Urban traffic path planning method and system

Abstract

The invention provides an urban traffic path planning method and system. The urban traffic path planning method comprises the following steps: taking an area between a starting point and an ending point of current path planning as a target area; extracting a path node meeting a passing requirement between a starting point and an ending point in the target area, and performing area division on the target area according to node specificity of the path node to obtain a plurality of target sub-areas; and target path node screening is performed on the path nodes included in each target sub-region, and a planned path is formed according to the screened target path nodes in combination with the corresponding road sections. The system comprises modules corresponding to the steps of the method.

Description

Technical Field

[0001] The present invention provides an urban traffic route planning method and system, belonging to the technical field of route planning. Background Art

[0002] With the acceleration of urbanization and the continuous expansion of cities, urban transportation systems are becoming increasingly complex, and traffic congestion is becoming increasingly severe, causing significant inconvenience to people's daily commutes. In the field of urban transportation, route planning, as a key technology for achieving efficient travel and alleviating traffic pressure, has attracted extensive attention and research. Traditional urban transportation route planning methods are primarily based on simple principles of shortest distance or shortest time, using static map data and pre-set traffic rules to plan routes. In early urban transportation environments, these methods were able to meet people's travel needs to a certain extent due to relatively low traffic volumes and simple road network structures. However, with the development of cities, traffic conditions have become extremely complex, and the limitations of traditional methods have become increasingly apparent. For one thing, traditional methods often only consider direct connections between starting and ending points, ignoring the complex traffic conditions within the target area and the differences in traffic characteristics between different areas. Different areas in an urban transportation network may have different traffic flow characteristics, road capacities, and traffic control regulations. For example, commercial areas may experience heavy traffic and severe road congestion during peak hours, while residential areas may experience lower traffic volumes at night, but some sections may be subject to restrictions or construction. Traditional methods fail to effectively distinguish and process these regional characteristics, resulting in the planned paths being suboptimal during actual driving and unable to adapt to complex traffic environments. On the other hand, traditional path planning methods lack specificity in selecting path nodes. Within the target area, there are a large number of path nodes, but not all nodes are suitable for constructing a planned path. Traditional methods may simply select some nodes for path combination, without fully considering the correlation between nodes and road sections and the importance of nodes in the overall path planning. For example, some nodes may be located at traffic bottlenecks, and selecting these nodes may lead to path congestion or excessive travel time; while some nodes with special traffic functions (such as overpasses, expressway entrances, etc.) may play an important role in optimizing the path, but traditional methods may not fully explore and utilize the advantages of these nodes.

[0003] Furthermore, existing urban traffic route planning methods are mostly based on static traffic data and lack the effective use of real-time traffic information. Urban traffic conditions are dynamic, and emergencies such as traffic accidents, road construction, and temporary traffic restrictions can occur at any time, resulting in reduced capacity or even impassability on certain road sections. Because traditional methods are unable to obtain and process this real-time information in a timely manner, the planned routes may not conform to actual conditions during driving, failing to provide travelers with accurate and reliable route guidance.

[0004] Therefore, in order to overcome the shortcomings of existing urban traffic path planning methods, improve the accuracy and adaptability of path planning, and meet people's growing travel needs, it is necessary to develop a new urban traffic path planning method that can fully consider the differences in traffic characteristics of the target area, screen target path nodes in a targeted manner, and combine real-time traffic information for path planning to achieve more efficient and reasonable urban traffic travel. Summary of the Invention

[0005] The present invention provides a method and system for urban traffic route planning to solve the above-mentioned technical problems existing in the prior art. The technical solutions adopted are as follows:

[0006] A method for urban traffic path planning, comprising:

[0007] The area between the starting point and the end point of the current path planning is used as the target area;

[0008] Extracting path nodes in the target area that meet the passage requirements between the starting point and the end point, and dividing the target area into regions according to the node characteristics of the path nodes to obtain multiple target sub-regions;

[0009] The target path nodes contained in each target sub-area are screened, and a planned path is formed based on the screened target path nodes and their corresponding road sections.

[0010] Furthermore, the target area is divided into regions according to the node specificity of the path nodes to obtain multiple target sub-regions, including:

[0011] The area between the starting point and the end point of the current path planning is retrieved as the target area and the path nodes within it that meet the traffic requirements between the starting point and the end point;

[0012] Get the straight-line distance between every two adjacent path nodes;

[0013] Retrieve the average traffic volume and average vehicle speed corresponding to each path node;

[0014] Obtaining a grid size based on the straight-line distance between each two adjacent path nodes combined with the average traffic flow and the average speed of vehicles corresponding to each path node;

[0015] The grid size is obtained by the following formula:

[0016]

[0017] Where L represents the grid size; L p represents the average distance corresponding to the straight-line distance between all two adjacent path nodes; n represents the number of path nodes; Y gi represents the average traffic flow corresponding to the i-th path node after normalization; V gi represents the average speed of the vehicle corresponding to the i-th path node after normalization; s represents the adjustment coefficient, and the adjustment coefficient is obtained by the following formula:

[0018]

[0019] Among them, σ L Indicates the standard deviation of the straight-line distance between each two adjacent path nodes; L max represents the maximum straight-line distance between every two adjacent path nodes; ε represents a preset non-zero minimum constant to prevent the numerator from being zero, and the value range of the non-zero minimum constant is 0.1-0.5;

[0020] The target area is divided into regions according to the grid size to obtain multiple target sub-regions.

[0021] Furthermore, target path nodes are screened for the path nodes contained in each target sub-area, and a planned path is formed based on the screened target path nodes and their corresponding road sections, including:

[0022] Obtaining dynamic index parameters of each path node according to the dynamic characteristics of the path nodes contained in each target sub-region;

[0023] Filter the path nodes of each target sub-area to obtain the target path nodes corresponding to each target sub-area;

[0024] The target path nodes are connected with the road sections between each target path node to form a planned path.

