A subway station crowd transfer route optimization method and device and a storage medium

Abstract

The application discloses a subway station crowd transfer route optimization method and device and a storage medium, wherein the method comprises the following steps: acquiring layout information of a subway station, and abstracting a subway station scene into a complete graph according to the layout information; screening edges in the complete graph according to a preset screening condition, so as to delete edges that do not meet the condition; constructing a mathematical model according to the screened complete graph, and determining an optimization target of the model; and according to the optimization target, optimizing the model by using an ant colony algorithm, so as to obtain a final transfer route scheme. The ant colony algorithm is applied to the subway station crowd transfer route optimization scheme, a real subway station scene simulation model is established by coding entity facility nodes in the subway station scene, a corresponding crowd transfer route facility design is abstracted into a path planning optimization problem to be solved, and an effective crowd transfer route design scheme can be better provided. The application can be widely applied to urban subway traffic and intelligent computing fields.

Description

A method, device, and storage medium for optimizing passenger transfer routes in subway stations. Technical Field

[0001] This invention relates to the fields of urban subway transportation and intelligent computing, and in particular to a method, apparatus and storage medium for optimizing passenger transfer routes in subway stations. Background Technology

[0002] In many city subway stations, pedestrian transfer route planning still relies on manual methods. Subway staff can guide passengers by setting up barriers or signs. However, during holidays or rush hours, passenger flow surges in some subway stations, especially those with multiple lines. In these high-traffic stations with multiple lines, relying solely on manual judgment to set up barriers or signs is insufficient to handle the increasingly complex passenger flow. Poorly designed transfer routes may cause people from different directions to pass through the same areas simultaneously, slowing passenger movement and significantly reducing transfer efficiency, potentially hindering the efficiency of the city's subway network. During peak hours, this can even lead to congestion or stampedes, posing a significant threat to public transportation safety. Therefore, researching how to plan subway passenger transfer routes is crucial for alleviating subway traffic pressure and reducing safety threats within stations. Summary of the Invention

[0003] In order to at least partially solve one of the technical problems existing in the prior art, the present invention aims to provide a method, device and storage medium for optimizing passenger transfer routes in subway stations.

[0004] The technical solution adopted in this invention is:

[0005] A method for optimizing passenger transfer routes in subway stations includes the following steps:

[0006] Obtain the layout information of the subway station, and abstract the subway station scene into a complete graph based on the layout information; where the obstacle objects in the subway station scene are the vertices of the complete graph, and the edge between any two vertices is used to represent a fence that prohibits pedestrian passage.

[0007] The edges in the complete graph are filtered according to preset filtering conditions to delete edges that do not meet the conditions.

[0008] A mathematical model is constructed based on the selected complete graph, and the optimization objective of the model is determined.

[0009] Based on the optimization objective, the ant colony algorithm is used to optimize the model and obtain the final transfer route plan.

[0010] Furthermore, the obstacles in the subway station scene include entities with obstacle attributes such as ticket machines, elevators, support columns, and others;

[0011] The process of abstracting the subway station scene into a complete graph based on the layout information includes:

[0012] Based on the obstacles in the subway station scene, obtain the node set V = {v1, v2, ..., v...} N};

[0013] By connecting any two nodes in the node set V, a complete graph G = (V, E) is constructed; where E represents the edge set of the complete graph G, and the element e in the edge set E is... ij Let v represent an edge in a complete graph G, representing the edge at node v. i and node v j A fence between them;

[0014] For element e ij have:

[0015] e ij ∈{(v i ,v j )|i≠j,(v i ,v j )∈V 2}

[0016] Furthermore, the step of filtering edges in the complete graph according to preset filtering conditions includes:

[0017] Set the upper limit of the side length L max In a complete graph G, the length exceeds the upper limit of the side length L. max After deleting the edges, we obtain the optimized edge set E':

[0018]

[0019] Among them, Distance(v i ,v j ) represents the key point v in the scene. i and scene key points v j The Eulerian distance between them.

[0020] Furthermore, the step of constructing a mathematical model based on the filtered complete graph and determining the optimization objective of the model includes:

[0021] The elements in edge set E' are represented lexicographically by scene keypoint pairs as X = {x1, x2, ..., x...} m}, where the locations of these key points can be selected for whether or not to place fences;

[0022] The problem of optimizing subway station transfer routes is transformed into finding the optimal subset of X, with the optimization objective being to minimize the congestion within the subway station:

[0023]

[0024] Where T is the maximum simulation time and N is the number of passengers in the subway station; Let be the angle between the forward directions of passengers i and j at time t in the simulation, the radii of passengers i and j, and the Eulerian distance between them; The exponent represents the difference between the radius and the Euler distance.

