Traffic operation state evaluation and early warning method, device and system

Abstract

The invention provides a traffic operation state evaluation and early warning method, device and system. The method comprises the steps that multi-source traffic data of a preset traffic road section are acquired, and the multi-source traffic data comprise operation data of a passing main body on different sections of the preset traffic road section, identification feature data of passing vehicles on the preset traffic road section and environment data of the preset traffic road section; the multi-source traffic data is acquired based on different sensing devices, and the passing main body comprises motor vehicles, non-motor vehicles and pedestrians; fusing and calculating the multi-source traffic data to obtain behavior characteristics of the traffic subjects; and an abnormal event is researched and judged according to the behavior characteristics, the abnormal event and the traffic situation are associated and deduced, and an early warning strategy is determined. According to the method, the discovery speed and the identification accuracy of the traffic road section abnormal event are improved, the conversion from passive response to active early warning is realized, and the safety and the management efficiency of traffic road section operation are enhanced.

Description

Technical Field

[0001] This application relates to the field of traffic safety, and in particular to a method, device and system for assessing and warning about traffic conditions. Background Technology

[0002] With the continuous development of transportation systems, real-time perception and early warning of road traffic conditions have become crucial for improving road safety and traffic efficiency. Currently, several traffic situation detection and accident tracing methods based on radar-visual fusion have been proposed.

[0003] However, current technologies are all designed for the detection and analysis of specific events. The data used for each event is relatively fixed, and a universal event judgment method has not been formed. It is not flexible enough and it is difficult to adapt to various actual business scenarios of road traffic conditions. Summary of the Invention

[0004] Therefore, it is necessary to provide a traffic situation assessment and early warning method, device and system to achieve trend prediction and accurate early warning of abnormal traffic events.

[0005] A traffic situation assessment and early warning method includes:

[0006] The system acquires multi-source traffic data for a preset traffic segment. The multi-source traffic data includes the operation data of the main traffic entity at different cross-sections on the preset traffic segment, the identification feature data of the vehicles passing through the preset traffic segment, and the environmental data of the preset traffic segment. The multi-source traffic data is acquired based on different sensing devices. The main traffic entities include motor vehicles, non-motor vehicles, and pedestrians.

[0007] The multi-source traffic data is fused and calculated to obtain the behavioral characteristics of each of the traffic subjects;

[0008] Based on the behavioral characteristics, abnormal events are identified, and the abnormal events are correlated and extrapolated with traffic conditions to determine early warning strategies.

[0009] In one embodiment, the step of judging abnormal events based on the behavioral characteristics, correlating and extrapolating the abnormal events with traffic conditions, and determining an early warning strategy includes:

[0010] Based on the behavioral characteristics and the spatial location constraints of the preset traffic segments, abnormal events of individual traffic entities are identified;

[0011] The abnormal events are aggregated and correlated with traffic conditions to identify potential macroscopic complex events in the preset traffic sections.

[0012] The early warning strategy is determined based on the event parameters and scoring model of the macroscopic complex event.

[0013] In one embodiment, determining the early warning strategy based on the event parameters and scoring model of the macroscopic composite event includes:

[0014] Based on the event parameters and scoring model of the macro-complex event, the overall score of the traffic situation of the preset traffic segment is calculated;

[0015] Obtain the early warning strategy corresponding to the overall score.

[0016] In one embodiment, the event parameters include traffic flow smoothness, vehicle speed, lane occupancy, risk level, and hazard severity corresponding to the macro-composite event; based on the event parameters and scoring model of the macro-composite event, an overall score for the operating status of the preset traffic segment is calculated, including:

[0017] Based on the traffic flow, vehicle speed, lane occupancy and corresponding scoring models of the macro-complex events, the corresponding traffic volume score, speed score and occupancy score are calculated respectively.

[0018] Based on the risk level, hazard severity and corresponding scoring model of the macro-complex event, the corresponding event comprehensive score and hazard comprehensive score are calculated respectively.

[0019] The overall score of the traffic situation of the preset traffic segment is obtained by weighting the traffic volume score, speed score, occupancy score, event comprehensive score and hidden danger comprehensive score.

[0020] In one embodiment, it further includes:

[0021] The overall score is mapped to a health level, which includes a perfect level and a level that needs improvement.

[0022] When the health level is in the level that needs improvement, analyze the dominant scoring items that cause the overall score to decline. The dominant scoring items include one or more of the traffic volume score, speed score, occupancy score, event comprehensive score and hidden danger comprehensive score.

[0023] The early warning strategy is updated based on the dominant scoring item.

[0024] In one embodiment, it further includes:

[0025] An early warning is triggered if any of the overall score, traffic volume score, speed score, occupancy rate score, event comprehensive score, or hidden danger comprehensive score falls below a preset threshold.

[0026] In one embodiment, the method further includes:

[0027] Based on the abnormal events, a safety risk heat map corresponding to the preset traffic segment is generated, and high-risk areas are marked.

[0028] In one embodiment, the method further includes:

[0029] The system displays real-time operational information of the preset traffic segments, as well as traffic volume scores, speed scores, occupancy scores, comprehensive event scores, comprehensive hazard scores, and a safety risk heat map.

[0030] A traffic operation status assessment and early warning system, comprising:

[0031] The data acquisition module is used to acquire multi-source traffic data of a preset traffic segment. The multi-source traffic data includes the operation data of the main traffic subject at different sections of the preset traffic segment, the identification feature data of the vehicles passing through the preset traffic segment, and the environmental data of the preset traffic segment. The multi-source traffic data is acquired based on different sensing devices. The main traffic subjects include motor vehicles, non-motor vehicles, and pedestrians.

