Vehicle driving problem determination method and device, electronic equipment and storage medium

Abstract

The invention discloses a driving data processing method and device, electronic equipment and a storage medium, and relates to the technical field of vehicle intelligent driving. The method comprises the steps that based on a preset configuration file template, preset dotting processing is carried out on vehicle driving data of different data types, target vehicle configuration data with a dotting label is determined, and the preset dotting processing is used for representing the processing process of dotting annotation of the vehicle driving data in a target driving scene; inputting the target vehicle configuration data into the trained multi-modal feature model for labeling training, and determining target labeling data corresponding to the target vehicle configuration data; and based on an external vehicle driving feature analysis algorithm, performing problem analysis on the target annotation data, and determining a driving problem of the vehicle in a driving process and a cause of the driving problem. According to the invention, problems occurring in the intelligent driving system can be positioned and analyzed, and the problem of poor vehicle driving data collaboration is reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle intelligent driving, and in particular to a vehicle driving problem determination method and device, an electronic device, and a storage medium. BACKGROUND

[0002] At present, with the rapid development of intelligent driving technology, data has become the core resource for algorithm iteration, system optimization, and function verification. Intelligent driving systems generate massive multi-source heterogeneous data during operation. How to efficiently collect, manage, label, and analyze these data and build a complete closed loop from data input to value mining has become a key to promoting the maturity of intelligent driving technology.

[0003] However, the traditional management of vehicle driving data cannot trace back and locate problems in the intelligent driving system, and has poor collaboration. SUMMARY

[0004] The present application provides a vehicle driving problem determination method. The embodiments provided by the present application solve the technical problem that the prior art cannot trace back and locate problems in the intelligent driving system and has poor collaboration. The present application can locate and analyze problems in the intelligent driving system and reduce the problem of poor collaboration of vehicle driving data.

[0005] In a first aspect of the embodiments of the present application, a vehicle driving problem determination method is provided, which includes: performing preset dotting processing on vehicle driving data of different data types based on a preset configuration file template to determine target vehicle configuration data with dotting labels, wherein the preset dotting processing is used to represent a processing process of dotting annotation on the vehicle driving data in a target driving scene; inputting the target vehicle configuration data into a trained multi-modal feature model for labeling training to determine target labeling data corresponding to the target vehicle configuration data; performing problem analysis on the target labeling data based on an external vehicle driving feature analysis algorithm to determine a driving problem in the driving process of the vehicle and a cause of the driving problem.

[0006] In a feasible implementation, the preset configuration file template includes driving item information, vehicle information, problem categories, and problem label information. The preset dotting processing on vehicle driving data of different data types based on the preset configuration file template to determine target vehicle configuration data with dotting labels includes: acquire target problem label information in the vehicle driving data of different data types based on the preset profile template, wherein the driving problem information is used to represent label information of a driving problem of the vehicle in the target driving scene; perform preset dotting processing on the vehicle driving data of different data types based on the target problem label information, and determine the target vehicle configuration data with dotting labels.

[0007] In an implementable embodiment, the performing preset dotting processing on the vehicle driving data of different data types based on the target problem label information, and determining the target vehicle configuration data with dotting labels, comprises: extracting data in the vehicle driving data of different data types within a preset time period based on a target problem dotting time in the target problem label information, and generating the target vehicle configuration data with dotting labels.

[0008] In an implementable embodiment, the inputting the target vehicle configuration data into the trained multi-modal feature model for annotation training, and determining target annotation data corresponding to the target vehicle configuration data, comprises: determining a target problem category corresponding to the target vehicle configuration data based on the problem category in the preset profile template; determining a target annotation task and an execution progress of the target annotation task corresponding to the target vehicle configuration data based on a preset problem category and annotation task mapping table; performing annotation quality verification on the target annotation task with the completed progress, and inputting the target vehicle configuration data into the trained multi-modal feature model for annotation training after the verification is completed, to determine target annotation data corresponding to the target vehicle configuration data.

[0009] In an implementable embodiment, the annotation quality verification on the target annotation task with the completed progress is performed in the following manner: verifying the target annotation task with the completed progress based on a preset cross-validation algorithm, and eliminating target vehicle configuration data that does not meet the quality verification requirements.

