Driving safety management method and system based on driving track monitoring

Abstract

The embodiment of the invention relates to the technical field of driving safety management, and particularly discloses a driving safety management method and system based on driving track monitoring. According to the embodiment of the invention, the driving state data of the target engineering vehicle is directly or cooperatively collected; generating smooth trajectory data, and performing anomaly evaluation on the smooth trajectory data; an optimal driving path is planned, and dynamic driving guidance is carried out; performing dynamic risk analysis and early warning prompt on the target engineering vehicle; and constructing a driving risk portrait, and performing periodic assessment on a target driver of the target engineering vehicle. Trajectory cleaning and reconstruction can be carried out, smooth trajectory data can be generated, abnormity assessment can be carried out, dynamic risk analysis and early warning prompt can be carried out on a target engineering vehicle, a driving risk portrait can be constructed, periodic assessment can be carried out, personalized management of engineering transport vehicle driving safety can be realized, management precision can be improved, and the engineering transport vehicle driving safety management efficiency can be improved. And the driving data can be effectively utilized, and a basic support is provided for management decision guidance and strategy optimization.

Description

Technical Field

[0001] The present invention belongs to the technical field of driving safety management, and in particular relates to a driving safety management method and system based on driving trajectory monitoring. Background Art

[0002] Driving safety management is a management activity that monitors and controls the entire driving process of motor vehicles through institutionalized, systematic and technological means to ensure the coordinated operation of various elements such as people, vehicles and roads, so as to minimize the risk of traffic accidents, ensure transportation efficiency and the safety of people's lives and property. Its main contents include driver behavior management, vehicle status monitoring, road environment assessment, and the establishment of emergency warning and handling mechanisms.

[0003] Modern driving safety management widely applies information technology, such as GPS positioning, trajectory analysis, video surveillance, and intelligent early warning systems, to achieve real-time monitoring and dynamic intervention of key indicators such as vehicle location, speed, operating trajectory, and fatigue driving.

[0004] In existing technologies, the driving safety management of engineering transport vehicles only determines whether they are speeding based on road speed limit regulations, ignoring the driver's specific behavior patterns and potential risk behaviors. This makes it impossible to achieve personalized management of the driving safety of engineering transport vehicles. In addition, there is a lack of data analysis, archiving, and feedback mechanisms, resulting in low data utilization and inability to guide management decisions and strategy optimization. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide a driving safety management method and system based on driving trajectory monitoring, aiming to solve the problems raised in the background technology.

[0006] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions: A driving safety management method based on driving trajectory monitoring, the method specifically comprising the following steps: Identify the target engineering vehicle and directly or collaboratively collect the driving status data of the target engineering vehicle; performing trajectory cleaning and reconstruction on the driving state data to generate smooth trajectory data, and performing anomaly assessment on the smooth trajectory data to obtain anomaly assessment data; receiving real-time traffic data, planning an optimal driving route based on the real-time traffic data and the driving status data, and providing dynamic driving guidance based on the optimal driving route; Performing dynamic risk analysis and early warning on the target engineering vehicle based on the optimal driving path and the driving status data; The driving status data is updated and recorded, a driving risk profile is constructed, and a periodic assessment is conducted on the target driver of the target engineering vehicle.

[0007] A driving safety management system based on driving trajectory monitoring is applied to the above-mentioned driving safety management method based on driving trajectory monitoring. The system includes a driving status acquisition unit, a trajectory anomaly assessment unit, a dynamic driving guidance unit, a risk warning prompt unit, and a driving cycle assessment unit, wherein: A driving status collection unit is used to determine the target engineering vehicle and directly or collaboratively collect the driving status data of the target engineering vehicle; a trajectory anomaly assessment unit, configured to perform trajectory cleaning and reconstruction on the driving state data to generate smooth trajectory data, and perform anomaly assessment on the smooth trajectory data to obtain anomaly assessment data; A dynamic driving guidance unit, configured to receive real-time traffic data, plan an optimal driving route based on the real-time traffic data and the driving status data, and provide dynamic driving guidance based on the optimal driving route; a risk warning prompt unit, configured to perform dynamic risk analysis and provide warning prompts for the target engineering vehicle based on the optimal driving path and the driving status data; The driving cycle assessment unit is used to update and record the driving status data, construct a driving risk profile, and conduct periodic assessments on the target drivers of the target engineering vehicles.

[0008] Compared with the prior art, the present invention has the following beneficial effects: The embodiments of the present invention directly or collaboratively collect driving status data of target engineering vehicles; generate smooth trajectory data and perform anomaly assessments on the smooth trajectory data; plan the optimal driving path and provide dynamic driving guidance; perform dynamic risk analysis and early warning prompts on the target engineering vehicles; construct driving risk profiles, and conduct periodic assessments on the target drivers of the target engineering vehicles. The system is capable of performing trajectory cleaning and reconstruction, generating smooth trajectory data and performing anomaly assessments, performing dynamic risk analysis and early warning prompts on the target engineering vehicles, constructing driving risk profiles, and conducting periodic assessments. This system can achieve personalized management of the driving safety of engineering transport vehicles, improve management accuracy, and effectively utilize driving data, providing basic support for management decision guidance and strategy optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention.