[0032] The data processing module is used to fuse and calculate the multi-source traffic data to obtain the behavioral characteristics of each of the traffic subjects;

[0033] The judgment and analysis module is used to judge abnormal events based on the behavioral characteristics, correlate and extrapolate the abnormal events with traffic conditions, and determine early warning strategies.

[0034] A traffic operation status assessment and early warning device, comprising:

[0035] Multiple identification devices are installed at the entrances and exits of preset traffic sections to collect vehicle images at the entrances and exits and extract vehicle identification feature data.

[0036] Multiple holographic devices are deployed at preset intervals within a preset traffic segment to collect multi-source traffic data. The multi-source traffic data includes the operation data of the main traffic vehicle at different cross-sections on the preset traffic segment, the identification feature data of the vehicles passing through the preset traffic segment, and the environmental data of the preset traffic segment. The main traffic vehicle includes motor vehicles, non-motor vehicles, and pedestrians.

[0037] The assessment and early warning equipment is used to fuse and calculate the multi-source traffic data, obtain the behavioral characteristics of each of the traffic subjects, judge abnormal events based on the behavioral characteristics, correlate and deduce the abnormal events with the traffic situation, and determine the early warning strategy.

[0038] The aforementioned traffic operation status assessment and early warning method, device, and system acquire multi-source traffic data from preset traffic segments. Utilizing multi-source data fusion technology, they match the operational data of traffic entities at different cross-sections of the preset traffic segments, the identification feature data of vehicles traveling on the preset traffic segments, and the environmental data of the preset traffic segments with high-precision spatiotemporal trajectories in real time. This accurately extracts micro-level driving behavior characteristics such as sudden deceleration and lane changes across solid lines, laying a high-quality data foundation for abnormal event analysis. Based on these behavioral characteristics, the system can identify abnormal events in real time and perform situational analysis by combining real-time traffic flow data. This achieves correlation analysis from micro-behavior to macro-state, thereby automatically triggering precise and clearly defined early warning strategies. This traffic operation status assessment and early warning method, device, and system improve the speed and accuracy of detecting abnormal events in traffic segments, realizing a shift from passive response to proactive early warning, and enhancing the safety and management efficiency of traffic segment operations. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in the embodiments of this application or the conventional technology, the drawings used in the description of the embodiments or the conventional technology will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0040] Figure 1 Here is a flowchart of a traffic situation assessment and early warning method according to one embodiment;

[0041] Figure 2 Here is a flowchart of a traffic situation assessment and early warning method according to another embodiment;

[0042] Figure 3 Here is a flowchart of a traffic situation assessment and early warning method according to another embodiment;

[0043] Figure 4 Here is a flowchart of a traffic situation assessment and early warning method according to another embodiment;

[0044] Figure 5 Here is a flowchart of a traffic situation assessment and early warning method according to another embodiment;

[0045] Figure 6 Here is a flowchart of a traffic situation assessment and early warning method according to another embodiment;

[0046] Figure 7 This is a module connection diagram of a traffic situation analysis and early warning device according to one embodiment;

[0047] Figure 8 This is a module connection diagram of a traffic situation assessment and early warning device according to another embodiment;

[0048] Figure 9 This is a block diagram of a traffic situation assessment and early warning system according to another embodiment;

[0049] Figure 10 This is an internal structural diagram of a computer device according to one embodiment.

[0050] Explanation of reference numerals in the attached diagram: 701, Data acquisition module; 702, Data simulation module; 703, Judgment and analysis module; 801, Data display module; 901, Identification device; 902, Holographic device; 903, Evaluation and early warning device. Detailed Implementation

[0051] To facilitate understanding of this application, a more complete description will be provided below with reference to the accompanying drawings, which illustrate embodiments of the present application. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that the disclosure of this application will be thorough and complete.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.

[0053] It is understood that the term "connection" in the following embodiments should be understood as "electrical connection," "communication connection," etc., if the connected circuits, modules, units, etc., have electrical signal or data transmission with each other.

[0054] It is understandable that "at least one" refers to one or more, and "multiple" refers to two or more. "At least a part of an element" refers to part or all of an element.

[0055] When used herein, the singular forms of “a,” “an,” and “the” may also include the plural forms unless the context clearly indicates otherwise. It should also be understood that the terms “comprising / including” or “having,” etc., specify the presence of the stated features, wholes, steps, operations, components, parts, or combinations thereof, but do not preclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts, or combinations thereof. Meanwhile, the term “and / or” as used in this specification includes any and all combinations of the associated listed items.

[0056] Existing technologies for traffic incident assessment rely on relatively fixed data usage and lack a universal approach, making them inflexible and difficult to adapt to various real-world road traffic situations. Therefore, this application provides a traffic situation assessment and early warning method, device, and system.

[0057] like Figure 1 As shown, a traffic situation assessment and early warning method in one embodiment includes steps 101, 102, and 103.

[0058] 101. Obtain multi-source traffic data for a preset traffic segment. The multi-source traffic data includes the operation data of the main traffic subject at different sections of the preset traffic segment, the identification feature data of the vehicles passing through the preset traffic segment, and the environmental data of the preset traffic segment. The multi-source traffic data is obtained based on different sensing devices. The main traffic subject includes motor vehicles, non-motor vehicles, and pedestrians.

