Transportation safety supervision system based on data analysis

Abstract

The invention discloses a traffic transportation safety supervision system based on data analysis, which relates to the technical field of traffic safety and comprises a data analysis module, a configuration acquisition module, a risk management and control module and a terminal interaction module, calculating a non-traffic flow factor influence degree in the traffic risk to obtain a recessive anomaly degree; the configuration acquisition module is used for sorting the recessive anomalies corresponding to the sub-road sections to obtain set coordinates of the multi-dimensional sensor and acquiring road section traffic data; the risk management and control module is used for calculating road section traffic data to obtain a traffic risk value corresponding to each sub road section, performing classification processing on the traffic risk values through an FCM clustering algorithm to obtain a self-adaptive risk level interval and performing traffic supervision; the display interaction unit is used for providing a display interface for a user and storing historical data. The cost is reduced, and accurate quantitative judgment and hierarchical supervision are realized by combining quantitative analysis.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic safety, and in particular to a transportation safety supervision system based on data analysis. Background Art

[0002] In recent years, road transport has maintained its crucial position in the logistics and express delivery industry. Thanks to innovative breakthroughs in information technologies like artificial intelligence and big data, the intelligence of transportation safety monitoring has continued to improve. In practical applications, the collection of multi-dimensional, comprehensive traffic data effectively supports the monitoring of transport vehicle safety. However, my country's highways are characterized by their long mileage, high density, and large scale of non-highway roads. Due to cost constraints and other factors, it is difficult for many regions to fully deploy high-precision monitoring sensors on all road sections.

[0003] Currently, a Chinese invention patent application with application number CN202311308097.8 discloses a transportation industry safety supervision system. This application includes: a data subsystem, a safety analysis subsystem, and a display subsystem. The safety analysis subsystem includes a monitoring module, a retrieval module, an analysis module, and an evaluation module. The data subsystem provides the analysis data source to the safety analysis subsystem. The monitoring module monitors business data, vehicle data, and employee behavior data to obtain monitoring data. The retrieval module calls the analysis data source and sends it to the analysis module for safety analysis to obtain analysis data. The evaluation module evaluates transportation hazards and hazard trends to obtain evaluation data. Finally, the display subsystem displays the evaluation data on a large screen. The system can monitor businesses, vehicles, and employees, and analyze and evaluate transportation safety hazards and hazard trends. Enterprises and traffic management departments can then investigate safety hazards and trends to avoid security vulnerabilities. However, this application lacks quantitative data analysis when processing detection data, insufficient data utilization, and lacks accurate predictions for transportation safety supervision. Summary of the Invention

[0004] The technical problem addressed by the present invention is that existing technologies rely on comprehensive, multi-dimensional traffic data for transportation safety supervision. However, in actual applications, due to factors such as cost, supervisors find it difficult to fully deploy high-precision monitoring sensor equipment at all traffic nodes and can only selectively collect data on certain road sections. Existing technologies lack research on how to deploy multi-dimensional sensors, and location selection relies heavily on personnel experience. There is insufficient utilization of historical transportation accident data, and the system fails to conduct multimodal data analysis of transportation from a holistic perspective and explore hidden safety risk factors. Furthermore, the processing of detection data lacks quantitative data calculation and analysis, and predictions for transportation safety supervision are lacking.

[0005] To solve the above technical problems, the present invention provides the following technical solutions, including: a data analysis module, a configuration collection module, a risk management module and a terminal interaction module;

[0006] The data analysis module is used to perform primary and secondary divisions on the target road to obtain a set of sub-segments. Based on the sub-segment set, the influence of non-traffic flow factors on traffic risk is calculated to obtain the implicit anomaly degree.

[0007] The configuration acquisition module is used to sort the implicit anomaly degrees corresponding to each sub-road section to obtain the setting coordinates of the multi-dimensional sensor, configure the multi-dimensional sensor based on the setting coordinates and collect the road section traffic data;

[0008] The risk control module is used to calculate the traffic data of the road section to obtain the traffic risk value corresponding to each sub-section, classify the traffic risk value through the FCM clustering algorithm to obtain the adaptive risk level interval, and perform traffic supervision based on the adaptive risk level interval;

[0009] The display interaction unit is used to provide a display interface to the user, receive user operation instructions and store historical data.