[0010] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0011] Figure 2 The figure shows a structural block diagram of a driving cycle assessment unit in a system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0012] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0013] Understandably, modern traffic safety management widely utilizes information technology, such as GPS positioning, trajectory analysis, video surveillance, and intelligent early warning systems, to enable real-time monitoring and dynamic intervention of key indicators such as vehicle location, speed, trajectory, and fatigue. Existing technologies for traffic safety management of construction transport vehicles rely solely on speed limit regulations to determine whether a vehicle is speeding, ignoring drivers' specific behavioral patterns and potential risky behaviors. This fails to personalize traffic safety management for construction transport vehicles, and the system lacks data analysis, archiving, and feedback mechanisms, resulting in low data utilization and inability to guide management decisions and strategy optimization.

[0014] To address the above-mentioned issues, embodiments of the present invention identify target engineering vehicles and directly or collaboratively collect driving status data of the target engineering vehicles; perform trajectory cleaning and reconstruction on the driving status data to generate smooth trajectory data, and perform anomaly assessment on the smooth trajectory data to obtain anomaly assessment data; receive real-time road condition data, combine the real-time road condition data and driving status data to plan the optimal driving path, and provide dynamic driving guidance based on the optimal driving path; perform dynamic risk analysis and early warning prompts on the target engineering vehicles based on the optimal driving path and driving status data; update and record the driving status data, construct a driving risk profile, and conduct periodic assessments on the target drivers of the target engineering vehicles. The ability to perform trajectory cleaning and reconstruction, generate smooth trajectory data and perform anomaly assessment, perform dynamic risk analysis and early warning prompts on the target engineering vehicles, construct a driving risk profile, and conduct periodic assessments can achieve personalized management of driving safety for engineering transport vehicles, improve management accuracy, and effectively utilize driving data, providing basic support for management decision guidance and strategy optimization.

[0015] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0016] Specifically, a driving safety management method based on driving trajectory monitoring includes the following steps: Step S101 : determining a target engineering vehicle, and directly or collaboratively collecting driving status data of the target engineering vehicle.

[0017] In an embodiment of the present invention, a target engineering vehicle for driving safety management is determined, and the transmission communication quality of the target engineering vehicle is obtained in real time, and the transmission communication quality is compared with a preset standard communication quality. When the transmission communication quality is greater than the standard communication quality, the driving status data of the target engineering vehicle (including the current position, current speed, current acceleration, vehicle head direction and vehicle operation status, etc.) is directly collected; and when the transmission communication quality is not greater than the standard communication quality, a collaborative engineering vehicle is selected, and a temporary communication connection is established between the target engineering vehicle and the collaborative engineering vehicle. Through the temporary communication connection between the target engineering vehicle and the collaborative engineering vehicle, the driving status data of the target engineering vehicle is collaboratively collected with the collaborative engineering vehicle as an intermediate medium.

[0018] Specifically, in a preferred embodiment of the present invention, the step of determining a target engineering vehicle and directly or collaboratively collecting driving status data of the target engineering vehicle specifically includes the following steps: Determine the target engineering vehicles for driving safety management; Acquiring the transmission communication quality of the target engineering vehicle, and comparing the transmission communication quality with a preset standard communication quality; When the transmission communication quality is greater than the standard communication quality, directly collecting the driving status data of the target engineering vehicle; When the transmission communication quality is not greater than the standard communication quality, selecting a cooperative engineering vehicle and establishing a temporary communication connection between the target engineering vehicle and the cooperative engineering vehicle; The driving status data of the target engineering vehicle is collaboratively collected through the collaborative engineering vehicle.

[0019] Specifically, in a preferred embodiment of the present invention, when the transmission communication quality is not greater than the standard communication quality, selecting a cooperative engineering vehicle and establishing a temporary communication connection between the target engineering vehicle and the cooperative engineering vehicle specifically includes the following steps: Acquire the three-dimensional axis acceleration data of the target engineering vehicle in real time, and simultaneously collect the original vibration spectrum data of all candidate engineering vehicles within the preset surrounding range; Perform a fast Fourier transform on the acceleration data of the target engineering vehicle and candidate vehicles to extract the energy distribution spectrum in the frequency range of 0.1–100 Hz. This will determine the main resonant frequency of the target engineering vehicle and the energy stability index of each axis of the candidate vehicles. The target engineering vehicle's main resonant frequency is determined. If the main resonant frequency falls within the communication frequency band (1.5–2.5 GHz) and the energy exceeds a threshold (e.g., 80 dB), it is marked as "equipment looseness risk" and a risk label is obtained. Based on the risk label, in high-risk scenarios, candidate vehicles with an orthogonal resonance axis and an energy stability index greater than 90 are selected for collaboration; in low-risk scenarios, candidate vehicles with the highest signal strength are selected for collaboration. The collaborative engineering vehicle ID and complementary axis identifier are obtained. Obtaining a construction site BIM model within a preset range around the target engineering vehicle, identifying metal structures in the construction site BIM model within the preset range around the target engineering vehicle that can serve as reflection sources, and obtaining the position coordinates of the metal structures; The target engineering vehicle's driving status data is modulated onto the ambient RF carrier. Based on the metal structure's location coordinates, the metal structure is illuminated by a directional antenna to obtain the phase jump generated by the reflected signal. A collaborative engineering vehicle is selected according to its ID, and a coherent detector is deployed on the collaborative engineering vehicle; according to its complementary axial identification, the coherent detector of the corresponding axial complementary collaborative engineering vehicle is enabled to demodulate phase jump and restore data to establish a bidirectional low-rate link.

