Urban traffic signal optimization management system and method based on multi-mode satellite navigation

Abstract

The application discloses a kind of urban traffic signal optimization management system and method based on multi-mode satellite navigation, it is related to traffic signal optimization technical field, system includes initial determination module, for determining target area;Distance group processing module, determine the distance between target area and the nearest traffic signal lamp in fixed direction, form distance group;Area influence radius analysis module, based on the number of distance group and target area lane, determine the area influence radius of target area;Multi-mode satellite monitoring module, determine the multi-mode satellite monitoring area of target area;Traffic prediction module, determine the traffic prediction data of target area;Traffic signal optimization module, determine traffic signal optimization instruction.The application integrates a variety of satellite navigation systems, can monitor the real-time state of each traffic area in real time, from the level of social practice, solve the early warning defects of existing traffic optimization algorithm.

Description

Technical Field

[0001] This invention relates to the field of traffic signal optimization technology, specifically a city traffic signal optimization management system and method based on multi-mode satellite navigation. Background Technology

[0002] Traffic signal optimization is a crucial component of modern urban traffic management, significantly impacting traffic congestion, improving traffic flow efficiency, and ensuring road safety. Current traffic signal optimization primarily utilizes several fundamental concepts defined under traffic flow, including flow rate, density, speed, and travel time. Flow rate refers to the number of vehicles passing through a given cross-section per unit time, serving as a key indicator of road utilization efficiency; density is the number of vehicles per unit length of road, reflecting the degree of congestion; speed is the distance a vehicle travels per unit time; and travel time is the total time required to complete a given journey. Existing traffic optimization algorithms almost all use these basic parameters as the foundation of their mathematical models to set optimization standards, which typically include minimizing total vehicle delays, reducing the number of stops, balancing traffic flow in different directions, and increasing intersection throughput. However, in actual use, most traffic optimization algorithms exist only in ideal scenarios. In social practice, apart from the aforementioned main parameter issues, traffic congestion is often caused by illegal lane occupation and arbitrary parking. From a social practice perspective, when traffic flow is not at a certain level, traffic optimization algorithms may lack certain early warnings. However, when traffic flow is not at a certain level, due to factors such as specific locations and times, there are usually a large number of temporary parkings in a certain area, causing traffic congestion. Therefore, how to establish effective prevention methods is a direction that many current traffic optimization algorithms have not addressed. Summary of the Invention

[0003] The purpose of this invention is to provide an urban traffic signal optimization management system and method based on multi-mode satellite navigation to solve the problems raised in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a method for optimizing and managing urban traffic signals based on multi-mode satellite navigation, the method comprising:

[0005] Define the target area;

[0006] Obtain the location of the nearest traffic light in a fixed direction for the target area, determine the distance between the target area and the nearest traffic light in the fixed direction, and form a distance group;

[0007] The radius of influence of the target area is determined based on the distance group and the number of lanes in the target area;

[0008] Based on the regional influence radius of the target area, a circular area is formed with the target area as the center and the regional influence radius as the multi-mode satellite monitoring area for determining the target area;

[0009] Acquire real-time traffic flow data within the multi-mode satellite monitoring area of ​​the target region to determine traffic forecast data for the target region;

[0010] Based on traffic forecast data for the target area, determine traffic signal optimization instructions.

[0011] According to the above technical solution, the fixed direction includes a first direction, a second direction, a third direction, and a fourth direction;

[0012] The first direction refers to the direction formed by the northeast and northwest of the target area; the second direction refers to the direction formed by the northeast and southeast; the third direction refers to the direction formed by the southeast and southwest; the fourth direction refers to the direction formed by the southwest and northwest; the boundary line between each direction belongs to any one of the directions.