[0059] Intelligent sensing devices deployed within a pre-defined traffic segment continuously collect micro-dynamic data, including operational data of each traffic entity at different cross-sections of the pre-defined traffic segment, identification feature data of vehicles passing through the pre-defined traffic segment, and environmental data of the pre-defined traffic segment. Operational data includes, but is not limited to, high-precision GIS coordinates (latitude and longitude), instantaneous speed, acceleration, lane number, heading angle, etc. Vehicle identification feature data includes, but is not limited to, license plate number, vehicle type, hazardous materials identification, etc. Environmental data includes, but is not limited to, visibility status, air quality status, and wireless communication signal strength of the traffic segment.

[0060] 102. The multi-source traffic data is fused and calculated to obtain the behavioral characteristics of each of the traffic subjects.

[0061] This involves fusing and calculating multi-source data, including outlier filtering, format standardization, and unit unification of the raw multi-source data. Based on a unified spatiotemporal coordinate system, the local coordinate data output by the holographic sensing device is unified to the tunnel's global coordinate system through a preset transformation matrix. A multi-target tracking algorithm is used to correlate observation data of the same vehicle at different cross-sections and from different sensors, forming a complete, smooth, and continuous trajectory of the vehicle within the tunnel.

[0062] Behavioral characteristics are the basic components of safety risks, including but not limited to rapid acceleration, rapid deceleration, frequent lane changes, and illegal lane changes.

[0063] 103. Based on the behavioral characteristics, analyze abnormal events, correlate and extrapolate the abnormal events with traffic conditions, and determine early warning strategies.

[0064] Abnormal events include, but are not limited to: traffic conditions, congestion conditions, and sudden traffic incidents. Traffic conditions include, but are not limited to, pedestrians running into traffic, non-motorized vehicles running into traffic, excessively fast driving, and excessively slow driving; congestion conditions include light congestion, moderate congestion, and severe congestion; sudden traffic incidents include, but are not limited to, sudden acceleration, sudden deceleration, sudden lane changes, continuous lane changes, sudden abnormalities, abnormal parking, and vehicles driving in the wrong direction.

[0065] This embodiment utilizes multi-source data fusion technology to match vehicle identity information with high-precision spatiotemporal trajectories in real time, accurately extracting micro-level driving behavior features such as sudden deceleration and lane changes over solid lines, laying a high-quality data foundation for anomaly event analysis. Through automatic analysis based on behavioral features, the system can identify anomalies in real time and perform situational analysis by combining real-time traffic flow data, achieving correlation analysis from micro-behavior to macro-state, thereby automatically triggering precise and clearly defined early warning strategies. This method improves the speed and accuracy of anomaly event detection in traffic segments, realizing a shift from passive response to proactive early warning, and enhancing the safety and management efficiency of traffic segment operations.

[0066] In some embodiments, the traffic segment also includes tunnels. The traffic operation status assessment and early warning method of this embodiment can analyze abnormal events inside the tunnel, correlate and extrapolate the abnormal events inside the tunnel with the overall traffic situation inside the tunnel, and determine early warning strategies. It is understood that the traffic segment also includes other road segments, which will not be listed in detail in this embodiment.

[0067] In another embodiment, such as Figure 2 As shown, step 103 includes: step 201, step 202, and step 203.

[0068] 201. Based on the behavioral characteristics and the spatial location constraints of the preset traffic segments, identify abnormal events of individual traffic entities.

[0069] For example, the system can detect whether a car complies with spatial position constraints, such as crossing a solid line to change lanes, and thus determine that it has "illegally changed lanes"; or whether a car's speed exceeds the speed limit of the traffic segment, etc. Based on the above judgments, the abnormal events of a single traffic subject can be obtained.

[0070] 202. Aggregate the abnormal events and correlate and extrapolate them with the traffic situation to identify potential macroscopic complex events in the preset traffic sections.

[0071] For example, if the system detects that the average speed of cars is less than 15 km / h and the vehicle density is greater than 33.3 vehicles / km in a certain section of a preset traffic segment, then the traffic segment is determined to be in a congestion event.

[0072] 203. Determine the early warning strategy based on the event parameters and scoring model of the macroscopic composite event.

[0073] For the identified macro-complex event of "congestion", the system calls its event parameters, such as congestion level and occurrence time, and processes the event parameters according to the preset scoring model to determine the early warning strategy to be issued to the user to optimize traffic segments.

[0074] This embodiment accurately identifies abnormal events of individual traffic entities through spatial rule constraints, performs spatiotemporal aggregation, and establishes causal relationships and deductions with the macro-traffic situation. This allows for the identification of more threatening macro-complex events, such as "local congestion caused by an accident." Based on the parameters of these macro-complex events (such as congestion level and risk level), the system can more comprehensively and profoundly assess the overall impact of the events on traffic segment operations.

[0075] In another embodiment, step 203 includes the following steps: step 301 and step 302.

[0076] 301. Based on the event parameters and scoring model of the macro-composite event, calculate the overall score of the traffic situation of the preset traffic segment.

[0077] The system inputs the aforementioned event parameters into a pre-trained and configured scoring model. This model is a comprehensive evaluation function whose purpose is to integrate multi-dimensional event parameters into a single overall score that comprehensively reflects the impact of the event on the overall traffic situation of the road segment.