[0020] In an embodiment of the present invention, engineering vehicles generate low-frequency mechanical vibrations (such as engine shaking and road bumps) during operation. When the vibration frequency approaches the inherent resonant frequency of the communication equipment (such as the antenna PCB board resonant frequency of 1.5-2.5GHz), it will cause antenna impedance mismatch and enhanced signal reflection, causing the communication bit error rate to soar. Traditional solutions only monitor the electromagnetic signal intensity (RSSI) and cannot identify this type of "invisible" interference. However, when the target vehicle vibrates violently in the X-axis direction (resonance frequency energy >80dB), the present invention selects a cooperative vehicle with stable Y-axis vibration (energy stability index >90). Because the mechanical vibrations in the orthogonal axes do not interfere with each other, the superposition of resonant energy can be avoided. This is equivalent to building a "mechanical vibration isolation zone" for the communication system. In addition, it is based on the temporary communication principle of environmental backscatter.

[0021] By utilizing the electromagnetic wave reflection characteristics of metal structures (such as steel bars) on the construction site, the target vehicle data is modulated onto the environmental radio frequency signal (such as the 900MHz carrier leaked from a nearby base station) through binary phase shift keying (BPSK).

[0022] For data "0," the reflected signal maintains its phase at 0° (original phase); for data "1," the reflected signal shifts its phase by 180° (inverted phase). The cooperating vehicle then uses a coherent detector to demodulate the data by comparing the phase difference between the reflected signal and a reference carrier. Because no active RF signal is required, relying solely on ambient electromagnetic waves, "zero-radiation" communication is achieved.

[0023] Because ambient backscatter communication consumes only 1 / 1000th the power of traditional RF transmission (measured target vehicle power consumption <1mW), it addresses the battery life bottleneck of engineering vehicles. Furthermore, the reflected signal power is below the ambient noise floor (<-110dBm), making it undetectable by conventional equipment. Furthermore, the phase-modulated signal requires precise carrier synchronization for decoding, making it impossible for non-cooperative parties to decipher it, thus preventing eavesdropping and tampering, and enhancing security.

[0024] Furthermore, the driving safety management method based on driving trajectory monitoring further includes the following steps: Step S102 : performing trajectory cleaning and reconstruction on the driving state data to generate smooth trajectory data, and performing anomaly assessment on the smooth trajectory data to obtain anomaly assessment data.

[0025] In an embodiment of the present invention, a Kalman filter and / or a Savitzky-Golay algorithm are used to perform trajectory cleaning on the driving state data to obtain cleaned state data. The cleaned state data is then subjected to trajectory smoothing to reconstruct smoothed trajectory data of the target engineering vehicle. The smoothed trajectory data is then subjected to an abnormality assessment based on multiple abnormal driving states (abnormality assessment is the process of evaluating abnormal states of the target engineering vehicle, such as sudden acceleration, sudden deceleration, abnormal parking, and illegal detours), to obtain abnormality assessment data.

[0026] Specifically, in a preferred embodiment of the present invention, the driving state data is cleaned and reconstructed to generate smooth trajectory data, and the smooth trajectory data is evaluated for abnormalities. Obtaining the abnormality evaluation data specifically includes the following steps: Using Kalman filtering and / or Savitzky-Golay algorithm, performing trajectory cleaning on the driving state data to obtain cleaned state data; Performing trajectory smoothing reconstruction on the cleaning state data to generate smooth trajectory data; According to a plurality of abnormal driving conditions, abnormality evaluation is performed on the smooth trajectory data to obtain abnormality evaluation data.

[0027] In a preferred embodiment of the present invention, the use of Kalman filtering and Savitzky-Golay algorithm to clean the driving state data to obtain the cleaned state data specifically includes the following steps: The driving state data is cleaned by using Kalman filtering and Savitzky-Golay algorithm respectively to obtain the Kalman filtering results and Savitzky-Golay filtering results; Determine the acceleration threshold based on historical data statistics and vehicle type; obtain the absolute value of the acceleration at the current moment based on driving status data; Compare the absolute value of the current acceleration with the acceleration threshold. If the absolute value of the current acceleration is less than the acceleration threshold, the vehicle is judged to be in a stable state, the weight is close to 0, and the Savitzky-Golay result is preferred. If the absolute value of the current acceleration is greater than or equal to the acceleration threshold, the vehicle is judged to be in a violent motion state, the weight is close to 1, and the Kalman filter result is preferred. According to the current driving state, different weights are assigned to the Kalman filter results and the Savitzky-Golay filter results to obtain the current acceleration dynamic weight value. If it is determined to be a stable state, the weight is close to 0, and the Savitzky-Golay result is preferred. If it is determined to be a violent motion state, the weight is close to 1, and the Kalman filter result is preferred. Apply the sigmoid function to the current acceleration dynamic weight value for smooth transition to obtain the smoothed acceleration dynamic weight value; The Kalman filter results and Savitzky-Golay filter results are linearly fused using the smoothed acceleration dynamic weight value to obtain the current moment filtered data; The filtered data at each time point is gradually acquired in time series to obtain the cleaning status data.