[0010] Preferably, the data analysis module includes a road segment division unit and an abnormality calculation unit;

[0011] The road segmentation unit is used to segment the target road into a set of sub-segments, with a primary division based on traffic flow direction and number of lanes, and a secondary division based on length;

[0012] The processing logic of the first division includes:

[0013] Divide the target road into one-way lane sections and two-way lane sections according to traffic flow direction;

[0014] Divide the one-way lanes in the target road into primary road segments;

[0015] Two-way lane sections are divided based on the number of lanes. Two-way lanes with four or fewer lanes are classified as intermediate sections, and two-way lanes with more than four lanes are classified as advanced sections.

[0016] The processing logic of the secondary division includes:

[0017] The primary road sections are divided into equal intervals based on the preset first road length, the intermediate road sections are divided into equal intervals based on the preset second road length, and the advanced road sections are divided into equal intervals based on the preset third road length. The divided sections are merged and the indexes are added to each of them to obtain a sub-section set.

[0018] Preferably, the abnormality calculation unit is used to calculate the comprehensive risk generated by non-traffic flow factors to obtain the implicit abnormality, and the processing logic includes:

[0019] Counting historical road data to obtain the number of accidents and average traffic flow data corresponding to each sub-section in the sub-section set, sorting the number of accidents corresponding to each sub-section in ascending order and assigning a rank to obtain the number of accidents rank corresponding to each sub-section, and sorting the average traffic flow data corresponding to each sub-section in ascending order and assigning a rank to obtain the traffic flow rank corresponding to each sub-section;

[0020] The rank difference data set is obtained by subtracting the rank of the number of accidents and the rank of the traffic flow corresponding to each sub-section. The explicit correlation of accidents is calculated using the Spearman correlation coefficient formula and the rank difference data set. The implicit anomaly degree is calculated based on the explicit correlation of accidents. The calculation expression is:

[0021]

[0022] SI=e -ρ ;

[0023] Among them, ρ represents the explicit correlation of accidents, d represents the rank difference, k represents the sub-section number, K represents the total number of sub-sections, SI represents the implicit abnormality, and e represents the natural constant.

[0024] Preferably, the configuration acquisition module includes a position allocation unit and a data acquisition unit;

[0025] The position allocation unit is used to sort the implicit abnormality values ​​corresponding to each sub-section in the sub-section set, and arrange them in descending order to obtain a priority sequence;

[0026] Based on the number of multi-dimensional sensors and the priority sequence, the midpoint position of each sub-section is marked in turn to obtain the configuration coordinate data.

[0027] Preferably, the data collection unit is used to collect road section traffic data, which includes operation data, vehicle data, road surface data and environmental data;

[0028] The operating data includes traffic flow data and road condition data, the vehicle data includes basic vehicle information and operating status data, the road surface data includes road geometric characteristics, surface conditions and traffic facility data, and the environmental data includes weather conditions and road surrounding environment data.

[0029] Preferably, the traffic flow data includes vehicle volume, lane occupancy and vehicle density, and the road condition data includes vehicle speed dispersion, overspeed rate and proportion of high-risk vehicles;

[0030] The basic vehicle information includes vehicle type, vehicle model, engine information and fuel type, and the vehicle identity information is obtained through the vehicle-mounted device RFID;

[0031] The operating status data includes real-time data of vehicle speed, driving route, engine status, vehicle braking system and vehicle steering system;

[0032] The road geometric characteristics include the width, length, slope and curvature of the road;

[0033] The surface condition includes the surface condition of the road, and the surface condition includes smoothness, potholes, cracks and wear ratio;

[0034] The traffic facility data includes the working status and location coordinates of traffic signs, traffic lights, roadblocks and isolation belts;

[0035] The weather condition obtains real-time weather data through meteorological sensors, and the real-time weather data includes temperature, humidity, wind speed, precipitation, visibility and air pressure;

[0036] The road surrounding environment data includes the number of intersections, driving sight distance and the integrity rate of guardrail markings.