[0078] 302. Obtain the early warning strategy corresponding to the overall score.

[0079] This embodiment calculates a comprehensive overall score by inputting the event parameters of macroscopic complex events into a preset scoring model. This transforms the complex impact of events into an intuitive and quantifiable overall state indicator, effectively solving the problems of difficulty in comprehensively evaluating multi-source information and fragmented decision-making basis. Compared to the traditional method using manual determination, this embodiment's method provides a faster, more objective, and consistent early warning response, improving decision-making efficiency and response accuracy in emergency situations, and providing clear and direct action instructions for traffic management.

[0080] In another embodiment, the event parameters include traffic flow smoothness, vehicle speed, lane occupancy, risk level, and hazard severity corresponding to the macroscopic composite event; wherein, for example... Figure 4 As shown, step 301 includes: step 401, step 402, and step 403.

[0081] 401. Based on the traffic flow, vehicle speed, lane occupancy and corresponding scoring models corresponding to the macro-composite events, calculate the corresponding traffic volume score, speed score and occupancy score respectively.

[0082] The traffic volume score is used to quantify the match between traffic demand and service capacity. It employs a relative difference calculation based on historical benchmarks to smooth out inherent differences across different dates and time periods. The historical benchmark is the average vehicle traffic volume over a preset time window, which can be manually selected by the user, such as the past 3 days, past 5 days, or past 7 days.

[0083] Traffic volume scoring calculation model:

[0084]

[0085] The model is explained as follows: when the current traffic volume is close to the historical average, the score is 100 points; when the traffic volume is significantly higher or lower than the historical average, the score decreases.

[0086] Speed ​​scores are used to quantify the smoothness of traffic flow. A relative difference method is also employed to encourage speeds to remain within historically efficient operating ranges. The historical benchmark is the average speed over a preset time window.

[0087] Speed ​​score calculation model:

[0088]

[0089] The model is explained as follows: the closer the current average speed is to the historical average speed, the higher the score.

[0090] Occupancy scores are used to quantify road space utilization and congestion. They directly reflect traffic load, and occupancy is negatively correlated with the score.

[0091] Market share rating calculation model:

[0092]

[0093] The model can be explained as follows: a higher occupancy rate indicates a smaller distance between vehicles, which increases the risk of accidents and therefore results in a lower score.

[0094] 402. Based on the risk level, hazard severity and corresponding scoring model of the macro-complex event, calculate the corresponding event comprehensive score and hazard comprehensive score respectively.

[0095] The comprehensive event scoring calculation model is shown below:

[0096]

[0097]

[0098] The parameters in the model are as follows:

[0099] Maximum number of events per day (configurable parameter);

[0100] Event risk level (1=low, 2=medium, 3=high, 4=severe);

[0101] The incident occurred days ago (0≤ ≤6);

[0102] Time decay coefficient;

[0103] : Total weight of 7 days.

[0104] The model is explained as follows: the higher the risk level, the greater the number of instances, and the closer the time is to the current day, the lower the score. This model introduces a "risk level weighting" (…). ")" and "time decay factor" It not only counts the number of events, but also emphasizes the severity of high-level and recent events, making risk assessment dynamic and memory-based, which is more in line with the logic of safety management.

[0105] The comprehensive hazard assessment model is shown below:

[0106]

[0107] The parameters in the model are as follows:

[0108] Safety score (0-100 points);

[0109] : Number of occurrences of the i-th type of hidden danger;

[0110] : Weight coefficient for the i-th type of hidden danger;

[0111] Tunnel length (km);

[0112] Baseline hazard value;

[0113] Total number of hazard types.

[0114] The model is described as follows: Hazards include, but are not limited to, abnormal events involving a single traffic entity (sudden acceleration, sudden deceleration, lane change, etc.), and the entry of hazardous materials. Different weights are assigned based on the degree of risk of the hazard. and through tunnel length Normalization is performed, ultimately resulting in a macroscopic tunnel safety score. This achieves causal quantification of the transition from microscopic driving misbehavior to a decline in macroscopic safety levels.

[0115] 403. Obtain the overall score of the traffic situation of the preset traffic segment based on the weighted sum of the traffic volume score, speed score, occupancy score, event comprehensive score and hidden danger comprehensive score.

[0116] Efficiency and safety scores are combined into a single overall score using configurable weights. This score condenses the complexities of tunnel operation into a single, intuitive number.

[0117] The overall score calculation model is shown below:

[0118]

[0119] The model is explained as follows: Based on the different types of scores and their corresponding weights, the model calculates the overall score for the preset road segment. The calculated overall score ranges from 0 to 100 points, with a higher score indicating a better operational status for the preset road segment. The weights for different types of scores can be determined based on importance and past experience, or dynamically adjusted by the user according to different management guidelines. For example, the weight of speed scores may be slightly higher during peak hours, or the weight of comprehensive hazard scores may be higher at night.

[0120] This embodiment decomposes the impact of macro-level complex events into five categories: traffic volume, speed, lane occupancy, event risk, and hazard severity. Corresponding scores are calculated for each category using a specific model, avoiding the bias of single-indicator assessments. The five sub-scores are then weighted and summed to form a total score, reflecting the different contributions of each dimension to the overall situation. Furthermore, the configurable weighting system allows the assessment model to flexibly adapt to different management orientations, enhancing the system's practicality and adaptability.

