Walking network three-dimensional optimization method and system taking traffic high efficiency as target
Through image map data preprocessing and genetic algorithm simulation optimization, the problems of incomplete data and lack of simulation methods in the existing pedestrian network optimization methods are solved, and more accurate and flexible pedestrian network optimization is achieved, which improves traffic efficiency and user satisfaction. .
Patent Information
- Application Number
- CN202411066625.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2044-08-05
AI Technical Summary
The existing three-dimensional optimization method of pedestrian networks relies on questionnaire surveys and on-site observations. The data samples are limited and susceptible to subjective factors, resulting in the optimization plan being not comprehensive and accurate enough, lacking systematic simulation methods, making it difficult to adjust flexibly, slow response speed, and low planning efficiency.
The preprocessing and analysis of image map data is used to construct a road network data set, and an optimization objective function based on the average path length and number of turns is established. Genetic algorithms are used to simulate and find optimization, optimize the walking network, and calculate the traffic efficiency indicators to adjust the optimization process.
It improves the accuracy and flexibility of three-dimensional optimization of the pedestrian network, generates the optimal solution that conforms to factual basis, improves the efficiency of residents' access and walking experience, meets the actual needs of users, and enhances the availability and convenience of the pedestrian network.
Smart Images

Figure CN119003672A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of urban three-dimensional pedestrian system planning, and in particular to a three-dimensional pedestrian network optimization method and system with high traffic efficiency as the goal. Background Art
[0002] At present, the construction of a three-dimensional pedestrian system with subways and commercial facilities as the core can effectively improve the efficiency of pedestrian traffic and enable pedestrians to reach their destinations conveniently and quickly. The three-dimensional optimization method for the existing pedestrian network is mainly based on human qualitative analysis, analyzing data such as crowd activities and traffic patterns through questionnaires and interviews. On this basis, urban planners rely on experience and theoretical knowledge to propose preliminary plans based on the current status of urban development and future development needs, and then evaluate the preliminary plans, listen to the opinions of the public and relevant departments, and make necessary adjustments and optimizations to the plans.
[0003] However, the above-mentioned method of building a three-dimensional road network based on the existing pedestrian network has significant defects, namely: the method mainly relies on questionnaire surveys and on-site observations. Due to the limited data samples and the susceptibility to subjective factors, the optimization scheme may not be comprehensive and accurate enough, and cannot provide effective theoretical guidance for practical applications. In addition, the traditional planning method lacks systematic simulation means, making it difficult to flexibly adjust and optimize according to actual usage, and the response speed is slow and the planning efficiency is low.
[0004] Therefore, it is necessary to propose a three-dimensional optimization method and system for pedestrian networks with the goal of efficient traffic flow, which can use automated simulation technology to quickly and efficiently perform three-dimensional optimization of pedestrian networks, and generate a fact-based and targeted optimal solution while comprehensively considering the overall pedestrian road network, thereby improving residents' traffic efficiency and walking experience, 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 a pedestrian network with the goal of improving traffic efficiency, so as to solve the technical problems of the existing three-dimensional optimization of pedestrian networks, such as incomplete data collection and analysis, lack of simulation means, insufficient optimization accuracy, and difficulty in flexible adjustment according to actual usage.
[0006] In order to achieve the above technical objectives, the present invention adopts the following technical solutions:
[0007] In a first aspect, the present invention provides a method for optimizing a pedestrian network with a three-dimensional structure and a high traffic efficiency as a goal, comprising:
[0008] Acquire image map data with a road system, preprocess and analyze and simplify the image map data, and construct a road network data set containing road nodes;
[0009] Based on the average path length of the three-dimensional pedestrian passage and the number of turns in the underground passage, an optimization objective function is established;
[0010] Simulating and optimizing the optimization objective function according to preset constraints and the road network data set to obtain an optimal solution consisting of road nodes so that the optimization objective function achieves an optimal balance;
[0011] The pedestrian network is optimized according to the optimal solution, the optimized traffic efficiency index is calculated, and the simulation optimization process is optimized based on the traffic efficiency index.