[0013] According to the above technical solution, determining the regional influence radius of the target area based on the distance group and the number of lanes in the target area includes:

[0014] The distance group data is denoted as {s1, s2, s3, s4}, where s1, s2, s3, and s4 represent the distances between the target area and the nearest traffic lights in each fixed direction, respectively. The number of lanes y in the target area is constructed, and a functional relationship is established between the distance group and the number of lanes in the target area, including:

[0015] The system constructs a decreasing function f(x) to explain the correlation between the distance x and the radius of influence of the target area. The calculation methods for the radius of influence of the target area include:

[0016]

[0017] Where R represents the radius of influence of the target area; f(s1), f(s2), f(s3), and f(s4) refer to the correlation function values ​​between the distances s1, s2, s3, and s4 and the radius of influence of the target area, respectively; k1 represents the weighted influence coefficient of the distance in the calculation; k2 represents the weighted influence coefficient of the number of lanes in the calculation; and L represents the distance amplification index, which is set by the system and used to amplify the influence value into a specific distance value.

[0018] In the above technical solution, the area influence radius of the target area is mainly to ensure sufficient reaction time when judging the target area. Therefore, if the distance between the target area and the nearest traffic lights in each fixed direction is long, the reaction time is sufficient. When defining the target area, a smaller area radius can be defined. The same applies to the number of lanes. A larger number of lanes can effectively alleviate traffic and provide reaction time from the side.

[0019] According to the above technical solution, the real-time traffic flow data within the multi-mode satellite monitoring area of ​​the target area includes:

[0020] All intersections within the multi-mode satellite monitoring area are marked to form the shortest route from each intersection to the target area. Based on real-time monitoring of vehicles at each intersection by multi-mode satellites, the vehicle is automatically marked when any vehicle arrives at any intersection, and the vehicle confidence score is obtained. The vehicle confidence score is calculated when a vehicle enters the multi-mode satellite monitoring area and arrives at any intersection. It is initially recorded as 1. If the vehicle travels along the shortest route from the intersection to the target area, the confidence score is increased by 1 for each intersection passed. If a vehicle does not travel along the shortest route from the intersection to the target area, the confidence score is changed back to the initial state of 1 at the first intersection where the confidence score changes. The counting stops when the vehicle leaves the multi-mode satellite monitoring area or arrives at the target area. The confidence score data of all vehicles within the multi-mode satellite monitoring area are obtained.

[0021] Historical data is analyzed to obtain the sum-average confidence score data, the maximum number of vehicles, and the total number of vehicles arriving in the target area within any multi-mode satellite monitoring area for any target area in any given period. Simultaneously, the total number of illegally parked vehicles in the current period is collected. The methods for obtaining the sum-average confidence score data and the maximum number of vehicles include:

[0022] Within any given period, the system establishes time-segmented acquisition points. At each time-segmented acquisition point, it collects the sum of confidence data and the total number of vehicles within the multi-mode satellite monitoring area. It then calculates the average value of the sum of confidence data and selects the maximum value of the total number of vehicles.

[0023] According to the above technical solution, the traffic prediction data for determining the target area includes:

[0024] Based on the sum and average of the confidence level data and the maximum number of vehicles as independent variables, and the total number of vehicles arriving at the target area in the current period as the dependent variable, a data fitting function is formed:

[0025]

[0026] Where M refers to the total number of vehicles arriving at the target area in the current period; a1 and a2 refer to the average of the confidence data and the maximum number of vehicles, respectively; n1 and n2 refer to the corresponding fitting parameters; Represents the error term;

[0027] During real-time monitoring, the sum of real-time confidence data and the total number of vehicles are taken as independent variable parameters, and a data fitting function is used to calculate the predicted value of the total number of vehicles arriving in the target area within a period.

[0028] The average value of the ratio of the total number of illegally parked vehicles in the current period to the total number of vehicles arriving at the target area in the current period, based on historical data, is calculated and used as the prediction output.

[0029] Based on the predicted total number of vehicles arriving in the target area within a period and the predicted output, the illegal parking situation in the target area is analyzed and used as the traffic prediction data output for the target area.

[0030] According to the above technical solution, determining traffic signal optimization instructions based on traffic prediction data of the target area includes:

[0031] The system acquires traffic prediction data for the target area and feeds it back to the administrator. The administrator makes a judgment based on the traffic flow prediction data generated by the traffic flow prediction algorithm and the traffic prediction data for the target area, and generates a new traffic signal optimization instruction.