[0025] Furthermore, the step of optimizing the model using an ant colony algorithm based on the optimization objective to obtain the final transfer route plan includes:

[0026] A1. Initialize pheromones; whereby the pheromones are distributed on the fence;

[0027] A2. Initialize the ant colony. At the beginning of each round of the loop, each ant will be given a fixed starting point. After each ant is given a starting point, the ant will select the next fence to traverse based on the heuristic information and pheromone information of the subway station scene.

[0028] A3. The ant selects the next fence to visit according to the preset rules;

[0029] A4. When an ant obtains the next fence to visit, it locally updates the pheromones on the fence it has passed through.

[0030] A5. Decode the path into a scene layout scheme, evaluate the congestion of the scheme, and calculate the fitness value of the layout scheme.

[0031] A6. Global Pheromone Update: In this transfer route optimization scheme, the elite ant pheromone update method is adopted; after all ants have completed path construction, the ants that have searched for the historical best solution will add extra pheromones to their corresponding routes.

[0032] A7. If the evolution has reached the maximum number of evaluations, proceed to step A8; otherwise, return to step A2 to enter the next round of evolution.

[0033] A8. Decode the path with the minimum fitness value to obtain the optimal layout of subway station passenger transfer routes.

[0034] Further, step A3 specifically includes:

[0035] In the i-th step of each ant, its next visit to the fence... The rules are as follows:

[0036]

[0037] Among them, Γ iμ fence The pheromone content on the surface, where q represents the current random number, and q0 represents a predefined number; η i fence Heuristic information on S r for:

[0038]

[0039] Where dsample represents discrete distribution sampling operation; represents pheromone influence factor, β represents heuristic information influence factor, and μ represents whether the fence is selected, μ∈{0,1};

[0040] As shown in formula (2), the heuristic information is a one-dimensional vector, which is calculated as follows:

[0041] η i =f(I i ),I i ={x i} (3)

[0042] Among them I i It is a path The candidate solutions obtained after decoding.

[0043] Furthermore, in step A4, the pheromones are locally updated using the following formula:

[0044]

[0045] in, Γ0 is the local pheromone evaporation factor, and Γ0 is the initial value of the pheromone.

[0046] Furthermore, in step A6, the following formula is used for global pheromone update:

[0047]

[0048] in, The optimal path x in this generation of candidate solutions best The fence on top, This represents the optimal fence. On the pheromone, Γ max Γ represents the maximum pheromone content. min This represents the minimum pheromone value. This refers to the local volatile factor of pheromones.

[0049] Another technical solution adopted in this invention is:

[0050] A subway station passenger transfer route optimization device includes:

[0051] At least one processor;

[0052] At least one memory for storing at least one program;

[0053] When the at least one program is executed by the at least one processor, the at least one processor implements the method described above.

[0054] Another technical solution adopted in this invention is:

[0055] A computer-readable storage medium storing a processor-executable program, which, when executed by a processor, performs the method described above.

[0056] The beneficial effects of this invention are: This invention applies the ant colony algorithm to the optimization scheme of passenger transfer routes in subway stations. By encoding the physical facility nodes in the subway station scene to establish a simulation model of the real subway station scene, the design of the corresponding passenger transfer route facilities is abstracted into a path planning optimization problem for solution, which can provide a better and more effective passenger transfer route design scheme. Attached Figure Description

[0057] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following description is provided with accompanying drawings of the relevant technical solutions in the embodiments of the present invention or the prior art. It should be understood that the accompanying drawings described below are only for the purpose of clearly illustrating some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0058] Figure 1 is a flowchart of the steps of a subway station passenger transfer route optimization method in an embodiment of the present invention;

[0059] Figure 2 is a flowchart of subway station passenger transfer route optimization based on ant colony algorithm in an embodiment of the present invention;

[0060] Figure 3 is a coding example diagram of a scene facility placement scheme in an embodiment of the present invention. Detailed Implementation

[0061] The embodiments of the present invention are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention. The step numbers in the following embodiments are set only for ease of explanation, and there is no limitation on the order between the steps. The execution order of each step in the embodiments can be adaptively adjusted according to the understanding of those skilled in the art.