[0025] Furthermore, the dynamic index parameters of each path node are obtained according to the dynamic characteristics of the path nodes contained in each target sub-region, including:

[0026] Extracting dynamic features of the path nodes contained in each target sub-region; wherein the dynamic features of the path nodes include the standard deviation of traffic flow, the standard deviation of the average speed of vehicles passing, and the peak traffic flow during the peak period;

[0027] The node dynamic parameters corresponding to each path node are obtained using the standard deviation of the traffic flow and the standard deviation of the average vehicle speed corresponding to each path node; wherein the standard deviation of the traffic flow refers to the standard deviation value obtained from the corresponding traffic flow values ​​within all unit time (the value range is 1h-3h);

[0028] The node dynamic parameters corresponding to each path node are obtained by the following formula:

[0029]

[0030] Among them, K represents the node dynamic parameter corresponding to each path node; σ gc and σ gv represents the normalized traffic flow standard deviation and the average vehicle speed standard deviation corresponding to each path node; U vmax Indicates the normalized traffic flow value corresponding to the maximum average speed of each path node;

[0031] According to the node dynamic parameters corresponding to each path node and the traffic flow peak value of each path node in the high traffic period, the dynamic index parameters corresponding to each path node are obtained;

[0032] The dynamic index parameter corresponding to each path node is obtained by the following formula:

[0033]

[0034] Among them, D represents the dynamic index parameter; K represents the node dynamic parameter corresponding to each path node; m represents the number of traffic peaks experienced by each path node; U i represents the normalized peak traffic volume corresponding to the i-th traffic peak period; U vmax Indicates the normalized traffic flow value corresponding to the maximum average speed of each path node; U max represents the normalized maximum value of traffic flow peak corresponding to m traffic peak periods; σ U Represents the normalized peak traffic flow standard deviation corresponding to m traffic peak periods.

[0035] Furthermore, the path nodes of each target sub-area are screened to obtain the target path nodes corresponding to each target sub-area, including:

[0036] Comparing the dynamic index parameter of each path node contained in each target sub-area with a preset dynamic index parameter threshold;

[0037] The path node corresponding to the dynamic index parameter not lower than the preset dynamic index parameter threshold is used as the target path node.

[0038] An urban traffic path planning system, comprising:

[0039] The target area acquisition module is used to take the area between the starting point and the end point of the current path planning as the target area;

[0040] a target sub-region acquisition module, configured to extract path nodes in the target region that meet the passage requirements between the starting point and the end point, and divide the target region into regions according to the node characteristics of the path nodes to obtain a plurality of target sub-regions;

[0041] The path planning module is used to screen the target path nodes contained in each target sub-area, and form a planned path based on the screened target path nodes and their corresponding road sections.

[0042] Furthermore, the target sub-region acquisition module includes:

[0043] The path node acquisition module is used to retrieve the area between the starting point and the end point of the current path planning as the target area and the path nodes within it that meet the traffic requirements between the starting point and the end point;

[0044] A distance information retrieval module is used to retrieve the straight-line distance between every two adjacent path nodes;

[0045] The vehicle information retrieval module is used to retrieve the average traffic flow and average vehicle speed corresponding to each path node;

[0046] A grid size acquisition module is used to acquire the grid size according to the straight-line distance between each two adjacent path nodes combined with the average traffic flow corresponding to each path node and the average speed of vehicles traveling;

[0047] The grid size is obtained by the following formula:

[0048]

[0049] Where L represents the grid size; L p represents the average distance corresponding to the straight-line distance between all two adjacent path nodes; n represents the number of path nodes; Y gi represents the average traffic flow corresponding to the i-th path node after normalization; V girepresents the average speed of the vehicle corresponding to the i-th path node after normalization; s represents the adjustment coefficient, and the adjustment coefficient is obtained by the following formula:

[0050]

[0051] Among them, σ L Indicates the standard deviation of the straight-line distance between each two adjacent path nodes; L max represents the maximum straight-line distance between every two adjacent path nodes; ε represents a preset non-zero minimum constant to prevent the numerator from being zero, and the value range of the non-zero minimum constant is 0.1-0.5;

[0052] The region division module is used to divide the target region into regions according to the grid size to obtain multiple target sub-regions.

[0053] Furthermore, the path planning module includes:

[0054] A dynamic index parameter acquisition module, configured to acquire dynamic index parameters of each path node according to the dynamic characteristics of the path nodes contained in each target sub-region;

[0055] A target path node determination module is used to screen the path nodes of each target sub-area and obtain the target path node corresponding to each target sub-area;

[0056] The planned path forming module is used to connect the target path nodes and the road sections between each target path node to form a planned path.

[0057] Furthermore, the dynamic indicator parameter acquisition module includes:

[0058] A dynamic feature extraction module is used to extract dynamic features of the path nodes contained in each target sub-area; wherein the dynamic features of the path nodes include the standard deviation of traffic flow, the standard deviation of the average speed of vehicles passing, and the peak traffic flow during the peak period;

[0059] The node dynamic parameter acquisition module is used to obtain the node dynamic parameters corresponding to each path node using the standard deviation of the traffic flow and the standard deviation of the average vehicle speed corresponding to each path node; wherein the standard deviation of the traffic flow refers to the standard deviation value obtained from the corresponding traffic flow values ​​within all unit time (the value range is 1 hour to 3 hours);

[0060] The node dynamic parameters corresponding to each path node are obtained by the following formula:

[0061]

[0062] Among them, K represents the node dynamic parameter corresponding to each path node; σ gc and σ gv represents the normalized traffic flow standard deviation and the average vehicle speed standard deviation corresponding to each path node; U vmax Indicates the normalized traffic flow value corresponding to the maximum average speed of each path node;

[0063] A dynamic index parameter acquisition execution module is used to obtain the dynamic index parameter corresponding to each path node according to the node dynamic parameter corresponding to each path node and the traffic flow peak value of the high traffic period corresponding to each path node;

[0064] The dynamic index parameter corresponding to each path node is obtained by the following formula:

[0065]

[0066] Among them, D represents the dynamic index parameter; K represents the node dynamic parameter corresponding to each path node; m represents the number of traffic peaks experienced by each path node; U i represents the normalized peak traffic volume corresponding to the i-th traffic peak period; U vmax Indicates the normalized traffic flow value corresponding to the maximum average speed of each path node; U max represents the normalized maximum value of traffic flow peak corresponding to m traffic peak periods; σ U Represents the normalized peak traffic flow standard deviation corresponding to m traffic peak periods.

[0067] Furthermore, the target path node determination module includes:

[0068] A comparison module, configured to compare the dynamic index parameter of each path node contained in each target sub-region with a preset dynamic index parameter threshold;

[0069] The target node screening and determination module is used to select the path node corresponding to the dynamic index parameter not lower than the preset dynamic index parameter threshold as the target path node.

