A multi-source data-based expressway congestion identification system and identification method

Abstract

The application relates to the technical field of intelligent traffic, and discloses a highway congestion identification system and method based on multi-source data, which comprises a multi-dimensional monitoring module and an intelligent identification module. The system obtains highway management data of all traffic areas, management data of all vehicles and influence factors of traffic scenes through the multi-dimensional monitoring module, and classifies and forms a data set, the intelligent identification module sets a fixed monitoring period, evaluates the maximum traffic capacity and road service level of the highway of each traffic area, generates the maximum traffic volume and saturation, analyzes the driving track of each vehicle, generates an estimated traffic duration, the multi-dimensional evaluation has high precision, the intelligent identification module judges the traffic areas with congestion problems in the highway, identifies and outputs the corresponding congestion sections, constructs a double-congestion positioning mechanism, considers the overall road network state and local abnormalities, reduces missed detection, improves the identification precision, and has high intelligent positioning response efficiency.

Description

Technical Field

[0001] This invention relates to the field of intelligent transportation technology, specifically to a highway congestion identification system and method based on multi-source data. Background Technology

[0002] In traffic management, congestion identification is a core component. Failure to identify congestion in a timely manner can lead to vehicles being stranded for hours, resulting in increased transportation costs and wasted resources. Congested road sections can easily trigger driver anxiety, leading to dangerous maneuvers such as reckless lane changes and sudden braking, significantly increasing the risk of rear-end collisions and minor accidents. If congestion is not detected in time, it can also delay accident rescue opportunities due to information lag. With the continuous expansion of the highway network and the constant growth of traffic flow, traditional traffic management methods based on manual inspections and fixed-point monitoring are no longer sufficient to meet the needs of real-time monitoring, accurate analysis, and efficient decision-making. Congestion identification systems based on AI and big data technologies can dynamically predict congestion trends by analyzing parameters such as traffic flow, vehicle speed, and vehicle density in real time, providing a scientific basis for traffic management and emergency response, and becoming an important direction for the future development of smart transportation.

[0003] Currently, traditional highway congestion identification systems lack real-time performance, making it difficult to assess maximum traffic volume in real time and limiting the accuracy of traffic condition analysis. In addition, their trajectory inference capabilities are weak, failing to accurately reconstruct the complete driving path of vehicles, resulting in low congestion identification accuracy. Furthermore, they fail to comprehensively consider multi-dimensional factors such as traffic flow, time, and weather, leading to a high misjudgment rate. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a highway congestion identification system and method based on multi-source data. It has the advantages of high accuracy in multi-dimensional assessment and high efficiency in intelligent positioning response, and solves the problems of insufficient real-time performance, weak trajectory inference capability and low congestion identification accuracy of traditional highway congestion identification systems.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a highway congestion identification system based on multi-source data, comprising a multi-dimensional monitoring module and an intelligent identification module;

[0006] The multi-dimensional monitoring module consists of a regional management unit, a vehicle management unit, and a scene data unit. The regional management unit collects regional datasets by connecting to a database via a network. The regional datasets include highway management data for all traffic areas. The vehicle management unit collects vehicle datasets by connecting to a monitoring device via a network. The vehicle datasets include management data for all vehicles. The scene data unit collects scene datasets by connecting to a big data platform via a network. The scene datasets include factors influencing traffic scenarios.

[0007] The intelligent recognition module consists of a traffic assessment unit, a trajectory analysis unit, and a congestion recognition unit. The traffic assessment unit is set with a monitoring period of a fixed number of days. Then, by combining regional and scenario datasets, the maximum capacity and level of service of highways in each traffic area are evaluated, and the corresponding maximum traffic volume is generated. and saturation The trajectory analysis unit analyzes the driving trajectory of each vehicle based on the regional dataset and the vehicle dataset, and generates the corresponding estimated travel time. The congestion identification unit uses regional datasets, vehicle datasets, scene datasets, and saturation data as its basis. and estimated travel time It identifies traffic areas with congestion problems on highways and outputs the corresponding congested road sections.

