Vehicle driving evaluation method and device, electronic equipment and storage medium

Abstract

The invention provides a vehicle driving evaluation method and device, electronic equipment and a storage medium, and the method comprises the steps: carrying out the data collection of a target vehicle in a first to-be-detected scene, and obtaining the multi-dimensional data affecting the driving of the target vehicle; analyzing the multi-dimensional data of the target vehicle to determine objective situation features and subjective situation features influencing the driving of the target vehicle; and based on fusion of the objective situation features and the subjective situation features, evaluating the driving state of the target vehicle in the first to-be-tested scene. According to the method and the device, the multi-dimensional data in the driving process is acquired, and evaluation deviation possibly caused by a single data source is avoided, so that the accuracy of safety evaluation is improved.

Description

Technical Field

[0001] The present application relates to the technical field of safety assessment, and in particular to a method, device, electronic device and storage medium for vehicle driving assessment. Background Art

[0002] With the development of various industries, cars have become one of the indispensable means of transportation. With the increasing number of cars, traffic accidents have occurred frequently. In order to ensure safe driving, it is necessary to evaluate the driving process of the vehicle.

[0003] The existing assessment methods for vehicles often rely on a single data source, such as only considering vehicle speed, driving trajectory, etc. However, there are often many factors that threaten vehicle driving, so the existing assessment methods fail to fully consider other factors. This results in large limitations in the assessment results and the problem of insufficient accuracy of the assessment results. Summary of the invention

[0004] In view of this, the purpose of the present application is to provide a method, device, electronic device and storage medium for vehicle driving evaluation to overcome the problems in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a method for evaluating vehicle driving, the method comprising:

[0006] For a target vehicle in a first test scenario, data collection is performed on the target vehicle to obtain multi-dimensional data that affects the driving of the target vehicle;

[0007] By analyzing the multi-dimensional data of the target vehicle, the objective situation characteristics and subjective situation characteristics that affect the driving of the target vehicle are determined;

[0008] Based on the fusion of the objective situation feature and the subjective situation feature, the driving state of the target vehicle in the first test scene is evaluated.

[0009] In some technical solutions of the present application, the multi-dimensional data includes: own driving data and external driving data; the objective situation characteristics and subjective situation characteristics affecting the driving of the target vehicle are determined by analyzing the multi-dimensional data of the target vehicle, including:

[0010] Analyzing the self-driving data to determine subjective situation characteristics that affect the driving of the target vehicle;

[0011] The external driving data is analyzed to determine objective situation characteristics that affect the driving of the target vehicle.

[0012] In some technical solutions of the present application, the above method fuses the objective situation feature and the subjective situation feature in the following manner:

[0013] According to the distribution information of the objective situation feature, the objective situation feature is converted into a first matrix;

[0014] According to the distribution information of the subjective situation feature, the subjective situation feature is converted into a second matrix;

[0015] The first matrix and the second matrix are superimposed to generate a pseudo image.

[0016] In some technical solutions of the present application, for the target vehicle in the first test scenario, data collection is performed on the target vehicle to obtain multi-dimensional data affecting the driving of the target vehicle, including:

[0017] For a target vehicle in a first test scene, data collection is performed on the target vehicle at multiple times to obtain multiple groups of multi-dimensional data; wherein each group of the multi-dimensional data corresponds to a pseudo image;

[0018] The evaluating the driving state of the target vehicle in the first test scene based on the fusion of the objective situation feature and the subjective situation feature includes:

[0019] Based on the pseudo-image sequence of the target vehicle in the first scene to be tested, the driving state of the target vehicle in the first scene to be tested is evaluated.

[0020] In some technical solutions of the present application, the evaluation of the driving state of the target vehicle in the first scene to be tested based on the pseudo-image sequence of the target vehicle in the first scene to be tested is implemented by a preset safety evaluation model, including:

[0021] By analyzing each of the fake images, the risk characteristics of the fake images at the corresponding moment are determined;

[0022] Based on the relationship between the risk features at different moments, the driving state of the target vehicle in the first test scenario is obtained.