[0070] Beneficial effects of the present invention:

[0071] The proposed urban traffic route planning method and system divides target sub-regions according to the characteristics of route nodes. This allows for planning strategies to be adapted to different regions based on differences in node function and capacity (e.g., transportation hubs, ordinary intersections, etc.). This allows each sub-region's route planning to be tailored to its specific characteristics, ensuring the rationality of the planned route across different road sections and improving the overall route's adaptability. Path nodes in each sub-region are screened to remove redundant and unreasonable nodes while retaining key, valid nodes. Combining road sections to form a planned route reduces invalid path exploration and shortens planning time, while ensuring the simplicity and efficiency of the route, improving traffic efficiency and reducing congestion. Through regional division and node screening, complex road conditions within the target region (e.g., both expressways and small alleyways) can be flexibly addressed. Customized planning is achieved for each sub-region, enabling diversified route planning to meet diverse travel needs (e.g., fast travel, convenient routes) while ensuring accessibility, thereby enhancing the flexibility and satisfaction of the transportation system's services. A systematic planning process is constructed, from regional demarcation and division to node screening and route formation. Each link is promoted layer by layer and coordinated with each other, so that the route planning has clear logic from the overall to the local, ensuring the scientificity and consistency of the planning results, providing orderly and efficient method support for urban traffic route planning, and helping urban traffic to run smoothly. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] Figure 1 A flow chart of the method of the present invention;

[0073] Figure 2 This is a system block diagram of the system of the present invention. DETAILED DESCRIPTION

[0074] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0075] The embodiment of the present invention proposes a method for urban traffic route planning, such as Figure 1 As shown, the urban traffic path planning method includes:

[0076] The area between the starting point and the end point of the current path planning is used as the target area;

[0077] Extracting path nodes in the target area that meet the passage requirements between the starting point and the end point, and dividing the target area into regions according to the node characteristics of the path nodes to obtain multiple target sub-regions;

[0078] The target path nodes contained in each target sub-area are screened, and a planned path is formed based on the screened target path nodes and their corresponding road sections.

[0079] The working principle and technical effect of the above technical solution are as follows: First, the target area between the starting and ending points is identified, and path nodes that meet traffic requirements are extracted. These nodes are then divided into multiple target sub-areas based on their characteristics. Path nodes within each sub-area are then screened and combined with corresponding road sections to form a planned path. Defining the target area between the starting and ending points narrows the spatial scope of path planning, avoiding interference from irrelevant areas, focusing planning on the areas where traffic is actually needed, improving planning relevance and efficiency, and quickly identifying the approximate space of potential paths. Dividing target sub-areas based on path node characteristics allows for planning strategies to be tailored to different areas based on the function and traffic capacity of nodes (such as transportation hubs and ordinary intersections). This allows path planning to be tailored to each sub-area's characteristics, ensuring the rationality of the planned path across different road sections and improving the overall path's traffic adaptability. Path nodes within each sub-area are screened to remove redundant and unreasonable nodes, retaining key, valid nodes. Combining road sections to form a planned path reduces the exploration of ineffective paths and shortens planning time, while ensuring a simple and efficient path, improving traffic efficiency, and reducing congestion. Through regional division and node screening, we can flexibly respond to complex road conditions in the target area (such as both expressways and small alleys). Customized planning is carried out according to the characteristics of different sub-regions. While ensuring traffic requirements, diversified route planning is implemented to meet different travel needs (such as fast, on the way), thereby improving the flexibility and satisfaction of transportation system services. From regional demarcation and division to node screening and route formation, a systematic planning process is constructed. Each link is promoted layer by layer and coordinated with each other, so that the route planning has a clear logic from the overall to the local, ensuring the scientificity and consistency of the planning results, providing an orderly and efficient method support for urban traffic route planning, and facilitating the smooth operation of urban traffic.

[0080] In one embodiment of the present invention, the target area is divided according to the node-specific information of the path nodes to obtain multiple target sub-areas, including:

[0081] The area between the starting point and the end point of the current path planning is retrieved as the target area and the path nodes within it that meet the traffic requirements between the starting point and the end point;

[0082] Get the straight-line distance between every two adjacent path nodes;

[0083] Retrieve the average traffic volume and average vehicle speed corresponding to each path node;

[0084] Obtaining a grid size based on the straight-line distance between each two adjacent path nodes combined with the average traffic flow and the average speed of vehicles corresponding to each path node;

[0085] The grid size is obtained by the following formula:

[0086]

[0087] Where L represents the grid size; L p represents the average distance corresponding to the straight-line distance between all two adjacent path nodes; n represents the number of path nodes; Y gi represents the average traffic flow corresponding to the i-th path node after normalization; V gi represents the average speed of the vehicle corresponding to the i-th path node after normalization; s represents the adjustment coefficient, and the adjustment coefficient is obtained by the following formula:

[0088]

[0089] Among them, σ L Indicates the standard deviation of the straight-line distance between each two adjacent path nodes; L max represents the maximum straight-line distance between every two adjacent path nodes; ε represents a preset non-zero minimum constant to prevent the numerator from being zero, and the value range of the non-zero minimum constant is 0.1-0.5;

[0090] The target area is divided into regions according to the grid size to obtain multiple target sub-regions.

[0091] The working principle and technical effect of the above technical solution are: obtain the target area (between the starting point and the end point) and the path nodes that meet the traffic requirements, collect the straight-line distance between adjacent nodes, the average traffic flow and the average speed of each node. First, use the average distance L p , number of nodes n, normalized traffic flow Y gi and vehicle speed V gi , using product logarithm operation to build the basic grid size association; then introduce the adjustment coefficient s (based on the distance standard deviation σ L , maximum distance L max , minimum constant ε calculation, balance distance fluctuation effect), and finally through the formula Calculate the grid size. Based on the calculated grid size, divide the target area into multiple target sub-areas.

[0092] The existing grid division technology mostly adopts fixed size (such as rectangular grid with uniform side length), which cannot adapt to the dynamic changes of traffic flow. This solution integrates the normalization of traffic flow and speed (Y gi 、V giParticipate in logarithmic operations) to dynamically associate the grid size with the node traffic load (traffic volume) and traffic efficiency (vehicle speed). In areas with heavy traffic and large speed differences, the grid size is adaptively adjusted to better fit the actual traffic flow distribution, thereby improving the adaptability of path planning to dynamic traffic. Accurately balance distance fluctuations Traditional grid division ignores the discreteness of path node spacing (such as the difference in spacing between main roads and small alleys in the city). This scheme introduces an adjustment coefficient s, quantifies spacing fluctuations through the distance standard deviation σL and the maximum distance Lmax, and combines the minimum constant ε to avoid calculation anomalies, so that the grid size can accurately balance the "node spacing discreteness" and "traffic characteristics", solve the problem of insufficient adaptation of fixed grids to complex spacing, and improve the spatial rationality of regional division. Multi-dimensional collaborative optimization Existing methods mostly divide grids based on geographic space (such as administrative boundaries, fixed distances). This scheme coordinates three dimensions: mean distance L, traffic flow (traffic volume, speed), and spacing fluctuations: mean distance L p Ensure the basic scale of the grid; integrate vehicle volume and speed through logarithmic operations to adapt to traffic dynamics; adjust the coefficient s to balance spacing fluctuations. Compared with single-dimensional division, multi-dimensional collaboration enables the grid to more accurately match traffic path planning needs, providing a more reasonable sub-region basis for subsequent path node screening and path generation. Improve path planning efficiency. Because grid division is more adapted to traffic characteristics, the subsequent screening and planning of path nodes in sub-regions can reduce invalid node traversal (such as nodes with extremely low traffic load or extremely poor traffic efficiency). Compared with fixed grid division, this solution can compress invalid planning space, improve the operating efficiency of the path planning algorithm, output reasonable traffic paths more quickly, and adapt to the real-time planning needs of urban traffic.