[0008] Preferably, the regional dataset includes traffic volume, total length of highways, number of toll stations, and number of accidents within each traffic area.

[0009] Preferably, the vehicle dataset includes the average speed, license plate number, location, and stop times for each vehicle.

[0010] Preferably, the scenario dataset includes holiday periods and severe weather periods, wherein severe weather includes heavy rain, heavy snow, dense fog, strong winds, and sandstorms.

[0011] Preferably, the maximum traffic volume The calculation process is as follows:

[0012] S11. Based on the regional dataset, determine the monitoring cycle. within, no. Highway management data within a traffic area, and the first Within a given traffic area, the daily traffic volume on highways is marked as follows: , to Indicates the first Within a transportation area, the first to the second day of the expressway Traffic volume per day;

[0013]

[0014] In the formula, Indicates the monitoring period within, no. Average traffic volume on highways within a given traffic area;

[0015] S12. Determine the monitoring cycle based on the scene dataset. Does it include holidays?

[0016] If monitoring cycle Includes holidays, and a conversion factor for average traffic volume. ≤1;

[0017] If monitoring cycle The conversion factor for average traffic flow does not include holidays. >1;

[0018]

[0019] In the formula, This indicates that the average traffic flow is converted to the first... Within a traffic area, the maximum traffic volume on the highway .

[0020] Preferably, the saturation The calculation process is as follows:

[0021] Based on the regional dataset, the first Within a traffic area, the current traffic flow on the highway at the specified time is marked as follows: ;

[0022]

[0023] In the formula, Indicates the first Within a traffic area, the saturation level of highways at the current time point. .

[0024] Preferably, the estimated travel time The calculation process is as follows:

[0025] Based on the regional dataset, the first The total length of expressways in each transportation zone is marked as follows: ;

[0026] Based on the license plate number, location, and stop time information contained in the vehicle dataset, the vehicle's driving trajectory is marked using map software. The known number of vehicles is... The vehicle is currently in operation. Driving on the highway in the traffic zone, the first sample was taken. The management data of the vehicle, and the first vehicle The average speed of each vehicle is marked as ;

[0027]

[0028] In the formula, Indicates the first Estimated travel time for each vehicle.

[0029] Preferably, the process for determining traffic areas with congestion problems on the highway is as follows:

[0030] If the current time is not during a period of severe weather, then the saturation A saturation level of ≥100% indicates that the traffic flow on the highways within the traffic area has exceeded the maximum capacity, and the highways within the traffic area are congested. When the percentage is less than 100%, it means that the traffic flow on the expressway within the traffic area has not exceeded the maximum capacity, and the expressway within the traffic area is in a smooth state.

[0031] If the current time is during a period of severe weather, then the saturation When the saturation level is ≥80%, it indicates that the traffic flow on the highways within the traffic area has exceeded the maximum capacity, and the highways within the traffic area are congested. When the percentage is less than 80%, it means that the traffic flow on the expressway within the traffic area has not exceeded the maximum capacity, and the expressway within the traffic area is in a smooth state.

[0032] Preferably, the congested road segment identification process is as follows:

[0033] S21. Based on the regional dataset, the first... The number of toll stations within a traffic area is marked as follows: ;

[0034] S22, Calculate the first Average single-station travel time per vehicle Its expression is as follows:

[0035]

[0036] S23. Based on the number of toll stations in the regional dataset, the first... The highways within each transportation area are divided into The number of accidents on each section of the highway is marked as... , to Indicates the first Within each traffic area, the first section to the... The number of accidents on a section of highway;

[0037] In the vehicle dataset, if the first... The total time a vehicle spends stopping at any two adjacent toll stations is greater than the average time spent at a single toll station. This indicates that the section of highway between the two corresponding toll stations is congested.

