Heavy truck safe driving dynamic scoring method and device based on road section risk and medium

Abstract

The invention discloses a heavy truck safe driving dynamic scoring method and device based on road segment risks and a medium, and relates to the technical field of driving safety assessment, and the method comprises the steps: obtaining driving road condition parameters, and carrying out the time-space reference synchronization of the driving road condition parameters, so as to determine road segment risk field parameters; performing dynamic risk layer fusion on the road section risk field parameters to obtain a road section risk field; based on the road section risk field, determining a real-time risk value of the road section through risk propagation prediction; performing score logic dynamic switching of linear interpolation on the real-time risk value of the road section to obtain a safe driving score of the current road section of the heavy truck; and according to the safe driving score of the current road section of the heavy truck, updating the driving ability of the logistics service to obtain a driver ability portrait. According to the method, the technical problems that existing safe driving scoring cannot adapt to dynamic road risks, and dynamic scoring and decision basis timeliness are poor are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of driving safety evaluation, in particular to a heavy truck safety driving dynamic scoring method based on road section risk, equipment and medium. BACKGROUND

[0002] As a core technology means of intelligent logistics transportation management, the heavy truck safety driving scoring system plays an important role in reducing traffic accident rate and optimizing vehicle fleet operation efficiency in recent years. The existing technology mainly realizes basic driving behavior analysis through vehicle-mounted OBD data and GPS positioning, and triggers static scoring rules in specific road sections based on electronic fence technology. With the increasing demand for high-value goods transportation safety in the logistics industry and the increasing proportion of night long-distance trunk transportation, the industry urgently needs safety evaluation capabilities for night special complex road conditions.

[0003] In the prior art, the technical scheme for heavy truck safety driving scoring has limitations. Firstly, road section analysis relies on discrete road section recognition of preset electronic fence, which cannot adapt to the continuous gradual change characteristics of road risk. Secondly, the safety scoring rules are fixed and do not consider the dynamic needs of road conditions and transportation scoring. Thirdly, the scoring results are separated from logistics management data, and safety warnings cannot be converted into business decision basis. SUMMARY

[0004] The embodiments of the present application provide a heavy truck safety driving dynamic scoring method based on road section risk, equipment and medium, which solves the technical problems of not adapting to dynamic road risk, dynamic scoring and poor timeliness of decision basis in existing safety driving scoring.

[0005] In the first aspect, the embodiments of the present application provide a heavy truck safety driving dynamic scoring method based on road section risk, characterized in that the method comprises: acquiring driving road condition parameters and synchronizing the driving road condition parameters with time and space benchmarks to determine road section risk field parameters; dynamically fusing the road section risk field parameters to obtain a road section risk field; determining a road section real-time risk value through risk propagation prediction based on the road section risk field; dynamically switching the scoring logic of linear interpolation of the road section real-time risk value to obtain a heavy truck current road section safety driving score; and updating the driving ability of logistics business according to the heavy truck current road section safety driving score to obtain a driver ability portrait.

[0006] In one implementation manner of the present application, the driving road condition parameters are synchronized with time and space benchmarks to determine the road section risk field parameters, specifically comprising: performing time protocol synchronization on the driving road condition parameters to obtain time-synchronized road condition parameters; and determining the road section risk field parameters through vehicle coordinate system conversion of UTM coordinates based on the time-synchronized road condition parameters.

[0007] In one implementation of this application, dynamic risk layer fusion is performed on road segment risk field parameters to obtain a road segment risk field. Specifically, this includes: calculating the basic risk of the road segment based on the road segment risk field parameters to obtain a static risk layer; determining a dynamic risk layer based on the road segment risk field parameters through multi-source risk fusion; wherein the types of multi-source risk fusion include: pavement condition quantification and visibility impact quantification; and performing risk layer fusion processing on the static risk layer and the dynamic risk layer to enhance nighttime risk, thereby obtaining the road segment risk field.

[0008] In one implementation of this application, a risk layer fusion process is performed on the static risk layer and the dynamic risk layer to enhance nighttime risk, thereby obtaining a road segment risk field. Specifically, this includes: performing linear boundary integration on the static risk layer to obtain a first fused risk layer; performing dynamic boundary integration on the dynamic risk layer to obtain a second fused risk layer; determining a continuous road segment risk field by risk layer boundary fusion based on the first and second fused risk layers; and adjusting the risk layer coefficients of the continuous road segment risk field for nighttime periods to obtain the road segment risk field.

