Road transportation government affair safety supervision and management method

Abstract

The invention discloses a road transportation government affair safety supervision and management method, and relates to the technical field of road transportation safety supervision data processing. The vehicle and road safety supervision and management method comprises the following steps: collecting passing driving dynamic information from any traffic observation device; the vehicle behavior monitoring device and the road surface state monitoring device are integrated, the vehicle driving behavior data and the road safety condition data are collected in real time, and the monitoring frequency is dynamically adjusted according to the space interval, the abnormal information and the historical data, so that the utilization efficiency of monitoring resources is improved, and the monitoring cost is reduced. The system collects historical data and real-time abnormal data of vehicle driving behaviors and road safety conditions, then a primary space and a secondary space are calculated through a calculation and analysis engine, corresponding correction coefficients are determined according to intervals and historical safety condition information, then the observation frequency of the monitoring device is adjusted, and the monitoring accuracy is improved. And resource allocation is optimized while the detection coverage rate of the system is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of road transportation safety supervision data processing, and specifically relates to a method for road transportation government affairs safety supervision and management. Background Art

[0002] Road transportation serves people's lives and production. What people need most is transportation safety. Road transportation safety management is closely related to the safety of the country and individuals' lives and property, and is closely related to the vital interests of the masses. The occurrence of each major traffic accident not only causes damage to thousands of families, but also causes damage to society. Once not handled properly, it will cause extremely bad negative impacts on society and lead to social instability.

[0003] Existing road transportation government affairs safety management systems mainly rely on fixed planned monitoring frequencies and lack flexibility in the face of changes in the road traffic environment. On the one hand, due to passive traffic conditions, areas with high density require more frequent monitoring, while areas with low density can reduce the monitoring frequency. Fixed frequencies cannot effectively cope with this difference. On the other hand, when emergencies or abnormal driving behaviors occur, the system cannot promptly increase the monitoring density, resulting in potential safety hazards being difficult to detect and respond to in a timely manner. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for road transportation government affairs safety supervision and management to solve the problems raised in the above background art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: A method for road transportation government affairs safety supervision and management, applicable to a road transportation government affairs safety supervision and management system, which is composed of multiple traffic monitoring devices and road condition monitoring devices. The traffic monitoring devices are used to collect vehicle driving behavior data, and the road condition monitoring devices are used to collect road safety condition data. The supervision and management method for vehicle and road safety includes:

[0006] Collect past driving dynamic information from any traffic observation device;

[0007] Capture current abnormal driving information provided by any traffic observation device that monitors abnormal driving conditions;

[0008] Collect historical safety condition information from any road surface condition monitoring device;

[0009] Obtain current abnormal safety condition information provided by any road surface condition monitoring device that monitors road safety anomalies.

[0010] As a specific solution of the technical solution of this application, the spatial and temporal interval considerations between the traffic observation device and the road surface condition monitoring device include:

[0011] Determine the primary spatial interval between the first traffic observation device and the second traffic observation device, and the secondary spatial interval between the first road surface monitoring device and the second road surface monitoring device;

[0012] Based on the primary spatial interval and the secondary spatial interval, calculate the first correction coefficient and the second correction coefficient respectively;

[0013] Use the first correction coefficient combined with past driving dynamic information to set the current observation frequency of the first traffic observation device;

[0014] Use the result of the second correction coefficient and the historical safety condition information to set the current observation frequency of the second traffic observation device;

[0015] Based on the current frequency of the first traffic observation device and the current observation frequency of the first road surface status monitoring device, adjust the observation frequencies of the corresponding devices respectively.

[0016] As a specific solution of the technical solution of the present application, the method for determining the correction coefficient based on the spatial interval includes:

[0017] Summarize the overall monitoring spatial intervals of all traffic monitoring devices and road status monitoring devices;

[0018] Based on the overall monitoring spatial interval, the primary spatial interval, and the secondary spatial reduction, obtain the first correction parameter and the second correction parameter;

[0019] Based on the preset correction parameter threshold and the specific values of the first correction parameter and the second correction parameter, complete the corresponding parameter acquisition.

[0020] As a specific solution of the technical solution of the present application, the method for processing based on abnormal driving information and safety condition information includes:

[0021] Classify based on the currently occurring abnormal driving behavior information and abnormal safety condition information to determine the abnormal category;

[0022] Based on the determined abnormal category, retrieve the corresponding third correction parameter and fourth correction parameter from the preset correction parameter threshold;

[0023] Based on the comprehensive consideration of the first correction parameter, the second correction parameter, the third correction parameter, and the fourth correction parameter, further adjust the monitoring frequency.

