Intelligent traffic dispersion method and system based on smart city

Abstract

The invention relates to the technical field of traffic management, and discloses an intelligent traffic dispersion method and system based on a smart city, and the method comprises the steps: determining a traffic facility operation and maintenance protocol corresponding to a traffic facility, and formulating a congestion evaluation factor of an urban traffic region; analyzing the traffic flow dimension state of the urban traffic area, calculating a congestion disturbance coefficient corresponding to the congestion evaluation element, and evaluating the congestion state intensity of the urban traffic area; analyzing vehicle behavior intention characteristics of vehicles in the urban traffic area, analyzing a traffic condition matrix of roads in the urban traffic area, and calculating traffic efficiency of the roads in the urban traffic area; extracting attraction element factors in the land utilization information and the real-time event information, and analyzing the traffic pressure conductivity of the surrounding area to the urban traffic area; and formulating a traffic intelligent dispersion strategy of the urban traffic area, and executing traffic dispersion work of the urban traffic area to obtain a traffic dispersion result. The intelligent traffic dispersion efficiency of the smart city can be improved.

Description

Technical Field

[0001] The present invention relates to a smart city-based intelligent traffic diversion method and system, belonging to the technical field of traffic management. Background Art

[0002] As the urbanization process continues to accelerate, the construction of smart cities has become an important direction for urban development. As the key lifeline of urban operations, the efficient operation of the transportation system is crucial to the development of smart cities. With the continuous growth of urban population and the sharp increase in the number of motor vehicles, traffic congestion is becoming increasingly serious, causing great inconvenience to urban residents' travel, while also increasing energy consumption and environmental pollution.

[0003] At present, urban traffic diversion mainly relies on traditional traffic light timing control and on-site command by traffic police. Traffic light timing control switches traffic lights according to a pre-set time plan. For example, during the morning rush hour, the green light duration of the main road is appropriately extended to ensure the passage of vehicles. However, this method lacks accurate perception and flexible response to real-time traffic flow changes. It is often the case that there is little traffic in one direction but the green light is always on, while the other direction is extremely congested but has to wait for a long time for the green light. On-site command by traffic police is limited by the distribution of police force and time, making it difficult to achieve effective coverage of all time periods and all areas. In addition, in special circumstances such as bad weather, the work efficiency of traffic police will be greatly affected, which will lead to low efficiency of intelligent traffic diversion in smart cities. Summary of the invention

[0004] The present invention provides a method and system for intelligent traffic diversion based on a smart city, the main purpose of which is to improve the efficiency of intelligent traffic diversion in the smart city.

[0005] To achieve the above object, the present invention provides a method for intelligent traffic diversion based on smart city, comprising: Obtaining an urban traffic area that requires traffic diversion, querying traffic facilities in the urban traffic area, determining traffic facility operation and maintenance regulations corresponding to the traffic facilities, and formulating congestion evaluation factors for the urban traffic area based on the traffic facility operation and maintenance regulations; Collecting real-time traffic data in the urban traffic area, analyzing the traffic flow dimension state of the urban traffic area based on the real-time traffic data, calculating the congestion disturbance coefficient corresponding to the congestion evaluation factor based on the traffic flow dimension state and the real-time traffic data, and evaluating the congestion state intensity of the urban traffic area based on the congestion disturbance coefficient; Using monitoring equipment in the urban traffic area to collect regional driving trajectory images and road scene holographic images of vehicles, analyzing vehicle behavior intention characteristics of vehicles in the urban traffic area based on the regional driving trajectory images, analyzing the traffic condition matrix of roads in the urban traffic area based on the road scene holographic images, and calculating the traffic efficiency of roads in the urban traffic area by combining the vehicle behavior intention characteristics and the traffic condition matrix; Collecting land use information and real-time event information of the surrounding areas of the urban traffic area, extracting attraction factors from the land use information and the real-time event information, and analyzing the degree of traffic pressure transmission from the surrounding areas to the urban traffic area based on the attraction factors; Based on the intensity of the congestion situation, the traffic efficiency and the traffic pressure conductivity, an intelligent traffic diversion strategy for the urban traffic area is formulated, and based on the intelligent traffic diversion strategy, traffic diversion work for the urban traffic area is performed to obtain traffic diversion results.

[0006] Optionally, the determining the traffic facility operation and maintenance regulations corresponding to the traffic facility includes: Collecting infrastructure information of the transportation facilities, and calculating information entropy corresponding to the infrastructure information; Based on the information entropy, extracting key facility information from the infrastructure information; Querying the facility operation and maintenance criteria corresponding to the transportation facility, and calculating the fit index between the key facility information and the facility operation and maintenance criteria; Based on the compatibility index and the key facility information, the transportation facility operation and maintenance regulations corresponding to the transportation facility are determined.

[0007] Optionally, the calculating the compatibility index between the key facility information and the facility operation and maintenance criteria includes: Extracting characteristic characters from the key facility information and the facility operation and maintenance criteria to obtain facility information characteristic characters and operation and maintenance criteria characteristic characters; Performing semantic analysis on the facility information characteristic characters and the operation and maintenance criteria characteristic characters respectively to obtain the first characteristic character semantics and the second characteristic character semantics; Performing vectorization processing on the first characteristic character semantics and the second characteristic character semantics to obtain a first semantic vector and a second semantic vector; Combining the first semantic vector and the second semantic vector, the matching index between the key facility information and the facility operation and maintenance criteria is calculated by the following formula: ; Where T represents the fit index between key facility information and facility operation and maintenance criteria, represents the i-th vector in the first semantic vector, i represents the sequence number of the first semantic vector, represents the jth vector in the second semantic vector, j represents the sequence number of the second semantic vector, It means taking the maximum vector between the i-th vector and the j-th vector, and q and r represent the number of the first semantic vector and the number of the second semantic vector respectively.

[0008] Optionally, the congestion evaluation factors of the urban traffic area are formulated based on the traffic facility operation and maintenance regulations, including: Performing element mining on the transportation facility operation and maintenance regulations to obtain key elements of the regulations; Constructing an element judgment matrix of the key elements of the specification, and calculating element weights corresponding to the key elements of the specification based on the element judgment matrix; The traffic industry standards of the urban traffic area are queried, and the congestion evaluation factors of the urban traffic area are formulated in combination with the factor weights, the traffic industry standards and the key elements of the regulations.

[0009] Optionally, analyzing the traffic flow state of the urban traffic area based on the real-time traffic data includes: Performing data cleaning on the real-time traffic data to obtain target traffic data; Extracting multi-dimensional traffic features of the target traffic data, and performing standard processing on the multi-dimensional traffic features to obtain standard traffic features; Performing feature dimensionality reduction processing on the standard traffic features to obtain reduced-dimensionality traffic features; Performing feature clustering processing on the dimension-reduced traffic features to obtain clustered traffic features; Performing spatiotemporal pattern analysis on the clustered traffic characteristics to obtain traffic spatiotemporal pattern characteristics; Based on the traffic spatiotemporal pattern characteristics, the traffic flow dimension of the urban traffic area is analyzed.

[0010] Optionally, the combining the traffic flow dimension state and the real-time traffic data to calculate the congestion disturbance coefficient corresponding to the congestion evaluation factor includes: Selecting a congestion-related dimension corresponding to the congestion evaluation element from the traffic flow dimension, and calculating a dimensional congestion disturbance coefficient corresponding to the congestion-related dimension based on the real-time traffic data; Based on the real-time traffic data, determine whether there is a traffic accident in the urban traffic area; if there is no traffic accident, calculate the congestion disturbance coefficient corresponding to the congestion evaluation factor in combination with the dimensional congestion disturbance coefficient; If a traffic accident occurs, extracting accident feature data related to the traffic accident from the real-time traffic data, and calculating the accident interference degree corresponding to the traffic accident based on the accident feature data; The congestion disturbance coefficient corresponding to the congestion evaluation factor is calculated by combining the accident interference degree and the dimensional congestion disturbance coefficient.