[0032] A city traffic signal optimization and management system based on multi-mode satellite navigation, the system includes:

[0033] The initial determination module is used to determine the target area;

[0034] The distance group processing module is used to obtain the location of the nearest traffic light in a fixed direction in the target area, determine the distance between the target area and the nearest traffic light in the fixed direction, and form a distance group;

[0035] The regional influence radius analysis module determines the regional influence radius of the target area based on the distance group and the number of lanes in the target area.

[0036] The multi-mode satellite monitoring module, based on the regional influence radius of the target area, forms a circular area centered on the target area and uses the regional influence radius as the multi-mode satellite monitoring area to determine the target area.

[0037] The traffic forecasting module is used to acquire real-time traffic flow data within the multi-mode satellite monitoring area of ​​the target area and determine the traffic forecast data for the target area.

[0038] The traffic signal optimization module determines traffic signal optimization instructions based on traffic prediction data for the target area.

[0039] The fixed directions include a first direction, a second direction, a third direction, and a fourth direction;

[0040] The first direction refers to the direction formed by the northeast and northwest of the target area; the second direction refers to the direction formed by the northeast and southeast; the third direction refers to the direction formed by the southeast and southwest; the fourth direction refers to the direction formed by the southwest and northwest; the boundary line between each direction belongs to any one of the directions.

[0041] The regional influence radius analysis module also includes:

[0042] The distance group data is denoted as {s1, s2, s3, s4}, where s1, s2, s3, and s4 represent the distances between the target area and the nearest traffic lights in each fixed direction, respectively. The number of lanes y in the target area is constructed, and a functional relationship is established between the distance group and the number of lanes in the target area, including:

[0043] The system constructs a decreasing function f(x) to explain the correlation between the distance x and the radius of influence of the target area. The calculation methods for the radius of influence of the target area include:

[0044]

[0045] Where R represents the radius of influence of the target area; f(s1), f(s2), f(s3), and f(s4) refer to the correlation function values ​​between the distances s1, s2, s3, and s4 and the radius of influence of the target area, respectively; k1 represents the weighted influence coefficient of the distance in the calculation; k2 represents the weighted influence coefficient of the number of lanes in the calculation; and L represents the distance amplification index, which is set by the system and used to amplify the influence value into a specific distance value.

[0046] The traffic prediction module also includes:

[0047] All intersections within the multi-mode satellite monitoring area are marked to form the shortest route from each intersection to the target area. Based on real-time monitoring of vehicles at each intersection by multi-mode satellites, the vehicle is automatically marked when any vehicle arrives at any intersection, and the vehicle confidence score is obtained. The vehicle confidence score is calculated when a vehicle enters the multi-mode satellite monitoring area and arrives at any intersection. It is initially recorded as 1. If the vehicle travels along the shortest route from the intersection to the target area, the confidence score is increased by 1 for each intersection passed. If a vehicle does not travel along the shortest route from the intersection to the target area, the confidence score is changed back to the initial state of 1 at the first intersection where the confidence score changes. The counting stops when the vehicle leaves the multi-mode satellite monitoring area or arrives at the target area. The confidence score data of all vehicles within the multi-mode satellite monitoring area are obtained.

[0048] Historical data is analyzed to obtain the sum-average confidence score data, the maximum number of vehicles, and the total number of vehicles arriving in the target area within any multi-mode satellite monitoring area for any target area in any given period. Simultaneously, the total number of illegally parked vehicles in the current period is collected. The methods for obtaining the sum-average confidence score data and the maximum number of vehicles include:

[0049] Within any given period, the system establishes time-segmented acquisition points. At each time-segmented acquisition point, it collects the total confidence data and the total number of vehicles within the multi-mode satellite monitoring area, calculates the average value of the total confidence data, and selects the maximum value of the total number of vehicles.

[0050] Based on the sum and average of the confidence level data and the maximum number of vehicles as independent variables, and the total number of vehicles arriving at the target area in the current period as the dependent variable, a data fitting function is formed:

[0051]

[0052] Where M refers to the total number of vehicles arriving at the target area in the current period; a1 and a2 refer to the average of the confidence data and the maximum number of vehicles, respectively; n1 and n2 refer to the corresponding fitting parameters; Represents the error term;

[0053] During real-time monitoring, the sum of real-time confidence data and the total number of vehicles are taken as independent variable parameters, and a data fitting function is used to calculate the predicted value of the total number of vehicles arriving in the target area within a period.