[0024] As a specific solution of the technical solution of the present application, the method for evaluating based on abnormal driving information and the current abnormal safety condition information includes:

[0025] Collect the past time series information associated with the current driving abnormal behavior records and real-time safety threat factors;

[0026] Map it to a two-dimensional plane based on historical information, construct a set of information data points, and perform linear slope averaging calculation or execute exponential curve approximation through the set of information data points to obtain the approximation degree;

[0027] Evaluate the approximation degree of the current information data point based on the calculated slope average value or approximation degree;

[0028] If the approximation degree is lower than a preset threshold, take corresponding measures to adjust the relevant calibration parameters.

[0029] As a specific solution of the technical solution of this application, the real-time monitoring and feedback method based on the traffic observation device and the road condition monitoring device includes:

[0030] Instantly capture the real-time monitoring information provided by the primary traffic monitoring device and the primary road condition sensor;

[0031] Evaluate the instant operation efficiency of the vehicle and the instant safety level of the road respectively based on the real-time monitoring information;

[0032] Determine the third calibration coefficient and the fourth calibration parameter based on the instant operation efficiency of the vehicle and the instant safety level of the road;

[0033] Dynamically adjust the monitoring frequency, and trigger a warning signal or send a notification message as needed.

[0034] As a specific solution of the technical solution of this application, it further includes constructing a road transportation safety risk prediction model, using vehicle driving behavior information and road safety condition information for potential risk prediction, and generating a risk warning report.

[0035] As a specific solution of the technical solution of this application, the construction of the road transportation safety risk prediction model includes:

[0036] Collect vehicle driving behavior data and road safety condition data from multiple sources to obtain a database;

[0037] Extract features or variables based on the database to obtain key information on vehicle driving behavior and road safety conditions;

[0038] Construct a road transportation safety risk prediction model based on the extracted features or variables.

[0039] A road transportation government affairs safety supervision and management system, which integrates several vehicle behavior monitoring devices and road surface condition monitoring devices. Each vehicle behavior monitoring device is responsible for capturing the driving dynamic information of the vehicle, and each road surface condition monitoring device focuses on collecting the safety condition information of the road. The system also includes a comprehensive data processing hub, and the data processing hub includes:

[0040] A data scraping module, responsible for extracting past record data and real-time abnormal data from the vehicle behavior monitoring device and the road condition monitoring device;

[0041] A calculation and analysis engine, responsible for calculating the first correction parameter and the second correction parameter, and based on the correction parameters and historical data, calculating the current monitoring requirement frequency, and evaluating the road transportation safety risk prediction model carried;

[0042] A management and control unit, used to calculate the monitoring requirement frequency, adjust the monitoring density of the vehicle behavior monitoring device and the road condition monitoring device, and activate the early warning system and the response measure execution process.

[0043] Compared with the prior art, the beneficial effects of the present invention are:

[0044] This road transportation government affairs safety supervision and management method integrates the vehicle behavior monitoring device and the road condition monitoring device, collects vehicle driving behavior data and road safety condition data in real time, and dynamically adjusts the monitoring frequency according to the spatial interval, abnormal information and historical data, so as to improve the utilization efficiency of monitoring resources. The system collects historical data and real-time abnormal data of vehicle driving behavior and road safety conditions, then uses the calculation and analysis engine to calculate the primary and secondary spaces, and determines the corresponding correction coefficients according to the interval and historical safety condition information, and then adjusts the observation frequency of the monitoring device to ensure that the system optimizes resource allocation while ensuring the detection coverage rate.

[0045] At the same time, the system also uses abnormal driving information and safety condition information to classify and analyze abnormal categories, and further adjusts the monitoring frequency according to the classification results. In addition, the system constructs a road transportation safety risk prediction model, predicts potential safety risks by analyzing vehicle driving behavior and road safety condition information, and generates a risk early warning report. Finally, through data residence, calculation and analysis, management and control, as well as risk prediction and alarm, the system can realize the factual monitoring, risk assessment and safety guarantee of road transportation, providing effective support for road transportation safety management. Description of the Drawings

[0046] Figure 1 It is a schematic flow chart of the supervision and management method for vehicle and road safety of the present invention;

[0047] Figure 2 It is a schematic flow chart of the road transportation safety risk prediction model of the present invention. Detailed Embodiments

[0048] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0049] It should be noted that in the description of the present invention, the orientation or positional relationship indicated by the terms "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. is based on the orientation or positional relationship shown in the accompanying drawings. It is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention.

[0050] In addition, it should be understood that for the convenience of description, the sizes of the various components shown in the accompanying drawings are not drawn according to the actual proportional relationship. For example, the thickness or width of some layers may be exaggerated relative to other layers.

[0051] It should be noted that similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined or described in one drawing, it will not be necessary to further discuss and describe it specifically in the description of the subsequent drawings.