[0093] In one embodiment of the present invention, target path nodes are screened for path nodes contained in each target sub-area, and a planned path is formed based on the screened target path nodes and their corresponding road segments, including:

[0094] Obtaining dynamic index parameters of each path node according to the dynamic characteristics of the path nodes contained in each target sub-region;

[0095] Filter the path nodes of each target sub-area to obtain the target path nodes corresponding to each target sub-area;

[0096] The target path nodes are connected with the road sections between each target path node to form a planned path.

[0097] The working principle and technical effect of the above technical solution are as follows: for the path nodes in each target sub-area, dynamic indicator parameters reflecting the real-time or dynamic characteristics of the nodes (such as real-time traffic volume, speed changes, congestion trends, etc.) are collected and calculated to quantify the traffic status of the nodes. Based on the dynamic indicator parameters, the path nodes in each sub-area are screened, and nodes with poor traffic conditions (such as long-term congestion, extremely low traffic efficiency) or no value for path planning are eliminated, retaining high-quality target path nodes. The screened target path nodes are connected according to the connectivity relationship of the road sections to form a complete planned path from the starting point to the end point.

[0098] Existing path planning often relies on static node attributes (such as fixed traffic volume and historical congestion data) and is unable to respond to dynamic traffic changes (such as sudden congestion and temporary traffic restrictions) in real time. This solution uses dynamic indicator parameters (reflecting the real-time status of nodes) to filter nodes, allowing the planned path to accurately adapt to the dynamic fluctuations of traffic flow, solving the problem of static planning lagging behind real-time traffic and improving path efficiency. Traditional planning methods often ignore sub-regional differences (such as the different traffic characteristics of different sub-regions within the same area) and adopt a global unified filtering logic. This solution independently filters the target sub-region and customizes the filtering rules based on the dynamic characteristics of the nodes in the sub-region. This allows the path nodes in each sub-region to adapt to its own traffic characteristics (for example, commercial sub-regions focus on congestion relief, while residential sub-regions focus on traffic efficiency), improving the adaptability of path planning in complex urban areas. Existing methods are prone to detours and congestion in planned paths due to the inclusion of invalid nodes (such as those under long-term construction or extremely poor traffic capacity). This solution eliminates invalid nodes through dynamic screening, focuses on high-quality target nodes, reduces invalid exploration in path planning, shortens planning time, and ensures that the path is "short, flat, and fast" (short distance, less congestion, and high efficiency), thereby improving the user's travel experience. Compared with the existing planning process of "undifferentiated regional division + extensive node processing", this solution connects with the dynamic grid division mentioned above (sub-regions adapted to traffic characteristics) and amplifies the value of regional division through dynamic node screening in sub-regions. This allows "region division-node screening-path connection" to form a collaborative closed loop, improving the scientificity and accuracy of path planning throughout the entire process, from spatial division to node quality, and solving the problem of "region and node separation" in traditional planning.

[0099] In one embodiment of the present invention, obtaining dynamic index parameters of each path node according to the dynamic characteristics of the path nodes contained in each target sub-region includes:

[0100] Extracting dynamic features of the path nodes contained in each target sub-region; wherein the dynamic features of the path nodes include the standard deviation of traffic flow, the standard deviation of the average speed of vehicles passing, and the peak traffic flow during the peak period;

[0101] The node dynamic parameters corresponding to each path node are obtained using the standard deviation of the traffic flow and the standard deviation of the average vehicle speed corresponding to each path node; wherein the standard deviation of the traffic flow refers to the standard deviation value obtained from the corresponding traffic flow values ​​within all unit time (the value range is 1h-3h);

[0102] The node dynamic parameters corresponding to each path node are obtained by the following formula:

[0103]

[0104] Among them, K represents the node dynamic parameter corresponding to each path node; σ gc and σ gv represents the normalized traffic flow standard deviation and the average vehicle speed standard deviation corresponding to each path node; U vmax Indicates the normalized traffic flow value corresponding to the maximum average speed of each path node;

[0105] According to the node dynamic parameters corresponding to each path node and the traffic flow peak value of each path node in the high traffic period, the dynamic index parameters corresponding to each path node are obtained;

[0106] The dynamic index parameter corresponding to each path node is obtained by the following formula:

[0107]

[0108] Among them, D represents the dynamic index parameter; K represents the node dynamic parameter corresponding to each path node; m represents the number of traffic peaks experienced by each path node; U i represents the normalized peak traffic volume corresponding to the i-th traffic peak period; U vmax Indicates the normalized traffic flow value corresponding to the maximum average speed of each path node; U max represents the normalized maximum value of traffic flow peak corresponding to m traffic peak periods; σ U Represents the normalized peak traffic flow standard deviation corresponding to m traffic peak periods.

[0109] The working principle and technical effect of the above technical solution are as follows: from the path nodes of the target sub-area, three types of dynamic characteristics are collected: traffic flow standard deviation (the degree of dispersion of traffic flow per unit time), vehicle average speed standard deviation (the degree of dispersion of vehicle speed per unit time), and traffic flow peak value during peak hours (the extreme value of traffic flow during peak hours), as the basic input of node dynamic state. Node dynamic parameter calculation: through the formula The standard deviation of traffic flow after fusion normalization σ gc , speed standard deviation σgv , and the traffic flow U at the maximum speed vmax , calculate the node dynamic parameter K, and quantify the comprehensive characteristics of the node traffic dynamic fluctuation. Dynamic index parameter calculation: Based on the node dynamic parameter K, combined with the number of traffic peaks m, the peak traffic flow Ui of each peak, and the traffic flow at the maximum speed U vmax , peak value U max , peak-to-peak standard deviation σ U , through the formula Calculate the dynamic index parameter D, integrate the node dynamic fluctuation and peak characteristics, and form the final quantitative value of the node dynamic state.