[0023] In some technical solutions of the present application, the above method further includes:

[0024] According to the evaluation result of the first scenario to be tested, the security evaluation model is updated to obtain an updated security evaluation model;

[0025] The safety assessment model is used to assess the driving state of the target vehicle in a second test scenario.

[0026] In some technical solutions of the present application, the above analysis of the self-driving data to determine the subjective situation characteristics that affect the driving of the target vehicle includes:

[0027] Using the subjective cognitive field strength distribution information in the own driving data as the subjective situation feature;

[0028] The analyzing the external driving data to determine objective situation characteristics that affect the driving of the target vehicle includes:

[0029] The objective risk field intensity distribution information in the external driving data is used as the objective situation feature.

[0030] In a second aspect, an embodiment of the present application provides a device for evaluating vehicle driving, the device comprising:

[0031] A collection module, for collecting data of a target vehicle in a first test scene, to obtain multi-dimensional data that affects the driving of the target vehicle;

[0032] An analysis module, used to determine objective situation characteristics and subjective situation characteristics that affect the driving of the target vehicle by analyzing the multi-dimensional data of the target vehicle;

[0033] A fusion module is used to evaluate the driving state of the target vehicle in the first test scene based on the fusion of the objective situation feature and the subjective situation feature.

[0034] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned vehicle driving evaluation method when executing the computer program.

[0035] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned vehicle driving evaluation method are executed.

[0036] The technical solution provided by the embodiments of the present application may have the following beneficial effects:

[0037] The method of the present application includes collecting data on a target vehicle in a first test scenario to obtain multi-dimensional data that affects the driving of the target vehicle; determining objective situation characteristics and subjective situation characteristics that affect the driving of the target vehicle by analyzing the multi-dimensional data of the target vehicle; and evaluating the driving state of the target vehicle in the first test scenario based on the fusion of the objective situation characteristics and the subjective situation characteristics.

[0038] This application obtains multi-dimensional data during the driving process, avoiding the evaluation bias that may be caused by a single data source, thereby improving the accuracy of safety assessment.

[0039] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0041] Figure 1 A schematic diagram showing a flow chart of a vehicle driving evaluation method provided in an embodiment of the present application;

[0042] Figure 2 A schematic diagram of a security assessment model update process provided by an embodiment of the present application is shown;

[0043] Figure 3 A schematic diagram of a vehicle driving evaluation device provided in an embodiment of the present application is shown;

[0044] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art can add one or more other operations to the flowchart under the guidance of the content of the present application, or remove one or more operations from the flowchart.

[0046] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0047] It should be noted that the term "comprising" will be used in the embodiments of the present application to indicate the existence of the features declared thereafter, but does not exclude the addition of other features.

[0048] With the development of various industries, cars have become one of the indispensable means of transportation. With the increasing number of cars, traffic accidents have occurred frequently. In order to ensure safe driving, it is necessary to evaluate the driving process of the vehicle.

[0049] The existing assessment methods for vehicles often rely on a single data source, such as only considering vehicle speed, driving trajectory, etc. However, there are often many factors that threaten vehicle driving, so the existing assessment methods fail to fully consider other factors. This results in large limitations in the assessment results and the problem of insufficient accuracy of the assessment results.

[0050] Based on this, the embodiments of the present application provide a method, device, electronic device and storage medium for vehicle driving evaluation, which are described below through embodiments.

[0051] Figure 1 A schematic flow chart of a vehicle driving evaluation method provided in an embodiment of the present application is shown, wherein the method includes steps S101-S103; specifically:

[0052] S101, collecting data on a target vehicle in a first test scenario to obtain multi-dimensional data that affects the driving of the target vehicle;

[0053] S102, determining objective situation characteristics and subjective situation characteristics that affect the driving of the target vehicle by analyzing the multi-dimensional data of the target vehicle;

[0054] S103: Based on the fusion of the objective situation feature and the subjective situation feature, the driving state of the target vehicle in the first test scenario is evaluated.