[0012] Furthermore, the image data is preprocessed and analyzed and simplified, including:
[0013] Use automatic vectorization tools to extract the road centerline in the image map, supplement and improve the underground road data, and manually calibrate the data to complete the construction of the road basic data set;
[0014] Based on graph theory, the basic road dataset is simplified, redundant data is merged and deleted, and network analysis tools are used to construct a road network dataset containing underground nodes and edges. The road network structure is converted into a point-edge relationship dataset to obtain a road network dataset containing multiple road nodes.
[0015] Furthermore, the preset constraints include:
[0016] Set nodes with function attributes to be mapped down;
[0017] The node depths of different nodes vertically mapped downwards meet the preset depth standards;
[0018] A vertical connection channel needs to be formed between the downward mapped nodes and the ground.
[0019] Furthermore, the objective function is:
[0020] fit=w1L+w2C
[0021]
[0022] Where L represents the average shortest path length of three-dimensional walking, C represents the number of turns in the underground passage, w1 and w2 are the weights of the average shortest path length of three-dimensional walking and the number of turns in the underground passage, N represents the number of effective paths, and d(s i ,t i ) represents the i-th pair of nodes (s i ,t i ), U represents the set of all underground nodes, N (μ)Represents the set of neighbor node pairs of node u. turn_indicator(v,u,w) represents an indicator function of whether the angle between neighbor nodes v and w of node u is greater than a preset threshold. If it is greater than the preset threshold, it is 1, otherwise it is 0.
[0023] Furthermore, the optimization objective function is simulated and optimized according to the preset constraint conditions and the road network data set, including:
[0024] Based on the iterative operation of selection, crossover and mutation of the genetic algorithm, the optimization objective function is solved so that the average shortest path and the number of turns in the underground passage in the optimization objective function reach the best balance.
[0025] Furthermore, based on the iterative operation of selection, crossover and mutation of the genetic algorithm, the optimization objective function is solved, including:
[0026] Generate an initial solution set containing multiple optimization solutions that meet preset constraints, and calculate the function value of the optimization objective function corresponding to each optimization solution in the initial solution set;
[0027] Each optimization solution in the initial solution set is treated as an individual for genetic iteration, and the individual with the smallest function value is taken 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, the parent generation individual is selected in a preset selection method, and the parent generation 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] The optimization objective function values of all individuals in the offspring solution set are calculated until the optimization objective function value converges, and then the optimal solution is output.
[0029] Furthermore, based on the optimization objective function value corresponding to each generation of individuals, the parent generation individuals are selected in a preset selection method, including:
[0030] Based on the optimization objective function value, parent individuals are selected in a tournament manner. Individuals with shorter paths and fewer underground turns have a greater probability of being selected.
[0031] Furthermore, the pedestrian network is optimized according to the optimal solution, the optimized traffic efficiency index is calculated, and the simulation optimization process is optimized based on the traffic efficiency index, including:
[0032] The SDNA analysis method is used to compare and analyze the traffic efficiency indicators of the three-dimensional pedestrian network system before and after optimization. If the difference in traffic efficiency indicators 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] In a second aspect, the present invention further provides a pedestrian network three-dimensional optimization system with the goal of improving traffic efficiency, comprising:
[0034] A data acquisition module is used to acquire image map data having a road system, pre-process and analyze and simplify the image map data, and construct a road network data set containing road nodes;
[0035] An 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] A simulation optimization module, used for performing simulation optimization on the optimization objective function according to preset constraints and the road network data set, obtaining an optimal solution consisting of road nodes, so that the optimization objective function achieves an optimal balance;
[0037] The efficiency optimization module is used to optimize the pedestrian network according to the optimal solution, calculate the optimized traffic efficiency index, and optimize the simulation optimization process based on the traffic efficiency index.
[0038] In a third aspect, the present invention further provides an electronic device comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, a three-dimensional optimization method for a pedestrian network with the goal of improving traffic efficiency is implemented as described in any of the above technical solutions.