[0110] Existing path planning methods that utilize node dynamic characteristics mostly focus on single indicators (such as real-time traffic flow) or simple statistics (such as average speed), which cannot accurately describe dynamic fluctuations. This solution integrates the standard deviation of traffic flow and speed (|σ in formula K) gc -σ gv ∣), and the correlation between traffic flow at maximum speed (U vmax ), finely quantifying the dynamic coupling relationship between node "traffic flow and vehicle speed", solving the problem of "coarse dynamic feature characterization" in traditional methods, and improving the accuracy of path planning in perceiving the dynamic state of nodes. Traditional planning often ignores the characteristic differences of traffic peaks (such as peak fluctuations in traffic volume during different peaks). This solution incorporates the number of peaks m and peak difference | U into the dynamic indicator parameter D. i -U vmax ∣、Peak value U max , peak fluctuation σ U This approach deeply integrates peak-hour traffic characteristics, enabling route planning to accurately adapt to the dynamic shift from off-peak to peak hours. This addresses the problem of poor peak-hour adaptability in traditional planning and improves peak-hour route efficiency. Existing methods often calculate dynamic indicators independently, lacking synergy. This solution, through the progressive calculation of K and D, achieves a synergistic effect between the "dynamic fluctuation parameter (K)" and the "peak characteristic parameter (D)": K characterizes the daily dynamic fluctuations of nodes, while D focuses on peak-hour characteristics. The combination of these two provides a more comprehensive quantification of node dynamic states. Compared to traditional independent indicators, the collaboratively optimized dynamic parameters provide richer and more accurate node status information for route planning. Because these dynamic indicator parameters are more accurate and comprehensive, subsequent route node screening and route planning can more clearly identify nodes with low dynamic fluctuations and excellent peak-hour adaptability. Compared to existing planning methods, this approach can generate routes that better adapt to real-time traffic changes (especially during peak hours), reduce congestion, improve travel efficiency, and address the core issue of traditional routes: insufficient dynamic traffic adaptation.

[0111] In one embodiment of the present invention, screening the path nodes of each target sub-area to obtain the target path nodes corresponding to each target sub-area includes:

[0112] Comparing the dynamic index parameter of each path node contained in each target sub-area with a preset dynamic index parameter threshold;

[0113] The path node corresponding to the dynamic index parameter not lower than the preset dynamic index parameter threshold is used as the target path node.

[0114] The working principle and technical effect of the above technical solution are as follows: first, the dynamic index parameters of the path nodes in each target sub-area are extracted, and then compared with the preset threshold. The path nodes with dynamic index parameters not lower than the threshold are selected as the target path nodes, providing a high-quality node foundation for subsequent path planning. By setting the dynamic index parameter threshold, path nodes with better traffic dynamic characteristics (such as traffic flow, speed fluctuation adaptation, and good peak characteristics) are accurately selected, and nodes with poor dynamic indicators are eliminated. This reduces invalid path exploration, improves the efficiency and quality of subsequent path planning, ensures that the planned path is more closely aligned with real-time traffic dynamics, and enhances the stability and efficiency of path passage.

[0115] The embodiment of the present invention proposes an urban traffic route planning system, such as Figure 2 As shown, the urban traffic path planning system includes:

[0116] The target area acquisition module is used to take the area between the starting point and the end point of the current path planning as the target area;

[0117] a target sub-region acquisition module, configured to extract path nodes in the target region that meet the passage requirements between the starting point and the end point, and divide the target region into regions according to the node characteristics of the path nodes to obtain a plurality of target sub-regions;

[0118] The path planning module is used to screen the target path nodes contained in each target sub-area, and form a planned path based on the screened target path nodes and their corresponding road sections.

[0119] The working principle and technical effect of the above technical solution are as follows: First, the target area between the starting and ending points is identified, and path nodes that meet traffic requirements are extracted. These nodes are then divided into multiple target sub-areas based on their characteristics. Path nodes within each sub-area are then screened and combined with corresponding road sections to form a planned path. Defining the target area between the starting and ending points narrows the spatial scope of path planning, avoiding interference from irrelevant areas, focusing planning on the areas where traffic is actually needed, improving planning relevance and efficiency, and quickly identifying the approximate space of potential paths. Dividing target sub-areas based on path node characteristics allows for planning strategies to be tailored to different areas based on the function and traffic capacity of nodes (such as transportation hubs and ordinary intersections). This allows path planning to be tailored to each sub-area's characteristics, ensuring the rationality of the planned path across different road sections and improving the overall path's traffic adaptability. Path nodes within each sub-area are screened to remove redundant and unreasonable nodes, retaining key, valid nodes. Combining road sections to form a planned path reduces the exploration of ineffective paths and shortens planning time, while ensuring a simple and efficient path, improving traffic efficiency, and reducing congestion. Through regional division and node screening, we can flexibly respond to complex road conditions in the target area (such as both expressways and small alleys). Customized planning is carried out according to the characteristics of different sub-regions. While ensuring traffic requirements, diversified route planning is implemented to meet different travel needs (such as fast, on the way), thereby improving the flexibility and satisfaction of transportation system services. From regional demarcation and division to node screening and route formation, a systematic planning process is constructed. Each link is promoted layer by layer and coordinated with each other, so that the route planning has a clear logic from the overall to the local, ensuring the scientificity and consistency of the planning results, providing an orderly and efficient method support for urban traffic route planning, and facilitating the smooth operation of urban traffic.

[0120] In one embodiment of the present invention, the target sub-region acquisition module includes:

[0121] The path node acquisition module is used to retrieve the area between the starting point and the end point of the current path planning as the target area and the path nodes within it that meet the traffic requirements between the starting point and the end point;

[0122] A distance information retrieval module is used to retrieve the straight-line distance between every two adjacent path nodes;

[0123] The vehicle information retrieval module is used to retrieve the average traffic flow and average vehicle speed corresponding to each path node;

[0124] A grid size acquisition module is used to acquire the grid size according to the straight-line distance between each two adjacent path nodes combined with the average traffic flow corresponding to each path node and the average speed of vehicles traveling;

[0125] The grid size is obtained by the following formula:

[0126]

[0127] Where L represents the grid size; L p represents the average distance corresponding to the straight-line distance between all two adjacent path nodes; n represents the number of path nodes; Y gi represents the average traffic flow corresponding to the i-th path node after normalization; V gi represents the average speed of the vehicle corresponding to the i-th path node after normalization; s represents the adjustment coefficient, and the adjustment coefficient is obtained by the following formula:

[0128]

[0129] Among them, σ L Indicates the standard deviation of the straight-line distance between each two adjacent path nodes; L max represents the maximum straight-line distance between every two adjacent path nodes; ε represents a preset non-zero minimum constant to prevent the numerator from being zero, and the value range of the non-zero minimum constant is 0.1-0.5;

[0130] The region division module is used to divide the target region into regions according to the grid size to obtain multiple target sub-regions.

[0131] The working principle and technical effect of the above technical solution are: obtain the target area (between the starting point and the end point) and the path nodes that meet the traffic requirements, collect the straight-line distance between adjacent nodes, the average traffic flow and the average speed of each node. First, use the average distance L p , number of nodes n, normalized traffic flow Y gi and vehicle speed V gi , using product logarithm operation to build the basic grid size association; then introduce the adjustment coefficient s (based on the distance standard deviation σ L , maximum distance L max , minimum constant ε calculation, balance distance fluctuation effect), and finally through the formula Calculate the grid size. Based on the calculated grid size, divide the target area into multiple target sub-areas.