[0055] This application obtains multi-dimensional data during the driving process, avoiding the evaluation bias that may be caused by a single data source, thereby improving the accuracy of safety assessment.

[0056] Some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0057] The present application provides a method for evaluating vehicle driving, in which the present application divides the driving process into a plurality of different test scenes (which can be set as the first test scene, the second test scene, the third test scene, etc. as needed). The scene here represents a driving process including a preset duration. For example, the first test scene is a three-second driving process. The present application refers to the vehicle that needs to be evaluated in the first test scene as a target vehicle.

[0058] In order to be able to more accurately evaluate the target vehicle under the first test scenario, the embodiment of the present application collects data on the target vehicle and obtains multi-dimensional data that affects the normal driving of the target vehicle. The multi-dimensional data here includes self-driving data and external driving data. The self-driving data represents the data that the vehicle itself affects normal driving, such as the target vehicle's own characteristics, the driver's driving behavior, etc. The external driving data represents the data that the target vehicle externally affects the normal driving of the target vehicle, such as the road environment, the driving route of other vehicles, etc. The specific collection can use the corresponding sensor. For example, the vehicle's own state (such as speed, acceleration, yaw angular velocity, etc.), the driver's driving behavior (such as accelerator pedal opening, brake master cylinder pressure, steering wheel angle, etc.), the state of traffic participants (relative speed, relative distance, etc.), and the road environment (such as lane lines, etc.) are collected through sensors on the vehicle (such as GPS, on-board cameras, radars, accelerometers, etc.).

[0059] After obtaining the multi-dimensional data, it is necessary to analyze the multi-dimensional data. Since the multi-dimensional data in the embodiment of the present application includes self-driving data and external driving data, it is necessary to analyze the multi-dimensional data separately. Analyze the self-driving data to obtain the subjective situation characteristics that affect the driving of the target vehicle; analyze the external driving data to obtain the objective situation characteristics that affect the driving of the target vehicle. Specifically, input the self-driving data into the driving cognition calculation module to obtain the distribution information of the subjective cognitive field strength in the future time and space, and use the distribution information of these subjective cognitive field strengths as the subjective situation characteristics. Input the external driving data into the objective situation field calculation module to obtain the distribution information of the objective risk field strength in the future time and space, and use the distribution information of these objective situation field strengths as the objective situation characteristics.

[0060] After obtaining the objective situation features and the subjective situation features, the objective situation features and the subjective situation features are fused, and based on the fused objective situation features and the subjective situation features, the driving state of the target vehicle in the first test environment is evaluated.

[0061] When fusing the objective situation features and the subjective situation features, the embodiment of the present application first converts the objective situation features and the subjective situation features into a matrix format: according to the distribution information of the objective situation features, the objective situation features are converted into a first matrix; according to the distribution information of the subjective situation features, the subjective situation features are converted into a second matrix; then, the first matrix and the second matrix are superimposed for fusion.

[0062] For example, the first matrix and the second matrix are both in a w*h*1 matrix format. After superimposing them in dimension, a pseudo-image with a structure of w*h*2 can be obtained, where the width of the image is w, which represents the length of the longitudinal prediction area, the height is h, which represents the length of the horizontal prediction area, and the dimension is 2, which represents the objective space-time situation and the subjective space-time situation. The value of each point in the image is the field strength describing the objective risk and subjective cognitive risk of the point. The fusion result is a comprehensive description of the driving safety of the scene at that moment by superimposing the objective space-time situation and the subjective space-time situation cognition.

