model, and determines a target configuration file adapted to the vehicle bus data among the plurality of candidate bus configuration files according to the adaptation probability between the vehicle bus data and the plurality of candidate bus configuration files; wherein the target prediction model is obtained by training an initial neural network model based on a plurality of historical vehicle diagnosis data, each of the historical vehicle diagnosis data comprising: historical vehicle bus data, and a bus configuration file adapted to the historical vehicle bus data;

[0031] The second client is used to perform remote diagnosis on the vehicle according to the target configuration file.

[0032] The second aspect and any implementation of the second aspect correspond to the first aspect and any implementation of the first aspect, respectively. The technical effects corresponding to the second aspect and any implementation of the second aspect can refer to the technical effects corresponding to the first aspect and any implementation of the first aspect, which will not be repeated here.

[0033] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the methods described above when executing the computer program.

[0034] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it implements any of the methods described above.

[0035] In a fifth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on an electronic device, the electronic device executes any one of the methods described in the first aspect.

[0036] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0037] The embodiments of the present application provide a remote diagnosis method, system, storage medium and electronic device for a vehicle. The remote diagnosis method for the vehicle obtains vehicle bus data of the vehicle; determines the adaptation probability of the vehicle bus data and multiple candidate bus configuration files based on a pre-trained target prediction model, wherein the target prediction model is obtained by training an initial neural network model based on multiple historical vehicle diagnostic data, each historical vehicle diagnostic data includes: historical vehicle bus data, and a bus configuration file adapted to the historical vehicle bus data; determines a target configuration file adapted to the vehicle bus data among multiple candidate bus configuration files based on the adaptation probability of the vehicle bus data and the multiple candidate bus configuration files; and performs remote diagnosis on the vehicle according to the target configuration file.

[0038] Analysis shows that since the target prediction model trained based on historical data can learn the relationship between different vehicle bus data features and various bus profiles, by calculating the adaptation probability of the newly acquired vehicle bus data, the target profile that best suits the current vehicle can be determined more accurately, thereby improving the accuracy of remote diagnosis.

[0039] Moreover, users do not need to perform a lot of manual configuration and try different configuration files. The pre-trained target prediction model can quickly calculate the adaptation probability and determine the target configuration file, greatly shortening the time of remote diagnosis. In addition, it can also avoid the misjudgment and inappropriate configuration selection that may occur in traditional vehicle diagnosis methods, solving the technical problem of inaccurate configuration file adaptation in existing vehicle remote diagnosis methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0041] Figure 1 It is a flowchart of a remote diagnosis method for a vehicle provided in an embodiment of the present application;

[0042] Figure 2 It is a flowchart of an optional vehicle remote diagnosis method provided in an embodiment of the present application;

[0043] Figure 3 It is a flowchart of an optional vehicle remote diagnosis method provided in an embodiment of the present application;

[0044] Figure 4 It is a flowchart of an optional vehicle remote diagnosis method provided in an embodiment of the present application;

[0045] Figure 5 is a schematic diagram of a model structure of an optional target prediction model provided in an embodiment of the present application;

[0046] Figure 6 It is a structural schematic diagram of a vehicle remote diagnosis system provided in an embodiment of the present application;

[0047] Figure 7 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0048] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0049] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0050] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0051] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0052] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0053] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0054] First, some terms in the embodiments of the present application are explained to facilitate understanding by those skilled in the art.

[0055] On-Board Diagnostics (OBD) system, OBD pin voltage refers to the voltage value corresponding to each pin on the OBD interface. Different pins have different functions and their voltages are also different.

[0056] In automotive electronic systems, the CAN (Controller Area Network) bus is a commonly used communication bus. CAN ID is an identifier used to distinguish different message information sources and destinations. Bus broadcast means that each node on the bus (such as different electronic control units ECU) will send a message with a specific CAN ID to propagate on the bus. All CAN IDs refer to the set of identifiers corresponding to various different messages appearing on the bus. These identifiers can be used to identify different data sources, message types, and priorities.

[0057] Diagnostic communication over Internet Protocol DOIP (Dignost i ccommunication over Internet Protocol) is an automobile diagnostic communication method based on the IP Internet network protocol.

[0058] The above is a brief introduction to the nouns involved in the embodiments of the present application, which will not be repeated below.

[0059] This application example provides an example of a remote diagnosis method for a vehicle, please refer to Figure 1 As shown, Figure 1 A schematic flow chart of a remote diagnosis method for a vehicle provided in the present application is shown. As an example but not a limitation, the method can be applied to a remote diagnosis system for a vehicle.