[0038] In the Within a traffic area, if the number of accidents on any section of highway is greater than or equal to 1, the corresponding highway is considered a congested section.

[0039] A method for highway congestion identification based on multi-source data includes the following steps:

[0040] Step 1: Connect to the database, monitoring devices, and big data platform via the network to obtain highway management data for all traffic areas, management data for all vehicles, and influencing factors of traffic scenarios, and classify them into regional datasets, vehicle datasets, and scenario datasets;

[0041] Step 2: Set a monitoring cycle of fixed number of days. Then, by combining regional and scenario datasets, the maximum capacity and level of service of highways in each traffic area are evaluated, and the corresponding maximum traffic volume is generated. and saturation ;

[0042] Step 3: Based on the regional dataset and vehicle dataset, analyze the travel trajectory of each vehicle and generate the corresponding estimated travel time. ;

[0043] Step 4: Based on the region dataset, vehicle dataset, scene dataset, and saturation... and estimated travel time It identifies traffic areas with congestion problems on highways and outputs the corresponding congested road sections.

[0044] Compared with existing technologies, the present invention provides a highway congestion identification system and method based on multi-source data, which has the following advantages:

[0045] 1. This invention connects a database, monitoring devices, and a big data platform via a multi-dimensional monitoring module network to acquire highway management data for all traffic areas, management data for all vehicles, and influencing factors of traffic scenarios. These data are then categorized into regional datasets, vehicle datasets, and scenario datasets, breaking down data silos and comprehensively considering static road attributes, dynamic vehicle behavior, and external environmental factors. This avoids misjudgments caused by single data sources. The intelligent identification module is set to a fixed monitoring cycle of several days. Then, by combining regional and scenario datasets, the maximum capacity and level of service of highways in each traffic area are evaluated, and the corresponding maximum traffic volume is generated. and saturation This provides a key indicator for assessing congestion under different weather conditions. The intelligent recognition module analyzes the driving trajectory of each vehicle based on regional and vehicle datasets to generate corresponding estimated travel times. The multidimensional assessment has high accuracy.

[0046] 2. This invention utilizes an intelligent recognition module based on regional datasets, vehicle datasets, scene datasets, and saturation. and estimated travel time It identifies traffic areas with congestion problems on highways, identifies and outputs corresponding congested road segments, and constructs a dual congestion positioning mechanism. It identifies macro traffic areas and then locates micro road segments, taking into account both the overall road network status and local anomalies. This reduces missed detections and improves identification accuracy, resulting in high intelligent positioning response efficiency. Attached Figure Description

[0047] Figure 1 This is a system flowchart of the present invention;

[0048] Figure 2 This is a diagram illustrating the steps of the method of the present invention. Detailed Implementation

[0049] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0050] Traditional highway congestion identification systems suffer from insufficient real-time performance, making it difficult to assess maximum traffic volume in real time and limiting the accuracy of traffic condition analysis. Furthermore, their weak trajectory inference capabilities prevent accurate reconstruction of complete vehicle travel paths, resulting in low congestion identification accuracy. The systems also fail to comprehensively consider multi-dimensional factors such as traffic flow, time, and weather, leading to a high false alarm rate. Therefore, please refer to [the relevant documentation / reference]. Figures 1-2 This invention provides a highway congestion identification system and method based on multi-source data, as detailed below:

[0051] A highway congestion identification system based on multi-source data includes a multi-dimensional monitoring module and an intelligent identification module;

[0052] The multi-dimensional monitoring module consists of a regional management unit, a vehicle management unit, and a scene data unit. The regional management unit collects regional datasets by connecting to a database via a network. The regional datasets include highway management data for all traffic areas, including traffic flow, total highway length, number of toll stations, and number of accidents for each traffic area.

[0053] The vehicle management unit collects vehicle datasets through network-connected monitoring devices. The vehicle datasets include management data for all vehicles, including the average speed, license plate number, location, and stop times for each vehicle.

