A three-dimensional optimization method and system for a pedestrian network aiming at high efficiency

Abstract

This invention discloses a method and system for three-dimensional optimization of pedestrian networks with the goal of improving traffic efficiency. The method includes: acquiring image data of the road system; preprocessing and simplifying the image data to construct a road network dataset containing multiple road nodes; establishing an optimization objective function based on the average path length of the three-dimensional pedestrian passage and the number of turns in the underpass; performing simulation optimization on the objective function according to preset constraints and the road network dataset to obtain the optimal solution composed of road nodes; optimizing the pedestrian network based on the optimal solution, calculating the optimized traffic efficiency index, and optimizing the simulation optimization process based on the traffic efficiency index. This invention not only improves the accuracy and flexibility of three-dimensional pedestrian network optimization but also enhances user comfort and satisfaction, providing a more scientific and flexible solution for urban planning and construction.

Description

Technical Field

[0001] This invention relates to the field of urban three-dimensional pedestrian system planning technology, specifically to a method and system for three-dimensional optimization of pedestrian networks with the goal of improving traffic efficiency. Background Technology

[0002] Currently, the construction of multi-level pedestrian systems centered around subways and commercial areas can effectively improve the efficiency of pedestrian traffic, enabling pedestrians to reach their destinations conveniently and quickly. The optimization methods for existing pedestrian networks are mainly qualitative, relying on methods such as questionnaires and interviews to analyze data on population activities and traffic patterns. Based on this, urban planners, drawing on experience and theoretical knowledge, propose preliminary plans according to the current state of urban development and future needs. These preliminary plans are then evaluated, and opinions from the public and relevant departments are solicited, leading to necessary adjustments and optimizations.

[0003] However, the aforementioned method of constructing a three-dimensional road network based on the existing pedestrian network has significant drawbacks. Firstly, it relies heavily on questionnaires and on-site observations. Due to limited data samples and susceptibility to subjective factors, the optimized solutions may not be comprehensive or accurate enough, failing to provide effective theoretical guidance for practical applications. Secondly, traditional planning methods lack systematic simulation tools, making it difficult to flexibly adjust and optimize based on actual usage, resulting in slow response times and low planning efficiency.

[0004] Therefore, there is a need to propose a three-dimensional optimization method and system for pedestrian networks with the goal of improving traffic efficiency. This system should be able to quickly and efficiently optimize pedestrian networks using automated simulation technology. While comprehensively considering the overall pedestrian network, it should generate the optimal solution that is based on factual evidence and is targeted, thereby improving the traffic efficiency and walking experience of residents and optimizing and improving traditional qualitative planning methods. Summary of the Invention

[0005] In view of this, the present invention provides a method and system for three-dimensional optimization of pedestrian networks with the goal of improving traffic efficiency, in order to solve the technical problems of insufficient optimization accuracy and difficulty in making flexible adjustments according to actual usage conditions in existing three-dimensional optimization of pedestrian networks due to incomplete data collection and analysis and lack of simulation methods.

[0006] To achieve the above-mentioned technical objectives, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a three-dimensional optimization method for pedestrian networks aimed at improving traffic efficiency, comprising:

[0008] Acquire image data containing road systems, preprocess and simplify the image data, and construct a road network dataset containing road nodes;

[0009] An optimization objective function is established based on the average path length of the elevated pedestrian walkway and the number of turns in the underground passage.

[0010] The optimization objective function is simulated and optimized based on preset constraints and the road network dataset to obtain the optimal solution composed of road nodes, so that the optimization objective function reaches the best balance.

[0011] The pedestrian network is optimized based on the optimal solution, and the optimized traffic efficiency index is calculated. The simulation optimization process is then optimized based on the traffic efficiency index.

[0012] Furthermore, the image data undergoes preprocessing and simplified analysis, including:

[0013] The road centerline in the image was extracted using an automatic vectorization tool, the underground road data was supplemented and improved, and the data was manually calibrated to complete the construction of the basic road dataset.

[0014] The road network dataset is simplified based on graph theory, redundant data is merged and removed, and a road network dataset containing underground nodes and connecting edges is constructed using network analysis tools. The road network structure is then transformed into a point-edge relationship dataset, resulting in a road network dataset containing multiple road nodes.

[0015] Furthermore, the preset constraints include:

[0016] Set nodes with functional attributes to be mapped downwards;

[0017] The depth of nodes vertically mapped downwards from different nodes conforms to the preset depth standard;

[0018] A vertical connection channel needs to be formed between the nodes mapped downwards and the ground.