[0132] The existing grid division technology mostly adopts fixed size (such as rectangular grid with uniform side length), which cannot adapt to the dynamic changes of traffic flow. This solution integrates the normalization of traffic flow and speed (Y gi 、V giParticipate in logarithmic operations) to dynamically associate the grid size with the node traffic load (traffic volume) and traffic efficiency (vehicle speed). In areas with heavy traffic and large speed differences, the grid size is adaptively adjusted to better fit the actual traffic flow distribution, thereby improving the adaptability of path planning to dynamic traffic. Accurately balance distance fluctuations Traditional grid division ignores the discreteness of path node spacing (such as the difference in spacing between main roads and small alleys in the city). This scheme introduces an adjustment coefficient s, quantifies spacing fluctuations through the distance standard deviation σL and the maximum distance Lmax, and combines the minimum constant ε to avoid calculation anomalies, so that the grid size can accurately balance the "node spacing discreteness" and "traffic characteristics", solve the problem of insufficient adaptation of fixed grids to complex spacing, and improve the spatial rationality of regional division. Multi-dimensional collaborative optimization Existing methods mostly divide grids based on geographic space (such as administrative boundaries, fixed distances). This scheme coordinates three dimensions: mean distance L, traffic flow (traffic volume, speed), and spacing fluctuations: mean distance L p Ensure the basic scale of the grid; integrate vehicle volume and speed through logarithmic operations to adapt to traffic dynamics; adjust the coefficient s to balance spacing fluctuations. Compared with single-dimensional division, multi-dimensional collaboration enables the grid to more accurately match traffic path planning needs, providing a more reasonable sub-region basis for subsequent path node screening and path generation. Improve path planning efficiency. Because grid division is more adapted to traffic characteristics, the subsequent screening and planning of path nodes in sub-regions can reduce invalid node traversal (such as nodes with extremely low traffic load or extremely poor traffic efficiency). Compared with fixed grid division, this solution can compress invalid planning space, improve the operating efficiency of the path planning algorithm, output reasonable traffic paths more quickly, and adapt to the real-time planning needs of urban traffic.

[0133] In one embodiment of the present invention, the path planning module includes:

[0134] A dynamic index parameter acquisition module, configured to acquire dynamic index parameters of each path node according to the dynamic characteristics of the path nodes contained in each target sub-region;

[0135] A target path node determination module is used to screen the path nodes of each target sub-area and obtain the target path node corresponding to each target sub-area;

[0136] The planned path forming module is used to connect the target path nodes and the road sections between each target path node to form a planned path.

[0137] The working principle and technical effect of the above technical solution are as follows: for the path nodes in each target sub-area, dynamic indicator parameters reflecting the real-time or dynamic characteristics of the nodes (such as real-time traffic volume, speed changes, congestion trends, etc.) are collected and calculated to quantify the traffic status of the nodes. Based on the dynamic indicator parameters, the path nodes in each sub-area are screened, and nodes with poor traffic conditions (such as long-term congestion, extremely low traffic efficiency) or no value for path planning are eliminated, retaining high-quality target path nodes. The screened target path nodes are connected according to the connectivity relationship of the road sections to form a complete planned path from the starting point to the end point.

[0138] Existing path planning often relies on static node attributes (such as fixed traffic volume and historical congestion data) and is unable to respond to dynamic traffic changes (such as sudden congestion and temporary traffic restrictions) in real time. This solution uses dynamic indicator parameters (reflecting the real-time status of nodes) to filter nodes, allowing the planned path to accurately adapt to the dynamic fluctuations of traffic flow, solving the problem of static planning lagging behind real-time traffic and improving path efficiency. Traditional planning methods often ignore sub-regional differences (such as the different traffic characteristics of different sub-regions within the same area) and adopt a global unified filtering logic. This solution independently filters the target sub-region and customizes the filtering rules based on the dynamic characteristics of the nodes in the sub-region. This allows the path nodes in each sub-region to adapt to its own traffic characteristics (for example, commercial sub-regions focus on congestion relief, while residential sub-regions focus on traffic efficiency), improving the adaptability of path planning in complex urban areas. Existing methods are prone to detours and congestion in planned paths due to the inclusion of invalid nodes (such as those under long-term construction or extremely poor traffic capacity). This solution eliminates invalid nodes through dynamic screening, focuses on high-quality target nodes, reduces invalid exploration in path planning, shortens planning time, and ensures that the path is "short, flat, and fast" (short distance, less congestion, and high efficiency), thereby improving the user's travel experience. Compared with the existing planning process of "undifferentiated regional division + extensive node processing", this solution connects with the dynamic grid division mentioned above (sub-regions adapted to traffic characteristics) and amplifies the value of regional division through dynamic node screening in sub-regions. This allows "region division-node screening-path connection" to form a collaborative closed loop, improving the scientificity and accuracy of path planning throughout the entire process, from spatial division to node quality, and solving the problem of "region and node separation" in traditional planning.

[0139] In one embodiment of the present invention, the dynamic indicator parameter acquisition module includes:

[0140] A dynamic feature extraction module is used to extract dynamic features of the path nodes contained in each target sub-area; wherein the dynamic features of the path nodes include the standard deviation of traffic flow, the standard deviation of the average speed of vehicles passing, and the peak traffic flow during the peak period;

[0141] The node dynamic parameter acquisition module is used to obtain the node dynamic parameters corresponding to each path node using the standard deviation of the traffic flow and the standard deviation of the average vehicle speed corresponding to each path node; wherein the standard deviation of the traffic flow refers to the standard deviation value obtained from the corresponding traffic flow values ​​within all unit time (the value range is 1 hour to 3 hours);

[0142] The node dynamic parameters corresponding to each path node are obtained by the following formula:

[0143]

[0144] Among them, K represents the node dynamic parameter corresponding to each path node; σ gc and σ gv represents the normalized traffic flow standard deviation and the average vehicle speed standard deviation corresponding to each path node; U vmax Indicates the normalized traffic flow value corresponding to the maximum average speed of each path node;

[0145] A dynamic index parameter acquisition execution module is used to obtain the dynamic index parameter corresponding to each path node according to the node dynamic parameter corresponding to each path node and the traffic flow peak value of the high traffic period corresponding to each path node;

[0146] The dynamic index parameter corresponding to each path node is obtained by the following formula:

[0147]

[0148] Among them, D represents the dynamic index parameter; K represents the node dynamic parameter corresponding to each path node; m represents the number of traffic peaks experienced by each path node; U i represents the normalized peak traffic volume corresponding to the i-th traffic peak period; U vmax Indicates the normalized traffic flow value corresponding to the maximum average speed of each path node; U max represents the normalized maximum value of traffic flow peak corresponding to m traffic peak periods; σ U Represents the normalized peak traffic flow standard deviation corresponding to m traffic peak periods.