[0037] Preferably, the risk management and control module includes a risk calculation unit and a classification management and control unit;

[0038] The risk calculation unit is used to calculate the traffic data of the road section to obtain the traffic risk value corresponding to each sub-section. The processing logic includes:

[0039] Based on the preset reference threshold set, the road section traffic data is assigned and coded to obtain the initial indicator data set. Based on the initial indicator data set, the information entropy and entropy weight corresponding to each indicator are calculated. The information entropy and entropy weight are calculated using the entropy-TOPSIS algorithm to obtain the traffic risk value. The calculation expression is:

[0040]

[0041] Among them, E j represents the information entropy of the jth indicator, n represents the total number of sub-segments, p ij The ratio of the jth indicator in the i-th sub-section, w j represents the entropy weight of the jth indicator, m represents the total number of indicators, R i represents the traffic risk value corresponding to the i-th sub-segment, x ij Indicates the value of the jth indicator in the i-th sub-section, minx j Indicates the minimum value of the j-th indicator, maxx j Indicates the maximum value of the j-th indicator.

[0042] Preferably, the classification control unit is used to classify the traffic risk value by using the FCM clustering algorithm to obtain an adaptive risk level interval, and perform traffic supervision according to the adaptive risk level interval. The processing logic includes:

[0043] The number of risk level intervals is set to four. The membership of each sub-section's traffic risk value corresponding to each risk level is randomly initialized to obtain the initial membership matrix. The cluster center of each risk level is calculated based on the initial membership matrix. The membership corresponding to each section is recalculated based on the cluster center to obtain the updated membership. The iteration is terminated after the change in the updated membership is less than the preset convergence threshold or the maximum number of iterations is reached. The traffic risk value of each sub-section is classified into the risk level with the highest membership to obtain the adaptive risk level interval.

[0044] Preferably, the classification control unit is used to control the road section according to the adaptive risk level interval, and the processing logic includes:

[0045] When the adaptive risk level interval is level 4, regular inspections are maintained for the corresponding sub-sections, signal light timing plans are optimized, and traffic efficiency on low-risk sections is improved;

[0046] When the adaptive risk level interval is level three, the corresponding sub-section will be marked as a possible risk location and sent to the traffic management center, and a voice prompt will be pushed to the driver in conjunction with the navigation software;

[0047] When the adaptive risk level interval is level 2, variable speed limits are implemented on the corresponding sub-sections. The speed limit is updated on the electronic road screen based on real-time traffic density, and graded deceleration prompts are pushed through the onboard terminal. Traffic light cycle adjustment technology is used to control the release frequency of upstream entrance ramps to maintain ramp flow balance. Patrol car inspections are increased in frequency, and low-speed vehicles occupying the road are persuaded to leave on the spot.

[0048] When the adaptive risk level interval is level one, an emergency response is carried out on the corresponding sub-section, prompting the traffic police department to arrive at the scene, activating lane signal lights to forcibly guide the main traffic flow, and closing the entrance ramp within 2 kilometers upstream of the sub-section.

[0049] Preferably, the terminal interaction module includes a display interaction unit and a data storage unit;

[0050] The display interaction unit is used to provide a display interface to the user and receive user operation instructions, and receive user instructions to adjust and set system parameters of the data analysis module, configuration acquisition module and risk management module;

[0051] The data storage unit generates a traffic safety log based on the output results of the risk management module and stores all output data of the data analysis module, configuration acquisition module and risk management module.

[0052] The beneficial effects of the present invention are as follows: it provides a quantitative calculation method for the layout position of traffic monitoring sensors, which eliminates the need to comprehensively deploy high-precision monitoring sensor equipment at all traffic nodes, and can accurately locate key sections of roads for data collection, effectively reducing the high cost of system installation and maintenance, rationally allocating limited funds, and being more adaptable and practical. By introducing implicit abnormality, the impact of non-traffic flow factors on accidents is analyzed from a holistic perspective in the absence of data, and by analyzing transportation data, the limitations of traditional methods that only focus on regulating specific explicit safety risk factors are reduced. After the sensors are deployed, the monitoring data is quantitatively analyzed while obtaining detailed data, which improves data utilization, facilitates accurate quantitative judgments on transportation safety supervision, reduces reliance on personnel experience, and provides hierarchical processing measures for traffic supervision. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 A schematic diagram of the basic framework of a transportation safety supervision system based on data analysis provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0054] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings. It is obvious that the described embodiments are only part of the embodiments of the present invention, but not all of the embodiments.

[0055] Reference Figure 1 , which is an embodiment of the present invention, provides a transportation safety supervision system based on data analysis, including:

[0056] Data analysis module, configuration collection module, risk management module and terminal interaction module;

[0057] The data analysis module is used to perform primary and secondary divisions on the target road to obtain a set of sub-segments. Based on the sub-segment set, the influence of non-traffic flow factors on traffic risk is calculated to obtain the implicit anomaly degree.