[0062] In the description of this invention, it should be understood that the orientation descriptions, such as up, down, front, back, left, right, etc., are based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limiting this invention.

[0063] In the description of this invention, "several" means one or more, "multiple" means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. The use of "first" and "second" in the description is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.

[0064] In the description of this invention, unless otherwise explicitly defined, terms such as "set up," "install," and "connect" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this invention in conjunction with the specific content of the technical solution.

[0065] The layout design of crowd guidance facilities falls under the category of traffic route planning problems, which can be optimized using ant colony optimization (ACO) systems. First proposed by Dorigo et al. in 1996, ACO is a variant of the ant colony algorithm that improves its performance. The ant colony algorithm is a probabilistic algorithm used to find optimal paths. It is inspired by the path-finding behavior of ants in their foraging activities. While the behavior of an individual ant is relatively simple, the ant colony as a whole exhibits intelligent behavior. Ants release pheromones along their paths, and the ants within the colony are able to sense these pheromones, guiding the next ant's movement. Ants on better paths release more pheromones, and as time progresses, the accumulated pheromone concentration on these better paths gradually increases, leading to more ants choosing these paths. Ultimately, the ant colony, under positive feedback, converges on the optimal path.

[0066] Ant colony optimization (ACO) features distributed computation, positive feedback, and heuristic search, offering new possibilities for solving complex problems. Compared with other optimization algorithms, ACO has the following characteristics: (1) It adopts a positive feedback mechanism, and the search process continuously converges, constantly approaching the optimal solution. (2) Each individual can perceive real-time changes in the surrounding environment and can indirectly communicate with other individuals by releasing pheromones to change the surrounding environment. (3) It adopts a heuristic probabilistic search method, making it less prone to getting trapped in local optima. (4) It has strong parallelism.

[0067] The ant colony system makes the following improvements to enhance its ability to search for better solutions: (1) State transition rule: The ant colony system introduces a parameter q0, which can adjust the degree to which ants explore new paths, effectively enhancing the ants' ability to search within the range of optimal solutions. (2) Global update rule: Global updates are no longer applied to all ants, but only to the best ant in each cycle. This increases the pheromone difference between the best and worst paths, causing the ants' search behavior to quickly concentrate near the best path, greatly improving search efficiency. (3) Local update rule: The ant colony algorithm only performs a global update on the pheromone once. However, in the ant colony system, ants not only perform a global update on the path after each cycle, but also perform a local update while constructing the path.

[0068] Because of its good performance in combinatorial optimization problems, the ant colony algorithm has been extensively studied over the past few decades, such as the traveling salesman problem, assignment problem, job-shop scheduling problem, vehicle routing problem, graph coloring problem, and network routing problem. The ant colony algorithm has also shown certain advantages in solving path planning problems.

[0069] As shown in Figure 1, this embodiment provides a method for optimizing passenger transfer routes in subway stations, including the following steps:

[0070] S1. Obtain the layout information of the subway station and abstract the subway station scene into a complete graph based on the layout information; where the obstacle objects in the subway station scene are the vertices of the complete graph, and the edge between any two vertices is used to represent a fence that prohibits pedestrian traffic.

[0071] Historical pedestrian flow data was collected from subway stations, including all entrances / exits, platforms, elevators, ticket gates, etc. This historical data was then combined with a virtual crowd simulation model to create a realistic subway station scene simulation model.

[0072] Specifically, step S1 includes steps S11-S12:

[0073] S11. Collect statistics on the entity elements of the subway station, such as ticket machines, elevators, support columns, and other obstacle attributes, and designate them as scene key points, numbering them as V={v1,v2,...,v...}. n}

[0074] S12. Using V as a node, construct a graph G = (V, E), where:

[0075]

[0076] (v i ,v j This indicates that at the key point v in the scene... i and scene key points v j Fences or movable walls between them.

[0077] S2. Filter the edges in the complete graph according to the preset filtering conditions to delete the edges that do not meet the conditions.

[0078] Let L max Let E' be the maximum length of the fence or movable wall. Based on this length, some unwanted edges can be removed, resulting in E':

[0079]

[0080] Among them, Distance(v i ,v j ) represents the key point v in the scene. i and scene key points v j The Eulerian distance between them.

[0081] S3. Construct a mathematical model based on the selected complete graph and determine the optimization objective of the model.