[0054] The scene data unit collects scene datasets by connecting to a big data platform via the network. The scene datasets include influencing factors of traffic scenes, and include holiday periods and severe weather periods. Severe weather includes heavy rain, heavy snow, heavy fog, strong winds and sandstorms.

[0055] Specifically, this invention breaks down data silos through a multi-dimensional monitoring module, integrating static road attributes, dynamic vehicle behavior, and external environmental factors to avoid misjudgments caused by a single data source.

[0056] The intelligent recognition module consists of a traffic assessment unit, a trajectory analysis unit, and a congestion recognition unit. The traffic assessment unit is set with a monitoring period of a fixed number of days. Then, by combining regional and scenario datasets, the maximum capacity and level of service of highways in each traffic area are evaluated, and the corresponding maximum traffic volume is generated. and saturation ;

[0057] Maximum traffic volume The calculation process is as follows:

[0058] S11. Based on the regional dataset, determine the monitoring cycle. within, no. Highway management data within a traffic area, and the first Within a given traffic area, the daily traffic volume on highways is marked as follows: , to Indicates the first Within a transportation area, the first to the second day of the expressway Traffic volume per day;

[0059]

[0060] In the formula, Indicates the monitoring period within, no. Average traffic volume on highways within a given traffic area;

[0061] S12. Determine the monitoring cycle based on the scene dataset. Does it include holidays?

[0062] If monitoring cycle Includes holidays, and a conversion factor for average traffic volume. ≤1;

[0063] If monitoring cycle The conversion factor for average traffic flow does not include holidays. >1;

[0064]

[0065] In the formula, This indicates that the average traffic flow is converted to the first... Within a traffic area, the maximum traffic volume on the highway This allows for precise quantification of the maximum throughput capacity at different time periods, providing a basis for subsequent real-time analysis of saturation. Data support was provided;

[0066] Saturation The calculation process is as follows:

[0067] Based on the regional dataset, the first Within a traffic area, the current traffic flow on the highway at the specified time is marked as follows: ;

[0068]

[0069] In the formula, Indicates the first Within a traffic area, the saturation level of highways at the current time point. This provides a key indicator for judging congestion status under different weather conditions.

[0070] The trajectory analysis unit analyzes the driving trajectory of each vehicle based on the regional dataset and the vehicle dataset, and generates the corresponding estimated travel time. ;

[0071] Estimated travel time The calculation process is as follows:

[0072] Based on the regional dataset, the first The total length of expressways in each transportation zone is marked as follows: ;

[0073] Based on the license plate number, location, and stop time information contained in the vehicle dataset, the vehicle's driving trajectory is marked using map software. The known number of vehicles is... The vehicle is currently in operation. Driving on the highway in the traffic zone, the first sample was taken. The management data of the vehicle, and the first vehicle The average speed of each vehicle is marked as ;

[0074]

[0075] In the formula, Indicates the first Estimated travel time for each vehicle;

[0076] Specifically, in actual implementation, in order to reduce the computational pressure on the system, target vehicles can be randomly selected as samples based on vehicle volume, thereby simplifying the process of judging congestion status and achieving high accuracy in multi-dimensional assessment.

[0077] The congestion identification unit uses regional datasets, vehicle datasets, scene datasets, and saturation data. and estimated travel time It uses differentiated thresholds to identify traffic areas with congestion problems on highways, identifies and outputs the corresponding congested road sections, accurately responds to weather changes, and avoids missing congestion reports due to excessively high thresholds in severe environments.

[0078] The procedure for identifying traffic congestion areas on highways is as follows:

[0079] If the current time is not during a period of severe weather, then the saturation A saturation level of ≥100% indicates that the traffic flow on the highways within the traffic area has exceeded the maximum capacity, and the highways within the traffic area are congested. When the percentage is less than 100%, it means that the traffic flow on the expressway within the traffic area has not exceeded the maximum capacity, and the expressway within the traffic area is in a smooth state.

