Method and device for handling driving problem, equipment, computer readable storage medium

Abstract

The application provides a driving problem processing method and device, equipment and a computer readable storage medium. The method comprises the following steps: obtaining driving problem information and target function information of a vehicle; performing scene matching based on the driving problem information to obtain a target scene corresponding to the driving problem information from a plurality of preset scenes; determining a target driving problem processing model from a plurality of preset driving problem processing models based on the target scene and the target function information; pre-processing the driving problem information by using the target driving problem processing model to determine a processing method corresponding to the driving problem information; and processing the driving problem information by using the processing method. In this process, the target scene corresponding to the driving problem information is determined according to the driving problem information, the target driving problem processing model is determined according to the target scene and the target function information, the processing method corresponding to the driving problem information is determined, and the driving problem information is processed, so that the efficiency of processing the driving problem can be improved.

Description

Technical Field

[0001] This application relates to the field of software development, and more particularly to a method, apparatus, device, and computer-readable storage medium for processing driving problems. Background Technology

[0002] Intelligent driving vehicles are comprehensive intelligent systems integrating environmental perception, planning and decision-making, behavior control and execution, encompassing knowledge from multiple disciplines such as mechanics, control, sensor technology, signal processing, pattern recognition, artificial intelligence, and computer technology. Developing intelligent vehicles with autonomous driving capabilities is of significant practical importance for developing vehicle active safety assistance driving products with independent intellectual property rights in my country, improving the intelligence level of Chinese-branded automobiles, improving road traffic safety, and developing intelligent transportation systems. In the process of researching intelligent driving vehicles, many driving problems are encountered during the development of intelligent driving programs.

[0003] Regarding technical issues, the existing approach involves R&D and testing personnel addressing each driving problem individually. However, due to the large number of driving problems, the efficiency of handling these issues is relatively low. Summary of the Invention

[0004] This application provides a method, apparatus, device, and computer-readable storage medium for handling driving problems, which can improve the efficiency of handling driving problems.

[0005] The technical solution of this application is implemented as follows:

[0006] This application provides a method for handling driving problems, the method including:

[0007] Obtain vehicle driving problem information and target function information; the target function information represents any one of at least one functional position.

[0008] Based on the driving problem information, scene matching is performed to obtain the target scene corresponding to the driving problem information from multiple preset scenes;

[0009] Based on the target scenario and the target function information, a target driving problem handling model is determined from multiple preset driving problem handling models; there is a correspondence between the preset driving problem handling models and the preset scenarios;

[0010] The driving problem information is identified using the target driving problem processing model, and the corresponding processing method is determined; then the driving problem information is processed using the processing method.

[0011] In the scheme, the target driving problem processing model is determined from the plurality of preset driving problem processing models based on the target scene and the target function information, including:

[0012] The candidate preset driving problem processing model is determined from the plurality of preset driving problem processing models based on the target scene and the correspondence between the preset driving problem processing model and the preset scene.

[0013] The target driving problem processing model is determined from the candidate preset driving problem processing model based on the target function information.

[0014] It can be understood that the vehicle server determines the candidate preset driving problem processing model from the plurality of preset driving problem processing models based on the target scene and the correspondence between the preset driving problem processing model and the preset scene, and determines the target driving problem processing model from the candidate preset driving problem processing model based on the target function information, so as to select the target driving problem processing model corresponding to the driving problem information from the plurality of preset driving problem processing models, which can improve the accuracy of solving the driving problem and facilitate subsequent processing of the driving problem by the target driving problem processing model.

[0015] In the scheme, the target function information includes first post information or second post information; the first post information represents information corresponding to a development type personnel; and the second post information represents information corresponding to a test type personnel.

[0016] The target driving problem processing model is determined from the candidate preset driving problem processing model based on the target function information, including:

[0017] If the target function information is the first post information, the preset driving problem processing model corresponding to the first post information is determined as the target driving problem processing model from the candidate preset driving problem processing model.

[0018] If the target function information is the second post information, the preset driving problem processing model corresponding to the second post information is determined as the target driving problem processing model from the candidate preset driving problem processing model.

[0019] It can be understood that the vehicle server can determine the target driving problem processing model corresponding to different post information from the candidate preset driving problem processing model through different target function information, so as to solve the driving problem by the target driving problem processing model, thereby improving the accuracy of processing the driving problem.

[0020] In the above scheme, before determining the target driving problem handling model from multiple preset driving problem handling models based on the target scenario and the target functional information, the method further includes:

[0021] Acquire various historical driving problem data and information on various functional positions during vehicle operation;

[0022] The various historical driving problem data are classified and processed to obtain sample data corresponding to different preset scenarios; the sample data is historical driving problem data with scenario labels.

[0023] Based on the information of various job functions and the sample data corresponding to different preset scenarios, multiple initial driving problem solving models are trained to determine the multiple preset driving problem handling models.

[0024] Understandably, the vehicle server acquires various historical driving problem data and job information from vehicle operation; it then classifies and processes this historical driving problem data to obtain sample data corresponding to different preset scenarios; based on the job information and the sample data corresponding to different preset scenarios, it trains multiple initial driving problem solving models to determine multiple preset driving problem processing models. This facilitates the subsequent handling of repetitive driving problems through multiple preset driving problem processing models, thereby improving the efficiency of handling driving problems.