[0010] In an implementable embodiment, the performing problem analysis on the target annotation data based on an external vehicle driving feature analysis algorithm, and determining a driving problem of a vehicle in a driving process and a cause of the driving problem, comprises: determining annotation data with the same characteristic attributes based on an external vehicle driving feature analysis algorithm; The problem is traced back to the labeled data with the same characteristic attribute, and the driving problem of the vehicle in the driving process and the cause of the driving problem are determined.

[0011] In an available implementation, after the problem analysis of the target labeled data based on the external vehicle driving feature analysis algorithm, the determination of the driving problem of the vehicle in the driving process and the cause of the driving problem are determined, the method further comprises: determining vehicle driving scene data in the labeled data; constructing a vehicle driving scene library based on the vehicle driving scene data.

[0012] In a second aspect of the embodiments of the application, the embodiments of the application provide a vehicle driving problem determination device, which comprises: A first determination module is configured to perform preset dotting processing on vehicle driving data of different data types based on a preset configuration file template to determine target vehicle configuration data with dotting labels, wherein the preset dotting processing is used to represent a dotting annotation processing process of the vehicle driving data in a target driving scene. A second determination module is configured to input the target vehicle configuration data into a trained multi-modal feature model for labeled training to determine target labeled data corresponding to the target vehicle configuration data. A third determination module is configured to perform problem analysis on the target labeled data based on an external vehicle driving feature analysis algorithm to determine the driving problem of the vehicle in the driving process and the cause of the driving problem.

[0013] In a third aspect of the embodiments of the application, the embodiments of the application provide an electronic device, which comprises a processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, and the machine readable instructions are executed by the processor to perform the steps of the vehicle driving problem determination method as described above.

[0014] In a fourth aspect of the embodiments of the application, the embodiments of the application provide a computer readable storage medium, which stores a computer program, and the computer program is executed by the processor to perform the steps of the vehicle driving problem determination method as described above.

[0015] Compared with the prior art, the embodiments provided in the application perform preset dotting processing on vehicle driving data of different data types based on a preset configuration file template, determine target vehicle configuration data with dotting labels, input the target vehicle configuration data into a trained multi-modal feature model for labeling training, determine target labeling data corresponding to the target vehicle configuration data, then perform problem analysis on the labeling data based on an external vehicle driving feature analysis algorithm, determine driving problems of the vehicle in the driving process and causes of the driving problems, the application can locate and analyze problems in the intelligent driving system, and reduces the problem of poor coordination of vehicle driving data. BRIEF DESCRIPTION OF DRAWINGS

[0016] Figure 1 A flow block diagram of a driving data processing method provided by an embodiment of the application is shown; Figure 2 A structural block diagram of a driving data processing apparatus provided by an embodiment of the application is shown; Figure 3 A structural schematic diagram of an electronic device provided by an embodiment of the application is shown.

[0017] Figure 2 And Figure 3 The correspondence between the reference signs and the drawing names in the drawings is as follows: 200, driving data processing apparatus; 210, first determining module; 220, second determining module; 230, third determining module; 300, electronic device; 310, processor; 320, memory; 330, bus. DETAILED DESCRIPTION

[0018] In order to better understand the technical solutions provided by the embodiments of the present specification, the technical solutions of the embodiments of the present specification will be described in detail below through the drawings and specific embodiments. It should be understood that the specific features in the embodiments of the present specification and the embodiments are detailed descriptions of the technical solutions of the embodiments of the present specification, and not limitations of the technical solutions of the present specification. In the case of no conflict, the technical features in the embodiments of the present specification and the embodiments can be combined with each other.

[0019] In this document, relational terms such as first and second and the like can be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. An element proceeded by "comprises... a" does not, without more constraints, exclude the existence of additional identical elements in the process, method, article, or apparatus that comprises the element. The terms "two or more" and "two or more than two" include both the recited number of entities and also greater than the recited number of entities.

[0020] Firstly, the application scenarios applicable to the present application are introduced. The embodiments provided by the present application are applicable to the field of vehicle intelligent driving technology.

[0021] At present, the management of traditional vehicle driving data cannot realize the backtracking and positioning of problems in the intelligent driving system, and the collaboration is poor.