[0080] If the current time is during a period of severe weather, then the saturation When the saturation level is ≥80%, it indicates that the traffic flow on the highways within the traffic area has exceeded the maximum capacity, and the highways within the traffic area are congested. When the traffic flow rate is less than 80%, it means that the traffic flow on the expressway within the traffic area has not exceeded the maximum capacity, and the expressway within the traffic area is in a smooth state.

[0081] The process for identifying congested road sections is as follows:

[0082] S21. Based on the regional dataset, the first... The number of toll stations within a traffic area is marked as follows: ;

[0083] S22, Calculate the first Average single-station travel time per vehicle Its expression is as follows:

[0084]

[0085] Specifically, the calculated first Average travel time per vehicle at a single station The first one has been excluded. To ensure that the data for each vehicle is representative of the sample, the data must be taken into account the impact of abnormal circumstances such as prolonged stay in service areas, breakdowns, or accidents.

[0086] S23. Based on the number of toll stations in the regional dataset, the first... The highways within each transportation area are divided into The number of accidents on each section of the highway is marked as... , to Indicates the first Within each traffic area, the first section to the... The number of accidents on a section of highway;

[0087] In the vehicle dataset, if the first... The total time a vehicle spends stopping at any two adjacent toll stations is greater than the average time spent at a single toll station. This indicates that the section of highway between the two corresponding toll stations is congested.

[0088] In the Within a traffic area, if the number of accidents on any section of highway is ≥1, the corresponding highway is considered a congested section.

[0089] Specifically, this invention constructs a dual congestion location mechanism through an intelligent identification module, which identifies macro-level traffic areas and then locates micro-level road segments, taking into account both the overall road network status and local anomalies. This reduces missed detections while improving identification accuracy and achieving high intelligent positioning response efficiency.

[0090] A method for highway congestion identification based on multi-source data includes the following steps:

[0091] Step 1: Connect to the database, monitoring devices, and big data platform via the network to obtain highway management data for all traffic areas, management data for all vehicles, and influencing factors of traffic scenarios, and classify them into regional datasets, vehicle datasets, and scenario datasets;

[0092] Step 2: Set a monitoring cycle of fixed number of days. Then, by combining regional and scenario datasets, the maximum capacity and level of service of highways in each traffic area are evaluated, and the corresponding maximum traffic volume is generated. and saturation ;

[0093] Step 3: Based on the regional dataset and vehicle dataset, analyze the travel trajectory of each vehicle and generate the corresponding estimated travel time. ;

[0094] Step 4: Based on the region dataset, vehicle dataset, scene dataset, and saturation... and estimated travel time It identifies traffic areas with congestion problems on highways and outputs the corresponding congested road sections.

[0095] Example 1

[0096] In this experiment, a suburban area during the National Day holiday was selected as the experimental subject. Statistics showed that the traffic volume on highways in this suburban area was 22,000, 20,000, and 21,000 vehicles in the first three days, respectively. The National Day holiday is a public holiday, and the conversion coefficient for the average traffic volume was determined. Set to 0.8, this represents the maximum daily traffic volume on the highway within the suburban area. The calculation process is as follows:

[0097]

[0098]

[0099] In the formula, This indicates the average traffic volume on highways in suburban areas during the National Day holiday. This indicates that the average traffic volume is converted into the maximum traffic volume on highways in suburban areas. The current time is the fourth day of the National Day holiday, with a daily traffic volume of 19,000 vehicles. What is the saturation level of the highways in this suburban area at this time? The calculation process is as follows:

[0100]

[0101] In the formula, This indicates the saturation level of highways within the suburban area at the current time. Assuming the current time is not during a period of severe weather, it is determined that the saturation level of highways in the suburban area is [not specified]. When the traffic flow rate is ≥100%, it indicates that the traffic volume on the expressways in the suburban area has exceeded the maximum capacity, and the expressways in the suburban area are congested.