[0082] For ease of representation, we will represent the elements in E' in lexicographical order of scene keypoint pairs as X={x1,x2,...,x m The locations of these key points can be adjusted by placing fences; in subsequent optimizations, x will be referred to as the fence slot in this embodiment. Therefore, we transform the subway station passenger transfer route optimization problem into solving for the optimal subset of X, with the optimization objective being to minimize the congestion within the subway station.

[0083]

[0084] Where T is the maximum simulation time and N is the number of passengers in the subway station. Let be the angle between the forward directions of passengers i and j at time t in the simulation, the radii of passengers i and j, and the Euler distance between them.

[0085] S4. Based on the optimization objective, the ant colony algorithm is used to optimize the model to obtain the final transfer route plan.

[0086] Using the ant colony algorithm, with the goal of minimizing congestion in the subway station, the transfer routes for subway passengers are calculated, resulting in a transfer route plan.

[0087] As an optional implementation, step S4 specifically includes steps S41-S48:

[0088] S41. Initialize pheromones. Unlike traditional ant colony optimization, in this algorithm, pheromones are distributed on the fence slots. In this stage, the initial values ​​of all pheromones are set to the maximum possible pheromone value.

[0089] τ0=τ max (1)

[0090] S42. Initialize the ant colony. At the beginning of each loop, each ant is assigned a fixed starting point. After being assigned a starting point, each ant selects the next fence slot to traverse based on heuristic information from the subway station scene and pheromone information.

[0091] S43. The ant selects the next fence slot to visit. In the i-th step of each ant, its next fence slot to visit is x. i μ The rules are as follows:

[0092]

[0093] Among them, Γ iμ For fence groove The pheromone content on the surface. η i For fence groove Based on the heuristic information above, it can be seen from formula (2) that the fence groove The heuristic information on it is β is the weight of heuristic information, which determines the relative importance between heuristic information and pheromone information. When β is large, ants tend to choose fence slots with higher heuristic information; when β is small, ants tend to choose the traversed fence slots according to the pheromone concentration; and when β = 0, ants only choose the traversed fence slots according to the pheromone. In this case, the algorithm will ignore the heuristic information of the problem itself, and the performance of the algorithm will be relatively poor, and the final subway station layout effect will not be satisfactory. q0 is a pseudo-random factor with a value between 0 and 1. When an ant needs to make a choice each time, the algorithm will randomly generate a random number q also between 0 and 1. When q < q0, the algorithm shows the characteristics of biased search, and the ant directly selects the next fence slot with the largest product of the β power of the heuristic information content and the pheromone content; when q ≥ q0, the algorithm shows the characteristics of exploitation, and the ant randomly selects the next fence slot to visit according to the discrete distribution sampling rule S r to randomly select the next fence slot to visit. S r is as follows:

[0094]

[0095] where, dsample represents the discrete distribution sampling operation. It can be seen from formula (3) that the heuristic information is a one-dimensional vector, and the calculation method of this vector is as shown in formula (4):<00003​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​

[0102]

[0103] In the problem of optimizing passenger transfer routes in subway stations, the evaluation function used can calculate the congestion level of the fence layout. Here, T represents the maximum simulation time, and N represents the number of passengers in the subway station. Let be the angle between the directions of travel of passengers i and j at time t in the simulation, the radii of passengers i and j, and the Eulerian distance between them. The lower the congestion level, the more sparsely distributed the passengers are in the subway station, the smoother the passenger flow, and the better the transfer effect; conversely, when passengers are relatively close to each other, they perceive the subway station as more crowded.

[0104] S46. Global Pheromone Update. In this transfer route optimization scheme, we adopt the elite ant pheromone update method. After all ants have completed path construction, the ants that have searched for the historical best solution so far will add extra pheromones to their corresponding routes.

[0105]

[0106] in The optimal path x in this generation of candidate solutions best The fence slots on the top. Execution continues after a global pheromone update. The introduction of elite ants helps guide the ant search bias, enabling ants to achieve both high solution accuracy and fast evolution speed.

[0107] S47. If the evolution has reached the maximum number of evaluations, proceed to step S48; otherwise, return to step S42 to enter the next round of evolution.

[0108] S48. Decode the path with the minimum fitness value to obtain the optimal layout of subway station passenger transfer routes.

[0109] The method of this embodiment will be explained in detail below with reference to the accompanying drawings and specific embodiments.

[0110] As shown in Figures 2 and 3, this embodiment provides a method for optimizing pedestrian transfer routes in urban subway stations based on ant colony optimization, including the following steps:

[0111] Step 1: Collect pedestrian flow data at the subway station, including historical pedestrian flow data for all entrances / exits, platforms, elevators, ticket gates, etc. Then, combine this historical pedestrian flow data with a virtual crowd simulation model to establish a realistic subway station scene simulation model.