[0022] Based on this, the present application provides a vehicle driving problem determination method. The embodiments provided by the present application solve the technical problems in the prior art that the problems in the intelligent driving system cannot be backtracked and positioned, and the collaboration is poor. The present application can position and analyze the problems in the intelligent driving system, and reduce the problem of poor collaboration of vehicle driving data.

[0023] Figure 1 A flowchart of a driving data processing method provided by an embodiment of the present application is shown. As shown in Figure 1 The driving data processing method includes the following steps: S101, based on a preset configuration file template, performing preset dotting processing on vehicle driving data of different data types to determine target vehicle configuration data with dotting labels, wherein the preset dotting processing is used to represent the processing process of annotating the vehicle driving data in the target driving scene.

[0024] In this step, before obtaining vehicle driving data of different data types, the embodiments provided by the present application first need to obtain vehicle original driving data of different data types, and then perform data format verification on the vehicle original driving data to determine vehicle driving data of different data types, so as to ensure the accuracy and safety of the original driving data. Moreover, the embodiments provided by the present application can specifically select to upload the above vehicle driving data to one or more data management platforms for management according to different application scenarios and business scenarios.

[0025] As in the joint development business scenario, the vehicle driving data of different data types described above can be selected to be uploaded to the data management platform of the local company and the data management platform of the partner, and the vehicle driving data of different data types described above is supported to be synchronously analyzed and processed.

[0026] It can be understood that in the embodiments provided in the present application, the data can be obtained through different types of data acquisition equipment or other ways of file or manual input, such as preset calibration parameters and scene logs.

[0027] It should be noted that before collecting the vehicle driving data of different data types, the embodiments provided in the present application will first preset a preset configuration file template, and then in the process of collecting the vehicle driving data of different data types, the vehicle driving data of different data types is preset to be processed based on the preset configuration file template, and a target vehicle configuration data with a dotting label is generated, wherein the target vehicle configuration data includes target driving item information, target vehicle information, target problem category, target problem label information and software version and the like.

[0028] Here, the embodiments provided in the present application can index the vehicle original driving data according to time, data type, acquisition equipment and the like, and store it in a classified manner, so as to realize long-term storage and quick retrieval of data.

[0029] The embodiments provided in the present application can identify missing values and abnormal values of the vehicle original driving data, and after the identification is completed, the identified abnormal values are marked or removed, and the missing values are processed by interpolation or removal, and the like, so as to convert the original data into "clean data" which can be further processed.

[0030] For example, the driving item information, vehicle information, problem category and problem label information included in the preset configuration file template are used to preset the dotting processing of the vehicle driving data of different data types based on the preset configuration file template, and the target vehicle configuration data with the dotting label is determined, including: Based on the preset configuration file template, the target problem label information in the vehicle driving data of different data types is obtained, wherein the driving problem information is used to represent the label information of the vehicle driving problem in the target driving scene; based on the target problem label information, the vehicle driving data of different data types is preset to be processed, and the target vehicle configuration data with the dotting label is determined.

[0031] Among them, the present application is: based on the target problem dotting time in the target problem label information, the data in the vehicle driving data of different data types within the preset time period is extracted, and the target vehicle configuration data with the dotting label is generated.

[0032] In the above, the preset time period in the embodiments provided by the present application can be customized, selected and used according to different application scenarios and use conditions. The preset time period in the embodiments provided by the present application can be specifically set as: the driving data 15 seconds before the preset dotting processing of the vehicle driving data of different data types to the driving data 15 seconds after the dotting processing.

[0033] Here, determining the target vehicle configuration data with the dotting label can realize fast uploading of data, save cloud storage space, and save storage resources of an external data management system.

[0034] It should be noted that in the embodiments provided by the present application, the uploading of full-amount vehicle configuration data can also be based on a preset configuration file template. Whether to upload full-amount vehicle configuration data or upload target vehicle configuration data with a dotting label is determined based on different business scenario types. For example, in a vehicle driving business scenario where there is a vehicle driving problem, only the target vehicle configuration data with a dotting label including key information such as a target problem category, target problem label information and a software version is uploaded to the cloud or an external data management system / platform. In a vehicle driving business scenario where there is no vehicle driving problem, full-amount vehicle configuration data containing a dotting label can be uploaded to the cloud or an external data management platform. At the same time, the full-amount vehicle configuration data containing a dotting label can be viewed on the corresponding external data management platform or cloud.