[0052] As Figure 1 - Figure 2 shown, the present invention provides a technical solution: a method for the safety supervision and management of road transportation government affairs, which is applicable to the road transportation government affairs safety supervision and management system. The system consists of multiple traffic monitoring devices and road condition monitoring devices. The traffic monitoring devices are used to collect vehicle driving behavior data, and the road condition monitoring devices are used to collect road safety condition data. The method for the supervision and management of vehicle and road safety includes:

[0053] Collect the past driving dynamic information from any traffic observation device. In this application, through the monitoring cameras installed on traffic sections, image recognition technology is used to capture information such as the driving trajectory, speed, and vehicle type of vehicles. The radar principle is used to detect the running state of vehicles, and the speed, distance, and density of vehicles can be measured. At the same time, through the geomagnetic sensors buried underground, the passing and staying conditions of vehicles are sensed, which are used to count traffic flow and average speed and other information. The position, direction, and speed information of vehicles can also be recorded in real time through GPS. In areas that are difficult to reach, such as mountain roads or remote areas, in this application, drones equipped with cameras and sensors are used to collect traffic information;

[0054] Capture the current abnormal driving information provided by any traffic observation device that monitors abnormal driving conditions. It needs to be clear that in the embodiments of the present application, as can be seen from the foregoing, specific abnormal behaviors can be accurately identified through camera and sensor detection, such as speeding, driving in the wrong direction, illegal lane changing, running a red light, and illegal parking, etc., and the specific events and locations where the abnormal driving behaviors occur are also recorded, and the specific driving status of the vehicle when the abnormal behavior occurs is detected through cameras or sensors, such as the vehicle's speed, acceleration, and form trajectory.

[0055] Collect historical safety condition information from any road condition monitoring device. In this application, as can be seen from the previous text, by deploying a variety of sensors along the road to monitor the temperature, humidity, icing conditions and water depth of the road surface, the sensors can try to collect road condition data and store the data in a database to form historical safety condition information. It should also be clear that in this application, the road condition monitoring device is equipped with a wireless communication module for wirelessly transmitting the monitored data to a data processing center. The data processing center stores and manages the data for a long time, thereby accumulating rich historical safety condition information. As can be seen from the previous text, in areas that are difficult to cover or require flexible monitoring, drones are equipped with cameras and sensors to patrol in the air. The road images and sensor data collected by the drones are used to analyze the damage of the road surface, water accumulation, etc., and the information is stored as historical safety condition information.

[0056] Obtain the current abnormal safety condition information provided by any road condition monitoring device that detects road safety anomalies. It should be clear that the abnormal safety condition information collected by the monitoring device will be transmitted to the data processing center through the wireless communication module. In the platform, the data is processed and analyzed in real time to determine the severity of the abnormal situation, and generate corresponding warning information according to the preset rules and algorithms. It should also be clear that in this application, the vehicle status is monitored by OBD. In some cases, the vehicle can be used as a mobile road monitoring node. For example, the tire pressure sensor and suspension system of the vehicle can sense the unevenness of the road surface, and upload this information to the cloud or traffic monitoring system through the vehicle communication system to provide supplementary data for road condition monitoring.

[0057] The time and space interval considerations of the traffic observation device and the road surface condition monitoring device include:

[0058] Determine the primary spatial interval between the first traffic observation device and the second traffic observation device, and the secondary spatial interval between the first road surface monitoring device and the second road surface monitoring device. In the application, by collecting data such as traffic flow and vehicle speed, analyzing the spatiotemporal distribution characteristics of traffic flow, and using a graph convolutional neural network learning model to extract the spatial relationship characteristics between traffic observation points, thereby determining the reasonable spatial interval of the traffic observation devices, and calculating the appropriate spacing between traffic observation devices based on parameters such as the design speed of the road and the lane width, combined with the traffic flow characteristics. For example, in the method of observing the spatial average speed of highway traffic flow using a fixed-wing aircraft model, the actual length of the road in the photo taken by the aircraft model is calculated through the relative speed of the aircraft model flight speed and the road design vehicle, thereby determining the spatial interval of the traffic observation devices. It should also be clear that the secondary spatial interval is obtained, and the layout position of the road surface monitoring device is determined by monitoring the road surface structure type. For example: for a composite road surface structure, the angle between the first type of optical fiber sensor and the center line of the monitored road surface is a preset angle, thereby determining its layout position, and then obtaining the lateral distribution characteristic information of the lane vehicle wheel tracks of the monitored road surface, and using the double Gaussian distribution algorithm to determine the layout position of the second type of optical fiber sensor, refer to the design specifications and scope of the road surface monitoring system, such as through the method of determining the sensor layout position, combined with the road surface structure type and the vehicle wheel track root characteristics, to reasonably determine the spatial interval of the road surface monitoring device.