[0058] The configuration acquisition module is used to sort the implicit anomaly degrees corresponding to each sub-road section to obtain the setting coordinates of the multi-dimensional sensor, configure the multi-dimensional sensor based on the setting coordinates and collect the road section traffic data;

[0059] The risk control module is used to calculate the traffic data of the road section to obtain the traffic risk value corresponding to each sub-section, classify the traffic risk value through the FCM clustering algorithm to obtain the adaptive risk level interval, and perform traffic supervision based on the adaptive risk level interval;

[0060] The display interaction unit is used to provide a display interface to the user, receive user operation instructions and store historical data.

[0061] In this embodiment, the data analysis module includes a road segment division unit and an abnormality calculation unit;

[0062] The road segmentation unit is used to segment the target road into a set of sub-segments, with a primary division based on traffic flow direction and number of lanes, and a secondary division based on length;

[0063] The processing logic of the first division includes:

[0064] Divide the target road into one-way lane sections and two-way lane sections according to traffic flow direction;

[0065] Divide the one-way lanes in the target road into primary road segments;

[0066] Two-way lane sections are divided based on the number of lanes. Two-way lanes with four or fewer lanes are classified as intermediate sections, and two-way lanes with more than four lanes are classified as advanced sections.

[0067] The processing logic of the secondary division includes:

[0068] The primary road sections are divided into equal intervals based on the preset first road length, the intermediate road sections are divided into equal intervals based on the preset second road length, and the advanced road sections are divided into equal intervals based on the preset third road length. The divided sections are merged and the indexes are added to each of them to obtain a sub-section set.

[0069] In this embodiment, the abnormality calculation unit is used to calculate the comprehensive risk caused by non-traffic flow factors to obtain the implicit abnormality. The processing logic includes:

[0070] Counting historical road data to obtain the number of accidents and average traffic flow data corresponding to each sub-section in the sub-section set, sorting the number of accidents corresponding to each sub-section in ascending order and assigning a rank to obtain the number of accidents rank corresponding to each sub-section, and sorting the average traffic flow data corresponding to each sub-section in ascending order and assigning a rank to obtain the traffic flow rank corresponding to each sub-section;

[0071] The rank difference data set is obtained by subtracting the rank of the number of accidents and the rank of the traffic flow corresponding to each sub-section. The explicit correlation of accidents is calculated using the Spearman correlation coefficient formula and the rank difference data set. The implicit anomaly degree is calculated based on the explicit correlation of accidents. The calculation expression is:

[0072]

[0073] SI=e -ρ;

[0074] Among them, ρ represents the explicit correlation of accidents, d represents the rank difference, k represents the sub-section number, K represents the total number of sub-sections, SI represents the implicit abnormality, and e represents the natural constant.

[0075] Ordinary roads without multi-dimensional sensors and monitoring systems typically only have traffic cameras installed at intersections, providing only basic data such as the number of accidents, location, and traffic volume. This application calculates the explicit correlation between the number of accidents and average traffic volume on each sub-segment. This calculation then uses the implicit anomaly to measure the overall impact of non-traffic factors, such as road conditions, on traffic safety. While it's reasonable to expect greater traffic volume to lead to more accidents, a high implicit anomaly indicates that a road segment violates this trend, making it more valuable to deploy multi-dimensional sensors there.

[0076] In this embodiment, the configuration acquisition module includes a position allocation unit and a data acquisition unit;

[0077] The position allocation unit is used to sort the implicit abnormality values ​​corresponding to each sub-section in the sub-section set, and arrange them in descending order to obtain a priority sequence;

[0078] Based on the number of multi-dimensional sensors and the priority sequence, the midpoint position of each sub-section is marked in turn to obtain the configuration coordinate data.

[0079] In this embodiment, the data acquisition unit is used to collect road section traffic data, which includes operation data, vehicle data, road surface data and environmental data;

[0080] The operating data includes traffic flow data and road condition data, the vehicle data includes basic vehicle information and operating status data, the road surface data includes road geometric characteristics, surface conditions and traffic facility data, and the environmental data includes weather conditions and road surrounding environment data.