[0102] Example 2

[0103] In this experiment, a highway with a total length of 1000km was selected as the experimental subject. Statistics showed that the highway had 10 toll stations, the average speed of the sample vehicles was 80km / h, and the estimated travel time for the sample vehicles was... The calculation process is as follows:

[0104]

[0105] Average single-station travel time of sample vehicles The calculation process is as follows:

[0106]

[0107] According to statistics, the total time spent by the sample vehicles when stopping at the first to second toll stations on the expressway was 2 hours; the total time spent by the sample vehicles when stopping at the second to third toll stations was 1 hour; the total time spent by the sample vehicles when stopping at the third to fourth toll stations was 1 hour; the total time spent by the sample vehicles when stopping at the fourth to fifth toll stations was 1 hour; the total time spent by the sample vehicles when stopping at the fifth to sixth toll stations was 2 hours; the total time spent by the sample vehicles when stopping at the sixth to seventh toll stations was 1 hour; the total time spent by the sample vehicles when stopping at the seventh to eighth toll stations was 1 hour; the total time spent by the sample vehicles when stopping at the eighth to ninth toll stations was 1 hour; and the total time spent by the sample vehicles when stopping at the ninth to tenth toll stations was 1 hour.

[0108] Based on the assessment, 2 hours is greater than the average travel time per station. This indicates that the section of the highway between the first and second toll stations is congested.

[0109] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value, it is acceptable.

[0110] The above formulas are all derived from software simulation using a large amount of data and are selected to be close to the actual values. The coefficients in the formulas are set by those skilled in the art according to the actual situation. The above description is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any equivalent substitutions or changes made by those skilled in the art within the technical scope disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the protection scope of the present invention.

Claims

1. A highway congestion identification system based on multi-source data, characterized in that: Includes a multi-dimensional monitoring module and an intelligent recognition module; The multi-dimensional monitoring module consists of a regional management unit, a vehicle management unit, and a scene data unit. The regional management unit collects regional datasets by connecting to a database via a network. The regional datasets include highway management data for all traffic areas. The vehicle management unit collects vehicle datasets by connecting to a monitoring device via a network. The vehicle datasets include management data for all vehicles. The scene data unit collects scene datasets by connecting to a big data platform via a network. The scene datasets include factors influencing traffic scenarios. The intelligent recognition module consists of a traffic assessment unit, a trajectory analysis unit, and a congestion recognition unit. The traffic assessment unit is set with a monitoring period of a fixed number of days. Then, by combining regional and scenario datasets, the maximum capacity and level of service of highways in each traffic area are evaluated, and the corresponding maximum traffic volume is generated. and saturation ; The maximum traffic volume The calculation process is as follows: S11. Based on the regional dataset, determine the monitoring cycle. within, no. Highway management data within a traffic area, and the first Within a given traffic area, the daily traffic volume on highways is marked as follows: , to Indicates the first Within a transportation area, the first to the second day of the expressway Traffic volume per day; In the formula, Indicates the monitoring period within, no. Average traffic volume on highways within a given traffic area; S12. Determine the monitoring cycle based on the scene dataset. Does it include holidays? If monitoring cycle Includes holidays, and a conversion factor for average traffic volume. ≤1; If monitoring cycle The conversion factor for average traffic flow does not include holidays. >1; In the formula, This indicates that the average traffic flow is converted to the first... Within a traffic area, the maximum traffic volume on the highway ; The saturation The calculation process is as follows: Based on the regional dataset, the first Within a traffic area, the current traffic flow on the highway at the specified time is marked as follows: ; In the formula, Indicates the first Within a traffic area, the saturation level of highways at the current time point. ; The trajectory analysis unit analyzes the driving trajectory of each vehicle based on the regional dataset and the vehicle dataset, and generates the corresponding estimated travel time. The congestion identification unit uses regional datasets, vehicle datasets, scene datasets, and saturation data as its basis. and estimated travel time It identifies traffic areas with congestion problems on highways and outputs the corresponding congested road sections.