[0054] The average value of the ratio of the total number of illegally parked vehicles in the current period to the total number of vehicles arriving at the target area in the current period, based on historical data, is calculated and used as the prediction output.

[0055] Based on the predicted total number of vehicles arriving in the target area within a period and the predicted output, the illegal parking situation in the target area is analyzed and used as the traffic prediction data output for the target area.

[0056] Compared with the prior art, the beneficial effects of the present invention are: the present invention integrates multiple satellite navigation systems, providing important technologies for high-precision and high-reliability positioning, navigation and timing services, and can monitor the real-time status of various traffic areas in real time. From the perspective of social practice, it solves the early warning defects of existing traffic optimization algorithms, proposes effective prevention methods, analyzes traffic obstacles caused by illegal parking, optimizes traffic instructions, and improves traffic optimization capabilities. Attached Figure Description

[0057] Figure 1 This is a schematic diagram illustrating the steps of the urban traffic signal optimization management method based on multi-mode satellite navigation of the present invention;

[0058] Figure 2 This is a schematic diagram of the urban traffic signal optimization management system based on multi-mode satellite navigation according to the present invention. Detailed Implementation

[0059] Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0060] Example: Figures 1-2 As shown, this invention provides a method for optimizing and managing urban traffic signals based on multi-mode satellite navigation, the method comprising:

[0061] Define the target area;

[0062] Obtain the location of the nearest traffic light in a fixed direction for the target area, determine the distance between the target area and the nearest traffic light in the fixed direction, and form a distance group;

[0063] The fixed directions include a first direction, a second direction, a third direction, and a fourth direction;

[0064] The first direction refers to the direction formed by the northeast and northwest of the target area; the second direction refers to the direction formed by the northeast and southeast; the third direction refers to the direction formed by the southeast and southwest; the fourth direction refers to the direction formed by the southwest and northwest; the boundary line between each direction belongs to any one of the directions.

[0065] The distance group data is constructed and denoted as {s1, s2, s3, s4}, where s1, s2, s3, and s4 refer to the distance between the target area and the nearest traffic light in each fixed direction, respectively.

[0066] The radius of influence of the target area is determined based on the distance group and the number of lanes in the target area;

[0067] Construct the number of lanes y in the target area, and establish a functional relationship between the distance group and the number of lanes in the target area, including:

[0068] The system constructs a decreasing function f(x) to explain the correlation between the distance x and the radius of influence of the target area. The calculation methods for the radius of influence of the target area include:

[0069]

[0070] Where R represents the radius of influence of the target area; f(s1), f(s2), f(s3), and f(s4) refer to the correlation function values ​​between the distances s1, s2, s3, and s4 and the radius of influence of the target area, respectively; k1 represents the weighted influence coefficient of the distance in the calculation; k2 represents the weighted influence coefficient of the number of lanes in the calculation; and L represents the distance amplification index, which is set by the system and used to amplify the influence value into a specific distance value.

[0071] Based on the regional influence radius of the target area, a circular area is formed with the target area as the center and the regional influence radius as the multi-mode satellite monitoring area for determining the target area;

[0072] Acquire real-time traffic flow data within the multi-mode satellite monitoring area of ​​the target region to determine traffic forecast data for the target region;

[0073] All intersections within the multi-mode satellite monitoring area are marked to form the shortest route from each intersection to the target area. Based on real-time monitoring of vehicles at each intersection by multi-mode satellites, the vehicle is automatically marked when any vehicle arrives at any intersection, and the vehicle confidence score is obtained. The vehicle confidence score is calculated when a vehicle enters the multi-mode satellite monitoring area and arrives at any intersection. It is initially recorded as 1. If the vehicle travels along the shortest route from the intersection to the target area, the confidence score is increased by 1 for each intersection passed. If a vehicle does not travel along the shortest route from the intersection to the target area, the confidence score is changed back to the initial state of 1 at the first intersection where the confidence score changes. The counting stops when the vehicle leaves the multi-mode satellite monitoring area or arrives at the target area. The confidence score data of all vehicles within the multi-mode satellite monitoring area are obtained.