[0081] In this embodiment, the traffic flow data includes vehicle volume, lane occupancy, and vehicle density, and the road condition data includes vehicle speed dispersion, overspeed rate, and proportion of high-risk vehicles;

[0082] The basic vehicle information includes vehicle type, vehicle model, engine information and fuel type, and the vehicle identity information is obtained through the vehicle-mounted device RFID;

[0083] The operating status data includes real-time data of vehicle speed, driving route, engine status, vehicle braking system and vehicle steering system;

[0084] The road geometric characteristics include the width, length, slope and curvature of the road;

[0085] The surface condition includes the surface condition of the road, and the surface condition includes smoothness, potholes, cracks and wear ratio;

[0086] The traffic facility data includes the working status and location coordinates of traffic signs, traffic lights, roadblocks and isolation belts;

[0087] The weather condition obtains real-time weather data through meteorological sensors, and the real-time weather data includes temperature, humidity, wind speed, precipitation, visibility and air pressure;

[0088] The road surrounding environment data includes the number of intersections, driving sight distance and the integrity rate of guardrail markings.

[0089] In this embodiment, the risk management and control module includes a risk calculation unit and a classification management and control unit;

[0090] The risk calculation unit is used to calculate the traffic data of the road section to obtain the traffic risk value corresponding to each sub-section. The processing logic includes:

[0091] Based on the preset reference threshold set, the road section traffic data is assigned and coded to obtain the initial indicator data set. Based on the initial indicator data set, the information entropy and entropy weight corresponding to each indicator are calculated. The information entropy and entropy weight are calculated using the entropy-TOPSIS algorithm to obtain the traffic risk value. The calculation expression is:

[0092]

[0093] Among them, E j represents the information entropy of the jth indicator, n represents the total number of sub-segments, p ij The ratio of the jth indicator in the i-th sub-section, w j represents the entropy weight of the jth indicator, m represents the total number of indicators, R i represents the traffic risk value corresponding to the i-th sub-segment, x ij Indicates the value of the jth indicator in the i-th sub-section, minx j Indicates the minimum value of the j-th indicator, maxx j Indicates the maximum value of the j-th indicator.

[0094] In this embodiment, the classification control unit is used to classify the traffic risk value using the FCM clustering algorithm to obtain an adaptive risk level interval, and perform traffic supervision based on the adaptive risk level interval. The processing logic includes:

[0095] The number of risk level intervals is set to four. The membership of each sub-section's traffic risk value corresponding to each risk level is randomly initialized to obtain the initial membership matrix. The cluster center of each risk level is calculated based on the initial membership matrix. The membership corresponding to each section is recalculated based on the cluster center to obtain the updated membership. The iteration is terminated after the change in the updated membership is less than the preset convergence threshold or the maximum number of iterations is reached. The traffic risk value of each sub-section is classified into the risk level with the highest membership to obtain the adaptive risk level interval.

[0096] In this embodiment, the classification control unit is used to control the road section according to the adaptive risk level interval. The processing logic includes:

[0097] When the adaptive risk level interval is level 4, regular inspections are maintained for the corresponding sub-sections, signal light timing plans are optimized, and traffic efficiency on low-risk sections is improved;

[0098] When the adaptive risk level interval is level three, the corresponding sub-section will be marked as a possible risk location and sent to the traffic management center, and a voice prompt will be pushed to the driver in conjunction with the navigation software;

[0099] When the adaptive risk level interval is level 2, variable speed limits are implemented on the corresponding sub-sections. The speed limit is updated on the electronic road screen based on real-time traffic density, and graded deceleration prompts are pushed through the onboard terminal. Traffic light cycle adjustment technology is used to control the release frequency of upstream entrance ramps to maintain ramp flow balance. Patrol car inspections are increased in frequency, and low-speed vehicles occupying the road are persuaded to leave on the spot.

[0100] When the adaptive risk level interval is level one, an emergency response is carried out on the corresponding sub-section, prompting the traffic police department to arrive at the scene, activating lane signal lights to forcibly guide the main traffic flow, and closing the entrance ramp within 2 kilometers upstream of the sub-section.

[0101] In this embodiment, the terminal interaction module includes a display interaction unit and a data storage unit;

[0102] The display interaction unit is used to provide a display interface to the user and receive user operation instructions, and receive user instructions to adjust and set system parameters of the data analysis module, configuration acquisition module and risk management module;

[0103] The data storage unit generates a traffic safety log based on the output results of the risk management module and stores all output data of the data analysis module, configuration acquisition module and risk management module.