[0025] In the above scheme, each type of functional position information corresponds to the third position information and the fourth position information;

[0026] The process involves training multiple initial driving problem-solving models based on the various job information and sample data corresponding to different preset scenarios, thereby determining the multiple preset driving problem-solving models, including:

[0027] For each type of functional position information corresponding to the third position information, the multiple initial driving problem solving models are trained using the sample data corresponding to different preset scenarios to obtain a first preset driving problem processing model corresponding to each type of functional position information; the first preset driving problem processing model has a corresponding relationship with the third position information; the third position information represents the information corresponding to development personnel.

[0028] For each type of functional position information corresponding to the fourth position information, the multiple initial driving problem solving models are trained using the sample data corresponding to different preset scenarios to obtain a second preset driving problem processing model corresponding to each type of functional position information; the second preset driving problem processing model has a corresponding relationship with the fourth position information; the fourth position information represents the information corresponding to the test personnel.

[0029] Based on the first preset driving problem processing model and the second preset driving problem processing model, the plurality of preset driving problem processing models are determined.

[0030] Understandably, the vehicle server uses various job information and sample data corresponding to different preset scenarios to train multiple initial driving problem solving models, determine multiple highly targeted preset driving problem handling models, and facilitate the use of preset driving problem handling models to solve driving problems, thereby improving the efficiency of handling driving problems.

[0031] In the above scheme, the step of identifying the driving problem information and determining the corresponding processing method through the target driving problem processing model includes:

[0032] The driving problem information is identified using the target driving problem processing model to obtain the identification result;

[0033] If the recognition result indicates successful recognition, then the processing method corresponding to the driving problem information is determined through the target driving problem processing model;

[0034] If the recognition result indicates recognition failure, then instruction information is generated based on the driving problem information; and in response to the instruction information, the processing method corresponding to the driving problem information is determined.

[0035] Understandably, the vehicle server identifies driving problem information using a target driving problem processing model and obtains the identification result. If the identification result indicates successful identification, the target driving problem processing model determines the corresponding processing method for the driving problem information. If the identification result indicates failure, instruction information is generated based on the driving problem information, and the corresponding processing method is determined in response to the instruction information. This allows the target driving problem processing model to handle repetitive driving problems as well as non-repetitive problems, ensuring that all driving problems can be solved, thus improving the efficiency and capability of handling driving problems.

[0036] In the above scheme, after determining the processing method corresponding to the driving problem information in response to the instruction information, the method further includes:

[0037] Based on the processing method corresponding to the driving problem information and the driving problem information, the target driving problem processing model is updated to determine the updated target driving problem processing model.

[0038] It is understandable that the vehicle server can update the target driving problem processing model based on the processing method corresponding to the driving problem information and the driving problem information, and determine the updated target driving problem processing model, which can improve the processing capability of the driving problem solving model.

[0039] This application provides a driving problem processing apparatus, which includes an acquisition unit and a determination unit, wherein...

[0040] The acquisition unit is used to acquire vehicle driving problem information and target function information; the target function information represents any one of at least one functional position; based on the driving problem information, scenario matching is performed to obtain the target scenario corresponding to the driving problem information from multiple preset scenarios;

[0041] The determining unit is configured to determine a target driving problem processing model from multiple preset driving problem processing models based on the target scenario and the target functional information; the preset driving problem processing models correspond to preset scenarios; the driving problem information is identified through the target driving problem processing model to determine the processing method corresponding to the driving problem information; and the driving problem information is processed through the processing method.

[0042] This application provides a device for processing driving problems, including:

[0043] Memory, used to store executable data instructions;

[0044] A processor is configured to execute executable instructions stored in the memory, and when the executable instructions are executed, the processor executes the driving problem processing method.

[0045] This application provides a computer-readable storage medium storing executable instructions, which, when executed by one or more processors, perform the driving problem processing method.

[0046] This application provides a method, apparatus, device, and computer-readable storage medium for handling driving problems. The method includes: acquiring driving problem information and target functional information of a vehicle; the target functional information represents any one of at least one functional position; performing scenario matching based on the driving problem information to obtain a target scenario corresponding to the driving problem information from multiple preset scenarios; determining a target driving problem handling model from multiple preset driving problem handling models based on the target scenario and the target functional information; a correspondence exists between the preset driving problem handling models and the preset scenarios; identifying the driving problem information using the target driving problem handling model to determine a handling method corresponding to the driving problem information; and processing the driving problem information using the handling method. In this solution, the target scenario corresponding to the driving problem information can be determined based on the driving problem information; the target driving problem handling model can be determined from multiple preset driving problem handling models based on the target scenario and target functional information; the handling method corresponding to the driving problem information can be determined using the target driving problem handling model; and the driving problem information can be processed using the handling method. This process does not require manual intervention, reducing resource usage. Furthermore, the driving problem handling model can solve repetitive driving problems, improving the efficiency of handling driving problems. Attached Figure Description

[0047] Figure 1 This application provides an optional flowchart illustrating a method for handling driving problems. Figure One ;

[0048] Figure 2 This application provides an optional flowchart illustrating a method for handling driving problems. Figure Two ;

[0049] Figure 3 This application provides an optional flowchart illustrating a method for handling driving problems. Figure Three ;

[0050] Figure 4 This application provides an optional flowchart illustrating a method for handling driving problems. Figure Four ;

[0051] Figure 5 This application provides a schematic diagram of the structure of a device for processing driving problems.