[0063] In an optional embodiment, when the embodiment of the present application evaluates the target vehicle in the first test scene, in order to ensure the accuracy of the evaluation result, the embodiment of the present application acquires data at multiple times when acquiring data, and obtains multiple groups of multi-dimensional data. According to the fusion process of the above embodiment, each group of multi-dimensional data corresponds to a pseudo-image. When performing the evaluation, the embodiment of the present application not only considers the risk of each pseudo-image, but also needs to consider the associated risks between different pseudo-images. In other words, when performing the evaluation, the embodiment of the present application does not use a single pseudo-image, but a pseudo-image sequence. Specifically: the pseudo-image sequence is input into the safety assessment model implementation, and the safety assessment model implementation determines the risk characteristics of the pseudo-image corresponding to the time by analyzing each of the pseudo-images; based on the relationship between the risk characteristics at different times, the driving state of the target vehicle in the first test scene is obtained.

[0064] In the specific implementation, the security assessment model adopts the CNN+Transformer network structure. The prediction process is divided into two parts. The first part requires feature extraction for each moment of the time series. The CNN network is used to extract features from each pseudo image. The CNN network has excellent local perception and powerful extraction capabilities for spatial features. Through the design of the convolution layer, it can capture the risk distribution characteristics in each pseudo image. Through the stacking of multiple convolution layers and pooling layers, the deep risk feature expression in each pseudo image can be fully extracted. Then, the Transformer network is used to analyze the risk characteristics at different moments to obtain the prediction results.

[0065] Since the first test scene is a time series, we need to not only process a single pseudo image, but also consider the relationship between pseudo images at different times. Therefore, the encoding and decoding layers in the Transformer of the second part are introduced to capture the global dependencies between feature sequences at different times.

[0066] The entire time series is input into the Transformer encoding layer, and the multi-head self-attention network is used to learn the relationship between risk features at different times. Through multiple self-attention networks of multiple encoding modules, the relationship between risk features at different times can be fully obtained. Finally, the MLP decoding layer is used to decode and obtain the safety prediction result of the entire scene. This completes the entire prediction process from driving scene to safety result.

[0067] The target vehicle in the first test scene is predicted to obtain a prediction result. The prediction result includes high risk and low risk. If the target vehicle is in a high risk state, an early warning is issued to send a warning signal to the driver.

[0068] In an optional implementation manner, in order to improve the prediction effect of the security assessment model, after evaluating the first test scenario and before evaluating the second test scenario, the method in the embodiment of the present application further includes: Figure 2 S201-S202 shown:

[0069] S201. According to the evaluation result of the first scenario to be tested, the security evaluation model is updated to obtain an updated security evaluation model;

[0070] S201: Use the safety assessment model to assess the driving state of the target vehicle in a second test scenario.

[0071] After obtaining the evaluation result of the first scene to be tested, the multi-dimensional data and the evaluation result of the first scene to be tested are stored in the cloud or local server, and then the evaluation result of the first scene to be tested is verified to determine whether it meets the preset accuracy. When the accuracy of the evaluation result of the first scene to be tested is high (greater than or equal to the preset accuracy threshold), the effect of characterizing the security assessment model is better; when the accuracy of the evaluation result of the first scene to be tested is low (less than the preset accuracy threshold), the effect of characterizing the security assessment model is poor.

[0072] When the effect of the security assessment model is good, the security assessment model can be updated and adjusted based on the evaluation results of the first scenario to be tested to obtain a more accurate security assessment model. When the effect of the security assessment model is poor, the security assessment model can be updated and adjusted based on the evaluation results of the first scenario to be tested so that the accuracy of the security assessment model meets the requirements (greater than or equal to the preset accuracy threshold).

[0073] After updating and adjusting the safety assessment model, an adjusted safety assessment model is obtained, and the driving state of the target vehicle in the second test scene is evaluated using the safety assessment model. The evaluation process for the second test scene is the same as the evaluation process for the first test scene, the only difference being that the updated and adjusted safety assessment model is used. Evaluating the second test scene using the updated and adjusted safety assessment model can improve the accuracy of the evaluation. Similarly, after evaluating the second test scene, the updated and adjusted safety assessment model can be adjusted and updated again based on the evaluation results of the second test scene.