[0028] In an embodiment of the present invention, the Kalman filter result suppresses trajectory data after sudden noise changes, but may introduce lag errors (such as position update delays during sudden braking). The Savitzky-Golay filter result retains detailed smooth trajectory data, but has a weaker ability to suppress drastically changing noise. The present invention uses an acceleration-driven dynamic fusion mechanism to adaptively switch or fuse algorithms based on the current vehicle acceleration dynamics, combining the advantages of the two algorithms to overcome the limitations of a single filtering algorithm, avoiding the lag defect of the Kalman filter and compensating for the lack of noise resistance of the Savitzky-Golay filter, so as to automatically switch to the optimal strategy when the motion state suddenly changes. In addition, the weights are smoothly switched through the sigmoid function to avoid trajectory jumps caused by sudden changes in the filtering strategy.

[0029] For example, in stable operating conditions (such as constant speed driving), the absolute value of acceleration is low. In this case, the Savitzky-Golay filter (SG) is dominant, and its local polynomial fitting characteristics are used to retain trajectory details (such as changes in curvature in slow turns).

[0030] Severe working conditions (such as sudden braking and bumpy roads): When the absolute value of acceleration exceeds the threshold, the Kalman filter (KF) takes the lead and suppresses sudden noise (such as GPS signal jumps) by fusing motion model prediction and measurement values.

[0031] In a preferred embodiment of the present invention, performing abnormality evaluation on the smooth trajectory data according to multiple abnormal driving conditions and obtaining abnormality evaluation data specifically include the following steps: Set different abnormal driving states and assign corresponding benchmark thresholds to each abnormal driving state; Compare the abnormal driving state data corresponding to the smooth trajectory data with the benchmark threshold, and normalize the comparison results to obtain the basic score of each abnormal type; Obtain the acceleration vector at each time point from the smooth trajectory data, and calculate the trajectory dynamic change rate based on the acceleration vector at each time point; Set corresponding sensitivity coefficients for different abnormal driving conditions, perform weighted exponential calculations on the sensitivity coefficients and the trajectory dynamic change rate, and obtain index calculation results for different abnormal driving conditions; Normalize the index calculation results of different abnormal driving states to obtain the dynamic weights of different abnormal driving states; The basic scores of each abnormality type are weighted by the dynamic weights of different abnormal driving states to obtain the final scores of different abnormal driving states. The final scores of different abnormal driving states are summed to obtain the comprehensive abnormality score; The final scores of different abnormal driving states and the comprehensive anomaly scores are encapsulated and associated with the corresponding timestamps, vehicle identifications, and metadata to obtain anomaly assessment data.

[0032] In this embodiment of the present invention, the corresponding abnormal driving state data in the smoothed trajectory data is compared with a baseline threshold, and a corresponding score is obtained based on the comparison result. This allows for real-time quantification of trajectory fluctuation intensity (e.g., sudden braking, bumpy road conditions) through the trajectory dynamic change rate. An exponential normalization function is then used to dynamically assign weights to each anomaly type based on the trajectory dynamic change rate. When the trajectory dynamic change rate is high (trajectory instability), the weights of anomaly types that are sensitive to change (e.g., sharp turns) are increased. Furthermore, a multi-dimensional anomaly fusion assessment mechanism has been designed. A basic score is independently calculated for each anomaly type (e.g., sudden acceleration, sharp turns), and then dynamically weighted to form a comprehensive score that reflects the overall risk level.

[0033] Furthermore, the driving safety management method based on driving trajectory monitoring further includes the following steps: Step S103: receiving real-time traffic data, planning an optimal driving route based on the real-time traffic data and the driving status data, and performing dynamic driving guidance based on the optimal driving route.

[0034] In an embodiment of the present invention, real-time road condition data including traffic maps, construction area restrictions, highway restrictions, etc. are received, and the optimal driving path is planned by combining the real-time road condition data and driving status data. Based on the optimal driving path, dynamic guidance information is generated, and the dynamic guidance information is broadcast to dynamically guide the target engineering vehicles.

[0035] Specifically, in a preferred embodiment of the present invention, receiving real-time traffic data, combining the real-time traffic data with the driving status data, planning an optimal driving path, and performing dynamic driving guidance based on the optimal driving path specifically include the following steps: Receive real-time traffic data; Planning an optimal driving route by combining the real-time traffic data and the driving status data; generating dynamic guidance information according to the optimal driving path; The dynamic guidance information is broadcasted to dynamically guide the target engineering vehicle.