[0052] Figure 6 This is a schematic diagram of the structure of a device for processing driving problems provided in an embodiment of this application. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the specific technical solutions of this application will be further described in detail below with reference to the accompanying drawings of the embodiments of this application. The following embodiments are used to illustrate this application, but are not intended to limit the scope of this application.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0055] In the following description, references to "some embodiments," "this embodiment," "this application embodiment," and examples, etc., describe a subset of all possible embodiments. However, it is understood that "some embodiments" may be the same subset or different subset of all possible embodiments and may be combined with each other without conflict.

[0056] If the application documents contain similar descriptions such as "first / second", the following explanation shall be added: In the following description, the terms "first / second / third" are used only to distinguish similar objects and do not represent a specific order of objects. It is understood that "first / second / third" may be interchanged in a specific order or sequence where permitted, so that the embodiments of this application described herein can be implemented in an order other than that illustrated or described herein.

[0057] This application provides a method for handling driving problems. Figure 1 This application provides an optional flowchart illustrating a method for handling driving problems. Figure One , will combine Figure 1 The steps shown are explained.

[0058] S101. Obtain vehicle driving problem information and target function information; the target function information represents any one of the at least one functional positions.

[0059] In some embodiments of this application, the target functional information includes: first job information or second job information; the first job information represents the information corresponding to development personnel; and the second job information represents the information corresponding to testing personnel.

[0060] In some embodiments of this application, the research process of intelligent driving involves many different functional positions, and different personnel correspond to the same intelligent position, such as testers and developers. The target functional information is the first position information or the second position information given that the functional positions are determined; the first position information is the position corresponding to the developer, and the second position information is the position corresponding to the testers.

[0061] In some embodiments of this application, the application is adapted to the scenario of research and development and testing of intelligent driving for vehicles.

[0062] In some embodiments of this application, the executing entity is a vehicle server.

[0063] In some embodiments of this application, during vehicle operation, the vehicle server can obtain vehicle driving problem information, as well as target functional information regarding the resolution of driving problem information.

[0064] It should be noted that driving problems are malfunctions that occur while the vehicle is in motion.

[0065] S102. Based on driving problem information, perform scene matching to obtain the target scene corresponding to the driving problem information from multiple preset scenes.

[0066] In some embodiments of this application, before obtaining driving problem information, multiple preset scenarios can be obtained through a large amount of sample data. These scenarios can be regarded as labels corresponding to driving problems. Each piece of driving problem information has a corresponding scenario.

[0067] In some embodiments of this application, the vehicle server can perform scene matching based on the acquired driving problem information to determine the target scene corresponding to the driving problem information from multiple preset scenes.

[0068] It should be noted that for the same preset scenario, the information about the driving problem may differ depending on the location where the problem occurs.

[0069] S103. Based on the target scenario and target function information, determine the target driving problem handling model from multiple preset driving problem handling models; there is a correspondence between the preset driving problem handling models and the preset scenarios.

[0070] In some embodiments of this application, there is a correspondence between preset scenarios and preset driving problem handling models. For the same preset scenario, the corresponding preset driving problem handling models are also different due to different target functional positions. That is, under the same preset scenario, the preset driving problem handling models corresponding to each functional position are different.

[0071] In some embodiments of this application, the vehicle server determines candidate preset driving problem processing models from multiple preset driving problem processing models based on the target scenario and the correspondence between preset driving problem processing models and preset scenarios; and determines the target driving problem processing model from the candidate preset driving problem processing models based on target functional information.

[0072] In some embodiments of this application, the vehicle server can determine a candidate preset driving problem processing model corresponding to the target scenario from multiple preset driving problem processing models, and then determine a target driving problem processing model corresponding to the target function information from the candidate preset driving problem processing models based on the target function information.

[0073] For example, based on target scenario A, candidate preset driving problem processing models are determined from multiple preset driving problem processing models, namely models A1, A2 and A3 respectively. Based on target functional information 2, the target driving problem processing model is determined to be A2.

[0074] It should be noted that the candidate preset driving problem handling model corresponding to the target scenario is not unique. That is, the target scenario corresponds to at least one preset driving problem handling model (for the same preset scenario, more than one functional department needs to participate, so the same preset scenario corresponds to multiple preset driving problem handling models). The target driving problem handling model can be determined based on the target functional information.

[0075] S104. Through the target driving problem processing model, identify driving problem information, determine the corresponding processing method for driving problem information, and process the driving problem information through the processing method.

[0076] In some embodiments of this application, the vehicle server can identify driving problem information through a target driving problem processing model. If the identified driving problem information is a repetitive technical problem, the target driving problem processing model is used to determine the corresponding processing method for the driving problem information, and the driving problem information is processed using the corresponding processing method.

[0077] In some embodiments of this application, the vehicle server identifies driving problem information through a target driving problem processing model and obtains an identification result. If the identification result indicates successful identification, the target driving problem processing model determines the processing method corresponding to the driving problem information. If the identification result indicates failure, instruction information is generated based on the driving problem information, and in response to the instruction information, the processing method corresponding to the driving problem information is determined.