[0039] Compared with the prior art, the system and method provided by the present invention can accurately construct a road network data set containing multiple road nodes by preprocessing and analyzing and simplifying the image map. Based on the real image map data, it not only accurately reflects the actual situation of the terrain and the road, but also facilitates the accuracy of subsequent path optimization. Based on the average path length and number of turns of the underground passage, the 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, and by calculating the traffic efficiency index, ensuring that the pedestrian passages finally designed are efficient and convenient in actual use. The present invention not only improves the accuracy and flexibility of the three-dimensional optimization of the pedestrian network, but also can better meet the actual needs of users, improve user comfort and satisfaction, enhance the availability and convenience of the pedestrian network, and provide further scientific and flexible solutions for urban planning and construction. BRIEF DESCRIPTION OF THE DRAWINGS
[0040] Figure 1 A schematic flow chart of a pedestrian network three-dimensional optimization method for traffic efficiency provided by the present invention;
[0041] Figure 2 A schematic diagram of the process of vectorizing an image provided by the present invention;
[0042] Figure 3 A schematic diagram of the structure of a pedestrian network three-dimensional optimization system aimed at improving traffic efficiency provided by the present invention;
[0043] Figure 4 This is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION
[0044] The preferred embodiments of the present invention are described in detail below in conjunction with the accompanying drawings, wherein the accompanying drawings constitute a 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 used to limit the scope of the present invention.
[0045] The present invention provides a three-dimensional optimization method for a pedestrian network with the goal of improving traffic efficiency, which is described below.
[0046] Combination Figure 1 As shown, a specific embodiment of the present invention discloses a pedestrian network three-dimensional optimization method with the goal of high traffic efficiency, including:
[0047] Step S101: acquiring image map data having a road system, preprocessing and analyzing and simplifying the image map data, and constructing a road network data set containing road nodes;
[0048] Step S102: establishing an optimization objective function based on the average path length of the three-dimensional pedestrian passage and the number of turns of the underground passage;
[0049] Step S103: simulating and optimizing the optimization objective function according to preset constraints and the road network data set to obtain a traffic subgraph composed of road nodes so that the optimization objective function reaches an optimal balance;
[0050] Step S104: Optimizing the pedestrian network according to the optimal solution, and calculating the optimized traffic efficiency index.
[0051] The method of this embodiment can accurately construct a road network data set containing multiple road nodes by preprocessing and analyzing the image map. Based on the real image map data, it not only accurately reflects the actual situation of the terrain and roads, but also facilitates the accuracy of subsequent path optimization; based on the average path length and number of turns of the underground passage, the optimization objective function is established and solved, the actual needs and behaviors of pedestrians are taken into account, and the accuracy of pedestrian network planning is effectively improved. By calculating the traffic efficiency index, it is ensured that the pedestrian passages finally designed are efficient and convenient in actual use. The present invention not only improves the accuracy and flexibility of the three-dimensional optimization of the pedestrian network, but also can better meet the actual needs of users, improve user comfort and satisfaction, enhance the availability and convenience of the pedestrian network, and provide further scientific and flexible solutions for urban planning and construction.
[0052] As a preferred embodiment, in step S101, the image is preprocessed and analyzed and simplified, including:
[0053] Use automatic vectorization tools to extract the road centerline in the image map, supplement and improve the underground road data, and manually calibrate the data to complete the construction of the road basic data set;
[0054] Based on graph theory, the basic road dataset is simplified, redundant data is merged and deleted, and network analysis tools are used to construct a road network dataset containing nodes and edges. The road network structure is converted into a point-edge relationship dataset to obtain a road network dataset containing multiple road nodes.
[0055] As a specific embodiment, first, an image map with a road system is obtained from a map platform, and the road centerline is extracted by using the automatic vectorization tool of the ArcGIS platform to initially construct a road dataset. On this basis, the unextracted and existing underground road data are supplemented and improved, and manual calibration is performed through field surveys to complete the construction of a preliminary road basic dataset.
[0056] Secondly, based on graph theory, the road data is simplified, redundant data is merged and deleted, and the network analysis tool of the ArcGIS platform is used to build a road network dataset containing underground nodes and edges. Then, the road network structure is converted into a point-edge relationship dataset through the newly created nearest facility point in the network analysis tool. At the same time, manual calibration is required to ensure that the starting point and end point of each edge are correctly connected to the corresponding node, such as Figure 2 As shown, Figure 2 A schematic diagram showing the process of vectorizing an image map.