[0121] In another embodiment, the overall score is mapped to a health level, which includes a completeness level and a need-to-improve level. When the health level is a need-to-improve level, the dominant scoring items that cause the overall score to drop are analyzed. The dominant scoring items include one or more of the following: traffic volume score, speed score, occupancy rate score, event comprehensive score, and hidden danger comprehensive score.

[0122] For example, if the lane occupancy rate increases from 20% in the previous time period to 80% in the current time period, the occupancy rate score will decrease, causing the overall score to drop from the "perfect" level to the "needs improvement" level. The dominant scoring item that causes the overall score to decrease is the occupancy rate score.

[0123] The warning strategy is updated based on the dominant scoring criteria.

[0124] For example, if the dominant scoring item that causes the overall score to decline is the occupancy score, the warning strategy can be updated as follows: If the occupancy of a certain traffic segment increases, it is recommended to remind following vehicles to maintain a safe distance to reduce the risk of rear-end collisions.

[0125] This embodiment can monitor each scoring item that causes a decrease in the overall score. Compared with improving traffic based on the overall score, the method provided in this embodiment can improve the accuracy of risk positioning of traffic segments, thereby making more targeted improvements to relevant factors.

[0126] In another embodiment, an early warning is triggered if any one of the overall score, traffic volume score, speed score, occupancy rate score, event comprehensive score, or hidden danger comprehensive score is lower than a preset threshold.

[0127] For example, the preset threshold can be 60 points. When the overall hazard score is below 60 points, it means that the risk of a traffic accident has increased. At this time, the system issues a warning to the user, indicating that the overall hazard score of a certain road section is below 60 points and is in a high-risk state, prompting the user to monitor that road section.

[0128] This embodiment provides an evaluation standard by setting a threshold. When any score falls below the threshold, the user will receive a warning from the system, ensuring the timeliness and relevance of the warning.

[0129] In another embodiment, such as Figure 5 As shown, it also includes step 501: generating a safety risk heat map corresponding to the preset traffic segment based on the abnormal event, and marking high-risk areas.

[0130] The system counts the number of potential hazards / events occurring at each cross-section inside the tunnel at preset time intervals (e.g., daily), then classifies the frequency of hazard / event occurrences for each cross-section. By quantifying frequency gradients and clarifying risk priorities, different gradients correspond to different colors. In the heatmap, the higher the risk level of a region, the darker the color. The rules for determining the risk level of a cross-section are as follows:

[0131] Extremely low risk: Number of occurrences of cross-section / potential risks < 4;

[0132] Low risk: 4 ≤ cross-section / number of hidden risks < 8;

[0133] Medium risk: 8 ≤ cross-section / number of hidden risks < 10;

[0134] High risk: 10 ≤ number of times the risk occurs per cross section.

[0135] It is understandable that the number of times different levels are applied in the risk level determination rules may vary depending on the different traffic sections.

[0136] This embodiment classifies the risk level of traffic segments based on the risk assessment rules of cross sections, and divides them into different colors according to different risk levels in the heat map, which improves the readability of the heat map, makes it easier for users to understand the current operating status of traffic segments, and helps users determine the priority of implementing improvements to the operating status.

[0137] In another embodiment, such as Figure 6 As shown, it also includes step 601: displaying in real time the operation information of the preset traffic segment and the traffic volume score, speed score, occupancy score, event comprehensive score and hidden danger comprehensive score, as well as the safety risk heat map.

[0138] The system displays to users the traffic volume score, speed score, occupancy score, event comprehensive score, and hidden danger comprehensive score obtained in the above embodiments. It also displays a safety risk heat map and marks high-risk areas. Users can click on the high-risk areas of the safety risk heat map to obtain specific risk sources.

[0139] In some embodiments, in addition to the aforementioned traffic volume score, speed score, occupancy score, comprehensive event score, comprehensive hazard score, and safety risk heatmap, the following may also be displayed:

[0140] Tunnel traffic flow: Displays real-time average vehicle speed, vehicle density, and cross-sectional traffic flow data for traffic segments, forming an overall description of traffic flow (such as "basically smooth" or "slightly congested"). This status is dynamically correlated with speed score and occupancy score.

[0141] Tunnel Speed: A heat map or curve visually representing the distribution of vehicle speeds on a traffic segment, showing the overall state and discreteness of vehicle speeds. The core data support for this view is the real-time calculated speed score.

[0142] Tunnel vehicle traffic flow: This shows the traffic flow and structural proportion of different vehicle types. The basic data for this analysis is also used in the model calculation of traffic volume scoring.

[0143] Traffic hazards: A dedicated area is set up on the signboard, displaying recently identified abnormal events (such as sudden acceleration, sudden deceleration, lane changes) of individual traffic entities through a scrolling list or map markers, and statistically analyzing their frequency and spatiotemporal distribution. This hazard data is the direct input source for the comprehensive hazard assessment.

[0144] Traffic incidents: For macro-level complex incidents (such as parking, fire, and littering), they are displayed in real time on the corresponding location on the map with prominent icons (such as pop-ups or flashing icons). The list and statistical information are the basis for the comprehensive scoring of the incident.

[0145] Overall tunnel status: The top of the signboard or the core area will prominently display the various scores quantified from the above multi-dimensional information, presented in a dashboard or large digital font.

[0146] This embodiment integrates traffic volume scores, speed scores, occupancy scores, event comprehensive scores, and hazard comprehensive scores with a safety risk heatmap for real-time display. This enables users to quickly locate the source of risk and make scientific decisions based on the trend of score changes, thereby promoting the transformation of traffic management from a passive response and experience-driven model to an intelligent model of proactive early warning and data-driven model, and improving the level of traffic management.