[0078] It should be noted that the driving problem information is a repetitive technical problem, that is, the driving problem information is a technical problem that the target driving problem processing model has previously processed.

[0079] For example, the driving problem information is that the indicator light cannot be recognized in XX location. The target driving problem processing model is the driving problem solution model corresponding to the inability to recognize the indicator light. The driving problem information is identified by the target driving problem processing model. It is identified that the driving problem information is a repetitive technical problem. The processing method corresponding to the inability to recognize the indicator light in XX location is directly determined by the target driving problem processing model.

[0080] The process involves acquiring vehicle driving problem information and target function information; based on the driving problem information, performing scenario matching to obtain the target scenario corresponding to the driving problem information from multiple preset scenarios; based on the target scenario and target function information, determining the target driving problem processing model from multiple preset driving problem processing models; pre-identifying the driving problem information using the target driving problem processing model to determine the corresponding processing method; and finally processing the driving problem information using the processing method. In this process, the target scenario corresponding to the driving problem information is determined based on the driving problem information; the target driving problem processing model is determined from multiple preset driving problem processing models based on the target scenario and target function information; the corresponding processing method is determined using the target driving problem processing model; and the driving problem information is processed using the processing method. This process does not require manual intervention, reducing resource usage. Furthermore, the driving problem resolution model can solve repetitive driving problems, improving the efficiency of handling driving problems.

[0081] In some embodiments of this application, Figure 2 This application provides an optional flowchart illustrating a method for handling driving problems. Figure Two ,like Figure 2 As shown, S103 can be implemented through S1031 and S1032, as follows:

[0082] S1031. Based on the target scenario, candidate preset driving problem processing models are determined from multiple preset driving problem processing models by means of the correspondence between preset driving problem processing models and preset scenarios.

[0083] In some embodiments of this application, the correspondence between preset driving problem handling models and preset scenarios can be as follows: preset scenarios include a first preset scenario, a second preset scenario, and a third preset scenario, etc., and preset driving problem handling models include a first preset driving problem handling model, a second preset driving problem handling model, and a third preset driving problem handling model, etc. The first preset scenario corresponds to the first preset driving problem handling model, the second preset scenario corresponds to the second preset driving problem handling model, and the third preset scenario corresponds to the third preset driving problem handling model. Each of the first, second, and third preset driving problem handling models includes at least two preset driving problem handling models.

[0084] In some embodiments of this application, the vehicle server can determine candidate preset driving problem processing models from multiple preset driving problem processing models based on the target scenario and by the correspondence between preset driving problem processing models and preset scenarios.

[0085] It should be noted that the candidate preset driving problem handling models include at least two preset driving problem handling models.

[0086] S1032. Based on the target functional information, determine the target driving problem processing model from the candidate preset driving problem processing models.

[0087] In some embodiments of this application, the vehicle server can determine the target driving problem processing model corresponding to the target function information from the candidate preset driving problem processing models based on the target function information.

[0088] In some embodiments of this application, if the target functional information is first job information, the preset driving problem processing model corresponding to the first job information is determined as the target driving problem processing model from the candidate preset driving problem processing models; if the target functional information is second job information, the preset driving problem processing model corresponding to the second job information is determined as the target driving problem processing model from the candidate preset driving problem processing models.

[0089] In some embodiments of this application, since the target job information is either first job information or second job information, the vehicle server can determine the target driving problem processing model corresponding to the first job information from the candidate preset driving problem processing models based on the first job information; or, based on the second job information, determine the target driving problem processing model corresponding to the second job information from the candidate preset driving problem processing models.

[0090] Understandably, the vehicle server determines candidate preset driving problem processing models from multiple preset driving problem processing models based on the target scenario and the correspondence between preset driving problem processing models and preset scenarios; based on target functional information, it determines the target driving problem processing model from the candidate preset driving problem processing models; and selecting the target driving problem processing model corresponding to the driving problem information from multiple preset driving problem processing models can improve the accuracy of solving driving problems and facilitate subsequent resolution of driving problems through the target driving problem processing model.

[0091] In some embodiments of this application, Figure 3 This application provides an optional flowchart illustrating a method for handling driving problems. Figure Three ,like Figure 3As shown, S104 can be implemented through S1041, S1042, and S1043, as follows:

[0092] S1041. Using the target driving problem processing model, identify driving problem information and obtain the identification results.

[0093] In some embodiments of this application, the vehicle server can identify driving problem information through a target driving problem processing model, determine whether the driving problem information is a repetitive technical problem, and thus obtain the identification result.

[0094] It should be noted that the recognition result is either successful or unsuccessful.

[0095] S1042. If the recognition result indicates successful recognition, then the processing method corresponding to the driving problem information is determined through the target driving problem processing model.

[0096] In some embodiments of this application, if the vehicle server identifies the driving problem information as a repetitive technical problem, that is, the identification result indicates successful identification, indicating that the target driving problem processing model has processed this type of driving problem, then the processing method corresponding to the driving problem information is determined through the target driving problem processing model.

[0097] For example, if the driving problem information is that the route sign cannot be identified on section XX, and the target driving problem processing model identifies the driving problem information as a repetitive technical problem, it can directly output the processing method corresponding to the route sign that cannot be identified on section XX, thereby solving the driving problem without requiring testers or R&D personnel to solve it manually.