[0060] S101, obtaining vehicle bus data of a vehicle.

[0061] Before the vehicle starts remote diagnosis, the vehicle bus data of the vehicle must be obtained first. Since it is necessary to connect to the vehicle bus system through a specific diagnostic device, such as the On-Board Diagnost i cs (OBD) interface or other dedicated diagnostic interfaces, the vehicle bus data may include but is not limited to the following:

[0062] OBD pin voltage: Measure the voltage values ​​of each pin of the OBD interface. These voltage values ​​can reflect the working status of the OBD system and its connection with other electronic systems of the vehicle.

[0063] CAN bus pinout, baud rate and CAN ID: Determine the pin locations to which the CAN bus is connected, as well as the baud rate currently used and all CAN identifiers broadcast by the bus. This information is critical to understanding the communication between the various electronic control units (ECUs) in the vehicle.

[0064] Related information during the DO IP identification process: If the vehicle supports DOIP, it is necessary to obtain relevant data at each stage of the DO IP identification process, such as the voltage value of a specific pin (such as an activation pin), to determine whether the vehicle supports DO IP and its configuration.

[0065] S102, determining the adaptation probability of the vehicle bus data and a plurality of candidate bus configuration files based on a pre-trained target prediction model.

[0066] The target prediction model is obtained by training an initial neural network model based on a plurality of historical vehicle diagnostic data, and each of the historical vehicle diagnostic data includes: historical vehicle bus data, and a bus configuration file adapted to the historical vehicle bus data.

[0067] In the example of the present application, the initial neural network model is trained in advance using historical vehicle diagnostic data, and the obtained target prediction model learns the relationship between different vehicle bus data features and various bus configuration files, so that the adaptation probability of new vehicle bus data with different alternative bus configuration files can be predicted.

[0068] After the vehicle bus data of the current vehicle is obtained, the vehicle bus data of the current vehicle is input into a pre-trained target prediction model. The target prediction model analyzes the characteristics of the vehicle bus data and calculates the matching probability of the vehicle bus data with multiple candidate bus configuration files. It should be understood that the matching probability of the vehicle bus data with an alternative bus configuration file represents the possibility that the bus configuration file is suitable for the current vehicle.

[0069] S103: Determine a target configuration file that is adapted to the vehicle bus data from among the plurality of candidate bus configuration files according to the adaptation probabilities between the vehicle bus data and the plurality of candidate bus configuration files.

[0070] S104 , performing remote diagnosis on the vehicle according to the target configuration file.

[0071] In the above method steps, the adaptation probabilities corresponding to the multiple candidate bus configuration files are evaluated and compared according to the adaptation probabilities between the vehicle bus data and the multiple candidate bus configuration files. For example, the configuration file with the highest adaptation probability among the multiple candidate bus configuration files can be determined as the target configuration file.

[0072] After determining the target configuration file, the vehicle can be remotely diagnosed based on the target configuration file. For example, the target configuration file can be sent to a first client and a second client. The first client is a client connected to the electronic control unit of the vehicle, i.e., the C-end (Consumer end, usually refers to the end facing the end user of the vehicle, i.e., the individual car owner), and the second client is a customer service end connected to the diagnostic device, i.e., the B-end (Business end, generally refers to the end facing commercial customer groups such as automobile manufacturers, dealers, and maintenance companies), so that the B-end and the C-end in the vehicle remote diagnosis system can perform parameter settings and communication adjustments according to the target configuration file.

[0073] Then, the vehicle remote diagnosis server interacts with the vehicle diagnostic device using the bus interfaces of the first client and the second client configured in the target configuration file to collect vehicle data, send diagnostic instructions, read fault codes, etc., so as to realize remote fault diagnosis and status monitoring of the vehicle.

[0074] In summary, the present application example provides a method for using a pre-trained target prediction model to determine a bus profile suitable for a vehicle and performing remote diagnosis based on the bus profile, which can improve the accuracy and efficiency of vehicle remote diagnosis.

[0075] In a possible implementation, the acquiring vehicle bus data of the vehicle includes:

[0076] The vehicle bus data of the vehicle collected by the first client is obtained, wherein the first client communicates and / or exchanges data with the vehicle through any type of bus after successfully shaking hands with the vehicle.