[0009] In one implementation of this application, the real-time risk value of a road segment is determined based on the road segment risk field and through risk propagation prediction. Specifically, this includes: obtaining vehicle speed vectors and obtaining vehicle orientation fields based on vehicle speed vectors through road topology correction; determining risk convection terms based on the vehicle orientation fields through main direction propagation calculation; determining risk diffusion terms based on the vehicle orientation fields through non-main direction propagation calculation; and determining the real-time risk value of the road segment through visibility gradient correction based on the current risk intensity, risk convection terms, and risk diffusion terms of the road segment risk field.

[0010] In one implementation of this application, the scoring logic of linear interpolation of real-time risk values ​​of road segments is dynamically switched to obtain the current safe driving score of the heavy truck on the road segment. Specifically, this includes: judging the regional status of real-time risk values ​​of road segments to obtain the divided risk areas; wherein the types of risk areas include: low-risk areas, high-risk areas, and transition areas; performing linear interpolation analysis on the transition areas to determine the risk boundary compensation value; and obtaining the current safe driving score of the heavy truck on the road segment based on the risk boundary compensation value and risk score compensation.

[0011] In one implementation of this application, a driver capability profile is obtained by updating the driving ability of the logistics business based on the current road safety driving score of the heavy truck. Specifically, this includes: analyzing the driving status of the heavy truck's current road safety driving score to determine the driver's capability dimensions; wherein, the driver's capability dimensions include: nighttime curve stability, low visibility emergency speed, and long downhill control; multi-dimensional scoring of the driver's capability dimensions to obtain a comprehensive driver capability score, and updating the comprehensive driver capability score to the historical driver capability profile to obtain the driver capability profile.

[0012] In one implementation of this application, after obtaining a driver capability profile by updating the driving ability of logistics business based on the current road section safety driving score of the heavy truck, the method further includes: determining the driver task allocation ratio based on the driver capability profile through logistics business indicator analysis.

[0013] Secondly, embodiments of this application also provide a dynamic scoring device for safe driving of heavy-duty trucks based on road segment risk. The device comprises: at least one processor; and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which, when executed, enable the at least one processor to: acquire driving road condition parameters and synchronize the driving road condition parameters with a spatiotemporal reference to determine road segment risk field parameters; perform dynamic risk layer fusion on the road segment risk field parameters to obtain a road segment risk field; determine the real-time risk value of the road segment based on the road segment risk field through risk propagation prediction; dynamically switch the scoring logic of linear interpolation on the real-time risk value of the road segment to obtain the current road segment safe driving score of the heavy-duty truck; and update the driver's capability profile based on the current road segment safe driving score of the heavy-duty truck through driving capability updates for logistics operations.

[0014] Thirdly, this application also provides a non-volatile computer storage medium for dynamic scoring of heavy-duty truck safe driving based on road segment risk, storing computer-executable instructions. The computer-executable instructions are characterized by: acquiring driving road condition parameters and synchronizing the driving road condition parameters with a spatiotemporal reference to determine road segment risk field parameters; performing dynamic risk layer fusion on the road segment risk field parameters to obtain a road segment risk field; determining the real-time risk value of the road segment based on the road segment risk field through risk propagation prediction; dynamically switching the scoring logic of linear interpolation on the real-time risk value of the road segment to obtain the current road segment safe driving score of the heavy-duty truck; and updating the driving ability of the logistics business based on the current road segment safe driving score of the heavy-duty truck to obtain a driver capability profile.

[0015] This application provides a method, device, and medium for dynamic scoring of safe driving of heavy trucks based on road segment risk. By dynamically switching the scoring logic of dynamic risk layer fusion, risk propagation prediction, and linear interpolation, it solves the technical problems of existing safe driving scoring that cannot adapt to dynamic road risks, dynamic scoring, and poor timeliness of decision-making basis. It realizes continuous quantitative perception of logistics road risks and improves the stability of the response of logistics heavy truck drivers to safe driving in multiple road conditions. Attached Figure Description

[0016] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0017] Figure 1 A flowchart of a dynamic scoring method for safe driving of heavy trucks based on road segment risk is provided for an embodiment of this application;

[0018] Figure 2 This is a schematic diagram of the internal structure of a dynamic scoring device for safe driving of heavy trucks based on road segment risk, provided in an embodiment of this application. Detailed Implementation

[0019] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0020] This application provides a method, device, and medium for dynamic scoring of safe driving of heavy trucks based on road segment risk. By dynamically switching the scoring logic of dynamic risk layer fusion, risk propagation prediction, and linear interpolation, it solves the technical problems of existing safe driving scoring that cannot adapt to dynamic road risks, dynamic scoring, and poor timeliness of decision-making basis. It realizes continuous quantitative perception of logistics road risks and improves the stability of the response of logistics heavy truck drivers to safe driving in multiple road conditions.