[0019] Furthermore, the objective function is:

[0020] fit=w1L+w2C

[0021]

[0022] In the formula, L represents the average shortest path length of the elevated pedestrian system, C represents the number of turns in the underground passage, w1 and w2 are the weights of the average shortest path length and the number of turns in the underground passage, respectively, N represents the number of effective paths, and d(s i ,t i ) represents the i-th pair of nodes (s) i ,t i The shortest path length between () and (), where U represents the set of all underground nodes, and N is the shortest path between () and () and () is the shortest path between ... (μ)This represents the set of neighboring node pairs of node u. The turn_indicator(v,u,w) is an indicator function that indicates whether the angle between neighboring nodes v and w of node u is greater than a preset threshold. It is 1 if it is greater than the preset threshold, and 0 otherwise.

[0023] Furthermore, the objective function is optimized through simulation based on preset constraints and the road network dataset, including:

[0024] Based on the iterative operations of selection, crossover, and mutation using a genetic algorithm, the optimization objective function is solved to achieve the optimal balance between the average shortest path and the number of turns in the underground passage.

[0025] Furthermore, the optimization objective function is solved based on iterative operations of selection, crossover, and mutation using a genetic algorithm, including:

[0026] Generate an initial solution set containing multiple optimization schemes that meet preset constraints, and calculate the function value of the optimization objective function corresponding to each optimization scheme in the initial solution set;

[0027] Each optimization scheme in the initial solution set is treated as an individual and subjected to genetic iteration. The individual with the smallest function value is selected as the current optimal individual and directly added to the offspring of the next iteration. At the same time, based on the optimization objective function value corresponding to each generation of individuals, a parent individual is selected in a preset selection method, and the parent individual is mutated to obtain the offspring of the next iteration, until the number of individuals in the offspring solution set reaches a preset number.

[0028] Calculate the optimization objective function value for all individuals in the child solution set, and output the optimal solution when the optimization objective function value converges.

[0029] Furthermore, based on the optimization objective function value corresponding to each generation of individuals, parent individuals are selected using a preset selection method, including:

[0030] Based on optimizing the objective function value, parent individuals are selected in a tournament-style manner. Individuals with shorter paths and fewer underground turns have a higher probability of being selected.

[0031] Furthermore, the pedestrian network is optimized based on the optimal solution, and the optimized traffic efficiency index is calculated. The simulated optimization process is then optimized based on the traffic efficiency index, including:

[0032] The SDNA analysis method is used to compare and analyze the traffic efficiency index of the three-dimensional pedestrian network system before and after optimization. If the difference in traffic efficiency index before and after optimization is less than the preset change threshold, the calculation parameters of the genetic algorithm are adjusted to find the optimal solution again.

[0033] Secondly, the present invention also provides a three-dimensional optimization system for pedestrian networks aimed at improving traffic efficiency, comprising:

[0034] The data acquisition module is used to acquire image data with road systems, preprocess and analyze the image data to simplify it, and construct a road network dataset containing road nodes.

[0035] The objective function establishment module is used to establish an optimization objective function based on the average path length of the three-dimensional pedestrian passage and the number of turns in the underground passage.

[0036] The simulation optimization module is used to simulate and optimize the objective function according to preset constraints and the road network dataset, so as to obtain the optimal solution composed of road nodes and make the objective function reach the best balance.

[0037] The efficiency optimization module is used to optimize the pedestrian network based on the optimal solution, calculate the optimized traffic efficiency index, and optimize the simulation optimization process based on the traffic efficiency index.

[0038] Thirdly, the present invention also provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the pedestrian network three-dimensional optimization method with the goal of improving traffic efficiency as described in any of the above technical solutions.

[0039] Compared to existing technologies, the system and method provided by this invention, through preprocessing and simplifying imagery, can accurately construct a road network dataset containing multiple road nodes. Based on real imagery data, it not only accurately reflects the actual terrain and road conditions but also improves the accuracy of subsequent path optimization. Based on the average path length and number of turns of the underpasses, an optimization objective function is established and solved, taking into account the actual needs and behaviors of pedestrians, effectively improving the accuracy of pedestrian network planning. By calculating traffic efficiency indicators, it ensures that the final designed pedestrian passages are efficient and convenient in actual use. This invention not only improves the accuracy and flexibility of three-dimensional pedestrian network optimization but also better meets the actual needs of users, improving user comfort and satisfaction, enhancing the usability and convenience of pedestrian networks, and providing further scientific and flexible solutions for urban planning and construction. Attached Figure Description

[0040] Figure 1 This is a flowchart illustrating the three-dimensional optimization method for pedestrian networks aimed at improving traffic efficiency provided by the present invention.