[0074] Historical data is analyzed to obtain the sum-average confidence score data, the maximum number of vehicles, and the total number of vehicles arriving in the target area within any multi-mode satellite monitoring area for any target area in any given period. Simultaneously, the total number of illegally parked vehicles in the current period is collected. The methods for obtaining the sum-average confidence score data and the maximum number of vehicles include:

[0075] Within any given period, the system establishes time-segmented acquisition points. At each time-segmented acquisition point, it collects the sum of confidence data and the total number of vehicles within the multi-mode satellite monitoring area. It then calculates the average value of the sum of confidence data and selects the maximum value of the total number of vehicles.

[0076] The traffic forecast data for determining the target area includes:

[0077] Based on the sum and average of the confidence level data and the maximum number of vehicles as independent variables, and the total number of vehicles arriving at the target area in the current period as the dependent variable, a data fitting function is formed:

[0078]

[0079] Where M refers to the total number of vehicles arriving at the target area in the current period; a1 and a2 refer to the average of the confidence data and the maximum number of vehicles, respectively; n1 and n2 refer to the corresponding fitting parameters; Represents the error term;

[0080] During real-time monitoring, the sum of real-time confidence data and the total number of vehicles are taken as independent variable parameters, and a data fitting function is used to calculate the predicted value of the total number of vehicles arriving in the target area within a period.

[0081] The average value of the ratio of the total number of illegally parked vehicles in the current period to the total number of vehicles arriving at the target area in the current period, based on historical data, is calculated and used as the prediction output.

[0082] Based on the predicted total number of vehicles arriving in the target area within a period and the predicted output, the illegal parking situation in the target area is analyzed and used as the traffic prediction data output for the target area.

[0083] The traffic signal optimization instructions determined based on traffic prediction data of the target area include:

[0084] The system acquires traffic prediction data for the target area and feeds it back to the administrator. The administrator makes a judgment based on the traffic flow prediction data generated by the traffic flow prediction algorithm and the traffic prediction data for the target area, and generates a new traffic signal optimization instruction.

[0085] In this embodiment, a multi-mode satellite navigation-based urban traffic signal optimization management system is also provided, the system comprising:

[0086] Initial determination module 101 is used to determine the target area;

[0087] The distance group processing module 102 is used to obtain the location of the nearest traffic light in a fixed direction in the target area, determine the distance between the target area and the nearest traffic light in the fixed direction, and form a distance group;

[0088] The regional influence radius analysis module 103 determines the regional influence radius of the target area based on the distance group and the number of lanes in the target area;

[0089] The multi-mode satellite monitoring module 104, based on the regional influence radius of the target area, forms a circular area centered on the target area and uses the regional influence radius as the multi-mode satellite monitoring area to determine the target area.

[0090] Traffic prediction module 105 is used to acquire real-time traffic flow data within the multi-mode satellite monitoring area of ​​the target area and determine traffic prediction data for the target area;

[0091] The traffic signal optimization module 106 determines traffic signal optimization instructions based on traffic prediction data for the target area.

[0092] The fixed directions include a first direction, a second direction, a third direction, and a fourth direction;

[0093] The first direction refers to the direction formed by the northeast and northwest of the target area; the second direction refers to the direction formed by the northeast and southeast; the third direction refers to the direction formed by the southeast and southwest; the fourth direction refers to the direction formed by the southwest and northwest; the boundary line between each direction belongs to any one of the directions.

[0094] The regional influence radius analysis module 103 also includes:

[0095] The distance group data is denoted as {s1, s2, s3, s4}, where s1, s2, s3, and s4 represent the distances between the target area and the nearest traffic lights in each fixed direction, respectively. The number of lanes y in the target area is constructed, and a functional relationship is established between the distance group and the number of lanes in the target area, including:

[0096] The system constructs a decreasing function f(x) to explain the correlation between the distance x and the radius of influence of the target area. The calculation methods for the radius of influence of the target area include:

[0097]

[0098] Where R represents the radius of influence of the target area; f(s1), f(s2), f(s3), and f(s4) refer to the correlation function values ​​between the distances s1, s2, s3, and s4 and the radius of influence of the target area, respectively; k1 represents the weighted influence coefficient of the distance in the calculation; k2 represents the weighted influence coefficient of the number of lanes in the calculation; and L represents the distance amplification index, which is set by the system and used to amplify the influence value into a specific distance value.