[0074] Figure 3 A schematic diagram of the structure of a vehicle driving evaluation device provided in an embodiment of the present application is shown, and the device includes:

[0075] A collection module, for collecting data of a target vehicle in a first test scene, to obtain multi-dimensional data that affects the driving of the target vehicle;

[0076] An analysis module, used to determine objective situation characteristics and subjective situation characteristics that affect the driving of the target vehicle by analyzing the multi-dimensional data of the target vehicle;

[0077] A fusion module is used to evaluate the driving state of the target vehicle in the first test scene based on the fusion of the objective situation feature and the subjective situation feature.

[0078] The multi-dimensional data includes: own driving data and external driving data; the objective situation characteristics and subjective situation characteristics affecting the driving of the target vehicle are determined by analyzing the multi-dimensional data of the target vehicle, including:

[0079] Analyzing the self-driving data to determine subjective situation characteristics that affect the driving of the target vehicle;

[0080] The external driving data is analyzed to determine objective situation characteristics that affect the driving of the target vehicle.

[0081] The objective situation feature and the subjective situation feature are integrated in the following manner:

[0082] According to the distribution information of the objective situation feature, the objective situation feature is converted into a first matrix;

[0083] According to the distribution information of the subjective situation feature, the subjective situation feature is converted into a second matrix;

[0084] The first matrix and the second matrix are superimposed to generate a pseudo image.

[0085] The step of collecting data on a target vehicle in a first test scenario to obtain multi-dimensional data that affects the driving of the target vehicle includes:

[0086] For a target vehicle in a first test scene, data collection is performed on the target vehicle at multiple times to obtain multiple groups of multi-dimensional data; wherein each group of the multi-dimensional data corresponds to a pseudo image;

[0087] The evaluating the driving state of the target vehicle in the first test scene based on the fusion of the objective situation feature and the subjective situation feature includes:

[0088] Based on the pseudo-image sequence of the target vehicle in the first scene to be tested, the driving state of the target vehicle in the first scene to be tested is evaluated.

[0089] The evaluating of the driving state of the target vehicle in the first scene to be tested based on the pseudo-image sequence of the target vehicle in the first scene to be tested is implemented by a preset safety evaluation model, including:

[0090] By analyzing each of the fake images, the risk characteristics of the fake images at the corresponding moment are determined;

[0091] Based on the relationship between the risk features at different moments, the driving state of the target vehicle in the first test scenario is obtained.

[0092] The device also includes:

[0093] An updating module, configured to update the security assessment model according to the assessment result of the first scenario to be tested, to obtain an updated security assessment model;

[0094] The safety assessment model is used to assess the driving state of the target vehicle in a second test scenario.

[0095] The analyzing the self-driving data to determine the subjective situation characteristics that affect the driving of the target vehicle includes:

[0096] Using the subjective cognitive field strength distribution information in the own driving data as the subjective situation feature;

[0097] The analyzing the external driving data to determine objective situation characteristics that affect the driving of the target vehicle includes:

[0098] The objective risk field intensity distribution information in the external driving data is used as the objective situation feature.

[0099] like Figure 4 As shown, an embodiment of the present application provides an electronic device for executing the vehicle driving evaluation method in the present application, the device includes a memory, a processor, a bus, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the vehicle driving evaluation method when executing the computer program.

[0100] Specifically, the above-mentioned memory and processor may be general-purpose memory and processor, which are not specifically limited here. When the processor runs the computer program stored in the memory, the above-mentioned vehicle driving evaluation method can be executed.

[0101] Corresponding to the vehicle driving evaluation method in the present application, an embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the above-mentioned vehicle driving evaluation method are executed.

[0102] Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk, etc. When the computer program on the storage medium is executed, the above-mentioned vehicle driving evaluation method can be executed.

[0103] In the embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. The system embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of systems or units, which can be electrical, mechanical or other forms.