[0104] Those skilled in the art will appreciate that embodiments of the present invention may provide methods, systems, or computer program products. Therefore, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The storage medium may be implemented by any type of volatile or non-volatile storage device, or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk. The computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, the instruction device being implemented in the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0105] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A transportation safety supervision system based on data analysis, characterized in that: include: Data analysis module, configuration collection module, risk management module and terminal interaction module; The data analysis module is used to perform primary and secondary divisions on the target road to obtain a set of sub-segments. Based on the sub-segment set, the influence of non-traffic flow factors on traffic risk is calculated to obtain the implicit anomaly degree. The configuration acquisition module is used to sort the implicit anomaly degrees corresponding to each sub-road section to obtain the setting coordinates of the multi-dimensional sensor, configure the multi-dimensional sensor based on the setting coordinates and collect the road section traffic data; The risk control module is used to calculate the traffic data of the road section to obtain the traffic risk value corresponding to each sub-section, classify the traffic risk value through the FCM clustering algorithm to obtain the adaptive risk level interval, and perform traffic supervision based on the adaptive risk level interval; The display interaction unit is used to provide a display interface to the user, receive user operation instructions and store historical data.

2. The transportation safety supervision system based on data analysis according to claim 1, characterized in that: The data analysis module includes a road segment division unit and an anomaly calculation unit; The road segmentation unit is used to segment the target road into a set of sub-segments, with a primary division based on traffic flow direction and number of lanes, and a secondary division based on length; The processing logic of the first division includes: Divide the target road into one-way lane sections and two-way lane sections according to traffic flow direction; Divide the one-way lanes in the target road into primary road segments; Two-way lane sections are divided based on the number of lanes. Two-way lanes with four or fewer lanes are classified as intermediate sections, and two-way lanes with more than four lanes are classified as advanced sections. The processing logic of the secondary division includes: The primary road sections are divided into equal intervals based on the preset first road length, the intermediate road sections are divided into equal intervals based on the preset second road length, and the advanced road sections are divided into equal intervals based on the preset third road length. The divided sections are merged and the indexes are added to each of them to obtain a sub-section set.

3. The transportation safety supervision system based on data analysis according to claim 2, characterized in that: The abnormality calculation unit is used to calculate the comprehensive risk caused by non-traffic flow factors to obtain the implicit abnormality. The processing logic includes: Counting historical road data to obtain the number of accidents and average traffic flow data corresponding to each sub-section in the sub-section set, sorting the number of accidents corresponding to each sub-section in ascending order and assigning a rank to obtain the number of accidents rank corresponding to each sub-section, and sorting the average traffic flow data corresponding to each sub-section in ascending order and assigning a rank to obtain the traffic flow rank corresponding to each sub-section; The rank difference data set is obtained by subtracting the rank of the number of accidents and the rank of the traffic flow corresponding to each sub-section. The explicit correlation of accidents is calculated using the Spearman correlation coefficient formula and the rank difference data set. The implicit anomaly degree is calculated based on the explicit correlation of accidents. The calculation expression is: YES=and -ρ ; Among them, ρ represents the explicit correlation of accidents, d represents the rank difference, k represents the sub-section number, K represents the total number of sub-sections, SI represents the implicit abnormality, and e represents the natural constant.

4. The transportation safety supervision system based on data analysis according to claim 1, characterized in that: The configuration acquisition module includes a position allocation unit and a data acquisition unit; The position allocation unit is used to sort the implicit abnormality values ​​corresponding to each sub-section in the sub-section set, and arrange them in descending order to obtain a priority sequence; Based on the number of multi-dimensional sensors and the priority sequence, the midpoint position of each sub-section is marked in turn to obtain the configuration coordinate data.

5. The transportation safety supervision system based on data analysis according to claim 4, characterized in that: The data acquisition unit is used to collect road traffic data, which includes operation data, vehicle data, road surface data and environmental data; The operating data includes traffic flow data and road condition data, the vehicle data includes basic vehicle information and operating status data, the road surface data includes road geometric characteristics, surface conditions and traffic facility data, and the environmental data includes weather conditions and road surrounding environment data.