[0147] Based on the same inventive concept as the above method, such as Figure 7 As shown, this application proposes a traffic operation status assessment and early warning system, including a data acquisition module 701, a data processing module 702, and a judgment and analysis module 703, which are used to perform the steps corresponding to the above method. Further description of each module can be found in the description of the above embodiments.

[0148] The data acquisition module 701 is used to acquire multi-source traffic data for preset traffic segments.

[0149] The data simulation module 702, connected to the data acquisition module 701, is used to fuse and calculate the multi-source traffic data to obtain the behavioral characteristics of each of the traffic subjects.

[0150] The judgment and analysis module 703, connected to the data simulation module 702, is used to judge abnormal events based on the behavioral characteristics, correlate and extrapolate the abnormal events with the traffic situation, and determine early warning strategies.

[0151] This device hardwareizes the analysis process through a modular architecture, enabling parallel processing and functional decoupling of data acquisition, fusion simulation, and intelligent analysis. This improves system processing efficiency and real-time performance, and enhances system stability, maintainability, and scalability.

[0152] In another embodiment, such as Figure 8 As shown, the traffic situation analysis and early warning device also includes: 801 and a data display module.

[0153] The data display module 801 and the judgment and analysis module 503 are connected in the same network. After the system deeply integrates the profile data such as scores, real-time events, and risk heat maps with business elements, the data display module 801 displays the operation information of the preset traffic segment, the traffic volume score, speed score, occupancy score, event comprehensive score, and hidden danger comprehensive score, as well as the safety risk heat map in real time.

[0154] In some embodiments, in addition to the aforementioned traffic volume score, speed score, occupancy score, comprehensive event score, comprehensive hazard score, and safety risk heatmap, the following may also be displayed:

[0155] Tunnel traffic flow: Displays real-time average vehicle speed, vehicle density, and cross-sectional traffic flow data for traffic segments, forming an overall description of traffic flow (such as "basically smooth" or "slightly congested"). This status is dynamically correlated with speed score and occupancy score.

[0156] Tunnel Speed: A heat map or curve visually representing the distribution of vehicle speeds on a traffic segment, showing the overall state and discreteness of vehicle speeds. The core data support for this view is the real-time calculated speed score.

[0157] Tunnel vehicle traffic flow: This shows the traffic flow and structural proportion of different vehicle types. The basic data for this analysis is also used in the model calculation of traffic volume scoring.

[0158] Traffic hazards: A dedicated area is set up on the signboard, displaying recently identified abnormal events (such as sudden acceleration, sudden deceleration, lane changes) of individual traffic entities through a scrolling list or map markers, and statistically analyzing their frequency and spatiotemporal distribution. This hazard data is the direct input source for the comprehensive hazard assessment.

[0159] Traffic incidents: For macro-level complex incidents (such as parking, fire, and littering), they are displayed in real time on the corresponding location on the map with prominent icons (such as pop-ups or flashing icons). The list and statistical information are the basis for the comprehensive scoring of the incident.

[0160] Overall tunnel status: The top of the signboard or the core area will prominently display the various scores quantified from the above multi-dimensional information, presented in a dashboard or large digital font.

[0161] For example, when the overall event score is below 60, the data display module 801 will pop up the overall event risk. Managers can quickly locate the event analysis module and pinpoint the high-risk locations in the tunnel based on the safety risk heat map, and then take targeted measures.

[0162] This embodiment introduces a data display module, which can show users intuitive scoring results and safety risk heatmaps, enabling users to quickly locate abnormal factors and improve the speed and accuracy of judgment.

[0163] Based on the same inventive concept as the methods and devices described above, this application proposes a traffic operation status assessment and early warning device, such as... Figure 9 As shown, it includes: multiple identification devices 901, at least two holographic devices 902, and assessment and early warning devices 903.

[0164] The identification device 901 is installed at the entrance and exit of a preset traffic segment to collect vehicle images at the entrance and exit and extract vehicle identification feature data. Optionally, the identification device 901 may include a license plate recognition camera, a vehicle type recognition camera, etc.

[0165] Holographic device 902 is deployed at preset intervals within a preset traffic segment to collect multi-source traffic data. This multi-source traffic data includes operational data of various traffic entities at different cross-sections along the preset traffic segment, identification feature data of vehicles traveling along the preset traffic segment, and environmental data of the preset traffic segment. The traffic entities include motor vehicles, non-motor vehicles, and pedestrians. Optionally, to achieve recognition accuracy and cost control, the preset interval can be 100-200 meters, such as 100 meters, 150 meters, and 200 meters. Optionally, holographic device 802 may include lidar, millimeter-wave radar, thermal imaging cameras, etc.

[0166] The assessment and early warning device 903 is used to fuse and calculate the multi-source traffic data, obtain the behavioral characteristics of each of the traffic subjects, judge abnormal events based on the behavioral characteristics, correlate and deduce the abnormal events with the traffic situation, and determine the early warning strategy.

[0167] During system operation, the identification device 901, holographic device 902, and evaluation and early warning device 903 continuously monitor the device voltage and offline status to avoid a decrease in the accuracy of the judgment due to device failure.