[0035] Among them, the dotting annotation is used to represent that in the process of collecting target vehicle configuration data, if a driving problem scene, a special scene and a scene that needs special attention are encountered, the time period of the scene will be labeled, which is convenient for later extraction.

[0036] S102, input the target vehicle configuration data into the trained multi-modal feature model for annotation training to determine the target annotation data corresponding to the target vehicle configuration data.

[0037] In this step, the embodiments provided by the present application further include the following before inputting the target vehicle configuration data into the trained multi-modal feature model for annotation training. Extract the key fields and information in the target vehicle configuration data with the dotting label; perform integrity check and abnormal value identification; perform format conversion and coordinate system processing to generate clean target vehicle configuration data with the dotting label.

[0038] Among them, the target annotation data provided by the embodiments of the present application can be specifically camera pictures or radar point cloud dynamic data, which is used to assist artificial rapid judgment of data and scene characteristics to provide intuitive reference for subsequent processing.

[0039] The embodiments provided in the application can also establish a target labeling data set based on the target labeling data to form a structured and reusable data set resource.

[0040] It can be understood that the embodiments provided in the application input the target vehicle configuration data into the trained multi-modal feature model for labeling training to determine the target labeling data corresponding to the target vehicle configuration data, including: determining the target problem category corresponding to the target vehicle configuration data based on the problem category in the preset configuration file template; determining the target labeling task and the execution progress of the target labeling task corresponding to the target vehicle configuration data based on the preset problem category and labeling task mapping table; performing labeling quality verification on the target labeling task with completed progress, and inputting the target vehicle configuration data into the trained multi-modal feature model for labeling training after the verification is completed to determine the target labeling data corresponding to the target vehicle configuration data.

[0041] It should be noted that the preset problem category and labeling task mapping table in the embodiments provided in the application can be selected and used according to different application scenarios and use conditions, and the preset problem category and labeling task mapping table in the embodiments provided in the application is specifically used to assign the problem category to the corresponding responsible person for disposal.

[0042] For example, the labeling quality verification on the target labeling task with completed progress is performed in the following way: The target labeling task with completed progress is verified based on a preset cross-validation algorithm, and the target vehicle configuration data that does not meet the quality verification requirement is removed.

[0043] It should be noted that in addition to using the preset cross-validation algorithm, the embodiments provided in the application can also use artificial automatic verification, remove the target vehicle configuration data that does not meet the quality verification requirement, confirm the generation of the target labeling data corresponding to the target vehicle configuration data, and perform system backhaul on the generated target labeling data.

[0044] S103, based on an external vehicle driving feature analysis algorithm, performing problem analysis on the target labeling data to determine the driving problem of the vehicle in the driving process and the cause of the driving problem.

[0045] In this step, after determining the target labeling data, the embodiments provided in the application input the target labeling data into the external vehicle driving feature analysis algorithm for problem analysis to trace the source of the driving problem in the driving process of the vehicle, and then determine the cause of the driving problem, such as perception error and decision abnormality, and locate the source of the problem data, such as sensor failure, labeling error, and algorithm defect.

[0046] The external vehicle driving feature analysis algorithm is used to represent a feature analysis algorithm for analyzing the target annotation data and confirming vehicle driving problems, such as a large language model commonly used in the market or a neural network model that can be deep learning.

[0047] For example, based on the external vehicle driving feature analysis algorithm, the problem analysis of the target annotation data is performed to determine the driving problem of the vehicle during driving and the cause of the driving problem, including: Based on the external vehicle driving feature analysis algorithm, the annotation data with the same feature attribute is determined; the problem is traced for the annotation data with the same feature attribute to determine the driving problem of the vehicle during driving and the cause of the driving problem.

[0048] It can be understood that the annotation data with the same feature attribute in the embodiments provided in the present application can be customized and used according to different business scenarios.

[0049] For example, the embodiments provided in the present application can also determine vehicle driving scene data in the annotation data; and construct a vehicle driving scene library based on the vehicle driving scene data.

[0050] It can be understood that in the embodiments provided in the present application, the scene triggering condition and the occurrence frequency can also be analyzed according to the vehicle driving scene data in different annotation data, the vehicle driving scene library is constructed, and the extracted scene features are stored in the scene library for test case design and algorithm optimization.