[0036] In a preferred embodiment of the present invention, the planning of the optimal driving route by combining the real-time traffic data and the driving status data specifically includes the following steps: The congestion coefficient is calculated based on real-time traffic data, and the congestion coefficient is smoothly transitioned using an S-shaped function to obtain the time weight; Set the safety weight according to the time weight, and set the safety weight and the time weight to be complementary; Calculate the ratio of the remaining fuel volume to the total fuel tank volume based on the driving status data to obtain the energy consumption weight; Based on the vehicle location and target location, the road network topology data is used to generate multiple routes; Obtain the minimum turning radius and maximum climbing grade of the vehicle, and filter multiple paths based on the minimum turning radius and maximum climbing grade of the vehicle to obtain multiple feasible paths; Count the congestion coefficients of each section in multiple feasible paths, and add up the estimated travel time to get the time cost; Count the number of construction closures along the route to obtain the safety cost; Obtaining feasible path length, vehicle fuel efficiency and slope data, and calculating total fuel consumption based on the feasible path length, vehicle fuel efficiency and slope data to obtain energy consumption cost; The time cost, safety cost and energy consumption cost are weighted and fused using time weight, safety weight and energy consumption weight respectively to obtain the weighted total cost value of each feasible path, and the feasible path with the smallest weighted total cost value is taken as the optimal driving path.

[0037] In an embodiment of the present invention, real-time road conditions, vehicle status, and heterogeneous data are integrated to find a balance solution among the conflicting goals of time, safety, and energy consumption. Information of different dimensions is quantified into a unified cost value through dynamic weighting to achieve an adaptive mapping of "scene perception-strategy generation". The weights are adjusted in real time with the road conditions and fuel status, solving the rigidity problem of fixed weight strategies.

[0038] Furthermore, the driving safety management method based on driving trajectory monitoring further includes the following steps: Step S104 : performing dynamic risk analysis and early warning on the target engineering vehicle based on the optimal driving path and the driving status data.

[0039] In an embodiment of the present invention, speeding is determined based on the optimal driving path and driving status data, and when speeding occurs, speeding levels are identified (including severe speeding, moderate speeding, and slight speeding, etc.) and warnings are issued. Road condition risk is determined based on the optimal driving path and driving status data, and when there is a road condition risk, risk warning information is generated. By broadcasting the risk warning information, target engineering vehicles are given road condition risk warnings (including reducing the speed limit in advance when the vehicle is about to enter a sharp bend or downhill section; issuing risk warnings when approaching a construction area or a mixed traffic area, etc.).

[0040] Specifically, in a preferred embodiment of the present invention, the dynamic risk analysis and early warning prompt for the target engineering vehicle based on the optimal driving path and the driving status data specifically includes the following steps: Performing speeding judgment based on the optimal driving path and the driving status data; When there is overspeed, it can identify and warn the speeding level; Performing road condition risk assessment based on the optimal driving path and the driving status data; Generate risk warning information when there is a road condition risk; The risk warning information is broadcasted to provide the target engineering vehicles with road risk warnings.

[0041] In a preferred embodiment of the present invention, the road condition risk assessment based on the optimal driving path and the driving status data specifically includes the following steps: Obtain the path point curvature and path point slope of the optimal driving path; According to the curvature of the path points, the risk of road curvature is calculated; Based on the slope of the path point, the slope risk is calculated; The static risk value of each path point is obtained by adding the road curvature risk and slope risk as the static risk value of the current path point; Obtain the vehicle's real-time speed and load, and calculate the speed modulation factor based on the vehicle's real-time speed and the current road safety speed limit; The risk of vehicle slipping is calculated by combining load and slope to obtain the load-slope coupling factor. Add the speed modulation factor and the load-slope factor to form the dynamic modulation coefficient of the current point; The static risk value of each path point is fused with the corresponding dynamic modulation coefficient to obtain the comprehensive risk value of each path point, and the road condition risk judgment is made based on the comprehensive risk value of each path point.

[0042] In this embodiment of the present invention, a static risk field is constructed by converting path geometric attributes (curvature, slope) into physical field strength. The greater the curvature or the steeper the slope, the stronger the field strength. Vehicle status (speed, load) serves as a "disturbance source." Exceeding speed amplifies the field strength, while the coupling of load and slope triggers nonlinear gain (e.g., exponentially increasing risk when climbing a slope with a full load). By superimposing the static field and dynamic disturbances, a comprehensive risk field is generated to assess road risk.

[0043] Furthermore, the driving safety management method based on driving trajectory monitoring further includes the following steps: Step S105 , updating and recording the driving status data, constructing a driving risk profile, and conducting periodic assessments on the target driver of the target engineering vehicle.

[0044] In an embodiment of the present invention, the driving status data is updated and recorded, the driving record data of the target engineering vehicle is obtained, and then the driving record data is identified using a machine learning algorithm to construct a driving risk profile and determine the driving assessment cycle. Then, according to the driving assessment cycle and the driving risk profile (generating multi-dimensional risk labels, such as sudden acceleration preference, frequent deviation, nighttime speeding tendency, etc.), the target driver of the target engineering vehicle is periodically assessed.

[0045] Specifically, in a preferred embodiment of the present invention, updating and recording the driving status data, constructing a driving risk profile, and performing periodic assessments on the target driver of the target engineering vehicle specifically include the following steps: Update and record the driving status data to obtain driving record data of the target engineering vehicle; Using machine learning algorithms to identify the driving record data and construct a driving risk profile; Determine the driving assessment cycle; According to the driving assessment cycle and the driving risk profile, a periodic assessment is conducted on the target driver of the target engineering vehicle.