[0168] Optionally, the identification device 901 and the holographic device 902 are connected to the evaluation and early warning device 903 via a switch. The communication protocol between them can be Hypertext Transfer Protocol (HTTP), WebSocket protocol, or Message Queuing Telemetry Transport (MQTT), etc.

[0169] This system collects vehicle identity and dynamic data through a network of front-end devices, including identification and holographic equipment, and then performs fusion analysis and model assessment by back-end central equipment, including analysis and early warning devices. This system achieves unified perception of motor vehicles, non-motor vehicles, and pedestrians, and can automatically determine abnormal traffic trends, improving the objectivity and timeliness of early warnings.

[0170] Based on the above embodiments, taking a city highway tunnel (2km, two lanes in one direction, speed limit 60km / h) as an example:

[0171] (I) Data Acquisition and Fusion

[0172] 1. Deploy front-end devices:

[0173] Fourteen holographic devices were installed inside the tunnel, covering all 14 sections in both directions. Recognition devices were deployed at the tunnel entrance and exit lanes to collect vehicle license plate information, model information, and other data.

[0174] 2. Data Collection:

[0175] Holographic equipment: Real-time collection of dynamic data inside the tunnel (such as vehicle location, lane number, lane changing behavior, license plate number, etc.), multiple times per second.

[0176] Identification equipment: Collects information such as vehicle license plate number, vehicle model, and hazardous materials markings.

[0177] 3. Data cleaning and fusion:

[0178] Data cleaning: Remove noisy data (such as invalid license plates, abnormal locations) and fill in missing values ​​(such as missing GIS data).

[0179] Data fusion:

[0180] 1. Match the holographic device data with the recognition device data.

[0181] 2. Exchange data from holographic devices at different cross-sections.

[0182] (II) Traffic Incident Analysis and Behavioral Feature Extraction

[0183] 1. Extraction of abnormal events for a single entity:

[0184] Deceleration behavior: The algorithm identified 6 instances of rapid deceleration, with a maximum acceleration of -2.2 m / s².

[0185] Other behaviors: No behavioral features such as rapid acceleration or continuous lane changes were extracted.

[0186] Output results: 1 lane change over a solid line (moderate). 1 lane change while stopped (severe). 2 sudden decelerations (acceleration -2.2 m / s²).

[0187] 2. Analysis of Macro-level Complex Events:

[0188] Solid line lane change event: The algorithm analyzes vehicle trajectory data and finds that a vehicle changed lanes across a solid line at a distance of 300 meters. Risk level: medium (L=2 points).

[0189] Parking incident: The algorithm analyzes vehicle trajectory data and finds that a vehicle has a speed of 0 at 300 meters. Risk level: severe (L=4 points).

[0190] Other events: No abnormal events such as going against traffic or pedestrian crossings were detected.

[0191] (III) Scoring Process

[0192] 1. Vehicle traffic volume score (current traffic volume is 28):

[0193]

[0194] 2. Speed ​​rating (current average speed is 55 km / h):

[0195]

[0196] 3. Lane occupancy score (current lane occupancy is 65%):

[0197]

[0198] 4. Overall Event Score:

[0199] According to the deduction system formula, M = 3.

[0200] 1) Calculate the deduction coefficient (C):

[0201]

[0202] 2) Calculate the contribution value of macroscopic composite events:

[0203] The event:

[0204] The event:

[0205] All events occur on the same day, time weighting:

[0206] Total contribution value:

[0207] 3) Calculate the deduction points:

[0208]

[0209] 4) Calculate the final score:

[0210]

[0211] result:

[0212] When M = 3, and there is one event with L = 2 and one event with L = 4 on that day, the score is 88.44.

[0213] 5. Overall Hazard Assessment:

[0214] Potential hazards of sudden deceleration:

[0215]

[0216] Calculation formula:

[0217]

[0218] Result: When B=2.0 and there are 2 hidden dangers with a weight of 0.8, the score is 60.

[0219] 4. Overall Score

[0220] Preset health levels: Excellent (≥60 points), Needs improvement (<60 points).

[0221] The preset scoring threshold is set to 60 points.

[0222] Weight configuration:

[0223] Traffic volume scoring weights:

[0224] Speed ​​rating weighting:

[0225] Lane occupancy score weighting:

[0226] Overall event score weighting:

[0227] Overall weighting of hazard assessment:

[0228] Calculation formula:

[0229]

[0230] Rating level: Above 60 points is considered excellent.

[0231] If the lane occupancy score is below a preset threshold of 35, the system issues a warning to the user, indicating that the current lane occupancy is too high and suggesting that the user display a reminder on the tunnel screen to maintain a safe following distance. In one embodiment, a computer device is provided, which can be a terminal, and its internal structure can be as follows: Figure 10As shown. This computer device includes a processor, memory, input / output interfaces, communication interfaces, a display unit, and input devices.

[0232] The computer device comprises a processor, memory, and input / output interfaces connected via a system bus. A communication interface, display unit, and input devices are also connected to the system bus via input / output interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The input / output interfaces are used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When executed by the processor, the computer program implements a traffic situation assessment and early warning method. The display unit is used to generate a visually visible image and can be a display screen, projection device, or virtual reality imaging device. The display screen can be an LCD screen or an e-ink screen. The input device of the computer device can be a touch layer covering the display screen, or buttons, trackballs, or touchpads set on the casing of the computer device, or external keyboards, touchpads, or mice, etc.

[0233] Those skilled in the art will understand that Figure 10 The structure shown is merely a block diagram of a portion of the structure related to this application and does not constitute a limitation on the computer device to which the solution of this application is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0234] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described in the above method embodiment.