[0099] The traffic prediction module 105 also includes:

[0100] All intersections within the multi-mode satellite monitoring area are marked to form the shortest route from each intersection to the target area. Based on real-time monitoring of vehicles at each intersection by multi-mode satellites, the vehicle is automatically marked when any vehicle arrives at any intersection, and the vehicle confidence score is obtained. The vehicle confidence score is calculated when a vehicle enters the multi-mode satellite monitoring area and arrives at any intersection. It is initially recorded as 1. If the vehicle travels along the shortest route from the intersection to the target area, the confidence score is increased by 1 for each intersection passed. If a vehicle does not travel along the shortest route from the intersection to the target area, the confidence score is changed back to the initial state of 1 at the first intersection where the confidence score changes. The counting stops when the vehicle leaves the multi-mode satellite monitoring area or arrives at the target area. The confidence score data of all vehicles within the multi-mode satellite monitoring area are obtained.

[0101] Historical data is analyzed to obtain the sum-average confidence score data, the maximum number of vehicles, and the total number of vehicles arriving in the target area within any multi-mode satellite monitoring area for any target area in any given period. Simultaneously, the total number of illegally parked vehicles in the current period is collected. The methods for obtaining the sum-average confidence score data and the maximum number of vehicles include:

[0102] Within any given period, the system establishes time-segmented acquisition points. At each time-segmented acquisition point, it collects the total confidence data and the total number of vehicles within the multi-mode satellite monitoring area, calculates the average value of the total confidence data, and selects the maximum value of the total number of vehicles.

[0103] Based on the sum and average of the confidence level data and the maximum number of vehicles as independent variables, and the total number of vehicles arriving at the target area in the current period as the dependent variable, a data fitting function is formed:

[0104]

[0105] Where M refers to the total number of vehicles arriving at the target area in the current period; a1 and a2 refer to the average of the confidence data and the maximum number of vehicles, respectively; n1 and n2 refer to the corresponding fitting parameters; Represents the error term;

[0106] During real-time monitoring, the sum of real-time confidence data and the total number of vehicles are taken as independent variable parameters, and a data fitting function is used to calculate the predicted value of the total number of vehicles arriving in the target area within a period.

[0107] The average value of the ratio of the total number of illegally parked vehicles in the current period to the total number of vehicles arriving at the target area in the current period, based on historical data, is calculated and used as the prediction output.

[0108] Based on the predicted total number of vehicles arriving in the target area within a period and the predicted output, the illegal parking situation in the target area is analyzed and used as the traffic prediction data output for the target area.

[0109] Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for urban traffic signal optimization management based on multi-mode satellite navigation, characterized in that: The method comprises: determining a target area; acquiring the position of the nearest traffic signal lamp in a fixed direction of the target area, determining the distance between the target area and the nearest traffic signal lamp in the fixed direction, and forming a distance group; determining the area influence radius of the target area based on the distance group and the number of lanes of the target area; forming a circular area as the multi-mode satellite monitoring area of the target area based on the area influence radius of the target area and taking the target area as the center; acquiring real-time traffic flow data in the multi-mode satellite monitoring area of the target area and determining the traffic prediction data of the target area; determining the traffic signal optimization instruction based on the traffic prediction data of the target area; the determination of the area influence radius of the target area based on the distance group and the number of lanes of the target area comprises: The distance group data is denoted as wherein, The distance between the target area and the nearest traffic signal lamp in each fixed direction is respectively denoted as y, the number of lanes of the target area is denoted as y, and a function relationship based on the distance group and the number of lanes of the target area is established, including: System constructs a decreasing function For explaining the correlation between the path distance X and the area influence radius of the target area, the calculation method of the area influence radius of the target area includes: ； Wherein, R represents the area influence radius of the target area; Respectively, the road distance The correlation function value between the area influence radius of the target area; The weight influence coefficient representing the road distance in the calculation; The weight influence coefficient representing the number of lanes in the calculation; L represents the distance amplification index, which is set by the system, and is used to amplify the influence value into a specific distance value.