[0011] Optionally, the calculating the accident interference degree corresponding to the traffic accident based on the accident characteristic data includes: Extracting accident damage records, accident handling cycles and accident occurrence points from the accident feature data, and evaluating the accident level corresponding to the traffic accident based on the accident damage records; Based on the accident handling cycle, determining the accident duration cycle corresponding to the traffic accident; Calculate the distance between the traffic accident and the adjacent road based on the accident occurrence point; In combination with the interval distance value, the accident duration period and the accident level, the accident interference degree corresponding to the traffic accident can be calculated by the following formula: ; Where D represents the accident interference degree corresponding to the traffic accident, E represents the accident level, d represents the interval distance value, and t represents the duration of the accident. Represents the distance influence factor.

[0012] Optionally, the analyzing the vehicle behavior intention characteristics of the vehicles in the urban traffic area based on the regional driving trajectory image includes: Performing image preprocessing on the driving trajectory image of the region to obtain an optimized driving trajectory image; Performing feature extraction processing on the optimized driving trajectory image to obtain a feature driving trajectory image; Identifying a vehicle motion trajectory in the characteristic driving trajectory image, and calculating a trajectory change rate of the vehicle in the urban traffic area based on the vehicle motion trajectory; Extracting the track point information corresponding to the characteristic driving track image, and calculating the behavior intention parameters of the vehicles in the urban traffic area based on the track point information; Based on the trajectory change rate and the behavior intention parameter, a vehicle behavior intention feature of the vehicle in the urban traffic area is generated.

[0013] Optionally, the calculating the trajectory change rate of the vehicle in the urban traffic area based on the vehicle motion trajectory includes: Acquire a standard motion trajectory of vehicles in the urban traffic area, and perform curve fitting processing on the vehicle motion trajectory and the standard motion trajectory respectively to obtain a first trajectory curve and a second trajectory curve; Based on the first trajectory curve, calculating a trajectory curvature sequence corresponding to the vehicle motion trajectory to obtain a first trajectory curvature sequence; Based on the second trajectory curve, calculating the trajectory curvature sequence corresponding to the standard motion trajectory to obtain a second trajectory curvature sequence; and calculating the trajectory lengths corresponding to the vehicle motion trajectory and the standard motion trajectory to obtain a first trajectory length and a second trajectory length; The trajectory change rate of the vehicle in the urban traffic area is calculated by combining the first trajectory curvature sequence, the second trajectory curvature sequence, the first trajectory length, and the second trajectory length using the following formula: ; Where F represents the trajectory change rate of vehicles in the urban traffic area, represents the fth curvature value in the first trajectory curvature sequence, represents the fth curvature value in the second trajectory curvature sequence, represents the length of the first trajectory, represents the length of the second trajectory, f represents the sequence number in the trajectory curvature sequence, and u represents the length of the trajectory curvature sequence.

[0014] In order to solve the above problems, the present invention also provides a traffic intelligent guidance system based on a smart city, the system comprising: A congestion assessment factor formulation module is used to obtain an urban traffic area that needs traffic diversion, query the traffic facilities in the urban traffic area, determine the traffic facility operation and maintenance regulations corresponding to the traffic facilities, and formulate congestion assessment factors for the urban traffic area based on the traffic facility operation and maintenance regulations; A congestion situation intensity evaluation module is used to collect real-time traffic data in the urban traffic area, analyze the traffic flow dimension of the urban traffic area based on the real-time traffic data, calculate the congestion disturbance coefficient corresponding to the congestion evaluation factor based on the traffic flow dimension and the real-time traffic data, and evaluate the congestion situation intensity of the urban traffic area based on the congestion disturbance coefficient; A traffic efficiency calculation module, used to collect regional driving trajectory images and road scene holographic images of vehicles using monitoring equipment in the urban traffic area, analyze vehicle behavior intention characteristics of vehicles in the urban traffic area based on the regional driving trajectory images, analyze the traffic condition matrix of roads in the urban traffic area based on the road scene holographic images, and calculate the traffic efficiency of roads in the urban traffic area by combining the vehicle behavior intention characteristics and the traffic condition matrix; A traffic pressure transmission degree analysis module, used to collect land use information and real-time event information of the surrounding areas of the urban traffic area, extract attraction element factors from the land use information and the real-time event information, and analyze the traffic pressure transmission degree of the surrounding areas to the urban traffic area based on the attraction element factors; The traffic diversion module is used to formulate an intelligent traffic diversion strategy for the urban traffic area based on the intensity of the congestion situation, the traffic efficiency and the traffic pressure conductivity, and to perform traffic diversion work in the urban traffic area based on the intelligent traffic diversion strategy to obtain traffic diversion results.

[0015] Compared with the problems described in the background technology, the present invention can obtain scientific and targeted maintenance and management criteria for the traffic facilities under different conditions by determining the traffic facility operation and maintenance regulations corresponding to the traffic facilities, thereby providing strong support for the subsequent formulation of congestion evaluation factors for the urban traffic area. Furthermore, the present invention can obtain the operation mode and change law of the traffic in the urban traffic area in different time and space dimensions by analyzing the traffic flow dimension state of the urban traffic area based on the real-time traffic data, which provides an important basis for the subsequent scientific calculation of the congestion disturbance coefficient. Furthermore, the present invention can better analyze the vehicle behavior intention characteristics of vehicles in the urban traffic area based on the driving trajectory image of the area. The purpose and trend of vehicle driving in traffic scenarios can be grasped to provide a basis for the subsequent calculation of road traffic efficiency. Furthermore, the present invention can comprehensively and accurately grasp the traffic impact of surrounding areas on urban traffic areas by collecting land use information and real-time event information in the surrounding areas, extracting the attracting factors therein, and analyzing the traffic pressure conductivity accordingly, so as to provide a strong basis for urban traffic planning and management. The present invention formulates intelligent traffic diversion strategies by comprehensively considering the intensity of the congestion situation, the traffic efficiency and the traffic pressure conductivity, and can grasp the urban traffic conditions from multiple dimensions, greatly improving the scientificity and pertinence of strategy formulation, and then carrying out traffic diversion work based on the strategy, thereby improving the efficiency of intelligent traffic diversion in smart cities. Therefore, the intelligent traffic diversion method and system based on smart cities provided in the embodiments of the present invention can improve the efficiency of intelligent traffic diversion in smart cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A flow chart of a method for intelligent traffic diversion based on a smart city provided by an embodiment of the present invention; Figure 2 A schematic diagram of a module for implementing the smart city-based intelligent traffic diversion method provided in one embodiment of the present invention.

[0017] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0018] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0019] The embodiment of the present application provides a method for intelligent traffic diversion based on smart cities. The execution subject of the method for intelligent traffic diversion based on smart cities includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for intelligent traffic diversion based on smart cities can be executed by software or hardware installed on a terminal device or a server device. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc.

[0020] Embodiment 1: Reference Figure 1 FIG. 1 is a flow chart of a method for intelligent traffic diversion based on a smart city provided by an embodiment of the present invention. In this embodiment, the method for intelligent traffic diversion based on a smart city includes: S1. Obtain an urban traffic area that requires traffic diversion, query the traffic facilities in the urban traffic area, determine the traffic facility operation and maintenance regulations corresponding to the traffic facilities, and formulate congestion evaluation factors for the urban traffic area based on the traffic facility operation and maintenance regulations.

[0021] By determining the traffic facility operation and maintenance regulations corresponding to the traffic facilities, the present invention can obtain scientific and targeted maintenance and management criteria for the traffic facilities under different conditions, thereby providing strong support for the subsequent formulation of congestion evaluation factors in the urban traffic area.

[0022] It should be explained that the urban traffic area that requires traffic diversion refers to the area where traffic congestion frequently occurs due to excessive traffic flow, road construction, emergencies, etc.; the traffic facilities include but are not limited to roads, bridges, traffic lights, bus stops, etc.; the traffic facility operation and maintenance regulations refer to the maintenance, management rules and standards formulated to ensure the normal operation of traffic facilities.

[0023] In detail, the determining of the traffic facility operation and maintenance regulations corresponding to the traffic facility includes: Collecting infrastructure information of the transportation facilities, and calculating information entropy corresponding to the infrastructure information; Based on the information entropy, extracting key facility information from the infrastructure information; Querying the facility operation and maintenance criteria corresponding to the transportation facility, and calculating the fit index between the key facility information and the facility operation and maintenance criteria; Based on the compatibility index and the key facility information, the transportation facility operation and maintenance regulations corresponding to the transportation facility are determined.