[0098] S1043. If the identification result indicates that the identification has failed, then based on the driving problem information, an instruction message is generated; and in response to the instruction message, the corresponding processing method for the driving problem information is determined.

[0099] In some embodiments of this application, if the vehicle server identifies the driving problem information as a non-repetitive technical problem, it indicates that the target driving problem processing model has not handled this type of driving problem before. Based on the driving problem information, instruction information is generated. In response to the instruction information, the processing method corresponding to the driving problem information is determined.

[0100] In some embodiments of this application, the vehicle server generates instruction information based on driving problem information, presents the instruction information to the terminal of the relevant staff, and the staff analyzes the problem to obtain the corresponding processing method for the driving problem information.

[0101] In some embodiments of this application, the vehicle server can associate similar scenario problems and assign them to relevant developers for resolution based on the priority of the association. If there are no associated objects, the problem will be prioritized and assigned to the domain manager for manual handling and classification to avoid situations where problems are unresolved and without any basis.

[0102] Understandably, the vehicle server identifies driving problem information using a target driving problem processing model and obtains the identification result. If the identification result indicates successful identification, the target driving problem processing model determines the corresponding processing method for the driving problem information. If the identification result indicates failure, instruction information is generated based on the driving problem information, and the corresponding processing method is determined in response to the instruction information. This allows the target driving problem processing model to handle repetitive driving problems as well as non-repetitive problems, ensuring that all driving problems can be solved, thus improving the efficiency and capability of handling driving problems.

[0103] In some embodiments of this application, after executing S1043, S1044 is also executed, as follows:

[0104] S1044. Based on the processing method corresponding to the driving problem information and the driving problem information, update the target driving problem processing model and determine the updated target driving problem processing model.

[0105] In some embodiments of this application, after determining that the driving problem information is a non-repetitive technical problem and the corresponding processing method, the vehicle server can update the target driving problem processing model based on the corresponding processing method and the driving problem information, thereby determining the updated target driving problem processing model.

[0106] It should be noted that the updated target driving problem handling model can handle more driving problems.

[0107] It is understandable that the vehicle server can update the target driving problem processing model based on the processing method corresponding to the driving problem information and the driving problem information, and determine the updated target driving problem processing model, which can improve the processing capability of the driving problem solving model.

[0108] In some embodiments of this application, S105, S106, and S107 are executed before S103, as follows:

[0109] S105. Obtain various historical driving problem data and various functional position information during vehicle operation.

[0110] In some embodiments of this application, the vehicle server can acquire various historical driving problem data during vehicle operation, and these various historical driving problem data are different types of driving problem data. Each type of functional position information in the multiple functional position information corresponds to third position information and fourth position information; the third position information represents the information corresponding to development personnel; and the fourth position information represents the information corresponding to testing personnel.

[0111] In some embodiments of this application, the vehicle server can acquire various historical driving problem data to establish a database. Specifically, this is mainly based on actual data collection tools and corresponding preliminary manual data classification. Data itself cannot generate intelligence; only through manual classification and labeling can data possess the crucial prerequisite for generating intelligence. General databases rely on the internet for generation, while intelligent driving databases must rely on actual vehicles and data collection software. Depending on the functions of the required intelligent assistant (i.e., the preset driving problem handling model), the functions of the data collection software also have considerable scalability. In scenarios where there is no initial version of intelligent driving software, the collected data consists only of the raw data from the actual vehicle. The development of intelligent driving relies on this raw data, and the role of the intelligent assistant, besides providing answers to problems, also provides a basis for the development direction of the intelligent driving software. If there is an initial version of intelligent driving software, then in addition to the raw data, a large amount of intermediate intelligent driving data needs to be collected, and this data can be saved to establish a database.

[0112] S106. Classify and process various historical driving problem data to obtain sample data corresponding to different preset scenarios.

[0113] In some embodiments of this application, the vehicle server can classify various historical driving problem data to obtain classification results, and then label the classification results to obtain sample data corresponding to different preset scenarios. The sample data is historical driving problem data with scenario labels.

[0114] S107. Based on various job information and sample data corresponding to different preset scenarios, train multiple initial driving problem solving models to determine multiple preset driving problem handling models.

[0115] In some embodiments of this application, the vehicle server can train multiple initial driving problem solving models and multiple preset driving problem processing models by using various job information and sample data corresponding to different preset scenarios.

[0116] In some embodiments of this application, during the training process, an initial driving problem solving model can be trained using sample data corresponding to a preset scenario and a job function, respectively, to determine the preset driving problem processing model.

[0117] It should be noted that different preset driving problem handling models are used for different preset scenarios. This avoids training only one preset driving problem handling model for all preset scenarios. This is because an all-encompassing preset driving problem handling model cannot be targeted and can only meet basic needs. Therefore, different preset driving problem handling models are trained according to different preset scenarios.

[0118] Understandably, the vehicle server acquires various historical driving problem data and job information from various functions and positions during vehicle operation; it then classifies and processes this historical driving problem data to obtain sample data corresponding to different preset scenarios; based on the job information and the sample data corresponding to different preset scenarios, it trains multiple initial driving problem solving models to determine multiple preset driving problem processing models. This facilitates the subsequent handling of repetitive driving problems through multiple preset driving problem processing models, thereby improving the efficiency of driving problem processing.