2. The multi-mode satellite navigation based urban traffic signal optimization management method according to claim 1, characterized in that: the fixed direction comprises a first direction, a second direction, a third direction and a fourth direction; the first direction refers to the direction formed by the northeast and northwest of the target area; the second direction refers to the direction formed by the northeast and southeast; the third direction refers to the direction formed by the southeast and southwest; and the fourth direction refers to the direction formed by the southwest and northwest; the boundary line between each direction belongs to any one direction.

3. The multi-mode satellite navigation based urban traffic signal optimization management method according to claim 1, characterized in that: the real-time traffic flow data in the multi-mode satellite monitoring area of the target area comprises: labeling all intersections in the multi-mode satellite monitoring area, forming the nearest route of each intersection to the target area, monitoring the vehicles at each intersection based on the multi-mode satellite, automatically labeling any vehicle when it arrives at any intersection, acquiring the confidence of the vehicle, the confidence of the vehicle refers to starting confidence calculation when the vehicle arrives at any intersection after entering the multi-mode satellite monitoring area, and the initial value is 1; if the vehicle travels according to the nearest route of each intersection to the target area, the confidence increases by 1 every time the vehicle passes an intersection; if there is a vehicle that does not travel according to the nearest route of each intersection to the target area, the confidence changes to the initial state 1 at the first changed intersection, and the counting stops until the vehicle leaves the multi-mode satellite monitoring area or arrives at the target area; and acquiring the confidence data of all vehicles in the multi-mode satellite monitoring area; calling historical data for analysis, acquiring the average value of the total confidence data, the maximum value of the total number of vehicles and the total number of vehicles arriving at the target area in the current period in the multi-mode satellite monitoring area of any target area in any period; at the same time, collecting the total number of vehicles violating the parking rules in the current period; and the acquisition method of the average value of the total confidence data and the maximum value of the total number of vehicles comprises: in any period, the system establishes a time segmentation collection point, collects the total confidence data and the total number of vehicles in the multi-mode satellite monitoring area at each time segmentation collection point, and calculates the average value of the total confidence data and selects the maximum value of the total number of vehicles.

4. The multi-mode satellite navigation based urban traffic signal optimization management method according to claim 3, characterized in that: the determination of the traffic prediction data of the target area comprises: Based on the confidence data sum average value, the vehicle total maximum value as the independent variable parameter, the total number of vehicles arriving at the target area in the current period as the dependent variable, a data fitting function is formed: ; Wherein, M refers to the total number of vehicles arriving at the target area in the current period; Respectively refer to the average value of the total sum of confidence data, the maximum value of the total number of vehicles; Refers to the corresponding fitting parameter; Represents the error term; in the process of real-time monitoring, taking the real-time total confidence data and the total number of vehicles as the independent variable parameters, and using a data fitting function to calculate the predicted value of the total number of vehicles arriving at the target area in the period; Solving the average value based on the proportion of the total number of vehicles in the current period that violate parking based on historical data and the total number of vehicles arriving at the target area in the current period as a prediction output; Based on the prediction value of the total number of vehicles arriving at the target area in the period and the prediction output, the analysis of the illegal parking situation of the target area is obtained as the traffic prediction data output of the target area.

5. The multi-mode satellite navigation based urban traffic signal optimization management method as claimed in claim 1, wherein: The traffic signal optimization instruction determined based on the traffic prediction data of the target area includes: The system obtains the traffic prediction data of the target area and feeds back to the administrator port. The administrator makes a judgment based on the traffic flow prediction data formed by the traffic flow prediction algorithm and the traffic prediction data of the target area, and forms a new traffic signal optimization instruction.

6. A multi-mode satellite navigation based urban traffic signal optimization management system for implementing the multi-mode satellite navigation based urban traffic signal optimization management method as claimed in claim 1, characterized in that: The system includes: An initial determination module for determining a target area; A distance group processing module for obtaining the nearest traffic signal position of the target area in a fixed direction, determining the distance between the target area and the nearest traffic signal in the fixed direction, and forming a distance group; A region influence radius analysis module for determining the region influence radius of the target area based on the distance group and the number of lanes of the target area; A multi-mode satellite monitoring module for determining the multi-mode satellite monitoring area of the target area based on the region influence radius of the target area and forming a circular area as the multi-mode satellite monitoring area of the target area according to the region influence radius; A traffic prediction module for obtaining real-time traffic flow data in the multi-mode satellite monitoring area of the target area and determining traffic prediction data of the target area; A traffic signal optimization module for determining a traffic signal optimization instruction based on the traffic prediction data of the target area.