[0024] Among them, the infrastructure information is the multi-dimensional basic information and operation status information of the transportation facilities, such as the construction time, service life, geographical location, daily maintenance records, failure frequency, surrounding traffic flow data, etc. The information entropy is a quantitative indicator used to measure the uncertainty or confusion of the infrastructure information. The key facility information is the information from the infrastructure information that has a greater impact on the normal operation of the transportation facilities and contains more key content. The facility operation and maintenance criteria are maintenance and management rules formulated by experts in the transportation field for different types of transportation facilities with reference to advanced domestic and foreign standards and combined with local realities. The fit index represents the degree of matching of each feature in the key facility information and the facility operation and maintenance criteria.

[0025] Furthermore, the infrastructure information of the transportation facilities can be collected through Internet of Things devices, and the information entropy corresponding to the infrastructure information can be calculated through the Shannon entropy algorithm; the information entropy is compared with a preset threshold, and when the information entropy is greater than the preset threshold, the key facility information in the infrastructure information is extracted; the facility operation and maintenance criteria corresponding to the transportation facilities can be queried through the standard document library formulated by the local transportation department; based on the fit index and the key facility information, the key facility information with a high fit index is cross-compared with the facility operation and maintenance criteria, and the unique or abnormal data in the key facility information is targetedly analyzed in combination with expert experience, and reference is made to successful operation and maintenance cases of similar transportation facilities in the past, and finally the transportation facility operation and maintenance regulations corresponding to the transportation facilities are determined.

[0026] Further, as an optional embodiment of the present invention, the calculating of the compatibility index between the key facility information and the facility operation and maintenance criteria includes: Extracting characteristic characters from the key facility information and the facility operation and maintenance criteria to obtain facility information characteristic characters and operation and maintenance criteria characteristic characters; Performing semantic analysis on the facility information characteristic characters and the operation and maintenance criteria characteristic characters respectively to obtain the first characteristic character semantics and the second characteristic character semantics; Performing vectorization processing on the first characteristic character semantics and the second characteristic character semantics to obtain a first semantic vector and a second semantic vector; Combining the first semantic vector and the second semantic vector, the matching index between the key facility information and the facility operation and maintenance criteria is calculated by the following formula: ; Where T represents the fit index between key facility information and facility operation and maintenance criteria, represents the i-th vector in the first semantic vector, i represents the sequence number of the first semantic vector, represents the jth vector in the second semantic vector, j represents the sequence number of the second semantic vector, It means taking the maximum vector between the i-th vector and the j-th vector, and q and r represent the number of the first semantic vector and the number of the second semantic vector respectively.

[0027] It should be explained that the facility information characteristic characters and the operation and maintenance criteria characteristic characters are respectively text symbols or codes used to describe and characterize the characteristics of the key facility information and the facility operation and maintenance criteria, and these characters are text expressions of key features extracted from the key facility information and the facility operation and maintenance criteria; the first characteristic character semantics and the second characteristic character semantics are respectively explanations of the meanings corresponding to the facility information characteristic characters and the operation and maintenance criteria characteristic characters, that is, explanations of the actual meanings expressed by these characters; the first semantic vector and the second semantic vector are respectively numerical vector representations corresponding to the first characteristic character semantics and the second characteristic character semantics, and by mathematically quantifying the character semantics and presenting them in the form of vectors, it is convenient for computers to perform calculations and analysis, and thus used for subsequent operations such as calculating the fit index.

[0028] Furthermore, the TextRank algorithm can be used to extract characteristic characters in the key facility information and the facility operation and maintenance criteria to obtain facility information characteristic characters and operation and maintenance criteria characteristic characters; the semantic analysis method can be used to perform semantic analysis on the facility information characteristic characters and the operation and maintenance criteria characteristic characters to obtain first characteristic character semantics and second characteristic character semantics; the Word2Vec model can be used to vectorize the first characteristic character semantics and the second characteristic character semantics to obtain first semantic vectors and second semantic vectors.

[0029] The present invention formulates the congestion evaluation factors of the urban traffic area based on the traffic facility operation and maintenance regulations, so as to accurately grasp the intrinsic connection between the operation of the traffic facilities and traffic congestion, and provide a quantitative basis for scientifically evaluating the traffic congestion situation. It should be noted that the congestion evaluation factors are the key indicators for measuring the congestion degree of the urban traffic area.

[0030] In detail, the congestion evaluation factors of the urban traffic area are formulated based on the traffic facility operation and maintenance regulations, including: Performing element mining on the transportation facility operation and maintenance regulations to obtain key elements of the regulations; Constructing an element judgment matrix of the key elements of the specification, and calculating element weights corresponding to the key elements of the specification based on the element judgment matrix; The traffic industry standards of the urban traffic area are queried, and the congestion evaluation factors of the urban traffic area are formulated in combination with the factor weights, the traffic industry standards and the key elements of the regulations.

[0031] It should be explained that the key elements of the regulations are the important parts in the traffic facility operation and maintenance regulations that have a great impact on traffic congestion; the element judgment matrix is ​​a square matrix used to compare which key elements of the regulations are more important; the element weight represents the value of how important each key element of the regulations is; the transportation industry standards are the norms and guidelines followed by urban transportation areas.

[0032] Furthermore, the traffic facility operation and maintenance regulations can be processed by natural language processing technology combined with domain knowledge graphs to obtain key regulations elements; the element judgment matrix of the key elements of the regulations can be constructed by matrix functions, such as zero matrix function, and based on the element judgment matrix, the element weights corresponding to the key elements of the regulations can be calculated by using the analytic hierarchy process (AHP) and professional matrix operation methods; The transportation industry standards of the urban transportation area can be queried through the transportation standardization information platform, and the congestion evaluation factors of the urban transportation area can be formulated in combination with the factor weights, the transportation industry standards and the key elements of the regulations. For example, taking the road maintenance frequency as a key element of the regulations as an example, its importance in the congestion evaluation can be judged according to its factor weight; referring to the specifications of the road maintenance frequency in the transportation industry standards, a reasonable numerical range can be set; based on these, the road maintenance frequency can be used as one of the congestion evaluation factors in the urban transportation area, and a scientific evaluation system can be formulated.

[0033] S2. Collect real-time traffic data in the urban traffic area, analyze the traffic flow dimension state of the urban traffic area based on the real-time traffic data, calculate the congestion disturbance coefficient corresponding to the congestion evaluation factor by combining the traffic flow dimension state and the real-time traffic data, and evaluate the congestion trend intensity of the urban traffic area based on the congestion disturbance coefficient.

[0034] The present invention analyzes the traffic flow dimension of the urban traffic area based on the real-time traffic data, and can obtain the operation mode and change law of the traffic in the urban traffic area in different time and space dimensions, which provides an important basis for the subsequent scientific calculation of the congestion disturbance coefficient. It should be explained that the real-time traffic data covers multi-dimensional information such as vehicle flow, vehicle speed, vehicle driving trajectory and traffic light status on the road. The traffic flow dimension is a comprehensive description of different traffic flow patterns in the urban traffic area in the time and space dimensions, reflecting the changes in traffic parameters such as traffic flow, speed, density in different areas and time periods, and is an important basis for measuring the operation status of urban traffic. Furthermore, the real-time traffic data in the urban traffic area can be obtained by real-time collection of equipment such as geomagnetic sensors, cameras, floating vehicles and intelligent traffic signal systems distributed in the urban traffic area.

[0035] In detail, the analyzing the traffic flow state of the urban traffic area based on the real-time traffic data includes: Performing data cleaning on the real-time traffic data to obtain target traffic data; Extracting multi-dimensional traffic features of the target traffic data, and performing standard processing on the multi-dimensional traffic features to obtain standard traffic features; Performing feature dimensionality reduction processing on the standard traffic features to obtain reduced-dimensionality traffic features; Performing feature clustering processing on the dimension-reduced traffic features to obtain clustered traffic features; Performing spatiotemporal pattern analysis on the clustered traffic characteristics to obtain traffic spatiotemporal pattern characteristics; Based on the traffic spatiotemporal pattern characteristics, the traffic flow dimension of the urban traffic area is analyzed.