[0119] In some embodiments of this application, S107 can be implemented by S1071, S1072, and S1073, as follows:

[0120] S1071. For the third job information corresponding to each functional job information, multiple initial driving problem solving models are trained using sample data corresponding to different preset scenarios to obtain the first preset driving problem processing model corresponding to each functional job information; the first preset driving problem processing model has a corresponding relationship with the third job information; the third job information represents the information corresponding to development personnel.

[0121] In some embodiments of this application, the vehicle server can train multiple initial driving problem solving models for each type of functional position information and the corresponding third position information using sample data from different preset scenarios, until the loss value of the trained driving problem solving model reaches a preset threshold, thereby obtaining a first preset driving problem processing model for each type of functional position information.

[0122] S1072. For the fourth job information corresponding to each functional job information, multiple initial driving problem solving models are trained using sample data corresponding to different preset scenarios to obtain a second preset driving problem processing model corresponding to each functional job information; the second preset driving problem processing model has a corresponding relationship with the fourth job information; the fourth job information represents the information corresponding to the test personnel.

[0123] In some embodiments of this application, the vehicle server trains multiple initial driving problem-solving models for each type of functional position information and the corresponding fourth position information using sample data from different preset scenarios, until the loss value of the trained driving problem-solving model reaches a preset threshold, thereby obtaining a second preset driving problem processing model corresponding to each type of functional position information.

[0124] S1073. Based on the first preset driving problem processing model and the second preset driving problem processing model, determine multiple preset driving problem processing models.

[0125] In some embodiments of this application, the vehicle server may determine multiple preset driving problem processing models based on a first preset driving problem processing model and a second preset driving problem processing model.

[0126] It should be noted that both the first preset driving problem handling model and the second preset driving problem handling model include at least one preset driving problem handling model.

[0127] Understandably, the vehicle server uses various job information and sample data corresponding to different preset scenarios to train multiple initial driving problem solving models, determine multiple preset driving problem handling models with strong targeting, and make it easier to use preset driving problem handling models to solve driving problems and improve the efficiency of driving problem handling.

[0128] In some embodiments of this application, Figure 4 This application provides an optional flowchart illustrating a method for handling driving problems. Figure Four ,like Figure 4 As shown, after acquiring driving problem data (i.e., various historical driving problem data), the vehicle server can analyze the problem scenarios, map the scenarios (i.e., preset scenarios) to the data, extract feature values ​​from the driving problem data (i.e., determine the scenarios corresponding to the driving problem data), and then train the scenario to obtain an artificial intelligence model (i.e., a preset driving problem handling model). After obtaining the artificial intelligence model, road tests are conducted, and the model is used to classify the data, resulting in recurring problems (i.e., repetitive technical problems) or entirely new problems (i.e., non-repetitive technical problems). If it is a recurring problem, it is solved by artificial intelligence; if it is an entirely new problem, it is solved by engineers (i.e., testers or developers), new feature values ​​are extracted for the entirely new problem, and the artificial intelligence model is updated using the new feature values.

[0129] It should be noted that data feature values ​​can also be extracted from a database, and new feature values ​​can also enrich the database.

[0130] In some embodiments of this application, human-computer interaction (HCI) is implemented after a preset driving problem handling model is determined. The purpose of HCI is to allow users to quickly interact with the model's database, updating and acquiring data, through interaction methods that meet their daily usage habits. This involves the interface layout and corresponding functions on different terminals. For testers' terminals, which are often located in actual vehicles, the interaction method should be simple and not easily triggered by accident. Compared to keyboard and mouse operation, steering wheel buttons and voice interaction are more suitable for testers. In addition, real-time interaction with intelligent assistants via mobile devices is also essential. All processes should be conducted on mobile devices with security measures or applications with security settings. For developers' terminals, compared to the confined environment of a real vehicle test environment, development environments are generally noisy and may not have a steering wheel, so keyboard and mouse operation is generally preferred.

[0131] Understandably, vehicle servers are designed to address the recurring issues in intelligent driving, providing developers and testers with a powerful and efficient development and testing tool. They can categorize and alert developers to real-time problems, summarize lessons learned from past issues, and warn of unforeseen problems, significantly improving development efficiency and making testers' data more reasonable and effective.

[0132] This application also provides a device for handling driving problems, such as... Figure 5 As shown, Figure 5 This is a schematic diagram of a driving problem processing device provided in an embodiment of this application. The driving problem processing device 5 includes: an acquisition unit 501 and a determination unit 502; wherein,

[0133] The acquisition unit 501 is used to acquire vehicle driving problem information and target function information; the target function information represents any one of at least one functional position; based on the driving problem information, scenario matching is performed to obtain the target scenario corresponding to the driving problem information from multiple preset scenarios;

[0134] The determining unit 502 is used to determine a target driving problem processing model from multiple preset driving problem processing models based on the target scenario and the target functional information; the preset driving problem processing models correspond to preset scenarios; the driving problem information is identified through the target driving problem processing model, the processing method corresponding to the driving problem information is determined, and the driving problem information is processed through the processing method.