[0077] In the above implementation, it is clarified that the executor of acquiring the vehicle bus data is the first client, which is oriented to the end user of the vehicle and is responsible for directly interacting with the vehicle and collecting the required vehicle bus data.

[0078] Furthermore, the first client starts to communicate and / or exchange data with the vehicle through a specific bus only after the handshake with the vehicle is successful. The handshake process can be understood as an initialization step for the client to establish a connection with the vehicle and confirm that both parties can communicate normally. Only after the handshake is successful can the first client perform subsequent data collection work.

[0079] The "any type of bus" mentioned in the example of this application may include but is not limited to CAN (Control Area Network) bus, K line, Internet Protocol-based diagnostic communication DO IP, etc. Different bus types have different characteristics and uses, and the first client can select a suitable bus for communication and data exchange according to the specific situation of the vehicle.

[0080] In one example, the vehicle bus data includes at least one of the following: a pin voltage value of an on-board self-diagnostic system, a bus pin, a bus baud rate, a bus broadcast identifier, and a pin voltage value of an activation pin of an Internet Protocol-based diagnostic communication DO IP interface.

[0081] As an example but not a limitation, the pin voltage value of the vehicle self-diagnostic system refers to the voltage value of each pin of the vehicle self-diagnostic system (OBD) interface of the vehicle, and these voltage values ​​can reflect the working status of the OBD system and the connection status with other electronic systems of the vehicle. For example, the voltage of the power pin can determine whether the power supply of the OBD system is normal, and the voltage of the data transmission pin can reflect the stability of communication.

[0082] Bus pins refer to the specific pin locations where different buses (such as CAN bus, K line, etc.) of the vehicle are connected. Different bus pins have different functions, such as data transmission, grounding, power supply, etc. Accurately identifying bus pins is crucial for correctly connecting diagnostic equipment and understanding the communication architecture of the vehicle's electronic system.

[0083] The bus baud rate refers to the speed at which data is transmitted on the bus. Different vehicle systems may use different baud rates for communication. Knowing the baud rate of the vehicle bus can ensure smooth data transmission between the diagnostic equipment and the vehicle, avoiding data transmission errors or losses caused by baud rate mismatch.

[0084] Bus broadcast identifier: In vehicle bus communication, different electronic control units (ECUs) broadcast messages on the bus through specific identifiers (CAN ID, etc.). These bus broadcast identifiers can help diagnostic equipment identify different data sources and message types, so as to better understand the operating status and fault information of various vehicle systems.

[0085] Pin voltage value of the activation pin of the Internet Protocol-based diagnostic communication DO IP interface: For vehicles that support specific diagnostic protocols (such as DO IP), the pin voltage value of the activation pin of the diagnostic hardware interface is of great significance. By monitoring the voltage value of this pin, it can be determined whether the vehicle supports the diagnostic protocol and the activation status of the diagnostic system. For example, during the DOIP identification process, the change in the voltage value of a specific pin (such as the activation pin: pin 8) can reflect the communication status of the DO IP system and whether it has been successfully activated.

[0086] In the DO IP identification process, a specific hardware interface is usually involved, and this hardware interface may have multiple pins. Pin 8 is one of the specific pins. The voltage value of pin 8 has a specific meaning in the DO IP identification process, which can be used to indicate a certain state, provide power, or transmit a specific signal. By measuring and analyzing the voltage value of this pin, it can help determine whether the DO IP system is working properly, what working state it is in, and whether there is a fault.

[0087] Please refer to Figure 2 As shown, Figure 2 1 is a flow chart of an optional vehicle remote diagnosis method provided by an embodiment of the present application. In a possible implementation, determining a target configuration file adapted to the vehicle bus data from among a plurality of candidate bus configuration files according to the adaptation probability between the vehicle bus data and a plurality of candidate bus configuration files includes:

[0088] S201, sorting a plurality of candidate bus configuration files according to the matching probabilities between the vehicle bus data and the plurality of candidate bus configuration files to obtain a sorting result.

[0089] S202: Selecting a candidate bus configuration file with the highest adaptation probability from a plurality of candidate bus configuration files according to the sorting result.

[0090] S202: If the adaptation probability of the candidate bus configuration file with the highest adaptation probability is greater than the probability threshold, the candidate bus configuration file with the highest adaptation probability is used as the target configuration file.

[0091] In the present application example, the adaptation probability between the vehicle bus data and each candidate configuration file is calculated, and then these candidate configuration files are sorted, selected and judged to finally determine the target configuration file.