[0041] Figure 2 This is a schematic diagram illustrating the process of vectorizing an image image according to the present invention.

[0042] Figure 3 This is a schematic diagram of the structure of the pedestrian network three-dimensional optimization system with the goal of improving traffic efficiency provided by the present invention;

[0043] Figure 4 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0044] Preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, which form part of this application and are used together with the embodiments of the present invention to illustrate the principles of the present invention, but are not intended to limit the scope of the present invention.

[0045] This invention provides a three-dimensional optimization method for pedestrian networks with the goal of improving traffic efficiency, which will be described in detail below.

[0046] Combination Figure 1 As shown, a specific embodiment of the present invention discloses a three-dimensional optimization method for pedestrian networks aimed at improving traffic efficiency, comprising:

[0047] Step S101: Obtain image data with road system, preprocess and analyze the image data to construct a road network dataset containing road nodes;

[0048] Step S102: Based on the average path length of the three-dimensional pedestrian passage and the number of turns in the underground passage, establish an optimization objective function;

[0049] Step S103: Based on the preset constraints and the road network dataset, the optimization objective function is simulated and optimized to obtain a traffic subgraph composed of road nodes, so that the optimization objective function reaches the best balance;

[0050] Step S104: Optimize the pedestrian network based on the optimal solution and calculate the optimized traffic efficiency index.

[0051] The method in this embodiment, through preprocessing and simplifying imagery analysis, can accurately construct a road network dataset containing multiple road nodes. Based on real imagery data, it not only accurately reflects the actual terrain and road conditions but also improves the accuracy of subsequent path optimization. Based on the average path length and number of turns of the underpasses, an optimization objective function is established and solved, taking into account the actual needs and behaviors of pedestrians, effectively improving the accuracy of pedestrian network planning. By calculating traffic efficiency indicators, it ensures that the final designed pedestrian passages are efficient and convenient in actual use. This invention not only improves the accuracy and flexibility of three-dimensional pedestrian network optimization but also better meets the actual needs of users, improving user comfort and satisfaction, enhancing the usability and convenience of pedestrian networks, and providing further scientific and flexible solutions for urban planning and construction.

[0052] In a preferred embodiment, step S101 involves preprocessing and simplifying the image, including:

[0053] The road centerline in the image was extracted using an automatic vectorization tool, the underground road data was supplemented and improved, and the data was manually calibrated to complete the construction of the basic road dataset.

[0054] The road network dataset is simplified based on graph theory, redundant data is merged and removed, and a road network dataset containing nodes and edges is constructed using network analysis tools. The road network structure is transformed into a point-edge relationship dataset, resulting in a road network dataset containing multiple road nodes.

[0055] As a specific implementation, firstly, imagery maps containing road systems are acquired from a map platform. Road centerlines are extracted using ArcGIS's automatic vectorization tools, thus initially constructing a road dataset. Based on this, supplementary data is added, including data on roads not yet extracted and existing underground roads. Manual calibration is performed through field surveys to complete the initial construction of the basic road dataset.

[0056] Secondly, road data is simplified based on graph theory, redundant data is merged and removed, and a road network dataset containing underground nodes and edges is constructed using the network analysis tools of the ArcGIS platform. Then, the road network structure is converted into a point-edge relationship dataset by creating the nearest facility point using the network analysis tools. Simultaneously, manual calibration is required to ensure that the start and end points of each edge are correctly connected to the corresponding nodes, such as... Figure 2 As shown, Figure 2 A schematic diagram illustrating the process of vectorizing an image is shown.

[0057] It's important to note that graph theory-based simplification of road data specifically uses a data structure composed of nodes (vertices) and edges connecting these nodes to describe the relationships between road entities. The road network structure is transformed into a vertex-edge relationship dataset, using linked lists or arrays to store information about nodes and their neighbors. This data structure is better suited for network analysis and simulation, allowing for the planning of pedestrian networks using shortest path methods, minimum spanning tree methods, and matching algorithms. Manual calibration ensures that the start and end points of each edge are correctly connected to their respective nodes, thereby improving the quality and usability of the dataset.