[0104] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0105] In addition, each functional unit in the embodiments provided in the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0106] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0107] It should be noted that similar numbers and letters represent similar items in the following figures. Therefore, once an item is defined in one figure, it does not need to be further defined and explained in subsequent figures. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description and are not to be understood as indicating or implying relative importance.

[0108] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-mentioned embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-mentioned embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application. They should all be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method for evaluating vehicle driving, characterized in that: The method comprises: For a target vehicle in a first test scenario, data collection is performed on the target vehicle to obtain multi-dimensional data that affects the driving of the target vehicle; By analyzing the multi-dimensional data of the target vehicle, the objective situation characteristics and subjective situation characteristics that affect the driving of the target vehicle are determined; Based on the fusion of the objective situation feature and the subjective situation feature, the driving state of the target vehicle in the first test scene is evaluated.

2. The method according to claim 1, characterized in that The multi-dimensional data includes: own driving data and external driving data; the objective situation characteristics and subjective situation characteristics affecting the driving of the target vehicle are determined by analyzing the multi-dimensional data of the target vehicle, including: Analyzing the self-driving data to determine subjective situation characteristics that affect the driving of the target vehicle; The external driving data is analyzed to determine objective situation characteristics that affect the driving of the target vehicle.

3. The method according to claim 2, characterized in that The method fuses the objective situation feature and the subjective situation feature in the following manner: According to the distribution information of the objective situation feature, the objective situation feature is converted into a first matrix; According to the distribution information of the subjective situation feature, the subjective situation feature is converted into a second matrix; The first matrix and the second matrix are superimposed to generate a pseudo image.

4. The method according to claim 3, characterized in that The step of collecting data on a target vehicle in a first test scenario to obtain multi-dimensional data that affects the driving of the target vehicle includes: For a target vehicle in a first test scene, data collection is performed on the target vehicle at multiple times to obtain multiple groups of multi-dimensional data; wherein each group of the multi-dimensional data corresponds to a pseudo image; The evaluating the driving state of the target vehicle in the first test scene based on the fusion of the objective situation feature and the subjective situation feature includes: Based on the pseudo-image sequence of the target vehicle in the first scene to be tested, the driving state of the target vehicle in the first scene to be tested is evaluated.

5. The method according to claim 4, characterized in that The evaluating of the driving state of the target vehicle in the first scene to be tested based on the pseudo-image sequence of the target vehicle in the first scene to be tested is implemented by a preset safety evaluation model, including: By analyzing each of the fake images, the risk characteristics of the fake images at the corresponding moment are determined; Based on the relationship between the risk features at different moments, the driving state of the target vehicle in the first test scenario is obtained.

6. The method according to claim 5, characterized in that The method further comprises: According to the evaluation result of the first scenario to be tested, the security evaluation model is updated to obtain an updated security evaluation model; The safety assessment model is used to assess the driving state of the target vehicle in a second test scenario.

7. The method according to claim 2, characterized in that The analyzing the self-driving data to determine the subjective situation characteristics that affect the driving of the target vehicle includes: Using the subjective cognitive field strength distribution information in the own driving data as the subjective situation feature; The analyzing the external driving data to determine objective situation characteristics that affect the driving of the target vehicle includes: The objective risk field intensity distribution information in the external driving data is used as the objective situation feature.

8. A vehicle driving evaluation device, characterized in that: The device comprises: A collection module, for collecting data of a target vehicle in a first test scene, to obtain multi-dimensional data that affects the driving of the target vehicle; An analysis module, used to determine objective situation characteristics and subjective situation characteristics that affect the driving of the target vehicle by analyzing the multi-dimensional data of the target vehicle; A fusion module is used to evaluate the driving state of the target vehicle in the first test scene based on the fusion of the objective situation feature and the subjective situation feature.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor, and when the electronic device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, the steps of the method for vehicle driving evaluation as described in any one of claims 1 to 7 are performed.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, which, when executed by a processor, executes the steps of the vehicle driving evaluation method as claimed in any one of claims 1 to 7.

Images