[0059] Based on the primary spatial interval and the secondary spatial interval, the first correction coefficient and the second correction coefficient are calculated respectively. In the application embodiment, the first correction coefficient is obtained, and the correction coefficient is calculated according to the changes in traffic flow and vehicle speed in the primary spatial interval. For example: the correction method in the practical traffic flow model is estimated by multiplying the measured average basic saturated flow by the correction coefficient of each influencing factor. If the traffic flow or speed in the primary spatial interval deviates from the standard value, the prediction result of the model is corrected by adjusting the correction coefficient. In traffic signal control, the correction coefficient is calculated by the signal control parameters in the primary spatial interval, such as phase duration, green light time and actual traffic conditions. For example: in the calculation of saturated flow, lane width correction coefficients, slope and large vehicle correction coefficients, etc. are used. The correction coefficient can be adjusted according to the actual traffic conditions and road conditions. In the present application, a correction coefficient is calculated to obtain a second correction coefficient based on the pavement structure type and material properties within the secondary spatial interval. For example, in road detection, the calculation of the pavement structure strength index PSSI involves correction coefficients for different pavement structure types. The coefficient is determined based on the strength, stiffness and other properties of the pavement material. At the same time, the correction coefficient is calculated based on the pavement disease conditions and maintenance history within the secondary spatial interval. For example, if there are many cracks, potholes and other diseases in the secondary spatial interval, the correction coefficient can be adjusted according to the severity of the disease and the repair effect to reflect the actual situation of the road surface.

[0060] Using the first correction coefficient and combining with past driving dynamic information, set the current observation frequency of the first traffic observation device. By collecting past driving dynamic information from the historical data of the traffic observation device, including vehicle speed, driving trajectory, and traffic flow, and then extracting features from the collected past driving dynamic information to identify periodic change features of traffic flow, vehicle behavior patterns, etc. According to the features of the past driving dynamic information and the first correction coefficient, establish a correction model. The first correction coefficient is used to adjust the model parameters to reflect the current traffic condition. Then, according to the change trend and abnormal situation of the past driving dynamic information, dynamically adjust the first correction coefficient. For example, if traffic congestion frequently occurs in the past data, the correction coefficient can be increased to improve the monitoring frequency, and using the corrected model, calculate the current monitoring frequency of the first traffic observation device. By adopting time series analysis methods, combining the correction coefficient and the autocorrelation of past data to predict the current monitoring frequency, and dynamically adjust the monitoring frequency according to the continuous update of real-time monitoring data and the first correction coefficient. For example, during traffic peak hours or special times, the detection frequency can be increased to obtain more detailed traffic information.

[0061] Using the second correction coefficient and combining with historical safety condition information, set the current observation frequency of the second traffic observation device. In the embodiment of the present application, collect historical safety condition information from the historical data of the road surface state monitoring device, including road surface temperature, humidity, icing condition, water accumulation depth, and road surface damage condition, and extract features from the collected historical safety condition information to identify the change trend and potential risk factors of the road surface condition. For example, analyze the change rules of the road surface under different seasons and weather conditions, and the development process of road surface diseases. According to the features of the historical safety condition information and the second correction coefficient, establish a correction model. The second correction coefficient is used to adjust the model parameters to reflect the impact of the current road surface condition on traffic observation requirements, and dynamically adjust the second correction coefficient through the change trend and abnormal situation of the historical safety condition information. For example, if historical data shows that a certain section of the road is prone to icing in winter, the correction coefficient can be increased to improve the observation frequency.

[0062] Based on the current frequency of the first traffic observation device and the current observation frequency of the first road surface condition monitoring device, the observation frequencies of the corresponding devices are adjusted respectively. In this application, as can be seen from the foregoing, by collecting and analyzing data at the current observation frequencies of the first traffic observation device and the first road surface condition monitoring device, through data analysis and performance evaluation, the deficiencies of the current observation frequencies are identified. For example, the data of the traffic observation device during peak hours is not detailed enough, or the data update of the road surface monitoring device in bad weather is not timely enough. According to the identified deficiencies, adjustment targets are set. For example, increase the observation frequency of the traffic observation device during peak hours to monitor traffic flow changes. Then, using historical data and real-time data, combined with data-driven methods, predict the data quality and device performance at different observation frequencies. For example, by analyzing historical traffic flow data, predict the accuracy of traffic flow monitoring at different observation frequencies. According to preset rules and standards, calculate the adjusted observation frequency. If the road surface condition is poor or the traffic flow is large, the observation frequency can be increased according to the preset rules. At the same time, in order to avoid too much impact on the system, the observation frequency can be adjusted gradually. For example, first slightly increase the observation frequency, observe the data and device performance for a period of time, and then make further adjustments according to the actual situation. During the adjustment process, monitor the performance and data quality of the device in real time, and timely feedback the adjustment effect. If the adjusted observation frequency can significantly improve the data quality and device performance, continue to execute; otherwise, it is necessary to re-evaluate and adjust.