[0058] As a specific embodiment, in step S102, in order to improve the efficiency of pedestrian traffic through the construction of a three-dimensional pedestrian network, the average shortest path length of the three-dimensional pedestrian passage and the number of turns in the underground passage are used as objective functions to evaluate whether the simulated generated scheme meets the requirements of pedestrian traffic efficiency, thereby screening multiple schemes and obtaining the optimal solution.

[0059] In a preferred embodiment, in step S103, the preset constraint conditions include:

[0060] Set nodes with functional attributes to be mapped downwards;

[0061] The depth of nodes vertically mapped downwards from different nodes conforms to the preset depth standard;

[0062] A vertical connection channel needs to be formed between the nodes mapped downwards and the ground.

[0063] Specifically, (1) nodes with functional attributes include nodes with functional attributes such as subway and commercial, which can be mapped downwards; (2) according to building codes, the depth of vertical mapping of different nodes downwards is limited to: -6 meters for subway, -4 or -6 meters for shopping mall; (3) nodes mapped downwards need to form a vertical connection channel with the ground so that the underground structure or facilities can be effectively connected to other facilities or services on the ground, such as elevators or stairs.

[0064] In a preferred embodiment, the objective function is:

[0065] fit=w1L+w2C

[0066]

[0067] In the formula, L represents the average shortest path length of the elevated pedestrian system, C represents the number of turns in the underground passage, w1 and w2 are the weights of the average shortest path length and the number of turns in the underground passage, respectively, N represents the number of effective paths, and d(s i ,t i ) represents the i-th pair of nodes (s) i,t i The shortest path length between () and (), where U represents the set of all underground nodes, and N is the shortest path between () and () and () is the shortest path between ... (μ) This represents the set of neighboring node pairs of node u. The turn_indicator(v,u,w) is an indicator function that indicates whether the angle between neighboring nodes v and w of node u is greater than a preset threshold. It is 1 if it is greater than the preset threshold, and 0 otherwise.

[0068] It should be noted that w1 and w2 are usually set to 0.5 because in pedestrian network planning, the average shortest path length and the number of turns in underground passages are equally important. To comprehensively consider these two objectives, the fitness of traffic efficiency is evaluated by calculating the average value. As a preferred embodiment, during the simulation optimization process, the highest pedestrian traffic efficiency is used as the objective, and a genetic algorithm is employed with iterative operations such as selection, crossover, and mutation to find the optimal solution for the efficient three-dimensional pedestrian system. The main purpose of the genetic algorithm in this problem is to optimize the three-dimensional road network structure and find an optimal subset of nodes that achieves an optimal balance between the average shortest path and the number of turns in the subgraph formed by these nodes.

[0069] In a preferred embodiment, the optimization objective function is solved based on iterative operations of selection, crossover, and mutation using a genetic algorithm, including:

[0070] Generate an initial solution set containing multiple optimization schemes that meet preset constraints, and calculate the function value of the optimization objective function corresponding to each optimization scheme in the initial solution set;

[0071] Each optimization scheme in the initial solution set is treated as an individual and subjected to genetic iteration. The individual with the smallest function value is selected as the current optimal individual and directly added to the offspring of the next iteration. At the same time, based on the optimization objective function value corresponding to each generation of individuals, a parent individual is selected in a preset selection method, and the parent individual is mutated to obtain the offspring of the next iteration, until the number of individuals in the offspring solution set reaches a preset number.

[0072] Calculate the optimization objective function value for all individuals in the child solution set, and output the optimal solution when the optimization objective function value converges.

[0073] In a preferred embodiment, the step of selecting parent individuals based on the optimized objective function value corresponding to each generation of individuals using a preset selection method includes:

[0074] Based on optimizing the objective function value, parent individuals are selected in a tournament-style manner. Individuals with shorter paths and fewer underground turns have a higher probability of being selected.

[0075] To better illustrate the above process, the solution process will be explained in detail, with the following steps:

[0076] S41: Randomly generate N sets of codes from the solution set S that meet the requirements of three-dimensional road network construction (preset constraints) to form the initial solution set P(1,1..N);

[0077] S42: Solve the traffic efficiency by setting the average shortest path and the number of turns, and then weight them to form the fitness function (i.e. the optimization objective function) F(P(1,1..N)) of all individuals in P(1,1..N);

[0078] S43: Begin genetic iteration. Each generation of the population is denoted as P(X,1..N), where X is the generation number of the iteration.