[0051] It should be noted that the vehicle driving scene library in the embodiments provided in the present application can include dangerous scenes, extreme scenes, and new scenes.

[0052] After the vehicle driving data collection is completed, the embodiments provided in the present application transmit the collected vehicle driving data to the data management platform. During the transmission, the vehicle driving data is sliced by a preset configuration file template, the information in the configuration file is formed into a label, the target vehicle configuration data with the dotting label is generated, the data classification is stored and retrieved, and then the target vehicle configuration data is input into the trained multi-modal feature model for annotation training to determine the target annotation data corresponding to the target vehicle configuration data. The problem analysis of the above target annotation data is performed by the data annotation system and the problem management system, the target annotation data with the same feature is extracted, and the data set management is performed by returning to the data management platform.

[0053] Compared with the prior art, the method for processing driving data provided in the embodiments of the present application performs preset dotting processing on vehicle driving data of different data types based on a preset configuration file template, determines target vehicle configuration data with dotting labels, inputs the target vehicle configuration data into a trained multi-modal feature model for labeling training, determines target labeling data corresponding to the target vehicle configuration data, and then performs problem analysis on the labeling data based on an external vehicle driving feature analysis algorithm to determine driving problems of the vehicle in the driving process and reasons for the driving problems. The present application can locate and analyze problems in the intelligent driving system, and reduces the problem of poor coordination of vehicle driving data.

[0054] The embodiments provided in the present application can cover the whole application from uploading, data quality and flow efficiency, solve the problems of scattered and poor coordination of intelligent driving data, make data flow in order, and the present application can determine driving problems of the vehicle in the driving process and reasons for the driving problems, and deduce the optimization system, continuously improve the adaptability and reliability of the intelligent driving system to complex scenes, accelerate technology iteration, and the flexible data uploading mode of the present application supports multi-platform uploading and customized uploading, adapts to various working scenarios, and ensures the efficiency of data uploading.

[0055] Figure 2 The structure block diagram of a vehicle driving problem determination device provided in the embodiments of the present application is shown in Figure 2 The driving data processing device 200 includes: A first determination module 210 is configured to perform preset dotting processing on vehicle driving data of different data types based on a preset configuration file template to determine target vehicle configuration data with dotting labels, wherein the preset dotting processing is used to represent a dotting annotation processing process of vehicle driving data in a target driving scene.

[0056] A second determination module 220 is configured to input the target vehicle configuration data into a trained multi-modal feature model for labeling training to determine target labeling data corresponding to the target vehicle configuration data.

[0057] A third determination module 230 is configured to perform problem analysis on the target labeling data based on an external vehicle driving feature analysis algorithm to determine driving problems of the vehicle in the driving process and reasons for the driving problems.

[0058] For example, the driving project information, vehicle information, problem category and problem label information included in the preset configuration file template, the first determination module 210 is specifically configured to: Based on the preset configuration file template, target problem label information in vehicle driving data of different data types is obtained, wherein the driving problem information is used to represent label information of a vehicle appearing a driving problem in a target driving scene.

[0059] Based on the target problem label information, preset dotting processing is performed on the vehicle driving data of different data types to determine target vehicle configuration data with dotting labels.

[0060] For example, based on the target problem label information, preset dotting processing is performed on the vehicle driving data of different data types to determine target vehicle configuration data with dotting labels, including: Based on the target problem dotting time in the target problem label information, data in the vehicle driving data of different data types within a preset time period is extracted to generate target vehicle configuration data with dotting labels.

[0061] For example, the second determination module 220 is specifically configured to: Based on the problem category in the preset configuration file template, a target problem category corresponding to the target vehicle configuration data is determined; based on a preset problem category and label task mapping table, a target label task corresponding to the target vehicle configuration data and an execution progress of the target label task are determined; annotation quality verification is performed on the target label task with the completed progress, and after the verification is completed, the target vehicle configuration data is input into a trained multi-modal feature model for annotation training to determine target annotation data corresponding to the target vehicle configuration data.

[0062] For example, the annotation quality verification is performed on the target label task with the completed progress in the following manner: based on a preset cross-validation algorithm, the target label task with the completed progress is verified, and target vehicle configuration data that does not meet the quality verification requirements is removed.