[0046] Specifically, in a preferred embodiment of the present invention, the use of a machine learning algorithm to identify the driving record data and construct a driving risk profile specifically includes the following steps: Extract spatiotemporal trajectory features from driving record data, such as the frequency of sudden acceleration, the number of sharp turns, and the proportion of nighttime driving time. Obtain real-time vehicle load data, such as empty, half-loaded, and fully loaded. Generate an environmental risk heat map using the comprehensive risk value of each path point. Extract the behavior fluctuation index from the spatiotemporal trajectory characteristics to obtain the behavior index; identify the load jump event from the load data to obtain the load status; convert the environmental risk heat map into the regional risk level to obtain the risk area label; A dual-channel spatiotemporal convolutional neural network is constructed, where the first channel is sequentially provided with three layers of temporal convolution, a spatial attention layer, and a decoding layer; the second channel is sequentially provided with two layers of one-dimensional convolution, a transition detection layer, and a decoding layer; The behavioral fluctuation index is input into the first channel to analyze the behavioral characteristics and obtain the time location and deviation value of the abnormal behavioral event; The load state is input into the second channel for load dynamic analysis to obtain the load mutation time point and state transition intensity; When the first channel detects a timestamp of abnormal behavior, the second channel is immediately activated to query the load status at the same time, and the behavior deviation value of the first channel is multiplied by the load ratio of the second channel (current load / rated load) to generate the load impact factor; The load influencing factors are dynamically weighted through cross-channel attention gating to obtain cross-channel fusion weights; The high-order features of the first channel after three layers of temporal convolution and the high-order features of the second channel after two layers of one-dimensional convolution are dimensionally aligned, and then weighted fused using cross-channel fusion weights to obtain the fused spatiotemporal feature tensor. The fused spatiotemporal feature tensor is passed through two fully connected layers to obtain the load-behavior coupling coefficient sequence. Create a grid cell of preset size centered on the vehicle location, map the environmental risk heat map onto the grid cell, and obtain a location-bound behavior-environmental risk mapping table. The comprehensive risk value of each path point corresponding to each event in the behavior-environment risk mapping table is adjusted using the load-behavior coupling coefficient sequence to obtain a weighted risk behavior event list; The weighted risk behavior event list is aggregated and statistically analyzed to generate driving risk profiles across different dimensions. These dimensions include behavioral preferences derived by calculating the weighted frequency of each event type, environmental sensitivity derived by calculating the proportion of events in high-risk environments, and load coupling derived by comparing behavior frequencies under different load conditions.

[0047] In this embodiment, multi-source information fusion integrates the three-dimensional interaction of "behavior, load, and environment," upgrading single-dimensional risk detection to multi-dimensional collaborative judgment. (Behavioral anomalies themselves may not be high-risk, but when combined with high-risk loads and high-risk environments, the potential risks are significantly increased.) Furthermore, temporal convolution is used to capture behavioral patterns over long and short periods, spatial attention focuses on key behavioral areas, one-dimensional convolution specifically detects mutation points, and the transition detection layer precisely targets load changes, improving event detection accuracy. Furthermore, the timing of behavioral anomalies is aligned with load status, enabling physical attribution of behavioral risks (e.g., a "sharp turn with a full load" carries a much higher risk than a "sharp turn without a load"). A dynamic gating weight mechanism has also been designed. Through cross-channel attention gating, the "risk contribution" can be flexibly adjusted based on specific scenarios and time periods, avoiding the generalization limitations associated with static weights. Furthermore, the environmental risk heat map is used as spatial context to further weight behavioral events, enabling dynamic risk adjustment based on the risk of the same behavior in different environments. Finally, a multi-dimensional risk profile is output, which breaks down behavioral preferences (such as high incidence of sudden acceleration), environmental sensitivity (such as the proportion of events in high-risk areas), and load coupling (changes in heavy-load behavior), providing a data basis for accurate driver risk profiling.

[0048] Further, Figure 2 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0049] Among them, in another preferred embodiment provided by the present invention, a driving safety management system based on driving trajectory monitoring is applied to the above-mentioned driving safety management method based on driving trajectory monitoring. The system includes a driving status acquisition unit 101, a trajectory abnormality assessment unit 102, a dynamic driving guidance unit 103, a risk warning prompt unit 104 and a driving cycle assessment unit 105, wherein: The driving status collection unit is used to determine the target engineering vehicle and directly or collaboratively collect the driving status data of the target engineering vehicle.

[0050] The trajectory anomaly assessment unit is used to perform trajectory cleaning and reconstruction on the driving state data to generate smooth trajectory data, and perform anomaly assessment on the smooth trajectory data to obtain anomaly assessment data.

[0051] The dynamic driving guidance unit is used to receive real-time traffic data, plan an optimal driving path based on the real-time traffic data and the driving status data, and perform dynamic driving guidance based on the optimal driving path.

[0052] The risk warning prompt unit is used to perform dynamic risk analysis and early warning prompts on the target engineering vehicle based on the optimal driving path and the driving status data.

[0053] The driving cycle assessment unit is used to update and record the driving status data, construct a driving risk profile, and conduct periodic assessments on the target drivers of the target engineering vehicles.