[0079] S44: The solution with the lowest fitness function F(P(X,1..N)) in P(X,1..N) is the current optimal solution, and it directly enters the next iteration P(X+1);

[0080] S45: Based on the fitness function F(P(X,1..N)), a solution P(X,A) is selected from P(X,1..N) in a tournament manner. The shorter the path and the fewer the number of turns, the greater the probability of the solution being selected.

[0081] S46: Select another solution P(X,B) from P(X,1..N) in a tournament manner according to the fitness function F(P(X,1..N)). The shorter the path and the fewer the number of turns, the greater the probability of selection.

[0082] S47: Randomly select the bitwise encoding of P(X,A) or P(X,B) to generate P(X,TEMP);

[0083] S48: Each bit of P(X,TEMP) is encoded with a probability of P;

[0084] S49: Verify the canonical compliance of P(X,TEMP). If it is compliant, add it to the next iteration P(X+1).

[0085] S410: Determine the size of the next generation population. If the number of individuals P(X+1) reaches N (the preset population size), proceed to S411; otherwise, return to S45.

[0086] S411: Solve the traffic efficiency by setting the average shortest path and the number of turns, and then weight them to form the fitness function F(P(X+1,1..N)) for all individuals in P(X+1,1..N);

[0087] S412: Determine if the algorithm has converged. If the fitness function corresponding to the optimal solution remains unchanged for M consecutive generations, the result is considered converged, and the optimal solution is output. Otherwise, return to S43 to start the next generation of genetic iteration.

[0088] In a preferred embodiment, the pedestrian network is optimized based on the optimal solution, the optimized traffic efficiency index is calculated, and the simulated optimization process is optimized based on the traffic efficiency index, including:

[0089] The SDNA analysis method is used to compare and analyze the traffic efficiency index of the three-dimensional pedestrian network system before and after optimization. If the difference in traffic efficiency index before and after optimization is less than the preset change threshold, the calculation parameters of the genetic algorithm are adjusted to find the optimal solution again.

[0090] It should be noted that the traffic efficiency indicators used in this invention include detour rate and connectivity. Detour rate refers to the proportion of extra walking distance in a transportation network due to the lack of direct paths. A high detour rate may indicate insufficient connectivity or unreasonable path design in the transportation network, affecting traffic efficiency. Connectivity refers to the degree and quality of connection between nodes in a pedestrian network. High connectivity means that multiple paths can be used to quickly reach the destination, avoiding situations where walking time is longer and the experience is worse due to a single path. These indicators not only help evaluate the overall operation of the pedestrian network system but also provide important references for the three-dimensional planning of pedestrian networks and infrastructure improvements.

[0091] As a specific implementation, in the ArcGIS platform, SDNA analysis is used to analyze indicators such as detour rate and connectivity of the before-and-after three-dimensional pedestrian network system. In ArcGIS, SDNA (Spatial Data Network Analysis) is mainly used to analyze and evaluate the spatial relationships between nodes and paths in a network system, and can be used to analyze indicators such as detour rate and connectivity of the three-dimensional pedestrian network system. The changes in the data before and after are compared. If the differences between the before and after results are not significant (do not meet the preset range of change), the number of iterations and population size of the genetic algorithm need to be adjusted until the optimal solution is found.

[0092] To verify the effectiveness of this invention in optimizing pedestrian traffic efficiency through the construction of a three-dimensional pedestrian system in practical applications, an experiment was conducted on a subway station and its surrounding 500-meter walking area in a certain city as the verification object. The existing pedestrian network was optimized and improved by constructing a three-dimensional pedestrian network using a genetic algorithm. The detour rate and connectivity of the entire road network before and after optimization were compared using the SDNA analysis method. The results are shown in Table 1 below.

[0093] Table 1 Comparison of detour rate and connectivity of the three-dimensional pedestrian network system before and after optimization.

[0094]

[0095]

[0096] As can be seen from the results in Table 1, the method of this embodiment shows significant effectiveness in improving traffic efficiency.

[0097] like Figure 3 As shown, this embodiment also provides a pedestrian network three-dimensional optimization system 300 aimed at improving traffic efficiency, including:

[0098] The data acquisition module is used to acquire image data with road systems, preprocess and analyze the image data to simplify it, and construct a road network dataset containing road nodes.