[0057] It should be noted that the simplified road data based on graph theory is specifically composed of a data structure consisting of nodes (Vertex) and edges (Edge) connecting these nodes, which is used to describe the relationship between road entities. The road network structure is converted into a point-edge relationship dataset, and the information of nodes and their adjacent nodes is stored in a linked list or array. The pedestrian network is planned using the shortest path method, minimum spanning tree method, matching algorithm, etc. This data structure is more suitable for network analysis and simulation. Manual calibration is used to ensure that the starting point and end point of each edge are correctly connected to the corresponding node, thereby improving the quality and availability of the dataset.
[0058] As a specific embodiment, in step S102, in order to improve the efficiency of pedestrian traffic by constructing a three-dimensional pedestrian network, the average shortest path length of the three-dimensional pedestrian channel and the number of turns in the underground channel are used as objective functions to evaluate whether the simulated generated scheme meets the efficiency of pedestrian traffic, thereby screening multiple schemes to obtain the optimal solution.
[0059] As a preferred embodiment, in step S103, the preset constraint conditions include:
[0060] Set nodes with function attributes to be mapped down;
[0061] The node depths of different nodes vertically mapped downwards meet the preset depth standards;
[0062] A vertical connection channel needs to be formed between the downward mapped nodes and the ground.
[0063] Specifically, (1) nodes with functional attributes include subways, commercial nodes, etc., which can be mapped downward; (2) according to building specifications, the depth of vertical mapping of different nodes is limited to: -6 meters for subways, -4 or -6 meters for shopping malls; (3) Nodes mapped downward need to form a vertical connection channel with the ground so that underground structures or facilities can be effectively connected with other facilities or services on the ground, such as elevators or stairs.
[0064] As a preferred embodiment, the objective function is:
[0065] fit=w1L+w2C
[0066]
[0067] Where L represents the average shortest path length of three-dimensional walking, C represents the number of turns in the underground passage, w1 and w2 are the weights of the average shortest path length of three-dimensional walking and the number of turns in the underground passage, N represents the number of effective paths, and d(s i ,t i ) represents the i-th pair of nodes (s i,t i ), U represents the set of all underground nodes, N (μ) Represents the set of neighbor node pairs of node u. turn_indicator(v,u,w) represents an indicator function of whether the angle between neighbor nodes v and w of node u is greater than a preset threshold. If it is greater than the preset threshold, it is 1, otherwise it is 0.
[0068] It should be noted that w1 and w2 are usually set to 0.5. This is because the average shortest path length and the number of turns in the underground passage are equally important in pedestrian network planning. In order to comprehensively consider the above two objectives, the fitness evaluation of traffic efficiency is performed by taking the average value. As a preferred embodiment, in the simulation optimization process, the highest pedestrian traffic efficiency is taken as the goal, and the iterative operations such as selection, crossover, and mutation of the genetic algorithm are used to solve the optimal solution of the three-dimensional pedestrian system with efficient traffic. 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 so that the subgraph composed of these nodes achieves the best balance in terms of average shortest path and number of turns.
[0069] As a preferred embodiment, the optimization objective function is solved based on iterative operations of selection, crossover and mutation of a genetic algorithm, including:
[0070] Generate an initial solution set containing multiple optimization solutions that meet preset constraints, and calculate the function value of the optimization objective function corresponding to each optimization solution in the initial solution set;
[0071] Each optimization solution in the initial solution set is treated as an individual for genetic iteration, and the individual with the smallest function value is taken 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, the parent generation individual is selected in a preset selection method, and the parent generation 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] The optimization objective function values of all individuals in the offspring solution set are calculated until the optimization objective function value converges, and then the optimal solution is output.
[0073] As a preferred embodiment, the method of selecting the parent generation individuals in a preset selection manner based on the optimization objective function value corresponding to each generation of individuals includes:
[0074] Based on the optimization objective function value, parent individuals are selected in a tournament manner. Individuals with shorter paths and fewer underground turns have a greater probability of being selected.