[0092] Specifically, first, the pre-trained target prediction model is used to calculate the matching probability between the vehicle bus data and each candidate bus profile. The matching probability is used to characterize the likelihood that a specific bus profile is suitable for the current vehicle. Then, the candidate bus profiles are sorted according to these matching probabilities. For example, the matching probabilities can be sorted from high to low, and it can be clearly seen which profile is most likely to be suitable for the current vehicle.

[0093] After sorting the candidate bus profiles, the candidate bus profile with the highest probability of adaptation is selected. This candidate bus profile is considered to be the most suitable for the current vehicle bus data in the current calculation results. Furthermore, a probability threshold is introduced in the example of this application. Even if the adaptation probability of a candidate bus profile is the highest among all candidate profiles, if this probability does not exceed the pre-set probability threshold, the candidate bus profile cannot be determined as the target profile.

[0094] Only when the adaptation probability of the candidate bus profile with the highest adaptation probability is greater than this threshold, it will be used as the target profile to ensure that the selected profile has sufficient reliability and applicability, avoiding incorrect configuration selection due to some inaccurate prediction results.

[0095] Please refer to Figure 3 As shown, Figure 3 : is a flow chart of an optional vehicle remote diagnosis method provided in an embodiment of the present application. In a possible implementation, the method further includes:

[0096] S301: If the adaptation probability of the candidate bus configuration file with the highest adaptation probability is less than or equal to the probability threshold, obtain the bus pin and bus baud rate in the vehicle bus data.

[0097] S302, generating a target configuration file according to the bus pin and bus baud rate in the vehicle bus data.

[0098] If the probability of the candidate bus profile with the highest probability of adaptation is less than or equal to the probability threshold, it means that the most likely profile recommended by the pre-trained target prediction model is not reliable enough and cannot be directly used as the target profile for vehicle remote diagnosis. In this case, other methods are needed to generate the target profile.

[0099] Specifically, in this case, the example of the present application can extract two key parameters, bus pin and bus baud rate, from the acquired vehicle bus data. The bus pin determines the specific location where the different buses of the vehicle are connected, and the bus baud rate determines the speed at which data is transmitted on the bus. It should be understood that these two parameters are crucial for vehicle communication and diagnosis.

[0100] Then, the extracted bus pin and bus baud rate information can be used to generate a target configuration file using a specific method. Of course, the generation process may refer to existing configuration file generation rules or make inferences based on historical experience. For example, a target configuration file suitable for the current vehicle can be generated based on the vehicle model, the specifications provided by the manufacturer, and the configuration of similar vehicles, combined with the current bus pin and bus baud rate. It should be understood that although the target configuration file is not as accurate as that obtained through model prediction, it can still be used as a backup plan to determine the target configuration file when the model prediction is unreliable to achieve remote diagnosis of the vehicle.

[0101] In a possible implementation, performing remote diagnosis on the vehicle according to the target configuration file includes:

[0102] The target configuration file is sent to a first client and a second client so as to perform remote diagnosis on the vehicle through the first client and the second client, wherein the second client is communicatively connected to a vehicle diagnostic device through any type of bus.

[0103] In the present application example, the first client (end C) usually interacts directly with the vehicle, communicates and exchanges data with the vehicle through a specific bus (such as CAN bus, K line, DO IP, etc.), collects vehicle data and transmits it to the second client (end B), and also receives instructions and configuration files issued by the server to adjust the interaction method with the vehicle.

[0104] The second client acts as an intermediate hub, receiving vehicle data collected from the first client on the one hand, and communicating with the vehicle diagnostic equipment through any type of bus on the other hand. The second client can process and analyze the data, feed back the diagnostic results to the diagnostic equipment, and also send the target configuration file to the first client to coordinate the entire remote diagnosis process.

[0105] When the vehicle remote diagnosis C-end and the vehicle remote diagnosis B-end receive the target configuration file, they can perform remote diagnosis on the vehicle according to this configuration file, for example, it may include adjusting communication parameters, setting specific diagnostic modes, activating certain vehicle systems for more in-depth diagnosis, etc.

[0106] For example, the C-end can adjust the communication mode with the vehicle according to the bus parameters in the target configuration file to ensure the accuracy and stability of data transmission. The B-end can send specific diagnostic instructions to the client according to the diagnostic requirements in the configuration file to guide the C-end to perform specific tests and data collection on the vehicle. At the same time, the B-end can also compare and analyze the collected data with the standards in the configuration file to determine whether the vehicle has a fault, and feed back the diagnostic results to the vehicle diagnostic equipment for further processing by maintenance personnel.