[0099] The objective function establishment module is used to establish an optimization objective function based on the average path length of the three-dimensional pedestrian passage and the number of turns in the underground passage.

[0100] The simulation optimization module is used to simulate and optimize the objective function according to preset constraints and the road network dataset, so as to obtain the optimal solution composed of road nodes and make the objective function reach the best balance.

[0101] The efficiency optimization module is used to optimize the pedestrian network based on the optimal solution, calculate the optimized traffic efficiency index, and optimize the simulation optimization process based on the traffic efficiency index.

[0102] like Figure 4 As shown in the above-described method for three-dimensional optimization of pedestrian networks with the goal of improving traffic efficiency, this invention also provides an electronic device 400, which can be a mobile terminal, desktop computer, laptop, handheld computer, server, or other computing device. The electronic device includes a processor 401, a memory 402, and a display 403.

[0103] In some embodiments, memory 402 may be an internal storage unit of a computer device, such as a hard disk or memory. In other embodiments, memory 402 may be an external storage device of a computer device, such as a plug-in hard disk, smart media card (SMC), secure digital card (SD), flash card, etc. Further, memory 402 may include both internal and external storage units of the computer device. Memory 402 is used to store application software and various types of data installed on the computer device, such as program code for installing the computer device. Memory 402 can also be used to temporarily store data that has been output or will be output. In one embodiment, memory 402 stores a pedestrian network 3D optimization method program 404 aimed at improving traffic efficiency. This pedestrian network 3D optimization method program 404 can be executed by processor 401 to implement a pedestrian network 3D optimization method aimed at improving traffic efficiency according to various embodiments of the present invention.

[0104] In some embodiments, processor 401 may be a central processing unit (CPU), microprocessor or other data processing chip, used to run program code stored in memory 402 or process data, such as executing a pedestrian network 3D optimization method program aimed at improving traffic efficiency.

[0105] In some embodiments, display 403 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an OLED (Organic Light-Emitting Diode) touchscreen. Display 403 is used to display information on the computer device and to display a visual user interface. Components 401-403 of the computer device communicate with each other via a system bus.

[0106] The pedestrian network 3D optimization method and system provided in this embodiment, aimed at improving traffic efficiency, enhances accuracy by utilizing automated simulation technology to provide more precise and complex data support. This effectively compensates for the shortcomings of traditional methods in data collection and analysis, thereby improving the accuracy of pedestrian network 3D optimization. In terms of flexibility, it enables dynamic adjustment of the pedestrian network 3D optimization scheme, allowing for adjustments to the overall network structure based on actual application conditions. This enables it to adapt to changes in scenarios and requirements, and accommodates the network's flexibility.

[0107] This invention not only improves the accuracy and flexibility of three-dimensional optimization of pedestrian networks, but also better meets the actual needs of users, improves user comfort and satisfaction, enhances the usability and convenience of pedestrian networks, and provides further scientific and flexible solutions for urban planning and construction.

[0108] The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention should be included within the scope of protection of the present invention.

Claims

1. A three-dimensional optimization method for a pedestrian network aiming at high efficiency of passage, characterized in that, include: Acquire image data containing road systems, preprocess and simplify the image data, and construct a road network dataset containing road nodes; An optimization objective function is established based on the average path length of the elevated pedestrian walkway and the number of turns in the underground passage. The optimization objective function is simulated and optimized based on preset constraints and the road network dataset to obtain the optimal solution composed of road nodes, so that the optimization objective function reaches the best balance. The preset constraints include: Set nodes with functional attributes to be mapped downwards; The depth of nodes vertically mapped downwards from different nodes conforms to the preset depth standard; A vertical connection channel needs to be formed between the nodes mapped downwards and the ground; The objective function is: In the formula, This represents the average shortest path length for multi-level pedestrian access. Indicates the number of turns in the underground passage. and These are the weights of the average shortest path length for elevated pedestrian walkways and the number of turns in underground passages, respectively. Indicates the number of valid paths. Indicates the first For nodes The shortest path length between them. Represents the set of all underground nodes. Represents a node The set of neighbor node pairs, Represents a node neighboring nodes and An indicator function indicating whether the included angle between them is greater than a preset threshold; it is 1 if it is greater than the preset threshold, and 0 otherwise. The optimization objective function is simulated and optimized based on preset constraints and the road network dataset, including: Based on the iterative operations of selection, crossover and mutation using a genetic algorithm, the optimization objective function is solved to achieve the best balance between the average shortest path and the number of turns in the underground passage in the optimization objective function. The pedestrian network is optimized based on the optimal solution, and the optimized traffic efficiency index is calculated. The simulation optimization process is then optimized based on the traffic efficiency index.