[0075] In order to better illustrate the above process, the solution process is described in detail. The steps are:
[0076] S41: Randomly generate N groups of codes from the solution set S that meets the requirements of the three-dimensional road network construction (preset constraints) to form an initial solution set P (1, 1..N);
[0077] S42: Solve the traffic efficiency by averaging the shortest path and the number of turns, and form the fitness function (i.e., optimization objective function) F(P(1,1..N)) of all individuals in P(1,1..N) after weighting;
[0078] S43: Genetic iteration begins, and each generation of population is recorded as P(X,1..N), where X is the number of iterations;
[0079] S44: The solution with the lowest fitness function F(P(X,1..N)) in P(X,1..N) is taken as the current optimal solution, and directly enters the next iteration P(X+1);
[0080] S45: Select a solution P(X,A) 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 lower the number of turns, the greater the probability of 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 lower the number of turns, the greater the probability of being selected.
[0082] S47: Randomly select the bitwise encoding of P(X,A) or P(X,B) to generate P(X,TEMP);
[0083] S48: mutate each bit of P(X,TEMP) with probability P;
[0084] S49: Verify the specification compliance of P(X,TEMP). If it complies, add it to the next generation iteration P(X+1).
[0085] S410: Determine the size of the next generation population. When the number of P(X+1) individuals reaches N (the preset population number), enter S411, otherwise return to S45;
[0086] S411: Solve the traffic efficiency by averaging the shortest path and the number of turns, and form the fitness function F(P(X+1,1..N)) of all individuals in P(X+1,1..N) after weighting;
[0087] S412: Determine whether the algorithm has converged. When the fitness function corresponding to the optimal solution of M consecutive generations remains unchanged, the result is considered to have converged and the optimal solution is output. Otherwise, return to S43 to start the next generation of genetic iteration.
[0088] As a preferred embodiment, the pedestrian network is optimized according to the optimal solution, the optimized traffic efficiency index is calculated, and the simulation 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 indicators of the three-dimensional pedestrian network system before and after optimization. If the difference in traffic efficiency indicators 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 here that the traffic efficiency indicators used in the present invention include detour rate and connectivity. The detour rate refers to the proportion of additional walking distance caused by the lack of direct paths in the transportation network. A high detour rate may indicate insufficient connections in the transportation network or unreasonable path design, which affects traffic efficiency; connectivity refers to the degree and quality of connection between nodes in the pedestrian network. High connectivity means that you can quickly reach your destination through multiple paths, avoiding longer walking time and a poorer experience due to a single path. These indicators not only help evaluate the overall operation of the pedestrian network system, but also provide an important reference for the three-dimensional planning of the pedestrian network and infrastructure improvement.
[0091] As a specific embodiment, in the ArcGIS platform, the SDNA analysis method is used to analyze the detour rate, connectivity and other indicators of the front and rear three-dimensional pedestrian network system. In the ArcGIS platform, SDNA (Spatial Data Network Analysis) is mainly used to analyze and evaluate the spatial relationship between nodes and paths in the network system, and can be used to analyze the detour rate, connectivity and other indicators of the three-dimensional pedestrian network system. By comparing the changes in the data before and after. If the difference between the before and after results is not obvious (not in line with the preset range of changes), it is necessary to adjust the number of iterations of the genetic algorithm, the number of populations and other parameters until the optimal solution is found.
[0092] In order to verify the effect of the present invention in optimizing the efficiency of pedestrian traffic through the construction of a three-dimensional pedestrian system in practical applications, the experiment selected a subway station in a certain city and a 500-meter walking range around it as the verification object, and used a genetic algorithm to optimize and improve the existing pedestrian network through the construction of a three-dimensional pedestrian network. The SDNA analysis method was used to compare the detour rate and connectivity of the entire road network before and after optimization. The results are shown in Table 1 below.
[0093] Table 1 Comparison of analysis results of detour rate and connectivity of the three-dimensional pedestrian network system before and after optimization
[0094]
[0095]
[0096] It can be seen from the results in Table 1 that the method of this embodiment shows remarkable results in improving traffic efficiency.