[0107] In short, by sending the target configuration file to the C-end and B-end of vehicle remote diagnosis and utilizing their ability to interact with the vehicle and diagnostic equipment, remote diagnosis of the vehicle can be achieved, thereby improving the efficiency and accuracy of vehicle remote diagnosis.

[0108] In a possible implementation, before determining the adaptation probability of the vehicle bus data and a plurality of candidate bus configuration files based on the pre-trained target prediction model, the method further includes:

[0109] The vehicle bus data is preprocessed, wherein the preprocessing includes at least one of the following: encoding conversion processing, vector conversion processing, and numerical scaling processing.

[0110] In the above optional implementation, it is very important to pre-process the vehicle bus data before determining the probability of matching the vehicle bus data with multiple candidate bus profiles based on the pre-trained target prediction model. Pre-processing can make the data more standardized, easier to process and analyze, and improve the accuracy and efficiency of the model.

[0111] Optionally, the specific method of preprocessing is at least one of the following:

[0112] Encoding conversion processing: For example, specific data is encoded and converted to better meet the input requirements of the model. For example, categorical variables such as the pin of the vehicle bus, the baud rate, and all CAN IDs broadcast by the bus can be converted to one-hot encoding. One-hot encoding converts categorical variables into binary vectors, where each category corresponds to a position in the vector, and only the value of this position is 1, while the rest of the positions are 0. This makes it easier for the model to process categorical variables and improves the accuracy of the model.

[0113] Vector conversion processing: For example, some data can be converted into vector form for better mathematical operations and analysis. For example, some features in vehicle bus data can be converted into vector form through feature extraction and other methods so that they can be input into the model for processing.

[0114] Numerical scaling: For numerical data in vehicle bus data, such as OBD pin voltage value, numerical scaling can be performed. For example, the voltage value is scaled from min to max to make it between [0,1]. The calculation formula is new_val = (val-min) / (max-min), where Val is the voltage value (i.e. the sampling value of the voltage), min is the minimum voltage value, and max is the maximum voltage value. This can make data in different numerical ranges comparable, avoid the influence of large numerical data on the model, and improve the stability and accuracy of the model.

[0115] Through the above preprocessing method, the vehicle bus data can be made more suitable for input into the target prediction model for processing, thereby improving the prediction accuracy and efficiency of the model.

[0116] Please refer to Figure 4 As shown, Figure 4 : is a flow chart of an optional vehicle remote diagnosis method provided in an embodiment of the present application. In a possible implementation, before obtaining vehicle bus data of the vehicle, the method further includes:

[0117] S401, obtaining a plurality of historical vehicle diagnostic data stored in the historical diagnostic log data, wherein the diagnostic result of each of the historical vehicle diagnostic data is a successful diagnosis.

[0118] Before obtaining the current vehicle bus data of the vehicle for remote diagnosis, it is necessary to first prepare for training the model, for example, obtaining multiple historical vehicle diagnostic data from historical diagnostic log data. It should be understood that the above historical diagnostic log is usually information recorded during the past vehicle diagnostic process, wherein the diagnostic result of each historical vehicle diagnostic data is a successful diagnosis, that is, these historical vehicle diagnostic data can be characterized as successful diagnosis cases to facilitate subsequent model training.

[0119] S402: extracting the historical vehicle bus data and a bus configuration file adapted to the historical vehicle bus data from each of the historical vehicle diagnostic data.

[0120] A training data extraction operation is performed from each historical vehicle diagnostic data. Specifically, the historical vehicle bus data is extracted, which may include various information similar to the vehicle bus data to be diagnosed currently, such as the pin voltage value of the on-board self-diagnostic system, the bus pin, the bus baud rate, the bus broadcast identifier, the pin voltage value of the activation pin of the Internet Protocol-based diagnostic communication DO IP interface, etc. At the same time, the bus configuration file adapted to these historical vehicle bus data is also extracted, that is, the configuration determined to be suitable for the vehicle bus data during the diagnosis process at that time.

[0121] S403, training the initial neural network model according to the historical vehicle bus data respectively extracted from the plurality of historical vehicle diagnostic data, and a bus configuration file adapted to the historical vehicle bus data, to obtain the target prediction model.