[0063] The method for determining the correction coefficient based on the spatial interval includes:

[0064] Summarize the overall monitoring spatial intervals of all traffic monitoring devices and road condition monitoring devices. It should be clear that in the embodiments of this application, the data collected from traffic monitoring devices and road condition monitoring devices are subjected to formatted standard processing for data integration and analysis. For example: unify the location information of all devices into the format of longitude and latitude coordinates, use a data integration platform to integrate the standardized data, correlate and fuse data from different sources to form a complete monitoring device spatial distribution database. By calculating the distances between adjacent traffic monitoring devices and road condition monitoring devices, obtain the spatial intervals between them. Use GIS software for spatial analysis, calculate the distances between each monitoring device, and then summarize the spatial intervals between all monitoring devices to obtain the overall monitoring spatial interval. Statistical indicators such as average spatial interval, maximum spatial interval, and minimum interval can be calculated to understand the spatial distribution of the monitoring devices and conduct in-depth analysis of the overall monitoring spatial interval to identify monitoring blind spots and overlapping areas. For example: if the intervals between monitoring devices in a certain area are too large, there may be monitoring blind spots; if the monitoring ranges of multiple monitoring devices overlap, there may be a waste of resources. According to the analysis results, optimize and adjust the layout of the monitoring devices, add monitoring devices in the monitoring blind spots, and reduce the number of monitoring devices in the overlapping areas to improve the monitoring efficiency and coverage.

[0065] Based on the overall monitoring spatial interval, primary spatial interval, and secondary spatial interval, obtain the first correction parameter and the second correction parameter. In this application, analyze the relationship between the overall monitoring spatial interval and the primary spatial interval. If the primary spatial interval is small, it indicates that the monitoring in key traffic areas is relatively dense, and it may be necessary to adjust the parameters of the observation device to adapt to a higher data collection frequency. According to the analysis results, establish a correction model. For example: the correction method of the traffic flow model can be adopted. By analyzing the dynamic information of past driving, determine the correction parameters under different spatial intervals. Use the correction model, combined with the primary spatial interval and the overall monitoring spatial interval, to calculate the first correction parameter. This parameter is used to adjust the observation frequency or data collection accuracy of the traffic observation device to ensure the monitoring effect in key areas. In the embodiments of this application, obtain the second correction parameter by analyzing the impact of the secondary spatial interval on the road surface condition monitoring. A relatively large secondary spatial interval may lead to insufficient timely detection of certain road surface diseases or abnormal conditions. According to the requirements of road surface condition monitoring, establish a correction model. By analyzing the changes in parameters such as road surface temperature and humidity, determine the correction parameters, and use the correction model, combined with the secondary spatial interval and the overall monitoring spatial interval, to calculate the second correction parameter. This parameter is used to adjust the monitoring frequency or data collection accuracy of the road surface condition monitoring device to improve the monitoring ability of road surface abnormal conditions.

[0066] Based on the preset correction parameter threshold, and the specific values ​​of the first correction parameter and the second correction parameter, the corresponding parameter acquisition is completed. According to the relevant traffic monitoring and road state monitoring standards, the threshold of the correction parameter is determined. For example, in the traffic state evaluation, the speed threshold and saturation threshold under different traffic conditions can be referred to. In this application, the traffic flow threshold can be set to 1,000 vehicles per hour. When the actual flow exceeds the threshold, the monitoring parameters need to be adjusted. The road surface temperature threshold is set to -5 degrees Celsius or 40 degrees Celsius. When the actual temperature exceeds the threshold, the monitoring frequency needs to be adjusted. Then, according to the current frequency of the traffic monitoring device and the past driving dynamic information, the specific data of the first correction parameter is calculated, and then the data is compared with the preset correction parameter threshold. If the value of the first correction parameter exceeds the preset threshold, it means that the current monitoring frequency may be too high or too low and needs to be adjusted. For example, if the traffic flow is large and the first correction parameter exceeds the threshold, the monitoring frequency can be appropriately increased.

[0067] The method for processing abnormal driving information and safety condition information includes:

[0068] Based on the current abnormal driving behavior information and abnormal safety status information, the abnormal category is determined; as mentioned above, real-time data is collected through traffic monitoring devices and road status monitoring devices, and deep learning algorithms are used for classification. The classification model is trained using historical data. The historical data contains different types of abnormal time and their characteristics. The feature vectors of the currently collected abnormal driving behavior information and abnormal safety status information are input into the trained classification model, and the model will output the category of abnormal time. For example: abnormal driving may be classified as speeding, driving in the wrong direction, illegal lane change, etc. Abnormal safety conditions may be classified as icy road surface, excessive water accumulation, etc.