[0036] It should be explained that the target traffic data is the available data obtained after the real-time traffic data has been cleaned by data operations such as removing outliers and filling missing values; the multi-dimensional traffic features are the multi-dimensional information reflecting the traffic operation status extracted from the target traffic data, such as vehicle flow, vehicle speed, traffic density, etc.; the standard traffic features are the data expression form of the multi-dimensional traffic features after eliminating dimensional differences; the reduced-dimensional traffic features are the standard traffic features, the data after reducing the dimensions while retaining the main information; the clustered traffic features are the data after the reduced-dimensional traffic features are divided into different categories based on the similarity of the data; the traffic spatiotemporal pattern features are the relevant features of the clustered traffic features regarding the distribution and change laws of traffic flow in the time and space dimensions.

[0037] Furthermore, the real-time traffic data can be cleaned by the box plot method to obtain the target traffic data; the multidimensional traffic characteristics of the target traffic data can be extracted by the trained convolutional neural network, and the multidimensional traffic characteristics can be processed by the maximum and minimum normalization method to obtain the standard traffic characteristics; the standard traffic characteristics can be processed by the principal component analysis (PCA) method to obtain the reduced-dimensional traffic characteristics; the reduced-dimensional traffic characteristics can be clustered by the K-Means clustering algorithm to obtain the clustered traffic characteristics; the clustered traffic characteristics can be analyzed by calculating the autocorrelation coefficient of the time series and the Moran index of the space to obtain the traffic spatiotemporal pattern characteristics. For example, in the time dimension, calculating the autocorrelation coefficient of the clustered traffic characteristics time series can reveal the similarity of traffic patterns in different time periods. and changing rules. For example, it is found that the autocorrelation coefficient of the evening rush hour congestion mode is high within several consecutive hours, indicating that the congestion has temporal continuity. In the spatial dimension, the Moran index is used to analyze the correlation of the spatial distribution of clustered traffic characteristics. If the Moran index is positive, it means that similar traffic patterns are clustered in space. For example, congestion clusters frequently occur in certain areas, revealing the spatial aggregation characteristics of congested areas. These analyses are combined to obtain the traffic spatiotemporal pattern characteristics; based on the traffic spatiotemporal pattern characteristics, the traffic flow dimension of the urban traffic area is analyzed. First, based on the traffic spatiotemporal pattern characteristics, from the time perspective, the changing rules of traffic flow in different time periods are analyzed, such as the start, peak value and duration of morning rush hour congestion; then from the spatial dimension, the distribution, aggregation and diffusion direction of the congested area are checked, and the spatiotemporal information is integrated to comprehensively analyze the dynamic change state of traffic flow in the urban traffic area, thereby obtaining the traffic flow dimension.

[0038] The present invention calculates the congestion disturbance coefficient corresponding to the congestion assessment factor by combining the traffic flow dimension and the real-time traffic data, so as to quantitatively assess the influence of the congestion assessment factor on traffic congestion, and provide a key indicator for accurately assessing the intensity of congestion trends in urban traffic areas. It should be explained that the congestion disturbance coefficient is a quantitative indicator used to represent the influence of each congestion assessment factor on the traffic congestion condition. The larger the value, the more significant the influence of the factor on traffic congestion.

[0039] In detail, the calculation of the congestion disturbance coefficient corresponding to the congestion evaluation factor by combining the traffic flow dimension state and the real-time traffic data includes: Selecting a congestion-related dimension corresponding to the congestion evaluation element from the traffic flow dimension, and calculating a dimensional congestion disturbance coefficient corresponding to the congestion-related dimension based on the real-time traffic data; Based on the real-time traffic data, determine whether there is a traffic accident in the urban traffic area; if there is no traffic accident, calculate the congestion disturbance coefficient corresponding to the congestion evaluation factor in combination with the dimensional congestion disturbance coefficient; If a traffic accident occurs, extracting accident feature data related to the traffic accident from the real-time traffic data, and calculating the accident interference degree corresponding to the traffic accident based on the accident feature data; The congestion disturbance coefficient corresponding to the congestion evaluation factor is calculated by combining the accident interference degree and the dimensional congestion disturbance coefficient.

[0040] It should be explained that the congestion-related dimension is a specific state expression in the traffic flow dimension that has a direct correlation and influence on the congestion assessment element; the dimensional congestion disturbance coefficient is a numerical indicator corresponding to the congestion-related dimension that is used to quantify the degree of disturbance caused by the dimension to traffic congestion; the accident characteristic data is specific information about traffic accidents in the real-time traffic data that can reflect the basic situation, scale, severity and handling of the accident; the accident interference degree represents a comprehensive measure of the degree of interference caused to normal traffic order by the traffic accident.

[0041] Furthermore, by setting a threshold range closely related to the congestion assessment factor and combining the method of data trend analysis, the congestion-related dimension corresponding to the congestion assessment factor can be screened out from the traffic flow dimension. Taking traffic flow as an example, the normal flow range is first determined based on historical data. For example, 500-800 vehicles per hour on a certain section of road during the morning rush hour on weekdays is normal. If the current flow exceeds this range, combined with the rising or falling trend of the flow over a period of time, it is determined whether it is related to congestion. If the flow continues to rise for multiple consecutive monitoring periods and exceeds the upper limit, it is included in the congestion-related dimension. Based on the real-time traffic data, the dimensional congestion disturbance coefficient corresponding to the congestion-related dimension is calculated. For example, for the traffic flow dimension, the coefficient can be calculated based on the degree of deviation of the current flow from the historical mean and the degree of impact of the deviation on congestion, and the impact of this deviation on congestion can be judged based on past experience. The larger it is, for example, every 10% exceeding the historical average, the degree of congestion aggravation is 0.1, then the dimensional congestion disturbance coefficient of the traffic flow dimension is calculated as: 0.1×(current flow-historical average) / historical average; based on the real-time traffic data, determine whether there is a traffic accident in the urban traffic area. If there is no traffic accident, sum the dimensional congestion disturbance coefficients to obtain the congestion disturbance coefficient corresponding to the congestion evaluation element; if there is a traffic accident, then by setting targeted data extraction rules, according to key identifiers such as accident timestamps, geographic positioning information, accident type tags, etc., the accident feature data of the traffic accident in the real-time traffic data can be extracted by precise query and screening from the real-time traffic database table; the accident interference degree and the dimensional congestion disturbance coefficient are added to obtain the congestion disturbance coefficient corresponding to the congestion evaluation element.

[0042] Further, as an optional embodiment of the present invention, the calculating the accident interference degree corresponding to the traffic accident based on the accident characteristic data includes: Extracting accident damage records, accident handling cycles and accident occurrence points from the accident feature data, and evaluating the accident level corresponding to the traffic accident based on the accident damage records; Based on the accident handling cycle, determining the accident duration cycle corresponding to the traffic accident; Calculate the distance between the traffic accident and the adjacent road based on the accident occurrence point; In combination with the interval distance value, the accident duration period and the accident level, the accident interference degree corresponding to the traffic accident can be calculated by the following formula: ; Where D represents the accident interference degree corresponding to the traffic accident, E represents the accident level, d represents the interval distance value, and t represents the duration of the accident. Represents the distance influence factor.

[0043] It should be explained that the accident damage record is a specific record of damage-related information such as the degree of vehicle damage, casualties, and property losses in the accident characteristic data; the accident handling cycle is the length of time from the occurrence of the accident to the completion of the accident handling (including on-site cleaning, responsibility determination, claims settlement, etc.) in the accident characteristic data; the accident level indicates the level corresponding to the traffic accident based on the severity of the accident (such as casualties, property losses, social impact, etc.); the interval distance value indicates the spatial straight-line distance or actual passable distance between the traffic accident and the adjacent road; the distance impact factor is a quantitative parameter that comprehensively considers the distance between the accident occurrence point and the adjacent road, and affects the degree of interference of the accident with the adjacent road traffic and the difficulty of rescue.