[0021] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0022] Figure 1 This document provides a flowchart of a dynamic scoring method for heavy-duty truck safe driving based on road segment risk, as illustrated in an embodiment of this application. Figure 1 As shown in the figure, the present application provides a dynamic scoring method for safe driving of heavy trucks based on road segment risk, which specifically includes the following steps:

[0023] Step 101: Obtain driving road condition parameters and synchronize the driving road condition parameters with a spatiotemporal reference to determine the road segment risk field parameters.

[0024] For example, this application achieves spatiotemporal synchronization of road condition status by synchronizing driving road condition parameters with a spatiotemporal reference, providing a data foundation for dynamic risk layer fusion.

[0025] Specifically, the driving condition parameters are synchronized with a spatiotemporal reference to determine the road segment risk field parameters, including: synchronizing the driving condition parameters with a time protocol to obtain time-synchronized road condition parameters; and determining the road segment risk field parameters based on the time-synchronized road condition parameters by transforming the vehicle coordinate system of UTM coordinates.

[0026] In one embodiment, road data is collected in real time by multiple source sensors and combined with static map attributes (slope, curvature) to obtain discrete driving condition parameters.

[0027] To synchronize discrete road condition parameters using a time protocol, the PTPv2 protocol can be used. By using SLAM technology to unify the sensor coordinate system to the vehicle coordinate system, UTM coordinate transformation can be used to determine the road segment risk field parameters.

[0028] Step 102: Perform dynamic risk layer fusion on the road segment risk field parameters to obtain the road segment risk field.

[0029] For example, existing electronic fence technology relies on preset geographical boundaries and cannot perceive the continuous and gradual risks on the road surface. This application achieves continuous quantitative perception of road risks by dynamically fusing road segment risk field parameters, avoiding the step-like abrupt changes in existing logistics road condition perception data and improving the smoothness of continuous analysis of road segment risks.

[0030] Specifically, dynamic risk layer fusion is performed on the road segment risk field parameters to obtain the road segment risk field, including: calculating the basic risk of the road segment based on the road segment risk field parameters to obtain the static risk layer; determining the dynamic risk layer based on the road segment risk field parameters through multi-source risk fusion; wherein, the types of multi-source risk fusion include: road surface condition quantification and visibility impact quantification; and performing risk layer fusion processing on the static risk layer and dynamic risk layer for nighttime risk enhancement to obtain the road segment risk field.

[0031] Furthermore, a risk layer fusion process is performed on the static risk layer and the dynamic risk layer to enhance nighttime risk, thereby obtaining the road segment risk field. Specifically, this includes: performing linear boundary integration on the static risk layer to obtain a first fused risk layer; performing dynamic boundary integration on the dynamic risk layer to obtain a second fused risk layer; determining the continuous risk field of the road segment by fusion of risk layer boundaries based on the first and second fused risk layers; and adjusting the risk layer coefficients of the continuous risk field of the road segment during nighttime periods to obtain the road segment risk field.

[0032] In one embodiment, the road is divided into 10m x 10m grid cells, each carrying multi-dimensional data, including a static risk layer and a dynamic attachment layer. Sensor data is collected every 0.1 seconds while the vehicle is in motion, and the grid cells are weighted by applying a risk assessment algorithm that diffuses the influence radius centered on the current detection point.

[0033] The fusion of the two levels requires the generation of continuous risk surfaces. The weighted static risk layer and dynamic attachment layer can be fused at the boundary to achieve risk layer boundary fusion and determine the continuous risk field of the road segment.

[0034] Due to poor visibility at night, the risk layer coefficient for nighttime driving needs to be adjusted. This application adopts a road section risk coefficient enhancement of 1.3 times to meet the risk assessment needs of nighttime driving.

[0035] Step 103: Based on the road segment risk field, determine the real-time risk value of the road segment through risk propagation prediction.