[0054] It should be understood that, although the various steps in the flow chart of each embodiment of the present invention are shown in sequence according to the indication of the arrows, these steps are not necessarily performed in sequence according to the order indicated by the arrows. Unless otherwise specified herein, the execution of these steps is not strictly limited in order, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0055] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When executed, the program can include the processes of the above-described method embodiments. Any reference to memory, storage, database, or other media used in the various embodiments provided herein may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct RAMbus dynamic RAM (DRDRAM), and RAMbus dynamic RAM (RDRAM).

[0056] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0057] The above-described embodiments merely illustrate several implementations of the present invention, and while their descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art would be able to make numerous variations and improvements without departing from the spirit of the present invention, all of which fall within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be determined by the appended claims.

[0058] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A driving safety management method based on driving trajectory monitoring, characterized in that: The method specifically comprises the following steps: Identify the target engineering vehicle and directly or collaboratively collect the driving status data of the target engineering vehicle; performing trajectory cleaning and reconstruction on the driving state data to generate smooth trajectory data, and performing anomaly assessment on the smooth trajectory data to obtain anomaly assessment data; receiving real-time traffic data, planning an optimal driving route based on the real-time traffic data and the driving status data, and providing dynamic driving guidance based on the optimal driving route; Performing dynamic risk analysis and early warning on the target engineering vehicle based on the optimal driving path and the driving status data; Update and record the driving status data, construct a driving risk profile, and conduct periodic assessments on target drivers of the target engineering vehicles; The step of determining the target engineering vehicle and directly or collaboratively collecting the driving status data of the target engineering vehicle specifically includes the following steps: Determine the target engineering vehicles for driving safety management; Acquiring the transmission communication quality of the target engineering vehicle, and comparing the transmission communication quality with a preset standard communication quality; When the transmission communication quality is greater than the standard communication quality, directly collecting the driving status data of the target engineering vehicle; When the transmission communication quality is not greater than the standard communication quality, selecting a cooperative engineering vehicle and establishing a temporary communication connection between the target engineering vehicle and the cooperative engineering vehicle; The driving status data of the target engineering vehicle is collaboratively collected through the collaborative engineering vehicle.

2. The driving safety management method based on driving trajectory monitoring according to claim 1 is characterized in that: The step of performing trajectory cleaning and reconstruction on the driving state data to generate smooth trajectory data, and performing abnormality assessment on the smooth trajectory data to obtain abnormality assessment data specifically includes the following steps: Using Kalman filtering and / or Savitzky-Golay algorithm, performing trajectory cleaning on the driving state data to obtain cleaned state data; Performing trajectory smoothing reconstruction on the cleaning state data to generate smooth trajectory data; According to a plurality of abnormal driving conditions, abnormality evaluation is performed on the smooth trajectory data to obtain abnormality evaluation data.

3. The driving safety management method based on driving trajectory monitoring according to claim 2 is characterized in that: The use of Kalman filtering and Savitzky-Golay algorithm to clean the driving state data to obtain the cleaned state data specifically includes the following steps: The driving state data is cleaned by using Kalman filtering and Savitzky-Golay algorithm respectively to obtain the Kalman filtering results and Savitzky-Golay filtering results; Determine the acceleration threshold based on historical data statistics and vehicle type; obtain the absolute value of the acceleration at the current moment based on driving status data; Compare the absolute value of the current acceleration with the acceleration threshold. If the absolute value of the current acceleration is less than the acceleration threshold, the vehicle is judged to be in a stable state. If the absolute value of the current acceleration is greater than or equal to the acceleration threshold, the vehicle is judged to be in a violent motion state. According to the current driving state, different weights are assigned to the Kalman filter results and the Savitzky-Golay filter results to obtain the acceleration dynamic weight value at the current moment; Apply the sigmoid function to the current acceleration dynamic weight value for smooth transition to obtain the smoothed acceleration dynamic weight value; The Kalman filter results and Savitzky-Golay filter results are linearly fused using the smoothed acceleration dynamic weight value to obtain the current moment filtered data; The filtered data at each time point is gradually acquired in time series to obtain the cleaning status data.

4. The driving safety management method based on driving trajectory monitoring according to claim 3 is characterized in that: The step of performing abnormality evaluation on the smooth trajectory data according to the plurality of abnormal driving conditions and obtaining abnormality evaluation data specifically comprises the following steps: Set different abnormal driving states and assign corresponding benchmark thresholds to each abnormal driving state; Compare the abnormal driving state data corresponding to the smooth trajectory data with the benchmark threshold, and normalize the comparison results to obtain the basic score of each abnormal type; Obtain the acceleration vector at each time point from the smooth trajectory data, and calculate the trajectory dynamic change rate based on the acceleration vector at each time point; Set corresponding sensitivity coefficients for different abnormal driving conditions, perform weighted exponential calculations on the sensitivity coefficients and the trajectory dynamic change rate, and obtain index calculation results for different abnormal driving conditions; Normalize the index calculation results of different abnormal driving states to obtain the dynamic weights of different abnormal driving states; The basic scores of each abnormality type are weighted by the dynamic weights of different abnormal driving states to obtain the final scores of different abnormal driving states. The final scores of different abnormal driving states are summed to obtain the comprehensive abnormality score; The final scores of different abnormal driving states and the comprehensive anomaly scores are encapsulated and associated with the corresponding timestamps, vehicle identifications, and metadata to obtain anomaly assessment data.