[0135] In some embodiments of this application, the determining unit 502 is further configured to determine a candidate preset driving problem processing model from the plurality of preset driving problem processing models based on the target scenario and through the correspondence between the preset driving problem processing model and the preset scenario; and to determine the target driving problem processing model from the candidate preset driving problem processing models based on the target functional information.

[0136] In some embodiments of this application, the target functional information includes: first job information or second job information; the first job information represents information corresponding to development personnel; the second job information represents information corresponding to testing personnel;

[0137] The determining unit 502 is further configured to, if the target functional information is the first job information, determine from the candidate preset driving problem processing models that the preset driving problem processing model corresponding to the first job information is the target driving problem processing model; and if the target functional information is the second job information, determine from the candidate preset driving problem processing models that the preset driving problem processing model corresponding to the second job information is the target driving problem processing model.

[0138] In some embodiments of this application, the acquisition unit 501 is further configured to acquire various historical driving problem data and various job information during vehicle operation before determining the target driving problem processing model from multiple preset driving problem processing models based on the target scenario and the target job information; classify the various historical driving problem data to obtain sample data corresponding to different preset scenarios; the sample data is historical driving problem data with scenario tags;

[0139] The determining unit 502 is further configured to train multiple initial driving problem solving models based on the multiple functional job information and the sample data corresponding to different preset scenarios, and determine the multiple preset driving problem processing models.

[0140] In some embodiments of this application, each type of functional position information in the multiple functional position information corresponds to third position information and fourth position information;

[0141] In some embodiments of this application, the acquisition unit 501 is further configured to, for each type of functional position information corresponding to the third position information, train the plurality of initial driving problem-solving models respectively using sample data corresponding to different preset scenarios to obtain a first preset driving problem-solving model corresponding to each type of functional position information; the first preset driving problem-solving model has a correspondence with the third position information; the third position information represents information corresponding to development personnel; for each type of functional position information corresponding to the fourth position information, train the plurality of initial driving problem-solving models respectively using sample data corresponding to different preset scenarios to obtain a second preset driving problem-solving model corresponding to each type of functional position information; the second preset driving problem-solving model has a correspondence with the fourth position information; the fourth position information represents information corresponding to testing personnel;

[0142] The determining unit 502 is further configured to determine the plurality of preset driving problem processing models based on the first preset driving problem processing model and the second preset driving problem processing model.

[0143] In some embodiments of this application, the acquisition unit 501 is further configured to identify the driving problem information through the target driving problem processing model and obtain an identification result; if the identification result indicates successful identification, then the processing method corresponding to the driving problem information is determined through the target driving problem processing model.

[0144] The determining unit 502 is further configured to, if the identification result indicates identification failure, generate instruction information based on the driving problem information; and, in response to the instruction information, determine the processing method corresponding to the driving problem information.

[0145] In some embodiments of this application, the determining unit 502 is further configured to, in response to the instruction information, determine the processing method corresponding to the driving problem information, and then, based on the processing method corresponding to the driving problem information and the driving problem information, update the target driving problem processing model and determine the updated target driving problem processing model.

[0146] Based on the driving problem processing method of the above embodiments, this application also provides a driving problem processing device, such as... Figure 6 As shown, Figure 6This is a schematic diagram of a driving problem processing device provided in an embodiment of this application. The driving problem processing device 6 includes a processor 601 and a memory 602. The memory 602 is used to store computer programs; the processor 601 is used to call and run the computer programs from the memory to execute the driving problem processing method as described in the above embodiment.

[0147] In the embodiments of this application, the processor 601 described above can be at least one of the following: Application-Specific Integrated Circuit (ASIC), Digital Signal Processor (DSP), Digital Signal Processing Device (DSPD), Programmable Logic Device (PLD), Field Programmable Gate Array (FPGA), Central Processing Unit (CPU), Controller, Microcontroller, and Microprocessor. It is understood that for different devices, the electronic device used to implement the above processor function can also be other types, and the embodiments of this application do not specifically limit it.

[0148] This application provides a computer-readable storage medium storing a computer program for implementing the driving problem processing method described in any of the above embodiments when executed by a processor.

[0149] For example, the program instructions corresponding to a driving problem processing method in this embodiment can be stored on storage media such as optical discs, hard disks, and USB flash drives. When the program instructions corresponding to a driving problem processing method in the storage media are read or executed by an electronic device, the driving problem processing method as described in any of the above embodiments can be implemented.

[0150] Furthermore, in the embodiments of this application, the functional modules can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional module.

[0151] If the integrated unit is implemented as a software functional module and is not sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this embodiment, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) or processor to execute all or part of the steps of the method of this embodiment. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0152] It should be understood that the phrases "one embodiment," "an embodiment," or "some embodiments" throughout the specification mean that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, "in one embodiment," "in one embodiment," or "in some embodiments" appearing throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It should be understood that in the various embodiments of this application, the sequence numbers of the above-described processes do not imply a sequential 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 this application. The sequence numbers of the above-described embodiments are merely descriptive and do not represent the superiority or inferiority of the embodiments. The descriptions of the various embodiments above tend to emphasize the differences between the various embodiments; their similarities or commonalities can be referred to mutually, and for the sake of brevity, they will not be repeated here.

[0153] The modules described above as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules. They may be located in one place or distributed across multiple network units. Some or all of the modules may be selected to achieve the purpose of this embodiment according to actual needs.