[0097] like Figure 3 As shown, this embodiment also provides a pedestrian network three-dimensional optimization system 300 with the goal of improving traffic efficiency, including:
[0098] A data acquisition module is used to acquire image map data having a road system, pre-process and analyze and simplify the image map data, and construct a road network data set containing road nodes;
[0099] An 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] A simulation optimization module, used for performing simulation optimization on the optimization objective function according to preset constraints and the road network data set, obtaining an optimal solution consisting of road nodes, so that the optimization objective function achieves an optimal balance;
[0101] The efficiency optimization module is used to optimize the pedestrian network according to 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, the present invention also provides an electronic device 400 for optimizing a pedestrian network with a goal of improving traffic efficiency. The electronic device may be a computing device such as a mobile terminal, a desktop computer, a notebook, a palm computer, and a server. The electronic device includes a processor 401, a memory 402, and a display 403.
[0103] In some embodiments, the memory 402 may be an internal storage unit of a computer device, such as a hard disk or memory of the computer device. In other embodiments, the memory 402 may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the computer device. Further, the memory 402 may also include both an internal storage unit of the computer device and an external storage device. The memory 402 is used to store application software and various types of data installed on the computer device, such as program codes for installing the computer device. The memory 402 may also be used to temporarily store data that has been output or is to be output. In one embodiment, a pedestrian network three-dimensional optimization method program 404 with a goal of high traffic efficiency is stored on the memory 402, and the pedestrian network three-dimensional optimization method program 404 with a goal of high traffic efficiency can be executed by the processor 401, thereby realizing a pedestrian network three-dimensional optimization method with a goal of high traffic efficiency in each embodiment of the present invention.
[0104] In some embodiments, the processor 401 can be a central processing unit (CPU), a microprocessor or other data processing chip, which is used to run the program code or process data stored in the memory 402, such as executing a pedestrian network three-dimensional optimization method program with the goal of improving traffic efficiency.
[0105] In some embodiments, the display 403 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, an OLED (Organic Light-Emitting Diode) touch device, etc. The display 403 is used to display information on the computer device and to display a visual user interface. The components 401-403 of the computer device communicate with each other through a system bus.
[0106] The method and system for optimizing the pedestrian network with high traffic efficiency provided in this embodiment can provide more accurate and complex data support by using automated simulation technology in terms of accuracy improvement, thereby effectively making up for the deficiencies of traditional methods in data collection and analysis, and improving the accuracy of the optimization of the pedestrian network. In terms of flexibility, the dynamic adjustment of the three-dimensional optimization scheme of the pedestrian network is realized, and the overall network structure can be adjusted according to the actual application situation, so as to cope with changes in scenarios and needs and adapt to the flexibility of the network.
[0107] The present invention not only improves the accuracy and flexibility of three-dimensional optimization of pedestrian networks, but also can better meet the actual needs of users, improve user comfort and satisfaction, enhance the availability and convenience of pedestrian networks, and provide further scientific and flexible solutions for urban planning and construction.
[0108] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.
Claims
1. A pedestrian network three-dimensional optimization method with the goal of high traffic efficiency, characterized in that: include: Acquire image map data with a road system, preprocess and analyze and simplify the image map data, and construct a road network data set containing road nodes; Based on the average path length of the three-dimensional pedestrian passage and the number of turns in the underground passage, an optimization objective function is established; Simulating and optimizing the optimization objective function according to preset constraints and the road network data set to obtain an optimal solution consisting of road nodes so that the optimization objective function achieves an optimal balance; The pedestrian network is optimized according to the optimal solution, the optimized traffic efficiency index is calculated, and the simulation optimization process is optimized based on the traffic efficiency index.
2. The pedestrian network three-dimensional optimization method with traffic efficiency as the goal according to claim 1 is characterized in that: Preprocessing and analyzing the image data includes: Use automatic vectorization tools to extract the road centerline in the image map, supplement and improve the underground road data, and manually calibrate the data to complete the construction of the road basic data set; Based on graph theory, the basic road dataset is simplified, redundant data is merged and deleted, and network analysis tools are used to construct a road network dataset containing underground nodes and edges. The road network structure is converted into a point-edge relationship dataset to obtain a road network dataset containing multiple road nodes.