[0044] Further, the accident damage record, accident handling cycle and accident occurrence point in the accident feature data can be extracted through an extraction function, and the extraction function is compiled by a programming language; based on the accident damage record, the accident level corresponding to the traffic accident is evaluated, such as according to the vehicle damage condition, the number and severity of casualties and the amount of property loss in the accident damage record, and compared with the pre-set accident level classification standard, such as serious injuries to 3 or more people or property losses exceeding 500,000, it is determined to be a major accident level, thereby evaluating the accident level corresponding to the traffic accident, 1-5 levels, 1 for minor, 5 for serious, the pre-set accident level classification standard is usually based on casualties (such as deaths, serious injuries, minor injuries), property loss amount (direct economic loss amount) and social impact of the accident (such as whether it causes long-term traffic congestion, whether it affects the operation of important areas, etc.) and other factors, traffic accidents are divided into different levels, such as minor accidents, general accidents, major accidents and major accidents; Based on the accident handling cycle, taking into account the accuracy of the accident time record and the completeness of the time connection of the intermediate links, the time difference calculation method is used and combined with the time definition rules of the traffic management department on the accident handling process to determine the accident duration corresponding to the traffic accident. For example, the time when the accident was first recorded is obtained, and then the time when the last processing link is completed is determined from the accident handling cycle, and the difference between the two is used to obtain the initial duration. Subsequently, according to the regulations of the traffic management department, the reasonable delay time caused by objective factors such as waiting for rescue and weather is adjusted to finally determine the accident duration; combined with the accident point, a high-precision geographic information system (GIS) is used to obtain the precise coordinates of the accident point, and the center line or boundary coordinates of the adjacent roads are determined at the same time. The interval distance value between the traffic accident and the adjacent roads is calculated through a spatial distance calculation algorithm (such as the Euclidean distance formula or the shortest path algorithm considering the actual road network).

[0045] The present invention evaluates the severity of urban traffic congestion by evaluating the congestion trend intensity of the urban traffic area based on the congestion disturbance coefficient. It should be explained that the congestion trend intensity is a comprehensive evaluation of the overall situation of urban traffic congestion, reflecting the degree of traffic congestion under the joint action of multiple congestion evaluation factors. Furthermore, based on the congestion disturbance coefficient, the congestion trend intensity of the urban traffic area is evaluated, and the congestion trend intensity is judged according to the size of the congestion disturbance coefficient. The larger the coefficient, the greater the impact of the evaluation factor on the congestion, and the higher the congestion trend intensity of the urban traffic area.

[0046] S3. Use the monitoring equipment in the urban traffic area to collect regional driving trajectory images and road scene holographic images of vehicles, analyze the vehicle behavior intention characteristics of vehicles in the urban traffic area based on the regional driving trajectory images, analyze the traffic condition matrix of the roads in the urban traffic area based on the road scene holographic images, and calculate the traffic efficiency of the roads in the urban traffic area by combining the vehicle behavior intention characteristics and the traffic condition matrix.

[0047] By analyzing the vehicle behavior intention characteristics of vehicles in the urban traffic area based on the regional driving trajectory image, the present invention can better grasp the driving purpose and trend of the vehicles in the traffic scene, and provide a basis for the subsequent calculation of the road traffic efficiency.

[0048] It should be explained that the regional driving trajectory image is an image of the vehicle driving path collected by surveillance cameras set at various key locations in the urban traffic area. The road scene holographic image is a full-range image information of the road and its surrounding environment, including road conditions, traffic light status, number of lanes, traffic signs and other information. The vehicle behavior intention characteristics reflect the vehicle's driving intention, such as acceleration, deceleration, turning, lane changing, parking and other behavior patterns. The traffic condition matrix describes the road's traffic conditions, including road width, lane availability, road congestion level, traffic light cycle and other information. Furthermore, the monitoring equipment in the urban traffic area can use high-definition cameras and sensor networks of intelligent transportation systems to ensure the quality and accuracy of the collected images and image information.

[0049] In detail, the analyzing the vehicle behavior intention characteristics of the vehicles in the urban traffic area based on the regional driving trajectory image includes: Performing image preprocessing on the driving trajectory image of the region to obtain an optimized driving trajectory image; Performing feature extraction processing on the optimized driving trajectory image to obtain a feature driving trajectory image; Identifying a vehicle motion trajectory in the characteristic driving trajectory image, and calculating a trajectory change rate of the vehicle in the urban traffic area based on the vehicle motion trajectory; Extracting the track point information corresponding to the characteristic driving track image, and calculating the behavior intention parameters of the vehicles in the urban traffic area based on the track point information; Based on the trajectory change rate and the behavior intention parameter, a vehicle behavior intention feature of the vehicle in the urban traffic area is generated.

[0050] It should be explained that the optimized driving trajectory image is an image obtained after image preprocessing (such as removing noise, adjusting brightness and contrast, etc.) of the regional driving trajectory image, and the characteristic driving trajectory image is an image with key motion information extracted from the optimized driving trajectory image. The vehicle motion trajectory is the route information of the vehicle on the road, and the trajectory change rate indicates the degree of change of the vehicle motion trajectory, such as the frequency of turning, the frequency of acceleration and deceleration, etc. The trajectory point information is the position, speed and other information of the vehicle at different times contained in the characteristic driving trajectory image. The behavior intention parameter is a quantitative indicator that describes the vehicle's behavior intention, such as the number of accelerations, decelerations, and lane changes of the vehicle within a certain period of time.

[0051] Furthermore, the image preprocessing of the regional driving trajectory image can be achieved through image filtering algorithms (such as Gaussian filtering, median filtering) and histogram equalization methods; the feature extraction processing of the optimized driving trajectory image can track the vehicle's motion trajectory through the optical flow method; the recognition of the vehicle's motion trajectory in the characteristic driving trajectory image can be achieved through Hough transform or a target tracking algorithm based on deep learning (such as YOLO, DeepSORT); the extraction of trajectory point information corresponding to the characteristic driving trajectory image can be obtained by analyzing the discrete points of the motion trajectory and calculating parameters such as the speed and acceleration of adjacent trajectory points; based on the trajectory point information, the behavior intention parameters of the vehicles in the urban traffic area are calculated, such as the number of times a vehicle accelerates beyond a certain threshold within one minute as the acceleration behavior intention parameter, and the same applies to deceleration. The lane change behavior can be judged by the angle of change in the direction of the trajectory line, thereby obtaining the behavior intention parameter; the trajectory change rate and the behavior intention parameter are used as the vehicle behavior intention characteristics of the vehicles in the urban traffic area.

[0052] Further, as an optional embodiment of the present invention, the calculating the trajectory change rate of the vehicle in the urban traffic area based on the vehicle motion trajectory includes: Acquire a standard motion trajectory of vehicles in the urban traffic area, and perform curve fitting processing on the vehicle motion trajectory and the standard motion trajectory respectively to obtain a first trajectory curve and a second trajectory curve; Based on the first trajectory curve, calculating a trajectory curvature sequence corresponding to the vehicle motion trajectory to obtain a first trajectory curvature sequence; Based on the second trajectory curve, calculating the trajectory curvature sequence corresponding to the standard motion trajectory to obtain a second trajectory curvature sequence; and calculating the trajectory lengths corresponding to the vehicle motion trajectory and the standard motion trajectory to obtain a first trajectory length and a second trajectory length; The trajectory change rate of the vehicle in the urban traffic area is calculated by combining the first trajectory curvature sequence, the second trajectory curvature sequence, the first trajectory length, and the second trajectory length using the following formula: ; Where F represents the trajectory change rate of vehicles in the urban traffic area, represents the fth curvature value in the first trajectory curvature sequence, represents the fth curvature value in the second trajectory curvature sequence, represents the length of the first trajectory, represents the length of the second trajectory, f represents the sequence number in the trajectory curvature sequence, and u represents the length of the trajectory curvature sequence.

[0053] It should be explained that the standard motion trajectory is the expected driving trajectory of the vehicle under ideal traffic conditions, the first trajectory curve and the second trajectory curve are mathematical representations after curve fitting of the actual and standard trajectories, the first trajectory curvature sequence and the second trajectory curvature sequence are respectively the curvature change sequences of the vehicle motion trajectory and the standard motion trajectory, and the first trajectory length and the second trajectory length are respectively the lengths of the vehicle motion trajectory and the standard motion trajectory.

[0054] Furthermore, the acquisition of the standard motion trajectory of vehicles in the urban traffic area can be simulated through historical data and traffic rules of the traffic planning department; the curve fitting processing of the vehicle motion trajectory and the standard motion trajectory can use polynomial fitting or spline curve fitting methods; the curvature of the first trajectory curve at different positions is calculated to obtain a first trajectory curvature sequence; the calculation of the second trajectory curvature sequence is similar; the trajectory lengths corresponding to the vehicle motion trajectory and the standard motion trajectory can be calculated by the integration method, and the curve length integral formula is applied to the corresponding curve.