[0036] For example, heavy trucks have long braking distances, and existing linear extrapolation methods cannot predict sudden risks outside the field of vision on curves. This application extends the truck risk prediction distance through risk propagation prediction, thereby improving the coverage of truck driver safety driving scores and driving safety.

[0037] Specifically, based on the road segment risk field, the real-time risk value of the road segment is determined through risk propagation prediction. This includes: obtaining vehicle speed vectors and, based on the vehicle speed vectors, obtaining the vehicle direction field through road topology correction; determining the risk convection term through main direction propagation calculation based on the vehicle direction field; determining the risk diffusion term through non-main direction propagation calculation based on the vehicle direction field; and determining the real-time risk value of the road segment through visibility gradient correction based on the current risk intensity, risk convection term, and risk diffusion term of the road segment risk field.

[0038] In one embodiment, the road risk field is a prediction field that combines dynamic and static fields. For the safety rating of heavy trucks, braking distance is the core safety parameter and is much longer than that of conventional vehicles.

[0039] First, calculate the heading angle based on the vehicle's longitudinal and lateral velocities to determine the principal direction of the direction field propagation. Then, calculate the deflection angle of the direction field based on the curvature of the current road conditions.

[0040] Then, the convection term of the road segment risk field is calculated by dynamic interpolation based on the main direction and deflection angle; among them, the risk convection term needs to be calculated based on the propagation of the main direction, and the risk diffusion term needs to be calculated by considering the anisotropy of the road segment risk field.

[0041] Finally, based on the current risk intensity value, the risk convection term and risk diffusion term are added, and the risk intensity is reinforced for the visibility of the current environment, still using 1.3 as the reinforcement coefficient, to determine the real-time risk value of the road segment.

[0042] Step 104: Dynamically switch the scoring logic of linear interpolation of the real-time risk value of the road segment to obtain the safe driving score of the heavy truck on the current road segment.

[0043] For example, the safety driving score of heavy truck drivers can change abruptly with dynamic changes in driver state and road conditions. Existing technologies typically result in discrete scores with numerous data fluctuations, which can easily lead to unreasonable scores and reduced usability in practical applications. This application addresses this by dynamically switching the scoring logic using linear interpolation. Through the division of risk intervals and linear interpolation of past intervals, it achieves a rationalization of the safety driving score for heavy truck drivers, reducing the probability of score abrupt changes.

[0044] Specifically, the scoring logic for linear interpolation of real-time risk values ​​of road segments is dynamically switched to obtain the safe driving score of heavy trucks on the current road segment. This includes: judging the regional status of real-time risk values ​​of road segments to obtain the divided risk areas; the types of risk areas include: low-risk areas, high-risk areas, and transition areas; performing linear interpolation analysis on the transition areas to determine the risk boundary compensation value; and obtaining the safe driving score of heavy trucks on the current road segment through risk score compensation based on the risk boundary compensation value.

[0045] In one embodiment, risk zones are first divided, and the regional status is determined based on the real-time risk value of the road segment. The risk zones are divided by the risk value R, including: low-risk zone (R<4.0), transition zone (4.0≤R≤6.0), and high-risk zone (R>6.0).

[0046] The existence of the transition zone allows for a relatively smooth driving safety score, while the risk values ​​in the risk zones on either side of it may still fluctuate significantly.

[0047] Therefore, based on the high-risk and low-risk values ​​of the current road segment, the interpolation value is obtained by subtracting the upper limit of a low-risk zone from the risk value and then averaging the results.

[0048] Through this interpolation calculation, the risk value parameter of the past interval can meet the requirement that there will not be excessive fluctuations in the edge values ​​under the two edge risk coefficients of 4.0 and 6.0. Thus, the risk boundary compensation value can be used to obtain a relatively stable safe driving score for heavy trucks on the current road section.

[0049] Step 105: Based on the current road safety driving score of the heavy truck, update the driving ability of the logistics business to obtain the driver's ability profile.

[0050] Specifically, based on the current road safety driving score of heavy trucks, the driving ability of logistics operations is updated to obtain a driver capability profile. This includes: analyzing the driving status of the current road safety driving score of heavy trucks to determine the driver capability dimensions; among which, the driver capability dimensions include: nighttime curve stability, low visibility emergency speed, and long downhill control; multi-dimensional scoring of the driver capability dimensions is performed to obtain a comprehensive driver capability score, and the comprehensive driver capability score is updated to the historical driver capability profile to obtain the driver capability profile.