3. The pedestrian network three-dimensional optimization method for traffic efficiency as the goal according to claim 1 is characterized in that: The preset constraints include: Set nodes with function attributes to be mapped down; The node depths of different nodes vertically mapped downwards meet the preset depth standards; A vertical connection channel needs to be formed between the downward mapped nodes and the ground.
4. The pedestrian network three-dimensional optimization method for traffic efficiency as the goal according to claim 1 is characterized in that: The objective function is: fit=w1L+w2C Where L represents the average shortest path length of three-dimensional walking, C represents the number of turns in the underground passage, w1 and w2 are the weights of the average shortest path length of three-dimensional walking and the number of turns in the underground passage, N represents the number of effective paths, and d(s i ,t i ) represents the i-th pair of nodes (s i ,t i ), U represents the set of all underground nodes, N (μ) Represents the set of neighbor node pairs of node u. turn_indicator(v,u,w) represents an indicator function of whether the angle between neighbor nodes v and w of node u is greater than a preset threshold. If it is greater than the preset threshold, it is 1, otherwise it is 0.
5. The method for three-dimensional optimization of pedestrian network with traffic efficiency as the goal according to claim 1, characterized in that: The optimization objective function is simulated and optimized according to the preset constraint conditions and the road network data set, including: Based on the iterative operation of selection, crossover and mutation of the genetic algorithm, the optimization objective function is solved so that the average shortest path and the number of turns in the underground passage in the optimization objective function reach the best balance.
6. The method for three-dimensional optimization of pedestrian network with traffic efficiency as the goal according to claim 5, characterized in that: The optimization objective function is solved based on iterative operations of selection, crossover and mutation of the genetic algorithm, including: Generate an initial solution set containing multiple optimization solutions that meet preset constraints, and calculate the function value of the optimization objective function corresponding to each optimization solution in the initial solution set; Each optimization solution in the initial solution set is treated as an individual for genetic iteration, and the individual with the smallest function value is taken 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, the parent generation individual is selected in a preset selection method, and the parent generation 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; The optimization objective function values of all individuals in the offspring solution set are calculated until the optimization objective function value converges, and then the optimal solution is output.
7. The method for optimizing pedestrian network three-dimensionally with traffic efficiency as the goal according to claim 6, characterized in that: Based on the optimization objective function value corresponding to each generation of individuals, the parent generation individuals are selected in a preset selection method, including: Based on the optimization objective function value, parent individuals are selected in a tournament manner. Individuals with shorter paths and fewer underground turns have a greater probability of being selected.
8. The method for optimizing pedestrian network three-dimensionally with traffic efficiency as the goal according to claim 6, characterized in that: The pedestrian network is optimized according to the optimal solution, the optimized traffic efficiency index is calculated, and the simulation optimization process is optimized based on the traffic efficiency index, including: The SDNA analysis method is used to compare and analyze the traffic efficiency indicators of the three-dimensional pedestrian network system before and after optimization. If the difference in traffic efficiency indicators 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.
9. A pedestrian network three-dimensional optimization system with the goal of improving traffic efficiency, characterized in that: include: A data acquisition module is used to acquire image map data having a road system, pre-process and analyze and simplify the image map data, and construct a road network data set containing road nodes; An 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; A simulation optimization module, used for performing simulation optimization on the optimization objective function according to preset constraints and the road network data set, obtaining an optimal solution consisting of road nodes, so that the optimization objective function achieves an optimal balance; The efficiency optimization module is used to optimize the pedestrian network according to the optimal solution, calculate the optimized traffic efficiency index, and optimize the simulation optimization process based on the traffic efficiency index.
10. An electronic device, characterized in that: It includes a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, a three-dimensional optimization method for a pedestrian network with traffic efficiency as the goal is implemented as described in any one of claims 1-8.
Citation Information
Patent Citations
Dynamic traffic network urban road feature model and modeling method thereof
CN103531024A
Block building volume intelligent generation method and system based on multi-objective genetic algorithm
CN116452373A
Management and control method and management and control device of self-adaptive speed adjusting system for managing and controlling vehicle
CN118369257A
Method and system for super-resolution reconstruction of heterogeneous stereoscopic images
EP4148658A1