[0122] In an optional example, before training the initial neural network model based on the extracted historical vehicle bus data and the bus configuration file adapted to the historical vehicle bus data, the historical vehicle bus data may be preprocessed, thereby making the historical vehicle bus data more standardized, easier to process and analyze, and improving the accuracy and efficiency of model training.

[0123] The initial neural network model is trained using historical vehicle bus data extracted from multiple historical vehicle diagnostic data and the bus configuration files adapted thereto. In the specific training process, the training data can be divided into a training set, a validation set, and a test set based on a preset ratio. After iterative training times and model validation, the target prediction model is finally obtained.

[0124] Optionally, the initial neural network model may be an initial neural model with an initial network structure and network parameters. For example, the loss function adopts classification cross entropy, and the optimizer adopts the stochastic gradient descent (SDG) algorithm or its further derived optimization algorithm, such as momentum optimization method (Momentum), adaptive learning rate optimization algorithm (AdaGrad or RMSProp), Adam algorithm, etc., but has not yet been trained for vehicle bus data and configuration files.

[0125] By inputting a large amount of historical vehicle bus data into the initial neural network model, the model learns the relationship between different vehicle bus data features and the corresponding bus profiles.

[0126] For example, Figure 5 An optional schematic diagram of the process of training the initial neural network model is shown. After the historical vehicle bus data is input into the initial neural network model, it passes through the input layer, fully connected layer 1, Dropout1 layer (first regularization layer), fully connected layer 2, Dropout2 layer, and fully connected layer 3 in sequence, and outputs the adaptation probability of the historical vehicle bus data and the corresponding historical bus configuration file through the output layer, or directly outputs the target configuration file adapted to the historical vehicle bus data.

[0127] In addition, activation function 1 usually follows fully connected layer 1, activation function 2 usually follows fully connected layer 2, and activation function 3 usually follows fully connected layer 3, which are used to introduce nonlinear characteristics. Taking activation function 1 as an example, activation function 1 operates on the output of fully connected layer 1. Different activation functions have different characteristics. You can choose a suitable activation function according to the specific problem to increase the flexibility of the model.

[0128] For example, in the process of vehicle remote diagnosis, the relationship between vehicle bus data and configuration files is often nonlinear, and the activation function can help the model better capture this nonlinear relationship. The activation functions in the examples of this application can be ReLU functions, which perform well in processing large-scale data.

[0129] During the training process, the initial neural network model continuously adjusts the model parameters to minimize the error between the prediction result and the actual configuration file. After a certain number of training iterations, verification and testing, the target prediction model is obtained. Then, the target prediction model can be used to predict the newly acquired vehicle bus data and determine the bus configuration file adapted to the data, thereby realizing remote diagnosis of the vehicle.

[0130] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0131] Corresponding to the remote diagnosis method of the vehicle described in the above embodiment, Figure 6 is a schematic diagram of a vehicle remote diagnosis system provided in an embodiment of the present application. According to an embodiment of the present application, an example of a vehicle remote diagnosis system is also provided. Please refer to Figure 6 As shown, the system includes:

[0132] The first client 601 is used to obtain vehicle bus data of a vehicle.

[0133] The vehicle remote diagnosis server 602 determines the adaptation probability of the vehicle bus data and a plurality of candidate bus configuration files based on a pre-trained target prediction model, and determines a target configuration file adapted to the vehicle bus data among the plurality of candidate bus configuration files according to the adaptation probability of the vehicle bus data and the plurality of candidate bus configuration files; wherein the target prediction model is obtained by training an initial neural network model based on a plurality of historical vehicle diagnostic data, and each of the historical vehicle diagnostic data includes: historical vehicle bus data, and a bus configuration file adapted to the historical vehicle bus data.

[0134] The second client 603 is used to perform remote diagnosis on the vehicle according to the target configuration file.

[0135] In the example of this application, the first client is responsible for obtaining the vehicle bus data of the vehicle. For example, by connecting to the communication interface of the vehicle (such as the OBD interface, etc.), various information in the vehicle bus system can be read, including but not limited to the pin voltage value of the on-board self-diagnosis system, bus pin, bus baud rate, bus broadcast identifier, and the pin voltage value of the activation pin of the Internet Protocol-based diagnostic communication DO IP interface.

[0136] The first client is also used to transmit the collected vehicle bus data to the vehicle remote diagnosis server so that the server can perform subsequent processing and analysis.