[0051] Furthermore, after obtaining a driver capability profile by updating the driving ability of logistics business based on the current road safety driving score of heavy trucks, the method also includes: determining the driver task allocation ratio based on the driver capability profile through logistics business indicator analysis.

[0052] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide a dynamic scoring device for safe driving of heavy trucks based on road segment risk, the structure of which is as follows: Figure 2 As shown.

[0053] Figure 2 This is a schematic diagram of the internal structure of a dynamic scoring device for safe driving of heavy trucks based on road segment risk, provided as an embodiment of this application. Figure 2 As shown, the device includes:

[0054] At least one processor 201;

[0055] And a memory 202 that is communicatively connected to at least one processor;

[0056] The memory 202 stores instructions executable by at least one processor, which are executed by at least one processor 201 to enable at least one processor 201 to:

[0057] The system acquires road condition parameters and synchronizes them with a spatiotemporal reference to determine road segment risk field parameters. It then performs dynamic risk layer fusion on these parameters to obtain the road segment risk field. Based on this risk field, it predicts and determines the real-time risk value of the road segment through risk propagation. Finally, it dynamically switches the scoring logic of linear interpolation on the real-time risk value to obtain the current road segment safe driving score for the heavy truck. Based on this score, it updates the driver's driving capabilities through logistics operations to obtain a driver capability profile.

[0058] Some embodiments of this application provide corresponding to Figure 1 A non-volatile computer storage medium for dynamic scoring of heavy-duty truck safe driving based on road segment risk, storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0059] The system acquires road condition parameters and synchronizes them with a spatiotemporal reference to determine road segment risk field parameters. It then performs dynamic risk layer fusion on these parameters to obtain the road segment risk field. Based on this risk field, it predicts and determines the real-time risk value of the road segment through risk propagation. Finally, it dynamically switches the scoring logic of linear interpolation on the real-time risk value to obtain the current road segment safe driving score for the heavy truck. Based on this score, it updates the driver's driving capabilities through logistics operations to obtain a driver capability profile.

[0060] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for IoT devices and media are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0061] The systems, media, and methods provided in this application are one-to-one correspondences. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0062] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0063] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations 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 processor, 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, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0064] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0065] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0066] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0067] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0068] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0069] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

[0070] The above are merely embodiments of this application and are not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A dynamic scoring method for safe driving of heavy-duty trucks based on road segment risk, characterized in that, The method includes: Acquire driving road condition parameters and synchronize the driving road condition parameters with a spatiotemporal reference to determine the road segment risk field parameters; Dynamic risk layer fusion is performed on the risk field parameters of the road segment to obtain the road segment risk field; Based on the risk field of the road segment, the real-time risk value of the road segment is determined through risk propagation prediction; The scoring logic for linear interpolation of the real-time risk value of the road segment is dynamically switched to obtain the safe driving score of the heavy truck on the current road segment; Based on the current road safety driving score of the heavy truck, the driver's capability profile is obtained by updating the driving ability of the logistics business.

2. The dynamic scoring method for heavy-duty truck safe driving based on road segment risk according to claim 1, characterized in that, The driving condition parameters are synchronized with a spatiotemporal reference to determine the road segment risk field parameters, specifically including: The driving road condition parameters are synchronized using a time protocol to obtain time-synchronized road condition parameters; Based on the time-synchronized road condition parameters, the risk field parameters of the road segment are determined through vehicle coordinate system transformation of UTM coordinates.

3. The dynamic scoring method for heavy-duty truck safe driving based on road segment risk according to claim 1, characterized in that, Dynamic risk layer fusion is performed on the road segment risk field parameters to obtain the road segment risk field, specifically including: The basic risk of the road segment is calculated based on the risk field parameters of the road segment to obtain the static risk layer; Based on the road segment risk field parameters, a dynamic risk layer is determined through multi-source risk fusion; wherein, the types of multi-source risk fusion include: road surface condition quantification and visibility impact quantification; The static risk layer and the dynamic risk layer are subjected to nighttime risk enhancement risk layer fusion processing to obtain the road segment risk field.