2. The highway congestion identification system based on multi-source data according to claim 1, characterized in that: The regional dataset includes traffic volume, total highway length, number of toll stations, and number of accidents for each traffic area.

3. The highway congestion identification system based on multi-source data according to claim 2, characterized in that: The vehicle dataset includes each vehicle's average speed, license plate number, location, and stop times.

4. A highway congestion identification system based on multi-source data according to claim 3, characterized in that: The scenario dataset includes holiday periods and periods of severe weather, including heavy rain, heavy snow, dense fog, strong winds, and sandstorms.

5. A highway congestion identification system based on multi-source data according to claim 4, characterized in that: The estimated travel time The calculation process is as follows: Based on the regional dataset, the first The total length of expressways in each transportation zone is marked as follows: ; Based on the license plate number, location, and stop time information contained in the vehicle dataset, the vehicle's driving trajectory is marked using map software. The known number of vehicles is... The vehicle is currently in operation. Driving on the highway in the traffic zone, the first sample was taken. The management data of the vehicle, and the first vehicle The average speed of each vehicle is marked as ; In the formula, Indicates the first Estimated travel time for each vehicle.

6. A highway congestion identification system based on multi-source data according to claim 5, characterized in that: The process for determining traffic areas with congestion problems on the highway is as follows: If the current time is not during a period of severe weather, then the saturation A saturation level of ≥100% indicates that the traffic flow on the highways within the traffic area has exceeded the maximum capacity, and the highways within the traffic area are congested. When the percentage is less than 100%, it means that the traffic flow on the expressway within the traffic area has not exceeded the maximum capacity, and the expressway within the traffic area is in a smooth state. If the current time is during a period of severe weather, then the saturation When the saturation level is ≥80%, it indicates that the traffic flow on the highways within the traffic area has exceeded the maximum capacity, and the highways within the traffic area are congested. When the percentage is less than 80%, it means that the traffic flow on the expressway within the traffic area has not exceeded the maximum capacity, and the expressway within the traffic area is in a smooth state.

7. A highway congestion identification system based on multi-source data according to claim 6, characterized in that: The process for identifying congested road sections is as follows: S21. Based on the regional dataset, the first... The number of toll stations within a traffic area is marked as follows: ; S22, Calculate the first Average single-station travel time per vehicle Its expression is as follows: S23. Based on the number of toll stations in the regional dataset, the first... The highways within each transportation area are divided into The number of accidents on each section of the highway is marked as... , to Indicates the first Within each traffic area, the first section to the... The number of accidents on a section of highway; In the vehicle dataset, if the first... The total time a vehicle spends stopping at any two adjacent toll stations is greater than the average time spent at a single toll station. This indicates that the section of highway between the two corresponding toll stations is congested. In the Within a traffic area, if the number of accidents on any section of highway is greater than or equal to 1, the corresponding highway is considered a congested section.

8. A highway congestion identification method based on multi-source data, applied to a highway congestion identification system based on multi-source data as described in any one of claims 1-7, characterized in that, Includes the following steps: Step 1: Connect to the database, monitoring devices, and big data platform via the network to obtain highway management data for all traffic areas, management data for all vehicles, and influencing factors of traffic scenarios, and classify them into regional datasets, vehicle datasets, and scenario datasets; Step 2: Set a monitoring cycle of fixed number of days. Then, by combining regional and scenario datasets, the maximum capacity and level of service of highways in each traffic area are evaluated, and the corresponding maximum traffic volume is generated. and saturation ; Step 3: Based on the regional dataset and vehicle dataset, analyze the driving trajectory of each vehicle and generate the corresponding estimated travel time. ; Step 4: Based on the region dataset, vehicle dataset, scene dataset, and saturation... and estimated travel time It identifies traffic areas with congestion problems on highways and outputs the corresponding congested road sections.

Images