[0137] The vehicle remote diagnosis server is used to receive vehicle bus data from a first client based on a pre-trained target prediction model, and determine the probability of matching the data with a plurality of candidate bus configuration files. It should be understood that the target prediction model is obtained by training an initial neural network model with a large amount of historical vehicle diagnosis data, and can analyze the matching degree with different candidate bus configuration files based on the input vehicle bus data characteristics.

[0138] The vehicle remote diagnosis server is further used to evaluate and sort multiple candidate bus configuration files according to the calculated adaptation probability to select the candidate bus configuration file with the highest adaptation probability, and when the adaptation probability of the candidate bus configuration file with the highest adaptation probability is greater than a probability threshold, determine it as a target configuration file adapted to the current vehicle bus data.

[0139] In addition, as an example but not a limitation, if the candidate bus profile with the highest adaptation probability does not meet the probability threshold, it may be necessary to generate the target profile in other ways.

[0140] The second client is specifically used to perform remote diagnosis on the vehicle according to the target configuration file determined by the vehicle remote diagnosis server. This may involve communicating with the vehicle diagnostic device through a specific bus (such as a CAN bus, etc.), sending the target configuration file to the first client, coordinating the interaction between the client and the vehicle, collecting vehicle data, sending diagnostic instructions, etc., to achieve remote fault diagnosis and status monitoring of the vehicle.

[0141] Therefore, in the example of this application, the vehicle remote diagnosis system collects vehicle bus data through the client, the vehicle remote diagnosis server uses the trained model to determine the target configuration file, and the server performs remote diagnosis. The various parts work together to improve the accuracy and efficiency of vehicle remote diagnosis.

[0142] It should be noted that the information interaction, execution process, etc. between the above-mentioned client / vehicle remote diagnosis server are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0143] An embodiment of the present application further provides an electronic device, the electronic device comprising one or more processors and a memory;

[0144] The memory is coupled to one or more processors, and the memory is used to store computer program codes, where the computer program codes include computer instructions. The one or more processors call the computer instructions to enable the electronic device to execute the aforementioned vehicle remote diagnosis method.

[0145] The electronic device may be a mobile phone, a smart screen, a tablet computer, a wearable electronic device, an in-vehicle electronic device, an augmented reality (AR) device, a virtual reality (VR) device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), a projector, or a communication device such as a server, a storage device, a base station, or a smart car, etc. The embodiments of the present application do not impose any restrictions on the specific types of electronic devices.

[0146] An embodiment of the present application also provides a computer-readable storage medium, in which computer instructions are stored; when the computer-readable storage medium is run on an electronic device, the electronic device executes the remote diagnosis method of the vehicle shown above.

[0147] The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium, or a semiconductor medium (e.g., a solid state drive (SSD)), etc.

[0148] The embodiment of the present application also provides a computer program product including computer instructions, which, when executed on an electronic device, enables the electronic device to execute the vehicle remote diagnosis method shown above.

[0149] The computer storage medium and computer program product provided in the above-mentioned embodiments of the present application are used to execute the method provided above. Therefore, the beneficial effects that can be achieved can refer to the corresponding beneficial effects of the method provided above, and will not be repeated here.

[0150] In the above embodiments, it can also be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (such as: coaxial cable, optical fiber, data subscriber line (Digital Subscriber Line, DSL)) or wireless (such as: infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access, or a data storage device such as a server or data center that contains one or more available media integrations. The available medium may be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a digital versatile disc (DVD)), or a semiconductor medium (such as a solid state drive (SSD)), etc.

[0151] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application, the electronic device 700 may be a mobile phone, a computer, a digital broadcast terminal, a message transceiver device, a game console, a tablet device, a medical device, a fitness device, a personal digital assistant, etc.

[0152] The memory 701 can be used to store computer software programs 702 and modules, and the processor 703 executes various functional applications and data processing of the electronic device by running the software programs and modules stored in the memory 701. The memory 701 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the electronic device (such as audio data, a phone book, etc.), etc. In addition, the memory 701 can include a high-speed random access memory, and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0153] Among them, the processor 703 may include one or more processors such as a central processing unit, an application processor (AP), a baseband processor, etc. The processor may be the nerve center and command center of the wireless router. The processor 703 may generate an operation control signal according to the instruction operation code and the timing signal to complete the control of fetching instructions and executing instructions. The memory 701 may be used to store computer executable program codes, and the executable program codes include instructions. The processor 703 executes various functional applications and data processing of the network device by running the instructions stored in the memory. The memory 701 may include a program storage area and a data storage area, such as storing data of a sound signal to be played. For example, the memory may be a double rate synchronous dynamic random access memory DDR or a flash memory Flash, etc.