6. The transportation safety supervision system based on data analysis according to claim 5, characterized in that: The traffic flow data includes vehicle volume, lane occupancy, and vehicle density; the road condition data includes vehicle speed dispersion, overspeed rate, and proportion of high-risk vehicles; The basic vehicle information includes vehicle type, vehicle model, engine information and fuel type, and the vehicle identity information is obtained through the vehicle-mounted device RFID; The operating status data includes real-time data of vehicle speed, driving route, engine status, vehicle braking system and vehicle steering system; The road geometric characteristics include the width, length, slope and curvature of the road; The surface condition includes the surface condition of the road, and the surface condition includes smoothness, potholes, cracks and wear ratio; The traffic facility data includes the working status and location coordinates of traffic signs, traffic lights, roadblocks and isolation belts; The weather condition obtains real-time weather data through meteorological sensors, and the real-time weather data includes temperature, humidity, wind speed, precipitation, visibility and air pressure; The road surrounding environment data includes the number of intersections, driving sight distance and the integrity rate of guardrail markings.

7. The transportation safety supervision system based on data analysis according to claim 1, characterized in that: The risk management and control module includes a risk calculation unit and a classification management and control unit; The risk calculation unit is used to calculate the traffic data of the road section to obtain the traffic risk value corresponding to each sub-section. The processing logic includes: Based on the preset reference threshold set, the road section traffic data is assigned and coded to obtain the initial indicator data set. Based on the initial indicator data set, the information entropy and entropy weight corresponding to each indicator are calculated. The information entropy and entropy weight are calculated using the entropy-TOPSIS algorithm to obtain the traffic risk value. The calculation expression is: Among them, E j represents the information entropy of the jth indicator, n represents the total number of sub-segments, p ij The ratio of the jth indicator in the i-th sub-section, w j represents the entropy weight of the jth indicator, m represents the total number of indicators, R i represents the traffic risk value corresponding to the i-th sub-segment, x ij Indicates the value of the jth indicator in the i-th sub-section, minx j Indicates the minimum value of the j-th indicator, maxx j Indicates the maximum value of the j-th indicator.

8. The transportation safety supervision system based on data analysis according to claim 7, characterized in that: The classification control unit is used to classify traffic risk values ​​using the FCM clustering algorithm to obtain adaptive risk level intervals, and to perform traffic supervision based on the adaptive risk level intervals. The processing logic includes: The number of risk level intervals is set to four. The membership of each sub-section's traffic risk value corresponding to each risk level is randomly initialized to obtain the initial membership matrix. The cluster center of each risk level is calculated based on the initial membership matrix. The membership corresponding to each section is recalculated based on the cluster center to obtain the updated membership. The iteration is terminated after the change in the updated membership is less than the preset convergence threshold or the maximum number of iterations is reached. The traffic risk value of each sub-section is classified into the risk level with the highest membership to obtain the adaptive risk level interval.

9. The transportation safety supervision system based on data analysis according to claim 8, characterized in that: The classification control unit is used to control road sections according to the adaptive risk level interval. The processing logic includes: When the adaptive risk level interval is level 4, regular inspections are maintained for the corresponding sub-sections, signal light timing plans are optimized, and traffic efficiency on low-risk sections is improved; When the adaptive risk level interval is level three, the corresponding sub-section will be marked as a possible risk location and sent to the traffic management center, and a voice prompt will be pushed to the driver in conjunction with the navigation software; When the adaptive risk level interval is level 2, variable speed limits are implemented on the corresponding sub-sections. The speed limit is updated on the electronic road screen based on real-time traffic density, and graded deceleration prompts are pushed through the onboard terminal. Traffic light cycle adjustment technology is used to control the release frequency of upstream entrance ramps to maintain ramp flow balance. Patrol car inspections are increased in frequency, and low-speed vehicles occupying the road are persuaded to leave on the spot. When the adaptive risk level interval is level one, an emergency response is carried out on the corresponding sub-section, prompting the traffic police department to arrive at the scene, activating lane signal lights to forcibly guide the main traffic flow, and closing the entrance ramp within 2 kilometers upstream of the sub-section.

10. The transportation safety supervision system based on data analysis according to claim 1, characterized in that: The terminal interaction module includes a display interaction unit and a data storage unit; The display interaction unit is used to provide a display interface to the user and receive user operation instructions, and receive user instructions to adjust and set system parameters of the data analysis module, configuration acquisition module and risk management module; The data storage unit generates a traffic safety log based on the output results of the risk management module and stores all output data of the data analysis module, configuration acquisition module and risk management module.

Images