[0069] Based on the determined abnormality category, the corresponding third correction parameter and fourth correction parameter are retrieved from the preset correction parameter threshold; the determined abnormality category is used as input to retrieve the preset correction parameter threshold table. The table contains the threshold ranges of the third correction parameter and the fourth correction parameter corresponding to each abnormality category, and the retrieved third correction parameter and the fourth correction parameter are used to adjust the parameters of the corresponding traffic monitoring device and the road state monitoring device. For example: if the retrieved third correction parameter indicates that the monitoring frequency needs to be increased, the observation interval of the device is adjusted accordingly. After adjusting the parameters, the performance and data quality of the monitoring device are monitored in real time to verify whether the adjustment effect reaches the expected goal. If the effect is not ideal, the correction parameters are further optimized.

[0070] Based on a comprehensive consideration of the first correction parameter, the second correction parameter, the third correction parameter, and the fourth correction parameter, the monitoring frequency is further adjusted. It should be clear that, first, different weights are assigned to the first correction parameter, the second correction parameter, the third correction parameter, and the fourth correction parameter according to the importance of the impact of each correction parameter on the monitoring frequency. For example: the first correction parameter mainly reflects the impact of traffic flow on the monitoring frequency, while the third correction parameter mainly reflects the impact of road icing on the monitoring frequency. Different weights can be assigned according to the actual situation. Multiply each correction parameter by its corresponding weight and then sum them to obtain a comprehensive score, which reflects the comprehensive demand for the monitoring frequency in the current monitoring environment. Then, different monitoring frequency adjustment rules are set according to the range of the comprehensive score. For example: if the comprehensive score is relatively low, it indicates that the current monitoring environment is relatively stable, and the monitoring frequency can be appropriately reduced. If the comprehensive score is relatively high, it indicates that the current monitoring environment is relatively complex or there are significant risks, and the monitoring frequency needs to be increased. And the calculation is performed through the set frequency adjustment formula:

[0071]

[0072] Among them, the basic monitoring frequency is the monitoring frequency under normal circumstances, and the score threshold is a preset reference value.

[0073] Then, according to the comprehensive score and the adjustment rules, the monitoring frequency of the monitoring device is adjusted. For example: the comprehensive score is 80, the score threshold is 100, and the basic monitoring frequency is 10 times per minute, then the new monitoring frequency can be adjusted to 18 times per minute.

[0074] The evaluation method based on abnormal driving information and current abnormal safety status information includes:

[0075] Collect past time series information associated with current driving abnormal behavior records and real-time safety threat factors; as can be seen from the previous text, the real-time monitoring data and past time series information are integrated to form a comprehensive data set, and then a machine learning algorithm is used to train the data set to establish an early warning model. The model can identify potential driving abnormal behaviors and safety threats, and input the real-time monitoring data and past time series information into the early warning model. The model judges whether there are potential risks according to the preset threshold. When an abnormality is detected, the model will trigger the early warning mechanism, and directly send early warning information to the driver through the in-vehicle display screen and voice prompt system, reminding them to pay attention to their driving behavior, and send the early warning information to the monitoring platform of the traffic management department. Relevant departments can take corresponding intervention measures according to the early warning information, such as adjusting traffic lights, dispatching rescue vehicles, etc. It should also be clear that the early warning system is configured with multi-dimensional early warning indicators, such as vehicle status, driver behavior, road surface conditions, etc., to ensure the comprehensiveness and accuracy of the early warning.

[0076] Map based on historical information to a two-dimensional plane, construct a set of information data points, and perform linear slope averaging or execute exponential curve approximation through the set of information data points to obtain the approximation degree; extract and analyze variables related to the target from historical data, with time as the X-axis and the corresponding tube test as the Y-axis, such as vehicle speed, road surface temperature, etc., map the extracted data points to the two-dimensional plane to form a set of data points, each data point corresponding to a time point and an observed value, form an ordered set of data points from the data points mapped to the two-dimensional plane, and use the linear regression slope calculation formula, i.e., the slope

[0077] Among them, and are the abscissa and ordinate values of the i-th data segment respectively, and are the mean values of the abscissa and ordinate respectively.