2. The three-dimensional optimization method for pedestrian networks with the goal of improving traffic efficiency as described in claim 1, characterized in that, The image data undergoes preprocessing and simplified analysis, including: The road centerline in the image was extracted using an automatic vectorization tool, the underground road data was supplemented and improved, and the data was manually calibrated to complete the construction of the basic road dataset. The road network dataset is simplified based on graph theory, redundant data is merged and removed, and a road network dataset containing underground nodes and connecting edges is constructed using network analysis tools. The road network structure is then transformed into a point-edge relationship dataset, resulting in a road network dataset containing multiple road nodes.

3. The method according to claim 1, wherein, The optimization objective function is solved based on iterative operations of selection, crossover, and mutation using a genetic algorithm, including: Generate an initial solution set containing multiple optimization schemes that meet preset constraints, and calculate the function value of the optimization objective function corresponding to each optimization scheme in the initial solution set; Each optimization scheme in the initial solution set is treated as an individual and subjected to genetic iteration. The individual with the smallest function value is selected as the current optimal individual and directly added to the offspring of the next iteration. At the same time, based on the optimization objective function value corresponding to each generation of individuals, a parent individual is selected in a preset selection method, and the parent individual is mutated to obtain the offspring of the next iteration, until the number of individuals in the offspring solution set reaches a preset number. Calculate the optimization objective function value for all individuals in the child solution set, and output the optimal solution when the optimization objective function value converges.

4. The three-dimensional optimization method for a pedestrian network targeting high efficiency of passage according to claim 3, characterized in that, Based on the optimization objective function value corresponding to each generation of individuals, parent individuals are selected using a preset selection method, including: Based on optimizing the objective function value, parent individuals are selected in a tournament-style manner. Individuals with shorter paths and fewer underground turns have a higher probability of being selected.

5. The method according to claim 3, wherein, The pedestrian network is optimized based on the optimal solution, and the optimized traffic efficiency index is calculated. The simulated optimization process is then optimized based on the traffic efficiency index, including: The SDNA analysis method is used to compare and analyze the traffic efficiency index of the three-dimensional pedestrian network system before and after optimization. If the difference in traffic efficiency index before and after optimization is less than the preset change threshold, the calculation parameters of the genetic algorithm are adjusted to find the optimal solution again.

6. A three-dimensional optimization system for a pedestrian network targeting high efficiency of passage, characterized by, include: The data acquisition module is used to acquire image data with road systems, preprocess and analyze the image data to simplify it, and construct a road network dataset containing road nodes. The objective function establishment module is used to establish an optimization objective function based on the average path length of the elevated pedestrian walkway and the number of turns in the underground passage; the objective function is: In the formula, This represents the average shortest path length for multi-level pedestrian access. Indicates the number of turns in the underground passage. and These are the weights of the average shortest path length for elevated pedestrian walkways and the number of turns in underground passages, respectively. Indicates the number of valid paths. Indicates the first For nodes The shortest path length between them. Represents the set of all underground nodes. Represents a node The set of neighbor node pairs, Represents a node neighboring nodes and An indicator function indicating whether the included angle between them is greater than a preset threshold; it is 1 if it is greater than the preset threshold, and 0 otherwise. The simulation optimization module is used to simulate and optimize the objective function according to preset constraints and the road network dataset, so as to obtain the optimal solution composed of road nodes and make the objective function reach the best balance. The preset constraints include: Set nodes with functional attributes to be mapped downwards; The depth of nodes vertically mapped downwards from different nodes conforms to the preset depth standard; A vertical connection channel needs to be formed between the nodes mapped downwards and the ground; The optimization objective function is simulated and optimized based on preset constraints and the road network dataset, including: Based on the iterative operations of selection, crossover and mutation using a genetic algorithm, the optimization objective function is solved to achieve the best balance between the average shortest path and the number of turns in the underground passage in the optimization objective function. The efficiency optimization module is used to optimize the pedestrian network based on the optimal solution, calculate the optimized traffic efficiency index, and optimize the simulation optimization process based on the traffic efficiency index.

7. An electronic device, comprising: It includes a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, it implements the pedestrian network three-dimensional optimization method with the goal of improving traffic efficiency as described in any one of claims 1-5.

Images