[0055] The present invention can comprehensively evaluate the traffic conditions of the roads by analyzing the traffic condition matrix of the roads in the urban traffic area based on the road scene holographic image, and calculate the traffic efficiency of the roads in the urban traffic area by combining the vehicle behavior intention characteristics and the traffic condition matrix, so as to evaluate the traffic efficiency of the roads and provide a reference for traffic management and planning. It should be explained that the traffic condition matrix is ​​a set of multi-dimensional indicators that reflect the traffic conditions of the roads, including the physical conditions of the roads (such as the slope of the roads, the road conditions) and the traffic facility conditions (such as the control strategy of the traffic lights, the setting of the traffic signs), etc. The traffic efficiency indicates the vehicle passing capacity and smoothness of the road within a certain period of time. Furthermore, based on the road scene holographic image, the traffic condition matrix of the roads in the urban traffic area is analyzed, such as evaluating the road by analyzing the texture of the road surface in the image. The smoothness of the surface is determined, the control effect of the traffic light is determined according to the flashing frequency and duration of the traffic light, the availability of the lane is determined by the clarity and integrity of the lane line, etc., so as to obtain the traffic condition matrix; combining the vehicle behavior intention characteristics and the traffic condition matrix, the steps of calculating the traffic efficiency of the roads in the urban traffic area are as follows: first calculate the condition difference between the standard traffic condition matrix and the current traffic condition matrix, as well as the intention difference between the standard vehicle behavior intention characteristics and the current vehicle behavior intention characteristics, respectively assign weights to the condition difference and the intention difference, multiply the condition difference and the intention difference with the corresponding weights and sum them up, calculate the traffic efficiency of the roads in the urban traffic area, and the weight assignment is based on traffic theory and actual experience to determine the weights of the influence of the condition difference and the intention difference on the traffic efficiency, such as through expert scoring method or historical data statistical analysis.

[0056] S4. Collect land use information and real-time event information of the surrounding areas of the urban traffic area, extract attraction factors from the land use information and the real-time event information, and analyze the transmission degree of traffic pressure from the surrounding areas to the urban traffic area based on the attraction factors.

[0057] The present invention collects land use information and real-time event information of surrounding areas, extracts attraction factors therein, and analyzes traffic pressure transmission degree accordingly, so as to comprehensively and accurately grasp the traffic impact of surrounding areas on urban traffic areas, and provide a strong basis for urban traffic planning and management. It should be explained that the land use information includes the land use types of surrounding areas, such as commercial land, residential land, industrial land, etc.; the real-time event information covers emergencies, such as traffic accidents, large-scale events, etc.; the attraction factors refer to those key factors that can attract the flow of people or vehicles, such as the business hours of commercial centers, the time and scale of events, etc. The traffic pressure transmission degree refers to the attraction factors generated by land use, real-time events, etc. in the surrounding areas in the urban traffic system, which cause the flow of people and vehicles to exert a quantitative degree of traffic pressure on the urban traffic area at different time periods and different sections. Furthermore, the collection of land use information can be achieved through The urban planning database and geographic information system (GIS) are used for implementation, and the real-time event information is collected with the help of traffic monitoring systems, social media and news reports. The steps of extracting the attraction meta-factors from the land use information and the real-time event information are as follows: the land use information is classified and processed, and divided into categories such as commercial, residential, industrial, and public services. For different types of land, the corresponding attraction meta-factors are extracted. For example, for commercial land, its business hours, popular business activity periods, etc. are extracted; for residential land, information such as the morning and evening peak travel periods of residents are extracted. The real-time event information is screened and sorted to identify events with traffic impacts, such as traffic accidents, and the time, location, and estimated processing time of the accident are extracted; for large-scale activities, the start and end time of the activity, the number of participants, and the traffic conditions around the activity venue are extracted. The various attraction meta-factors extracted from the land use information and real-time event information are integrated to obtain the attraction meta-factors.

[0058] Furthermore, based on the attraction element factors, the step of analyzing the degree of traffic pressure transmission from the surrounding areas to the urban traffic area is as follows: constructing a traffic pressure transmission model, which comprehensively considers factors such as the type and strength of the attraction element factors and the distance from the urban traffic area. For example, a large commercial center that is close to the urban traffic area and has concentrated business hours has a strong attraction element factor and a significant impact on traffic pressure transmission; while events that are far away and have a smaller scale of activity have relatively little impact.

[0059] The constructed model is calibrated and verified using historical traffic data and geographic information. By analyzing data such as traffic flow changes and congestion conditions under similar historical attracting factors, the model parameters are adjusted to ensure that the model can accurately reflect the laws of traffic pressure transmission.

[0060] The extracted attractor factors are input into the calibrated model to calculate the transmission value of traffic pressure from the surrounding area to the urban traffic area at different time periods and different road sections. For example, the model calculates that during the business hours of the commercial center, the transmission degree of traffic pressure of a surrounding connecting road is 0.8 (the value range is 0-1, the larger the value, the greater the traffic pressure transmission), indicating that this road is under greater traffic pressure during this period due to the attractor factors of the commercial center.

[0061] It should be explained that the traffic pressure transmission model is the core tool for analyzing the degree of traffic pressure transmission. Comprehensive consideration of multiple factors can make the model more realistic; calibration and verification of the model can ensure its accuracy and reliability; the traffic pressure transmission degree value calculated by the model intuitively reflects the degree of influence of the surrounding areas on the traffic pressure of the urban traffic area, and provides a quantitative basis for the traffic management department to formulate measures such as traffic diversion and traffic restrictions.

[0062] S5. Based on the intensity of the congestion situation, the traffic efficiency and the traffic pressure conductivity, formulate an intelligent traffic diversion strategy for the urban traffic area, and based on the intelligent traffic diversion strategy, perform traffic diversion work in the urban traffic area to obtain a traffic diversion result.

[0063] The present invention formulates an intelligent traffic diversion strategy by comprehensively considering the intensity of the congestion trend, the traffic efficiency and the traffic pressure conductivity, which can grasp the urban traffic conditions from multiple dimensions, greatly improving the scientificity and pertinence of strategy formulation, and then carrying out traffic diversion work based on the strategy, so as to improve the efficiency of intelligent traffic diversion in smart cities. It should be explained that the intelligent traffic diversion strategy is a series of specific traffic diversion methods and measures formulated for urban traffic areas, and its purpose is to alleviate traffic congestion and improve traffic smoothness.

[0064] Furthermore, the steps for formulating the intelligent traffic diversion strategy for the urban traffic area are as follows: Classification of traffic conditions: Based on the numerical range of congestion intensity, traffic efficiency and traffic pressure conductivity, the traffic conditions in urban traffic areas are divided into four levels: smooth, light congestion, moderate congestion and heavy congestion. For example, when the congestion intensity is lower than 0.3, the traffic efficiency is higher than 0.8 and the traffic pressure conductivity is lower than 0.2, it is judged as smooth; when the congestion intensity is between 0.3-0.5, the traffic efficiency is between 0.6-0.8 and the traffic pressure conductivity is between 0.2-0.4, it is judged as light congestion. And so on, a clear classification standard is formulated.

[0065] Develop strategies for different levels: Smoothness level: Maintain the existing traffic signal timing plan, maintain normal traffic patrols, and ensure stable traffic order. At the same time, use the traffic big data platform to collect and analyze traffic flow data in real time, provide data support for subsequent traffic planning, strengthen daily maintenance of traffic facilities, ensure that road signs and markings are clear and visible, and traffic lights operate normally.

[0066] Mild congestion level: Appropriately adjust the timing of traffic lights, extend the green light duration in the congested direction, and shorten the green light duration in the non-congested direction to balance the traffic flow. Add traffic coordinators on key sections to guide vehicles to pass in an orderly manner and avoid vehicles cutting in and overtaking. Release real-time traffic information to citizens in a timely manner through traffic broadcasts, mobile phone apps and other channels to guide citizens to reasonably choose travel routes.