5. The driving safety management method based on driving trajectory monitoring according to claim 4 is characterized in that: The receiving of real-time traffic data, combining the real-time traffic data with the driving status data, planning an optimal driving path, and performing dynamic driving guidance according to the optimal driving path specifically includes the following steps: Receive real-time traffic data; Planning an optimal driving route by combining the real-time traffic data and the driving status data; generating dynamic guidance information according to the optimal driving path; The dynamic guidance information is broadcasted to dynamically guide the target engineering vehicle.

6. The driving safety management method based on driving trajectory monitoring according to claim 5 is characterized in that: The planning of the optimal driving route by combining the real-time traffic data and the driving status data specifically includes the following steps: The congestion coefficient is calculated based on real-time traffic data, and the congestion coefficient is smoothly transitioned using an S-shaped function to obtain the time weight; Set the safety weight according to the time weight, and set the safety weight and the time weight to be complementary; Calculate the ratio of the remaining fuel volume to the total fuel tank volume based on the driving status data to obtain the energy consumption weight; Based on the vehicle location and target location, the road network topology data is used to generate multiple routes; Obtain the minimum turning radius and maximum climbing grade of the vehicle, and filter multiple paths based on the minimum turning radius and maximum climbing grade of the vehicle to obtain multiple feasible paths; Count the congestion coefficients of each section in multiple feasible paths, and add up the estimated travel time to get the time cost; Count the number of construction closures along the route to obtain the safety cost; Obtain feasible path length, vehicle fuel efficiency and slope data, and calculate total fuel consumption based on the feasible path length, vehicle fuel efficiency and slope data to obtain energy consumption cost; The time cost, safety cost and energy consumption cost are weighted and fused using time weight, safety weight and energy consumption weight respectively to obtain the weighted total cost value of each feasible path, and the feasible path with the smallest weighted total cost value is taken as the optimal driving path.

7. The driving safety management method based on driving trajectory monitoring according to claim 6 is characterized in that: The performing of dynamic risk analysis and early warning on the target engineering vehicle based on the optimal driving path and the driving status data specifically includes the following steps: Performing speeding judgment based on the optimal driving path and the driving status data; When there is overspeed, it can identify and warn the speeding level; Performing road condition risk assessment based on the optimal driving path and the driving status data; Generate risk warning information when there is a road condition risk; The risk warning information is broadcasted to provide the target engineering vehicles with road risk warnings.

8. The driving safety management method based on driving trajectory monitoring according to claim 7 is characterized in that: The road condition risk judgment based on the optimal driving path and the driving status data specifically includes the following steps: Obtain the path point curvature and path point slope of the optimal driving path; According to the curvature of the path points, the risk of road curvature is calculated; Based on the slope of the path point, the slope risk is calculated; The static risk value of each path point is obtained by adding the road curvature risk and slope risk as the static risk value of the current path point; Obtain the vehicle's real-time speed and load, and calculate the speed modulation factor based on the vehicle's real-time speed and the current road safety speed limit; The risk of vehicle slipping is calculated by combining load and slope to obtain the load-slope coupling factor. Add the speed modulation factor and the load-slope factor to form the dynamic modulation coefficient of the current point; The static risk value of each path point is fused with the corresponding dynamic modulation coefficient to obtain the comprehensive risk value of each path point, and the road condition risk judgment is made based on the comprehensive risk value of each path point.

9. The driving safety management method based on driving trajectory monitoring according to claim 8 is characterized in that: The updating and recording of the driving status data, the construction of a driving risk profile, and the periodic assessment of the target driver of the target engineering vehicle specifically include the following steps: Update and record the driving status data to obtain driving record data of the target engineering vehicle; Using machine learning algorithms to identify the driving record data and construct a driving risk profile; Determine the driving assessment cycle; According to the driving assessment cycle and the driving risk profile, a periodic assessment is conducted on the target driver of the target engineering vehicle.

10. A driving safety management system based on driving trajectory monitoring, the system being applied to the driving safety management method based on driving trajectory monitoring according to any one of claims 1 to 9, characterized in that: The system includes a driving status acquisition unit, a trajectory anomaly assessment unit, a dynamic driving guidance unit, a risk warning prompt unit, and a driving cycle assessment unit, wherein: A driving status collection unit is used to determine the target engineering vehicle and directly or collaboratively collect the driving status data of the target engineering vehicle; a trajectory anomaly assessment unit, configured to perform trajectory cleaning and reconstruction on the driving state data to generate smooth trajectory data, and perform anomaly assessment on the smooth trajectory data to obtain anomaly assessment data; A dynamic driving guidance unit, configured to receive real-time traffic data, plan an optimal driving route based on the real-time traffic data and the driving status data, and provide dynamic driving guidance based on the optimal driving route; a risk warning prompt unit, configured to perform dynamic risk analysis and provide warning prompts for the target engineering vehicle based on the optimal driving path and the driving status data; The driving cycle assessment unit is used to update and record the driving status data, construct a driving risk profile, and conduct periodic assessments on the target drivers of the target engineering vehicles.

Images