[0149] The working principle and technical effect of the above technical solution are as follows: from the path nodes of the target sub-area, three types of dynamic characteristics are collected: traffic flow standard deviation (the degree of dispersion of traffic flow per unit time), vehicle average speed standard deviation (the degree of dispersion of vehicle speed per unit time), and traffic flow peak value during peak hours (the extreme value of traffic flow during peak hours), as the basic input of node dynamic state. Node dynamic parameter calculation: through the formula The standard deviation of traffic flow after fusion normalization σ gc , speed standard deviation σ gv , and the traffic flow U at the maximum speed vmax , calculate the node dynamic parameter K, and quantify the comprehensive characteristics of the node traffic dynamic fluctuation. Dynamic index parameter calculation: Based on the node dynamic parameter K, combined with the number of traffic peaks m, the peak traffic flow Ui of each peak, and the traffic flow at the maximum speed U vmax , peak value U max , peak-to-peak standard deviation σ U , through the formula Calculate the dynamic index parameter D, integrate the node dynamic fluctuation and peak characteristics, and form the final quantitative value of the node dynamic state.

[0150] Existing path planning methods that utilize node dynamic characteristics mostly focus on single indicators (such as real-time traffic flow) or simple statistics (such as average speed), which cannot accurately describe dynamic fluctuations. This solution integrates the standard deviation of traffic flow and speed (|σ in formula K) gc -σ gv ∣), and the correlation between traffic flow at maximum speed (U vmax ), finely quantifying the dynamic coupling relationship between node "traffic flow and vehicle speed", solving the problem of "coarse dynamic feature characterization" in traditional methods, and improving the accuracy of path planning in perceiving the dynamic state of nodes. Traditional planning often ignores the characteristic differences of traffic peaks (such as peak fluctuations in traffic volume during different peaks). This solution incorporates the number of peaks m and peak difference | U into the dynamic indicator parameter D. i -U vmax ∣、Peak value U max , peak fluctuation σ U This approach deeply integrates peak-hour traffic characteristics, enabling route planning to accurately adapt to the dynamic shift from off-peak to peak hours. This addresses the problem of poor peak-hour adaptability in traditional planning and improves peak-hour route efficiency. Existing methods often calculate dynamic indicators independently, lacking synergy. This solution, through the progressive calculation of K and D, achieves a synergistic effect between the "dynamic fluctuation parameter (K)" and the "peak characteristic parameter (D)": K characterizes the daily dynamic fluctuations of nodes, while D focuses on peak-hour characteristics. The combination of these two provides a more comprehensive quantification of node dynamic states. Compared to traditional independent indicators, the collaboratively optimized dynamic parameters provide richer and more accurate node status information for route planning. Because these dynamic indicator parameters are more accurate and comprehensive, subsequent route node screening and route planning can more clearly identify nodes with low dynamic fluctuations and excellent peak-hour adaptability. Compared to existing planning methods, this approach can generate routes that better adapt to real-time traffic changes (especially during peak hours), reduce congestion, improve travel efficiency, and address the core issue of traditional routes: insufficient dynamic traffic adaptation.

[0151] In one embodiment of the present invention, the target path node determination module includes:

[0152] A comparison module, configured to compare the dynamic index parameter of each path node contained in each target sub-region with a preset dynamic index parameter threshold;

[0153] The target node screening and determination module is used to select the path node corresponding to the dynamic index parameter not lower than the preset dynamic index parameter threshold as the target path node.

[0154] The working principle and technical effect of the above technical solution are as follows: first, the dynamic index parameters of the path nodes in each target sub-area are extracted, and then compared with the preset threshold. The path nodes with dynamic index parameters not lower than the threshold are selected as the target path nodes, providing a high-quality node foundation for subsequent path planning. By setting the dynamic index parameter threshold, path nodes with better traffic dynamic characteristics (such as traffic flow, speed fluctuation adaptation, and good peak characteristics) are accurately selected, and nodes with poor dynamic indicators are eliminated. This reduces invalid path exploration, improves the efficiency and quality of subsequent path planning, ensures that the planned path is more closely aligned with real-time traffic dynamics, and enhances the stability and efficiency of path passage.

[0155] Obviously, those skilled in the art may make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if such changes and modifications fall within the scope of the claims and their equivalents, the present invention is intended to include such changes and modifications.

Claims

1. A method for urban traffic path planning, characterized in that: The urban traffic path planning method comprises: The area between the starting point and the end point of the current path planning is used as the target area; Extracting path nodes in the target area that meet the passage requirements between the starting point and the end point, and dividing the target area into regions according to the node characteristics of the path nodes to obtain multiple target sub-regions; The target path nodes contained in each target sub-area are screened, and a planned path is formed based on the screened target path nodes and their corresponding road sections.

2. The urban traffic route planning method according to claim 1, characterized in that: The target area is divided into regions according to the node specificity of the path node to obtain multiple target sub-regions, including: The area between the starting point and the end point of the current path planning is retrieved as the target area and the path nodes within it that meet the traffic requirements between the starting point and the end point; Get the straight-line distance between every two adjacent path nodes; Retrieve the average traffic volume and average vehicle speed corresponding to each path node; Obtaining a grid size based on the straight-line distance between each two adjacent path nodes combined with the average traffic flow and the average speed of vehicles corresponding to each path node; The grid size is obtained by the following formula: Where L represents the grid size; L p represents the average distance corresponding to the straight-line distance between all two adjacent path nodes; n represents the number of path nodes; Y gi represents the average traffic flow corresponding to the i-th path node after normalization; V gi represents the average speed of the vehicle corresponding to the i-th path node after normalization; s represents the adjustment coefficient, and the adjustment coefficient is obtained by the following formula: Among them, σ L Indicates the standard deviation of the straight-line distance between each two adjacent path nodes; L max represents the maximum straight-line distance between every two adjacent path nodes; ε represents a preset non-zero minimum constant to prevent the numerator from being zero, and the value range of the non-zero minimum constant is 0.1-0.5; The target area is divided into regions according to the grid size to obtain multiple target sub-regions.

3. The urban traffic route planning method according to claim 1, characterized in that: Target path nodes are screened for the path nodes contained in each target sub-area, and a planned path is formed based on the screened target path nodes and their corresponding road sections, including: Obtaining dynamic index parameters of each path node according to the dynamic characteristics of the path nodes contained in each target sub-region; Filter the path nodes of each target sub-area to obtain the target path nodes corresponding to each target sub-area; The target path nodes are connected with the road sections between each target path node to form a planned path.