[0067] Moderate congestion level: Initiate regional traffic coordination and control strategies, implement linkage control of traffic lights at adjacent intersections based on the congestion conditions of different road sections, realize green wave passage for vehicles, implement tidal lane measures for some severely congested sections, flexibly adjust lane directions based on changes in traffic flow, strengthen traffic management of trucks, motorcycles and other vehicles, and restrict their entry into congested areas during congested periods.

[0068] Severe congestion level: Implement traffic control in core congested areas, such as one-way traffic, restricting the passage of specific vehicles, etc. Call emergency rescue vehicles to promptly handle traffic accidents and faulty vehicles, restore road traffic capacity, cooperate with public transportation departments, increase the frequency of bus and subway departures, and encourage citizens to choose public transportation and reduce the use of private cars.

[0069] Dynamically adjust strategies: Establish a real-time traffic monitoring system to continuously track changes in congestion intensity, traffic efficiency, and traffic pressure transmission. Based on real-time monitoring data, dynamically adjust intelligent traffic diversion strategies to ensure that the strategies always adapt to actual traffic conditions. For example, when congestion in a certain area is alleviated, timely adjust signal timing and traffic control measures to restore normal traffic order.

[0070] Based on the intelligent traffic diversion strategy formulated above, the relevant traffic management departments organize police forces and staff to strictly implement traffic diversion work in urban traffic areas. By rationally allocating human and material resources, they ensure the effective implementation of various diversion measures and ultimately obtain traffic diversion results, including the degree of improvement in traffic congestion, the increase in the average vehicle speed, and feedback data on citizens' travel satisfaction, providing a basis for subsequent optimization of traffic diversion strategies.

[0071] Compared with the problems described in the background technology, the present invention can obtain scientific and targeted maintenance and management criteria for the traffic facilities under different conditions by determining the traffic facility operation and maintenance regulations corresponding to the traffic facilities, thereby providing strong support for the subsequent formulation of congestion evaluation factors for the urban traffic area. Furthermore, the present invention can obtain the operation mode and change law of the traffic in the urban traffic area in different time and space dimensions by analyzing the traffic flow dimension state of the urban traffic area based on the real-time traffic data, which provides an important basis for the subsequent scientific calculation of the congestion disturbance coefficient. Furthermore, the present invention can better analyze the vehicle behavior intention characteristics of vehicles in the urban traffic area based on the driving trajectory image of the area. The purpose and trend of vehicle driving in traffic scenarios can be grasped to provide a basis for the subsequent calculation of road traffic efficiency. Furthermore, the present invention can comprehensively and accurately grasp the traffic impact of surrounding areas on urban traffic areas by collecting land use information and real-time event information in the surrounding areas, extracting the attracting factors therein, and analyzing the traffic pressure conductivity accordingly, so as to provide a strong basis for urban traffic planning and management. The present invention formulates intelligent traffic diversion strategies by comprehensively considering the intensity of the congestion situation, the traffic efficiency and the traffic pressure conductivity, and can grasp the urban traffic conditions from multiple dimensions, greatly improving the scientificity and pertinence of strategy formulation, and then carrying out traffic diversion work based on the strategy, thereby improving the efficiency of intelligent traffic diversion in smart cities. Therefore, the intelligent traffic diversion method and system based on smart cities provided in the embodiments of the present invention can improve the efficiency of intelligent traffic diversion in smart cities.

[0072] Embodiment 2: like Figure 2 The figure shows a functional module diagram of a smart traffic diversion system based on a smart city according to the present invention.

[0073] The intelligent traffic diversion system 200 based on smart city described in the present invention can be installed in an electronic device. According to the functions implemented, the intelligent traffic diversion system based on smart city can include a congestion evaluation factor formulation module 201, a congestion state intensity evaluation module 202, a traffic efficiency calculation module 203, a traffic pressure conductivity analysis module 204 and a traffic diversion module 205. The module described in the present invention can also be called a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0074] In the embodiment of the present invention, the functions of each module / unit are as follows: The congestion evaluation factor formulation module 201 is used to obtain an urban traffic area that needs traffic diversion, query the traffic facilities in the urban traffic area, determine the traffic facility operation and maintenance regulations corresponding to the traffic facilities, and formulate the congestion evaluation factors of the urban traffic area based on the traffic facility operation and maintenance regulations; The congestion situation intensity evaluation module 202 is used to collect real-time traffic data in the urban traffic area, analyze the traffic flow dimension of the urban traffic area based on the real-time traffic data, calculate the congestion disturbance coefficient corresponding to the congestion evaluation factor based on the traffic flow dimension and the real-time traffic data, and evaluate the congestion situation intensity of the urban traffic area based on the congestion disturbance coefficient; The traffic efficiency calculation module 203 is used to collect regional driving trajectory images and road scene holographic images of vehicles using monitoring equipment in the urban traffic area, analyze vehicle behavior intention characteristics of vehicles in the urban traffic area based on the regional driving trajectory images, analyze the traffic condition matrix of roads in the urban traffic area based on the road scene holographic images, and calculate the traffic efficiency of roads in the urban traffic area by combining the vehicle behavior intention characteristics and the traffic condition matrix; The traffic pressure transmission degree analysis module 204 is used to collect land use information and real-time event information of the surrounding areas of the urban traffic area, extract attraction element factors from the land use information and the real-time event information, and analyze the traffic pressure transmission degree of the surrounding areas to the urban traffic area based on the attraction element factors; The traffic diversion module 205 is used to formulate an intelligent traffic diversion strategy for the urban traffic area based on the intensity of the congestion situation, the traffic efficiency and the traffic pressure conductivity, and to perform traffic diversion work in the urban traffic area based on the intelligent traffic diversion strategy to obtain traffic diversion results.

[0075] In detail, each module in the intelligent traffic management system 200 based on smart city in the embodiment of the present invention is used in the same manner as above. Figure 1 The same technical means are used as the intelligent traffic diversion method based on smart cities described in the text, and can produce the same technical effects, so I will not go into details here.

[0076] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A traffic intelligent guidance method based on smart city, characterized in that: The method comprises: Obtaining an urban traffic area that requires traffic diversion, querying traffic facilities in the urban traffic area, determining traffic facility operation and maintenance regulations corresponding to the traffic facilities, and formulating congestion evaluation factors for the urban traffic area based on the traffic facility operation and maintenance regulations; Collecting real-time traffic data in the urban traffic area, analyzing the traffic flow dimension state of the urban traffic area based on the real-time traffic data, calculating the congestion disturbance coefficient corresponding to the congestion evaluation factor based on the traffic flow dimension state and the real-time traffic data, and evaluating the congestion state intensity of the urban traffic area based on the congestion disturbance coefficient; Using monitoring equipment in the urban traffic area to collect regional driving trajectory images and road scene holographic images of vehicles, analyzing vehicle behavior intention characteristics of vehicles in the urban traffic area based on the regional driving trajectory images, analyzing the traffic condition matrix of roads in the urban traffic area based on the road scene holographic images, and calculating the traffic efficiency of roads in the urban traffic area by combining the vehicle behavior intention characteristics and the traffic condition matrix; Collecting land use information and real-time event information of the surrounding areas of the urban traffic area, extracting attraction factors from the land use information and the real-time event information, and analyzing the degree of traffic pressure transmission from the surrounding areas to the urban traffic area based on the attraction factors; Based on the intensity of the congestion situation, the traffic efficiency and the traffic pressure conductivity, an intelligent traffic diversion strategy for the urban traffic area is formulated, and based on the intelligent traffic diversion strategy, traffic diversion work for the urban traffic area is performed to obtain traffic diversion results.

2. The intelligent traffic diversion method based on smart city as claimed in claim 1, characterized in that: The determining of the traffic facility operation and maintenance regulations corresponding to the traffic facility includes: Collecting infrastructure information of the transportation facilities, and calculating information entropy corresponding to the infrastructure information; Based on the information entropy, extracting key facility information from the infrastructure information; Querying the facility operation and maintenance criteria corresponding to the transportation facility, and calculating the fit index between the key facility information and the facility operation and maintenance criteria; Based on the compatibility index and the key facility information, the transportation facility operation and maintenance regulations corresponding to the transportation facility are determined.