[0063] For example, the third determination module 230 is specifically configured to: Based on an external vehicle driving feature analysis algorithm, label data with the same feature attribute is determined.

[0064] For the label data with the same feature attribute, problem tracing is performed to determine a driving problem of a vehicle in a driving process and a reason for the driving problem.

[0065] For example, vehicle driving scene data in the label data is determined.

[0066] Based on the vehicle driving scene data, a vehicle driving scene library is constructed.

[0067] Compared with the prior art, the driving data processing device 200 provided in the embodiments of the present application performs preset dotting processing on vehicle driving data of different data types based on a preset configuration file template, determines target vehicle configuration data with dotting labels, inputs the target vehicle configuration data into a trained multi-modal feature model for labeling training, determines target labeling data corresponding to the target vehicle configuration data, and then performs problem analysis on the labeling data based on an external vehicle driving feature analysis algorithm to determine driving problems of the vehicle in the driving process and reasons for the driving problems. The present application can locate and analyze problems in the intelligent driving system, and reduces the poor coordination of vehicle driving data.

[0068] The embodiments provided in the present application can cover the whole application from uploading, improve data quality and flow efficiency, solve the problems of scattered and poor coordination of intelligent driving data, make data flow in order, determine driving problems of the vehicle in the driving process and reasons for the driving problems, and deduce the optimization system to continuously improve the adaptability and reliability of the intelligent driving system to complex scenes, accelerate technology iteration, and the flexible data uploading mode of the present application supports multi-platform uploading and customized uploading, adapts to various working scenarios, and ensures the efficiency of data uploading.

[0069] Please refer to Figure 3 , Figure 3 The structure of the electronic device provided in the embodiments of the present application is shown in the structure schematic diagram of the electronic device. Figure 3 The electronic device 300 includes a processor 310, a memory 320 and a bus 330.

[0070] The memory 320 stores machine readable instructions executable by the processor 310. When the electronic device 300 is running, the processor 310 and the memory 320 communicate through the bus 330. When the machine readable instructions are executed by the processor 310, the steps of the vehicle driving problem determination method in the method embodiments shown in the above Figure 1 The specific implementation can be referred to the method embodiments, which will not be repeated here.

[0071] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program. When the computer program is run by a processor, the steps of the vehicle driving problem determination method in the method embodiments shown in the above Figures 1 to 2 The specific implementation can be referred to the method embodiments, which will not be repeated here.

[0072] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described system, device and unit can refer to the corresponding process in the foregoing method embodiments, which will not be repeated here.

[0073] It should be noted that the description of the various embodiments has been presented for purposes of clarity and that it is not necessary to describe each and every embodiment separately or enumerate all its possible variations. It will be apparent to those skilled in the art that additional embodiments can be practiced which depart from the specific details of the described embodiments.

[0074] Those skilled in the art will appreciate that embodiments of the application can be devised for a method, a system, or a computer program product. Accordingly, the present application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-readable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage media, etc.) embodying computer readable program code.

[0075] The present application is described with reference to the flowcharts and / or block diagrams of the methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowcharts and / or block diagrams, and combinations of blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowcharts and / or block diagrams block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0076] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks. Figure 1 one or more functions specified in the flowchart and / or block diagram block or blocks.

[0078] The embodiment of the present application further provides a computer program product, which comprises computer software instructions, and when the computer software instructions run on a processing device, the processing device executes the flow of the determination method of the vehicle driving problem.

[0079] The computer program product comprises one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the flow or function according to the embodiment of the present application is generated wholly or partially. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable devices. The computer instructions can be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center through a wired (for example, coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (for example, infrared, wireless, microwave, etc.) manner. The computer readable storage medium can be any available medium that can be stored by the computer or a data storage device such as a server, data center, etc. containing one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a magnetic tape), an optical medium (for example, a DVD), or a semiconductor medium (for example, a solid state disk (SSD)) and the like.

[0080] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0081] In several embodiments provided in the present application, it should be understood that the disclosed devices, apparatuses and methods can be implemented in other ways. For example, the apparatus embodiments described above are only schematic. The division of the units is only a logical function division. In actual implementation, another division mode can be used, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0082] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0083] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0084] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0085] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the present application.

[0086] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to the embodiments once they know the basic inventive concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0087] Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application also intends to include these modifications and variations.