[0235] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described in the above method embodiment.

[0236] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the steps of the method described in the above method embodiments.

[0237] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0238] In the description of this specification, references to terms such as "some embodiments," "other embodiments," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative descriptions of the above terms do not necessarily refer to the same embodiments or examples.

[0239] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0240] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these modifications and improvements all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for assessing and issuing early warnings of traffic operation status, characterized in that, include: The system acquires multi-source traffic data for a preset traffic segment. The multi-source traffic data includes the operation data of the main traffic entity at different cross-sections on the preset traffic segment, the identification feature data of the vehicles passing through the preset traffic segment, and the environmental data of the preset traffic segment. The multi-source traffic data is acquired based on different sensing devices. The main traffic entities include motor vehicles, non-motor vehicles, and pedestrians. The multi-source traffic data is fused and calculated to obtain the behavioral characteristics of each of the traffic subjects; Based on the behavioral characteristics, abnormal events are identified, and the abnormal events are correlated and extrapolated with traffic conditions to determine early warning strategies.

2. The method according to claim 1, characterized in that, The step of judging abnormal events based on the behavioral characteristics, correlating and extrapolating the abnormal events with traffic conditions, and determining early warning strategies includes: Based on the behavioral characteristics and the spatial location constraints of the preset traffic segments, abnormal events of individual traffic entities are identified; The abnormal events are aggregated and correlated with traffic conditions to identify potential macroscopic complex events in the preset traffic sections. The early warning strategy is determined based on the event parameters and scoring model of the macroscopic complex event.

3. The method according to claim 2, characterized in that, The step of determining the early warning strategy based on the event parameters and scoring model of the macroscopic composite event includes: Based on the event parameters and scoring model of the macro-complex event, the overall score of the traffic situation of the preset traffic segment is calculated; Obtain the early warning strategy corresponding to the overall score.

4. The method according to claim 3, characterized in that, The event parameters include the traffic flow, vehicle speed, lane occupancy, risk level, and severity of potential hazards corresponding to the macro-composite event. Based on the event parameters and scoring model of the aforementioned macroscopic composite event, the overall score of the preset traffic segment's operating status is calculated, including: Based on the traffic flow, vehicle speed, lane occupancy and corresponding scoring models of the macro-complex events, the corresponding traffic volume score, speed score and occupancy score are calculated respectively. Based on the risk level, hazard severity and corresponding scoring model of the macro-complex event, the corresponding event comprehensive score and hazard comprehensive score are calculated respectively. The overall score of the traffic situation of the preset traffic segment is obtained by weighting the traffic volume score, speed score, occupancy score, event comprehensive score and hidden danger comprehensive score.

5. The method according to claim 4, characterized in that, Also includes: The overall score is mapped to a health level, which includes a perfect level and a level that needs improvement. When the health level is in the level that needs improvement, analyze the dominant scoring items that cause the overall score to decline. The dominant scoring items include one or more of the traffic volume score, speed score, occupancy score, event comprehensive score and hidden danger comprehensive score. The early warning strategy is updated based on the dominant scoring item.

6. The method according to claim 4, characterized in that, Also includes: An early warning is triggered if any of the overall score, traffic volume score, speed score, occupancy rate score, event comprehensive score, or hidden danger comprehensive score falls below a preset threshold.

7. The method according to any one of claims 4-6, characterized in that, The method further includes: Based on the abnormal events, a safety risk heat map corresponding to the preset traffic segment is generated, and high-risk areas are marked.

8. The method according to claim 7, characterized in that, The method further includes: The system displays real-time operational information of the preset traffic segments, as well as traffic volume scores, speed scores, occupancy scores, comprehensive event scores, comprehensive hazard scores, and a safety risk heat map.

9. A traffic operation status assessment and early warning system, characterized in that, include: The data acquisition module is used to acquire multi-source traffic data of a preset traffic segment. The multi-source traffic data includes the operation data of the main traffic subject at different sections of the preset traffic segment, the identification feature data of the vehicles passing through the preset traffic segment, and the environmental data of the preset traffic segment. The multi-source traffic data is acquired based on different sensing devices. The main traffic subjects include motor vehicles, non-motor vehicles, and pedestrians. The data processing module is used to fuse and calculate the multi-source traffic data to obtain the behavioral characteristics of each of the traffic subjects; The judgment and analysis module is used to judge abnormal events based on the behavioral characteristics, correlate and extrapolate the abnormal events with traffic conditions, and determine early warning strategies.

10. A traffic operation status assessment and early warning device, characterized in that, include: Multiple identification devices are installed at the entrances and exits of preset traffic sections to collect vehicle images at the entrances and exits and extract vehicle identification feature data. Multiple holographic devices are deployed at preset intervals within a preset traffic segment to collect multi-source traffic data. The multi-source traffic data includes the operation data of the main traffic vehicle at different cross-sections on the preset traffic segment, the identification feature data of the vehicles passing through the preset traffic segment, and the environmental data of the preset traffic segment. The main traffic vehicle includes motor vehicles, non-motor vehicles, and pedestrians. The assessment and early warning equipment is used to fuse and calculate the multi-source traffic data, obtain the behavioral characteristics of each of the traffic subjects, judge abnormal events based on the behavioral characteristics, correlate and deduce the abnormal events with the traffic situation, and determine the early warning strategy.

Images