4. The urban traffic route planning method according to claim 3, characterized in that: According to the dynamic characteristics of the path nodes contained in each target sub-region, the dynamic index parameters of each path node are obtained, including: Extracting dynamic features of the path nodes contained in each target sub-region; wherein the dynamic features of the path nodes include the standard deviation of traffic flow, the standard deviation of the average speed of vehicles passing, and the peak traffic flow during the peak period; The node dynamic parameters corresponding to each path node are obtained using the standard deviation of the traffic flow and the standard deviation of the average vehicle speed corresponding to each path node; wherein the standard deviation of the traffic flow refers to the standard deviation value obtained from the corresponding traffic flow values ​​within all unit times; The node dynamic parameters corresponding to each path node are obtained by the following formula: Among them, K represents the node dynamic parameter corresponding to each path node; σ gc and σ gv represents the normalized traffic flow standard deviation and the average vehicle speed standard deviation corresponding to each path node; U vmax Indicates the normalized traffic flow value corresponding to the maximum average speed of each path node; According to the node dynamic parameters corresponding to each path node and the traffic flow peak value of each path node in the high traffic period, the dynamic index parameters corresponding to each path node are obtained; The dynamic index parameter corresponding to each path node is obtained by the following formula: Among them, D represents the dynamic index parameter; K represents the node dynamic parameter corresponding to each path node; m represents the number of traffic peaks experienced by each path node; U i represents the normalized peak traffic volume corresponding to the i-th traffic peak period; U vmax Indicates the normalized traffic flow value corresponding to the maximum average speed of each path node; U max represents the normalized maximum value of traffic flow peak corresponding to m traffic peak periods; σ U Represents the normalized peak traffic flow standard deviation corresponding to m traffic peak periods.

5. The urban traffic route planning method according to claim 3, characterized in that: Filter the path nodes of each target sub-area to obtain the target path nodes corresponding to each target sub-area, including: Comparing the dynamic index parameter of each path node contained in each target sub-area with a preset dynamic index parameter threshold; The path node corresponding to the dynamic index parameter not lower than the preset dynamic index parameter threshold is used as the target path node.

6. An urban traffic route planning system, characterized in that: The urban traffic path planning system includes: The target area acquisition module is used to take the area between the starting point and the end point of the current path planning as the target area; a target sub-region acquisition module, configured to extract path nodes in the target region that meet the passage requirements between the starting point and the end point, and divide the target region into regions according to the node characteristics of the path nodes to obtain a plurality of target sub-regions; The path planning module is used to screen the target path nodes contained in each target sub-area, and form a planned path based on the screened target path nodes and their corresponding road sections.

7. The urban traffic route planning system according to claim 6, characterized in that: The target sub-region acquisition module includes: The path node acquisition module is used to retrieve the area between the starting point and the end point of the current path planning as the target area and the path nodes within it that meet the traffic requirements between the starting point and the end point; A distance information retrieval module is used to retrieve the straight-line distance between every two adjacent path nodes; The vehicle information retrieval module is used to retrieve the average traffic flow and average vehicle speed corresponding to each path node; A grid size acquisition module is used to acquire the grid size according to the straight-line distance between each two adjacent path nodes combined with the average traffic flow corresponding to each path node and the average speed of vehicles traveling; The grid size is obtained by the following formula: Where L represents the grid size; L p represents the average distance corresponding to the straight-line distance between all two adjacent path nodes; n represents the number of path nodes; Y gi represents the average traffic flow corresponding to the i-th path node after normalization; V gi represents the average speed of the vehicle corresponding to the i-th path node after normalization; s represents the adjustment coefficient, and the adjustment coefficient is obtained by the following formula: Among them, σ L Indicates the standard deviation of the straight-line distance between each two adjacent path nodes; L max represents the maximum straight-line distance between every two adjacent path nodes; ε represents a preset non-zero minimum constant to prevent the numerator from being zero, and the value range of the non-zero minimum constant is 0.1-0.5; The region division module is used to divide the target region into regions according to the grid size to obtain multiple target sub-regions.

8. The urban traffic route planning system according to claim 6, characterized in that: The path planning module includes: A dynamic index parameter acquisition module, configured to acquire dynamic index parameters of each path node according to the dynamic characteristics of the path nodes contained in each target sub-region; A target path node determination module is used to screen the path nodes of each target sub-area and obtain the target path node corresponding to each target sub-area; The planned path forming module is used to connect the target path nodes and the road sections between each target path node to form a planned path.

9. The urban traffic route planning system according to claim 8, characterized in that: The dynamic indicator parameter acquisition module includes: A dynamic feature extraction module is used to extract dynamic features of the path nodes contained in each target sub-area; wherein the dynamic features of the path nodes include the standard deviation of traffic flow, the standard deviation of the average speed of vehicles passing, and the peak traffic flow during the peak period; A node dynamic parameter acquisition module is used to obtain the node dynamic parameters corresponding to each path node using the standard deviation of the traffic flow and the standard deviation of the average vehicle speed corresponding to each path node; wherein the standard deviation of the traffic flow refers to the standard deviation value obtained from the corresponding traffic flow values ​​within all unit times; The node dynamic parameters corresponding to each path node are obtained by the following formula: Among them, K represents the node dynamic parameter corresponding to each path node; σ gc and σ gv represents the normalized traffic flow standard deviation and the average vehicle speed standard deviation corresponding to each path node; U vmax Indicates the normalized traffic flow value corresponding to the maximum average speed of vehicles at each path node; A dynamic index parameter acquisition execution module is used to obtain the dynamic index parameter corresponding to each path node according to the node dynamic parameter corresponding to each path node and the traffic flow peak value of the high traffic period corresponding to each path node; The dynamic index parameter corresponding to each path node is obtained by the following formula: Among them, D represents the dynamic index parameter; K represents the node dynamic parameter corresponding to each path node; m represents the number of traffic peaks experienced by each path node; U i represents the normalized peak traffic volume corresponding to the i-th traffic peak period; U vmax Indicates the normalized traffic flow value corresponding to the maximum average speed of each path node; U max represents the normalized maximum value of traffic flow peak corresponding to m traffic peak periods; σ U Represents the normalized peak traffic flow standard deviation corresponding to m traffic peak periods.

10. The urban traffic route planning system according to claim 8, characterized in that: The target path node determination module includes: A comparison module, configured to compare the dynamic index parameter of each path node contained in each target sub-region with a preset dynamic index parameter threshold; The target node screening and determination module is used to select the path node corresponding to the dynamic index parameter not lower than the preset dynamic index parameter threshold as the target path node.

Images