[0154] In addition, each functional module in the various embodiments of this application can be integrated into one processing unit, or each module can be a separate unit, or two or more modules can be integrated into one unit; the integrated modules can be implemented in hardware or in the form of hardware plus software functional units.

[0155] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media that can store program code, such as mobile storage devices, read-only memory (ROM), magnetic disks, or optical disks.

[0156] The methods disclosed in the several method embodiments provided in this application can be arbitrarily combined without conflict to obtain new method embodiments.

[0157] The features disclosed in the several product embodiments provided in this application can be arbitrarily combined without conflict to obtain new product embodiments.

[0158] The features disclosed in the several method or device embodiments provided in this application can be arbitrarily combined without conflict to obtain new method or device embodiments.

[0159] The above description is merely an embodiment of this application, but the protection scope of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application. Therefore, the protection scope of this application should be determined by the protection scope of the claims.

Claims

1. A method of handling a driving problem, characterized by, The method comprises the following steps: obtaining driving problem information and target function information of a vehicle; the target function information represents any one of at least one function post; based on the driving problem information, scene matching is performed to obtain a target scene corresponding to the driving problem information from a plurality of preset scenes; based on the target scene and the target function information, a target driving problem processing model is determined from a plurality of preset driving problem processing models; the preset driving problem processing model and the preset scene have a corresponding relationship; the target driving problem processing model is used to identify the driving problem information, and a processing method corresponding to the driving problem information is determined; and the driving problem information is processed by the processing method; wherein, based on the target scene and the target function information, the target driving problem processing model is determined from a plurality of preset driving problem processing models, comprising: based on the target scene, a candidate preset driving problem processing model is determined from the plurality of preset driving problem processing models through the corresponding relationship between the preset driving problem processing model and the preset scene; based on the target function information, the target driving problem processing model is determined from the candidate preset driving problem processing model; the target function information comprises first post information or second post information; the first post information represents information corresponding to development personnel; the second post information represents information corresponding to test personnel; based on the target function information, the target driving problem processing model is determined from the candidate preset driving problem processing model, comprising: if the target function information is the first post information, the preset driving problem processing model corresponding to the first post information is determined as the target driving problem processing model from the candidate preset driving problem processing model; if the target function information is the second post information, the preset driving problem processing model corresponding to the second post information is determined as the target driving problem processing model from the candidate preset driving problem processing model.

2. The method of claim 1, wherein, Before the target driving problem processing model is determined based on the target scene and the target function information from the plurality of preset driving problem processing models, the method further comprises: obtaining a plurality of historical driving problem data and a plurality of function post information during vehicle driving; classifying the plurality of historical driving problem data to obtain sample data corresponding to different preset scenes respectively; the sample data is historical driving problem data with scene labels; based on the plurality of function post information and the sample data corresponding to different preset scenes respectively, a plurality of initial driving problem solving models are trained respectively to determine the plurality of preset driving problem processing models.

3. The method of claim 2, wherein, each of the plurality of function post information corresponds to third post information and fourth post information; based on the plurality of function post information and the sample data corresponding to different preset scenes respectively, a plurality of initial driving problem solving models are trained respectively to determine the plurality of preset driving problem processing models, comprising: For the third post information corresponding to each function post information, the plurality of initial driving problem solving models are trained respectively through the sample data corresponding to different preset scenes, to obtain a first preset driving problem processing model corresponding to each function post information; the first preset driving problem processing model has a corresponding relationship with the third post information; the third post information represents information corresponding to a development type personnel; For the fourth post information corresponding to each function post information, the plurality of initial driving problem solving models are trained respectively through the sample data corresponding to different preset scenes, to obtain a second preset driving problem processing model corresponding to each function post information; the second preset driving problem processing model has a corresponding relationship with the fourth post information; the fourth post information represents information corresponding to a test type personnel; Based on the first preset driving problem processing model and the second preset driving problem processing model, the plurality of preset driving problem processing models are determined.

4. The method of claim 1, wherein, The method further comprises: Based on the processing method corresponding to the driving problem information and the driving problem information, the target driving problem processing model is updated to determine an updated target driving problem processing model. The method further comprises: The method further comprises:

5. The method of claim 4, wherein, The method further comprises: The method further comprises:

6. A driving problem processing device characterized by comprising: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The method further comprises: The The determining unit is further configured to determine a candidate preset driving problem processing model from the plurality of preset driving problem processing models based on the target scenario and a correspondence between the preset driving problem processing models and the preset scenarios, and determine the target driving problem processing model from the candidate preset driving problem processing models based on the target function information. The target function information includes first post information or second post information. The first post information represents information corresponding to a development personnel. The second post information represents information corresponding to a test personnel. The determining unit is further configured to determine, if the target function information is the first post information, a preset driving problem processing model corresponding to the first post information from the candidate preset driving problem processing models as the target driving problem processing model, and determine, if the target function information is the second post information, a preset driving problem processing model corresponding to the second post information from the candidate preset driving problem processing models as the target driving problem processing model.

7. A driving problem processing device characterized by comprising: Comprising: a memory for storing executable data instructions; a processor for executing the executable instructions stored in the memory to implement the driving problem processing method of any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, executable instructions stored in the memory for causing the processor to execute to implement the driving problem processing method of any one of claims 1 to 5.

Images