4. The dynamic scoring method for heavy-duty truck safe driving based on road segment risk according to claim 3, characterized in that, The static risk layer and the dynamic risk layer are subjected to nighttime risk enhancement risk layer fusion processing to obtain the road segment risk field, specifically including: Linear boundary integration is performed on the static risk layer to obtain the first fused risk layer; Dynamic boundary integration is performed on the dynamic risk layer to obtain a second fused risk layer; Based on the first fusion risk layer and the second fusion risk layer, the continuous risk field of the road segment is determined by fusion of the risk layer boundaries; The risk layer coefficient of the continuous risk field of the road segment is adjusted during the nighttime period to obtain the risk field of the road segment.

5. The dynamic scoring method for safe driving of heavy trucks based on road segment risk according to claim 1, characterized in that, Based on the road segment risk field, the real-time risk value of the road segment is determined through risk propagation prediction, specifically including: Obtain the vehicle velocity vector, and based on the vehicle velocity vector, obtain the vehicle orientation field through road topology correction; Based on the vehicle orientation field, risk convection terms are determined through propagation calculations in the main direction. Based on the vehicle orientation field, risk diffusion terms are determined through non-dominant direction propagation calculations. Based on the current risk intensity of the road segment risk field, the risk convection term, and the risk diffusion term, the real-time risk value of the road segment is determined through visibility gradient correction.

6. The dynamic scoring method for safe driving of heavy trucks based on road segment risk according to claim 1, characterized in that, The scoring logic for linear interpolation of the real-time risk value of the road segment is dynamically switched to obtain the safe driving score of the heavy truck on the current road segment, specifically including: The real-time risk value of the road segment is used to determine the regional status to obtain the divided risk areas; wherein, the types of risk areas include: low-risk area, high-risk area, and transition area; Linear interpolation analysis is performed on the transition zone to determine the risk boundary compensation value; Based on the risk boundary compensation value, the safe driving score of the heavy truck on the current road segment is obtained through risk score compensation.

7. The dynamic scoring method for safe driving of heavy trucks based on road segment risk according to claim 1, characterized in that, Based on the current road safety driving score of the heavy truck, the driver's capability profile is obtained by updating the driving ability of the logistics business, specifically including: The driving status analysis is performed on the current road section safety driving score of the heavy truck to determine the heavy truck driver's ability dimensions; wherein, the heavy truck driver's ability dimensions include: nighttime curve stability, low visibility emergency speed, and long downhill control; The heavy-duty truck driver's ability dimensions are scored in multiple dimensions to obtain a comprehensive score for the heavy-duty truck driver's ability, and the comprehensive score for the heavy-duty truck driver's ability is updated to the historical driver ability profile to obtain the driver ability profile.

8. The dynamic scoring method for heavy-duty truck safe driving based on road segment risk according to claim 1, characterized in that, After obtaining a driver capability profile by updating the driving ability of the heavy truck based on the current road safety driving score and the driving ability of the logistics business, the method further includes: Based on the driver capability profile, the driver task allocation ratio is determined through logistics business indicator analysis.

9. A dynamic scoring device for safe driving of heavy-duty trucks based on road segment risk, characterized in that, The device includes: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to: Acquire driving road condition parameters and synchronize the driving road condition parameters with a spatiotemporal reference to determine the road segment risk field parameters; Dynamic risk layer fusion is performed on the risk field parameters of the road segment to obtain the road segment risk field; Based on the risk field of the road segment, the real-time risk value of the road segment is determined through risk propagation prediction; The scoring logic for linear interpolation of the real-time risk value of the road segment is dynamically switched to obtain the safe driving score of the heavy truck on the current road segment; Based on the current road safety driving score of the heavy truck, the driver's capability profile is obtained by updating the driving ability of the logistics business.

10. A non-volatile computer storage medium for dynamic scoring of heavy-duty truck safe driving based on road segment risk, storing computer-executable instructions, characterized in that, The computer-executable instructions are set as follows: Acquire driving road condition parameters and synchronize the driving road condition parameters with a spatiotemporal reference to determine the road segment risk field parameters; Dynamic risk layer fusion is performed on the risk field parameters of the road segment to obtain the road segment risk field; Based on the risk field of the road segment, the real-time risk value of the road segment is determined through risk propagation prediction; The scoring logic for linear interpolation of the real-time risk value of the road segment is dynamically switched to obtain the safe driving score of the heavy truck on the current road segment; Based on the current road safety driving score of the heavy truck, the driver's capability profile is obtained by updating the driving ability of the logistics business.

Images