[0078] Select an exponential function model, such as , where a and b are undetermined parameters, use the least squares method, evaluate the model parameters a and b according to the set of data points, and make the fitting degree of the practical model curve and the data points the highest, evaluate the approximation degree of the exponential curve by calculating the fitting error to obtain the approximation degree. Evaluate the approximation degree of the current information data point with the calculated average slope or approximation degree; compare the calculated average slope with the slope of the exponential model to evaluate the approximation degree of the model to the data. If the average slope is close to the model slope, it indicates that the model fits well. If the approximation degree is lower than the preset threshold, take corresponding measures to adjust the relevant correction parameters. As can be seen from the previous text, the approximation degree is evaluated by calculating the fitting error, and the calculation formula is:

[0079]

[0080] where yi is the value of the actual data point, is the value predicted by the model.

[0081] Compare the calculated fitting error with the preset threshold. If the error is lower than the threshold, it indicates that the approximation degree of the current model is good enough and the correction parameters do not need to be adjusted. If the error is higher than the threshold, adjustment is required. If the approximation degree is insufficient, increase the monitoring frequency to collect data more frequently and improve the fitting accuracy of the model. For example, adjust the monitoring frequency from once a minute to once every 30 seconds. According to the above measures, adjust the correction parameters and run the model again, and calculate the fitting error of the adjusted model again to verify whether the adjustment effect reaches the expected goal. If the error is still higher than the threshold, continue to adjust until the approximation degree meets the requirements.

[0082] The instant monitoring and feedback method based on the traffic observation device and the road condition monitoring device includes:

[0083] Instantaneously capture the real-time monitoring information provided by the primary traffic monitoring device and the primary road condition sensor; as can be seen from the foregoing, in this application, cameras and sensors are used for monitoring, which is prior art and will not be elaborated herein.

[0084] Based on the real-time monitoring information, respectively evaluate the instant operation efficiency of the vehicle and the instant safety level of the road; in the embodiments of this application, use the vehicle operation efficiency data analysis index system to evaluate the instant operation efficiency of the vehicle. It includes average fuel consumption, operation cost, vehicle utilization rate, failure rate, etc. For example: by calculating the average speed and fuel consumption of the vehicle within a specific time period and combining with the driving mileage, evaluate the fuel economy and operation efficiency of the vehicle.

[0085] Based on the instant operation efficiency of the vehicle and the instant safety level of the road, determine the third correction coefficient and the fourth correction parameter. According to the evaluation result of the vehicle operation efficiency, calculate the third correction coefficient. For example: if the average speed of the vehicle is lower than a certain threshold, a correction coefficient can be increased to improve the sensitivity of the monitoring device. According to the evaluation result of the road safety level, determine the fourth correction parameter. For example, if the road is slippery, adjust the parameters of the monitoring device so that it can detect the sliding condition of the vehicle.

[0086] In this application, it also includes constructing a road transportation safety risk prediction model, using vehicle driving behavior information and road safety condition information to conduct potential risk prediction, and generating a risk warning report. The construction of the road transportation safety risk prediction model includes the following steps:

[0087] Collect vehicle driving behavior data and road safety condition data from multiple sources to obtain a database; as can be seen from the foregoing, in this application, cameras and sensors are used to obtain vehicle driving behavior data and road safety condition data from multiple sources and form a database, which is prior art and will not be elaborated herein.

[0088] Extract features or variables based on a database to obtain key information on vehicle driving behavior and road safety conditions. Extract the average speed, maximum speed, and speed fluctuations of the vehicle from the database, and use these features to reflect the driving style of the driver and the operating state of the vehicle. Analyze the vehicle's driving trajectory data, extract trajectory-related features, and use them to evaluate the driving stability of the vehicle and the driving ability of the driver. Frame driving behavior indicators such as the number of hard accelerations, the number of hard decelerations, and the frequency of fatigue driving. For example: Set a speed change threshold to count the number of hard accelerations and hard decelerations, and then extract features such as road surface temperature, humidity, and icing conditions from the database to reflect the safety conditions of the road surface. Analyze traffic flow data, extract traffic flow density and traffic flow change trend features, and use them to evaluate the congestion level of the road and potential safety risks. Use the traffic accident dataset to extract accident-prone sections, accident type distributions, and accident severity levels, and use them to identify high-risk areas and formulate safety measures. Based on the extracted features or variables, construct a road transportation safety risk prediction model.

[0089] Although the embodiments of the present invention have been shown and described, it will be understood by those of ordinary skill in the art that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended embodiments and their equivalents.

Claims

1. A road transport government safety supervision and management method, applicable to a road transport government safety supervision and management system, the system is composed of a plurality of traffic monitoring devices and road condition monitoring devices, the traffic monitoring devices are used to collect vehicle driving behavior data, and the road condition monitoring devices are used to collect road safety status data, characterized in that: The method for supervising and managing vehicle and road safety comprises the following steps: Collect past driving dynamic information from any traffic observation device; Capturing current abnormal driving information provided by any traffic observation device that detects abnormal driving conditions; Collect historical safety condition information from any pavement condition monitoring device; Acquire current abnormal safety condition information provided by any road surface condition monitoring device that detects road safety abnormality.