[0154] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0155] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments applied for herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0156] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0157] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0158] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A remote diagnosis method for a vehicle, characterized in that: include: Get vehicle bus data of the vehicle; Based on a pre-trained target prediction model, determining the adaptation probability of the vehicle bus data and a plurality of candidate bus configuration files, wherein the target prediction model is obtained by training an initial neural network model based on a plurality of historical vehicle diagnostic data, each of the historical vehicle diagnostic data comprising: historical vehicle bus data, and a bus configuration file adapted to the historical vehicle bus data; Determining a target configuration file adapted to the vehicle bus data from among the plurality of candidate bus configuration files according to the adaptation probabilities of the vehicle bus data and the plurality of candidate bus configuration files; Remote diagnosis is performed on the vehicle according to the target profile.

2. The method according to claim 1, characterized in that The step of obtaining vehicle bus data of a vehicle comprises: Acquiring vehicle bus data of the vehicle collected by the first client, wherein the first client communicates and / or exchanges data with the vehicle through any type of bus after successfully shaking hands with the vehicle; The vehicle bus data includes at least one of the following: a pin voltage value of an on-board self-diagnostic system, a bus pin, a bus baud rate, a bus broadcast identifier, and a pin voltage value of an activation pin of a diagnostic communication DOIP interface based on Internet Protocol.

3. The method according to claim 1, characterized in that The step of determining a target configuration file adapted to the vehicle bus data from among the plurality of candidate bus configuration files according to the adaptation probability between the vehicle bus data and the plurality of candidate bus configuration files comprises: sorting the plurality of candidate bus configuration files according to the matching probabilities between the vehicle bus data and the plurality of candidate bus configuration files to obtain a sorting result; According to the ranking result, selecting a candidate bus configuration file with the highest adaptation probability from the plurality of candidate bus configuration files; If the adaptation probability of the candidate bus profile with the highest adaptation probability is greater than the probability threshold, the candidate bus profile with the highest adaptation probability is used as the target profile.

4. The method according to claim 3, characterized in that The method further comprises: If the adaptation probability of the candidate bus configuration file with the highest adaptation probability is less than or equal to the probability threshold, obtaining the bus pin and bus baud rate in the vehicle bus data; The target configuration file is generated according to the bus pin and the bus baud rate in the vehicle bus data.

5. The method according to claim 1, characterized in that Performing remote diagnosis on the vehicle according to the target configuration file includes: The target configuration file is sent to a first client and a second client so as to perform remote diagnosis on the vehicle through the first client and the second client, wherein the second client is communicatively connected to a vehicle diagnostic device through any type of bus.

6. The method according to claim 1, characterized in that Before determining the adaptation probability of the vehicle bus data and a plurality of candidate bus configuration files based on the pre-trained target prediction model, the method further includes: The vehicle bus data is preprocessed, wherein the preprocessing includes at least one of the following: encoding conversion processing, vector conversion processing, and numerical scaling processing.

7. The method according to claim 1, characterized in that Before acquiring the vehicle bus data of the vehicle, the method further includes: Acquire a plurality of the historical vehicle diagnostic data stored in the historical diagnostic log data, wherein the diagnostic result of each of the historical vehicle diagnostic data is a successful diagnosis; Extracting the historical vehicle bus data and a bus configuration file adapted to the historical vehicle bus data from each of the historical vehicle diagnostic data; The target prediction model is obtained by training the initial neural network model based on the historical vehicle bus data respectively extracted from the plurality of historical vehicle diagnostic data and a bus configuration file adapted to the historical vehicle bus data.

8. A vehicle remote diagnosis system, characterized in that: include: A first client, used to obtain vehicle bus data of a vehicle; The vehicle remote diagnosis server determines the adaptation probability between the vehicle bus data and a plurality of candidate bus configuration files based on a pre-trained target prediction model, and determines a target configuration file adapted to the vehicle bus data among the plurality of candidate bus configuration files according to the adaptation probability between the vehicle bus data and the plurality of candidate bus configuration files; wherein the target prediction model is obtained by training an initial neural network model based on a plurality of historical vehicle diagnosis data, each of the historical vehicle diagnosis data comprising: historical vehicle bus data, and a bus configuration file adapted to the historical vehicle bus data; The second client is used to perform remote diagnosis on the vehicle according to the target configuration file.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images