Claims

1. A method of determining a vehicle driving problem, characterized by, The vehicle driving problem determination method comprises the following steps: Based on the preset configuration file template, the vehicle driving data of different data types is subjected to preset dotting processing to determine target vehicle configuration data with dotting labels, wherein the preset dotting processing is used to represent the dotting annotation processing process of the vehicle driving data in the target driving scene; The target vehicle configuration data is input into the trained multi-modal feature model for annotation training to determine target annotation data corresponding to the target vehicle configuration data; Based on an external vehicle driving feature analysis algorithm, the target annotation data is analyzed to determine the driving problems of the vehicle during driving and the causes of the driving problems.

2. The method of determining a vehicle driving problem according to claim 1, wherein The driving project information, vehicle information, problem category and problem label information included in the preset configuration file template, the vehicle driving data of different data types is subjected to preset dotting processing based on the preset configuration file template to determine target vehicle configuration data with dotting labels, comprising: Based on the preset configuration file template, target problem label information in the vehicle driving data of different data types is obtained, wherein the driving problem information is used to represent the label information of the driving problem of the vehicle in the target driving scene; Based on the target problem label information, the vehicle driving data of different data types is subjected to preset dotting processing to determine the target vehicle configuration data with dotting labels.

3. The method of claim 2, wherein Based on the target problem label information, the vehicle driving data of different data types is subjected to preset dotting processing to determine the target vehicle configuration data with dotting labels, comprising: Based on the target problem dotting time in the target problem label information, data in the vehicle driving data of different data types within a preset time period is extracted to generate the target vehicle configuration data with dotting labels.

4. The method of claim 2, wherein The target vehicle configuration data is input into the trained multi-modal feature model for annotation training to determine target annotation data corresponding to the target vehicle configuration data, comprising: Based on the problem category in the preset configuration file template, the target problem category corresponding to the target vehicle configuration data is determined; Based on a preset problem category and annotation task mapping table, the target annotation task corresponding to the target vehicle configuration data and the execution progress of the target annotation task are determined; The target annotation task with completed progress is subjected to annotation quality verification, and after the verification is completed, the target vehicle configuration data is input into the trained multi-modal feature model for annotation training to determine the target annotation data corresponding to the target vehicle configuration data.

5. The method of claim 4, wherein The target annotation task with completed progress is subjected to annotation quality verification in the following way: Based on a preset cross-validation algorithm, the target annotation task with completed progress is verified, and target vehicle configuration data that does not meet the quality verification requirements is removed.

6. The method of determining a vehicle driving problem according to claim 1, wherein Based on an external vehicle driving feature analysis algorithm, the target annotation data is analyzed to determine the driving problems of the vehicle during driving and the causes of the driving problems, comprising: Based on the external vehicle driving feature analysis algorithm, determine the labeled data with the same characteristic attributes; For the labeled data with the same characteristic attributes, trace the problem, determine the driving problem of the vehicle in the driving process and the cause of the driving problem.

7. The method of claim 6, wherein After the problem analysis of the target labeled data based on the external vehicle driving feature analysis algorithm, the method further comprises: Determine the vehicle driving scene data in the labeled data; Based on the vehicle driving scene data, build a vehicle driving scene library.

8. A vehicle driving problem determination apparatus characterized by comprising: The vehicle driving problem determination device comprises: A first determination module is configured to perform preset dotting processing on vehicle driving data of different data types based on a preset configuration file template to determine target vehicle configuration data with dotting labels, wherein the preset dotting processing is used to represent the dotting annotation process of the vehicle driving data in the target driving scene. A second determination module is configured to input the target vehicle configuration data into a trained multi-modal feature model for labeling training to determine target labeled data corresponding to the target vehicle configuration data. A third determination module is configured to perform problem analysis on the target labeled data based on an external vehicle driving feature analysis algorithm to determine the driving problem of the vehicle in the driving process and the cause of the driving problem.

9. An electronic device, comprising: It comprises: A processor, a memory and a bus, the memory stores machine readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, the machine readable instructions are executed by the processor to execute the steps of the vehicle driving problem determination method in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores a computer program, the computer program is executed by the processor to execute the steps of the vehicle driving problem determination method in any one of claims 1-7.

Images