3. The intelligent traffic diversion method based on smart city as claimed in claim 2 is characterized in that: The calculating the compatibility index between the key facility information and the facility operation and maintenance criteria includes: Extracting characteristic characters from the key facility information and the facility operation and maintenance criteria to obtain facility information characteristic characters and operation and maintenance criteria characteristic characters; Performing semantic analysis on the facility information characteristic characters and the operation and maintenance criteria characteristic characters respectively to obtain the first characteristic character semantics and the second characteristic character semantics; Performing vectorization processing on the first characteristic character semantics and the second characteristic character semantics to obtain a first semantic vector and a second semantic vector; Combining the first semantic vector and the second semantic vector, the matching index between the key facility information and the facility operation and maintenance criteria is calculated by the following formula: ； Where T represents the fit index between key facility information and facility operation and maintenance criteria, represents the i-th vector in the first semantic vector, i represents the sequence number of the first semantic vector, represents the jth vector in the second semantic vector, j represents the sequence number of the second semantic vector, It means taking the maximum vector between the i-th vector and the j-th vector, and q and r represent the number of the first semantic vector and the number of the second semantic vector respectively.

4. The intelligent traffic diversion method based on smart city as claimed in claim 1, characterized in that: The congestion evaluation factors of the urban traffic area are formulated based on the traffic facility operation and maintenance regulations, including: Performing element mining on the transportation facility operation and maintenance regulations to obtain key elements of the regulations; Constructing an element judgment matrix of the key elements of the specification, and calculating element weights corresponding to the key elements of the specification based on the element judgment matrix; The traffic industry standards of the urban traffic area are queried, and the congestion evaluation factors of the urban traffic area are formulated in combination with the factor weights, the traffic industry standards and the key elements of the regulations.

5. The intelligent traffic diversion method based on smart city as claimed in claim 1, characterized in that: The analyzing the traffic flow state of the urban traffic area based on the real-time traffic data includes: Performing data cleaning on the real-time traffic data to obtain target traffic data; Extracting multi-dimensional traffic features of the target traffic data, and performing standard processing on the multi-dimensional traffic features to obtain standard traffic features; Performing feature dimensionality reduction processing on the standard traffic features to obtain reduced-dimensionality traffic features; Performing feature clustering processing on the dimension-reduced traffic features to obtain clustered traffic features; Performing spatiotemporal pattern analysis on the clustered traffic characteristics to obtain traffic spatiotemporal pattern characteristics; Based on the traffic spatiotemporal pattern characteristics, the traffic flow dimension of the urban traffic area is analyzed.

6. The intelligent traffic diversion method based on smart city as claimed in claim 1, characterized in that: The step of calculating the congestion disturbance coefficient corresponding to the congestion evaluation factor by combining the traffic flow dimension state and the real-time traffic data includes: Selecting a congestion-related dimension corresponding to the congestion evaluation element from the traffic flow dimension, and calculating a dimensional congestion disturbance coefficient corresponding to the congestion-related dimension based on the real-time traffic data; Based on the real-time traffic data, determine whether there is a traffic accident in the urban traffic area; if there is no traffic accident, calculate the congestion disturbance coefficient corresponding to the congestion evaluation factor in combination with the dimensional congestion disturbance coefficient; If a traffic accident occurs, extracting accident feature data related to the traffic accident from the real-time traffic data, and calculating the accident interference degree corresponding to the traffic accident based on the accident feature data; The congestion disturbance coefficient corresponding to the congestion evaluation factor is calculated by combining the accident interference degree and the dimensional congestion disturbance coefficient.

7. The intelligent traffic diversion method based on smart city as claimed in claim 6, characterized in that: The calculating the accident interference degree corresponding to the traffic accident based on the accident characteristic data includes: Extracting accident damage records, accident handling cycles and accident occurrence points from the accident feature data, and evaluating the accident level corresponding to the traffic accident based on the accident damage records; Based on the accident handling cycle, determining the accident duration cycle corresponding to the traffic accident; Calculate the distance between the traffic accident and the adjacent road based on the accident occurrence point; In combination with the interval distance value, the accident duration period and the accident level, the accident interference degree corresponding to the traffic accident can be calculated by the following formula: ； Where D represents the accident interference degree corresponding to the traffic accident, E represents the accident level, d represents the interval distance value, and t represents the duration of the accident. Represents the distance influence factor.

8. The intelligent traffic diversion method based on smart city as claimed in claim 1, characterized in that: The analyzing the vehicle behavior intention characteristics of the vehicles in the urban traffic area based on the regional driving trajectory image includes: Performing image preprocessing on the driving trajectory image of the region to obtain an optimized driving trajectory image; Performing feature extraction processing on the optimized driving trajectory image to obtain a feature driving trajectory image; Identifying a vehicle motion trajectory in the characteristic driving trajectory image, and calculating a trajectory change rate of the vehicle in the urban traffic area based on the vehicle motion trajectory; Extracting the track point information corresponding to the characteristic driving track image, and calculating the behavior intention parameters of the vehicles in the urban traffic area based on the track point information; Based on the trajectory change rate and the behavior intention parameter, a vehicle behavior intention feature of the vehicle in the urban traffic area is generated.

9. The intelligent traffic diversion method based on smart city as claimed in claim 8, characterized in that: The calculating the trajectory change rate of the vehicle in the urban traffic area based on the vehicle motion trajectory includes: Acquire a standard motion trajectory of vehicles in the urban traffic area, and perform curve fitting processing on the vehicle motion trajectory and the standard motion trajectory respectively to obtain a first trajectory curve and a second trajectory curve; Based on the first trajectory curve, calculating a trajectory curvature sequence corresponding to the vehicle motion trajectory to obtain a first trajectory curvature sequence; Based on the second trajectory curve, calculating the trajectory curvature sequence corresponding to the standard motion trajectory to obtain a second trajectory curvature sequence; and calculating the trajectory lengths corresponding to the vehicle motion trajectory and the standard motion trajectory to obtain a first trajectory length and a second trajectory length; The trajectory change rate of the vehicle in the urban traffic area is calculated by combining the first trajectory curvature sequence, the second trajectory curvature sequence, the first trajectory length, and the second trajectory length using the following formula: ； Where F represents the trajectory change rate of vehicles in the urban traffic area, represents the fth curvature value in the first trajectory curvature sequence, represents the fth curvature value in the second trajectory curvature sequence, represents the length of the first trajectory, represents the length of the second trajectory, f represents the sequence number in the trajectory curvature sequence, and u represents the length of the trajectory curvature sequence.

10. A traffic intelligent guidance system based on smart city, characterized in that: The system comprises: A congestion assessment factor formulation module is used to obtain an urban traffic area that needs traffic diversion, query the traffic facilities in the urban traffic area, determine the traffic facility operation and maintenance regulations corresponding to the traffic facilities, and formulate congestion assessment factors for the urban traffic area based on the traffic facility operation and maintenance regulations; A congestion situation intensity evaluation module is used to collect real-time traffic data in the urban traffic area, analyze the traffic flow dimension of the urban traffic area based on the real-time traffic data, calculate the congestion disturbance coefficient corresponding to the congestion evaluation factor based on the traffic flow dimension and the real-time traffic data, and evaluate the congestion situation intensity of the urban traffic area based on the congestion disturbance coefficient; A traffic efficiency calculation module, used to collect regional driving trajectory images and road scene holographic images of vehicles using monitoring equipment in the urban traffic area, analyze vehicle behavior intention characteristics of vehicles in the urban traffic area based on the regional driving trajectory images, analyze the traffic condition matrix of roads in the urban traffic area based on the road scene holographic images, and calculate the traffic efficiency of roads in the urban traffic area by combining the vehicle behavior intention characteristics and the traffic condition matrix; A traffic pressure transmission degree analysis module, used to collect land use information and real-time event information of the surrounding areas of the urban traffic area, extract attraction element factors from the land use information and the real-time event information, and analyze the traffic pressure transmission degree of the surrounding areas to the urban traffic area based on the attraction element factors; The traffic diversion module is used to formulate an intelligent traffic diversion strategy for the urban traffic area based on the intensity of the congestion situation, the traffic efficiency and the traffic pressure conductivity, and to perform traffic diversion work in the urban traffic area based on the intelligent traffic diversion strategy to obtain traffic diversion results.

Images