2. A road transport government affairs safety supervision and management method according to claim 1, characterized in that: The spatial interval consideration between the traffic observation device and the road surface condition monitoring device includes the following steps: determining a primary spatial separation between the first traffic observation device and the second traffic observation device, and a secondary spatial separation between the first road surface monitoring device and the second road surface monitoring device; Based on the primary spatial interval and the secondary spatial interval, respectively, a first correction coefficient and a second correction coefficient are calculated; Using the first correction coefficient in combination with past driving dynamic information, setting the current observation frequency of the first traffic observation device; Using the second correction coefficient result historical safety condition information, setting the current observation frequency of the second traffic observation device; Based on the current frequency of the first traffic observation device and the current observation frequency of the first road condition monitoring device, the observation frequencies of the corresponding devices are adjusted respectively.

3. A road transport government affairs safety supervision and management method according to claim 1, characterized in that: The method for determining the correction coefficient based on the spatial interval includes: Summarize the overall monitoring space intervals of all traffic monitoring devices and road status monitoring devices; Obtaining a first correction parameter and a second correction parameter based on the overall monitoring space interval, the primary space interval, and the secondary space weight loss; Based on the preset correction parameter threshold, and the specific values ​​of the first correction parameter and the second correction parameter, corresponding parameter acquisition is completed.

4. A road transport government affairs safety supervision and management method according to claim 1, characterized in that: The method for processing abnormal driving information and safety condition information includes: Based on the current abnormal driving behavior information and abnormal safety status information, the abnormal category is determined; Based on the determined abnormality category, the corresponding third correction parameter and fourth correction parameter are retrieved from a preset correction parameter threshold; Based on comprehensive consideration of the first correction parameter, the second correction parameter, the third correction parameter and the fourth correction parameter, the monitoring frequency is further adjusted.

5. A road transport government affairs safety supervision and management method according to claim 1, characterized in that: The evaluation method based on abnormal driving information and current abnormal safety status information includes: Collecting past time series information associated with current abnormal driving behavior records and real-time safety threat factors; Based on the mapping of historical information to a two-dimensional plane, a set of information data points is constructed, and a linear slope average calculation or exponential curve approximation is performed through the set of information data points to obtain the degree of approximation; The calculated slope average or approximation is used to evaluate the approximation of the current information data point; If the approximation degree is lower than a preset threshold, corresponding measures are taken to adjust the relevant correction parameters.

6. A road transport government affairs safety supervision and management method according to claim 1, characterized in that: The instant monitoring and feedback method based on the traffic observation device and the road state monitoring device includes: Instantly capture the real-time monitoring information provided by the primary traffic monitoring device and the primary road status sensor; Based on real-time monitoring information, the vehicle's instant operating efficiency and the road's instant safety level are evaluated respectively; determining a third correction coefficient and a fourth correction parameter based on the instantaneous operating efficiency of the vehicle and the instantaneous safety level of the road; Dynamically adjust the monitoring frequency and trigger early warning signals or send notification information as needed.

7. A road transport government affairs safety supervision and management method according to claim 1, characterized in that: The method also includes constructing a road transport safety risk prediction model, using vehicle driving behavior information and road safety status information to predict potential risks, and generating a risk warning report.

8. A road transport government affairs safety supervision and management method according to claim 1, characterized in that: The method of constructing a road transportation safety risk prediction model comprises the following steps: Collect vehicle driving behavior data and road safety status data from multiple sources to obtain a database; Extract features or variables based on the database to obtain key information on vehicle driving behavior and road safety conditions; Based on the extracted features or variables, a road transport safety risk prediction model is constructed.

9. A road transport government safety supervision and management system, the system integrates a number of vehicle behavior monitoring devices and road surface status monitoring devices, each vehicle behavior monitoring device is responsible for capturing vehicle driving dynamic information, while each road surface status monitoring device focuses on collecting road safety condition information, the system also includes a comprehensive data processing hub, characterized in that: The data processing hub includes: The data capture module is responsible for extracting past recorded data and real-time abnormal data from the vehicle behavior monitoring device and the road condition monitoring device; The calculation and analysis engine is responsible for calculating the first correction parameter and the second correction parameter, and calculating the current monitoring demand frequency based on the correction parameters and historical data, and evaluating the road transportation safety risk prediction model on board; The management and control unit is used to calculate the monitoring demand frequency, adjust the monitoring density of the vehicle behavior monitoring device and the road condition monitoring device, and activate the early warning system and the response measure execution process.

Images