7. The multi-mode satellite navigation based urban traffic signal optimization management system as claimed in claim 6, wherein: The fixed direction includes a first direction, a second direction, a third direction, and a fourth direction; The first direction refers to the direction formed by the northeast and northwest of the target area; the second direction refers to the direction formed by the northeast and southeast; the third direction refers to the direction formed by the southeast and southwest; the fourth direction refers to the direction formed by the southwest and northwest; the boundary line between each direction belongs to any one direction.

8. The multi-mode satellite navigation based urban traffic signal optimization management system as claimed in claim 7, wherein: The region influence radius analysis module further includes: The distance group data is denoted as wherein, respectively, the road distance between the target area and the nearest traffic signal lamp in each fixed direction, the number of lanes y of the target area, and a function relationship based on the distance group and the number of lanes of the target area is established, including: System constructs a decreasing function For explaining the correlation between the path distance X and the area influence radius of the target area, the calculation method of the area influence radius of the target area includes: ； Wherein, R represents the area influence radius of the target area; Respectively, the road distance The correlation function value between the area influence radius of the target area; The weight influence coefficient representing the road distance in the calculation; The weight influence coefficient representing the number of lanes in the calculation; L represents the distance amplification index, which is set by the system, and is used to amplify the influence value into a specific distance value.

9. The multi-mode satellite navigation based urban traffic signal optimization management system as claimed in claim 7, wherein: The traffic prediction module further includes: Mark all intersections in the multi-mode satellite monitoring area to form the nearest route of each intersection to the target area, monitor the vehicles at each intersection in real time based on the multi-mode satellite, and automatically mark the vehicle when any vehicle arrives at any intersection. Get the vehicle confidence, the vehicle confidence refers to starting confidence calculation when the vehicle enters the multi-mode satellite monitoring area and arrives at any intersection, initially marked as 1, if the vehicle travels according to the nearest route of each intersection to the target area, the confidence increases by 1 every time a intersection is passed, if there is a vehicle that does not travel according to the nearest route of each intersection to the target area, the confidence changes to the initial state 1 at the first changed intersection, and the counting stops when the vehicle exits the multi-mode satellite monitoring area or reaches the target area, and the confidence data of all vehicles in the multi-mode satellite monitoring area is obtained. The call history data is analyzed to obtain the average value of the confidence data sum, the maximum value of the vehicle total number, and the total number of vehicles arriving at the target area in the current period in the multi-mode satellite monitoring area of any target area in any period. At the same time, the total number of vehicles in violation of parking in the current period is collected. The average value of the confidence data sum and the maximum value of the vehicle total number are obtained in the following manner: In any period, the system establishes a time division collection point, and collects the confidence data sum and the vehicle total number in the multi-mode satellite monitoring area at each time division collection point, calculates the average value of the confidence data sum, and selects the maximum value of the vehicle total number; Based on the confidence data sum average value, the vehicle total maximum value as the independent variable parameter, the total number of vehicles arriving at the target area in the current period as the dependent variable, a data fitting function is formed: ; wherein M refers to the total number of vehicles arriving at the target area in the current period; respectively refer to the average value of the total sum of confidence data and the maximum value of the total number of vehicles; refers to the corresponding fitting parameter; represents the error term; In the real-time monitoring process, the real-time confidence data sum and the vehicle total number are taken as independent variable parameters, and a data fitting function is used to calculate the predicted value of the total number of vehicles arriving at the target area in the period; Based on the ratio of the total number of vehicles in violation of parking in the current period to the total number of vehicles arriving at the target area in the current period, the average value is solved as the prediction output; Based on the predicted value of the total number of vehicles arriving at the target area in the period and the prediction output, the illegal parking situation of the target area is analyzed as the traffic prediction data output of the target area.

Images