[0112] Step 2: Count the entity elements in the subway station, such as ticket machines, elevators, support columns, and other obstacle attributes. These entities will be designated as key points in the scene and numbered as V = {v1, v2, ..., v...} n}

[0113] Step 3: Using V as a node, construct a graph G = (V, E), where

[0114]

[0115] (v i ,v j This indicates that at the key point v in the scene... i and scene key points v j Fences or movable walls between them.

[0116] Step 4, let L max Let E' be the maximum length of the fence or movable wall. Based on this length, some unwanted edges can be removed, resulting in E':

[0117]

[0118] Where Distance(v i ,v j ) represents the key point v in the scene. i and scene key points v j For ease of representation, we denote the Eulerian distance between the elements in E' as X = {x1, x2, ..., x...} in lexicographical order of key pairs. m The locations of these key points can be adjusted by placing fences; in subsequent optimizations, this invention refers to x as the fence slot. Therefore, we transform the subway station passenger transfer route optimization problem into solving for the optimal subset of X, with the optimization objective being to minimize the congestion within the subway station.

[0119]

[0120] Where T is the maximum simulation time and N is the number of passengers in the subway station. Let r be the angle between the forward directions of passengers i and j at time t in the simulation, the radii of passengers i and j, and the Eulerian distance between them. ij -d ij When r is large, the fitness function assumes that passengers are sparsely distributed in the subway station, passenger flow is smooth, and transfer efficiency is good; when r is large, the fitness function assumes that passengers are sparsely distributed in the subway station, passenger flow is smooth, and transfer efficiency is good. ij -d ijWhen λ is small or negative, the fitness function considers the subway station to be very crowded. λ is a hyperparameter with a value between 0 and 1, controlling the optimization weight of crowding between homogeneous and heterogeneous passengers. When λ = 1, the fitness function only objectively considers the static crowding within the scene; when passengers are relatively close together, the subway station is considered crowded. When λ = 0, the fitness function focuses on the crowding between passengers with different destinations (heterogeneous passengers), while the crowding between passengers traveling in the same direction (homogeneous passengers) is ignored.

[0121] Step 5: Ant colony algorithm design.

[0122] Step 5.1, Construction of the solution

[0123] To adapt to the ant colony optimization algorithm, this optimization problem can be abstracted into a path planning problem. Using... This indicates that the candidate solution x′ contains x i ,and The candidate solution x′ does not contain x i Based on this rule, a directed graph G is constructed. map The construction of the solution involves the following two steps.

[0124] (1) Ant initialization

[0125] In the ant colony algorithm, at the beginning of each loop, each ant will choose a fixed starting point and use it as the starting point to begin the transfer route.

[0126] (2) Constructing a scheduling solution

[0127] In the problem of optimizing passenger transfer routes in subway stations, pheromones are distributed on fenced slots. Furthermore, heuristic information is incorporated into the computation of historical fenced slots to continuously guide ants in choosing subsequent paths.

[0128] η i =f(I i ),I i ={x i} (11)

[0129] At each step of the path-building process, each ant selects the next fence slot to reach according to a random proportional rule. This rule includes a pheromone sum rule.

[0130]

[0131]

[0132] Among them, Γ iμ For fence groove The pheromone content on η i is the fence slot The heuristic information on it. Therefore, as can be seen from formula (12), the fence slot The heuristic information on it is β is the weight of heuristic information, which determines the relative importance between heuristic information and pheromone information. When β is large, ants tend to choose fence slots with higher heuristic information; when β is small, ants tend to choose the traversed fence slots according to the pheromone concentration; and when β = 0, ants only choose the traversed fence slots according to pheromone. In this case, the algorithm will ignore the heuristic information of the problem itself, and the performance of the algorithm will be relatively poor, and the final subway station layout effect will not be satisfactory. q0 is a pseudo-random factor with a value between 0 and 1. When an ant needs to make a choice each time, the algorithm will randomly generate a random number q also between 0 and 1. When q < qo, the algorithm shows the characteristic of biased search, and the ant directly selects the next fence slot with the largest product of the β exponent of the heuristic information content and the pheromone content; when q ≥ q0, the algorithm shows the characteristic of exploitation, and the ant randomly selects the next fence slot to visit according to the discrete distribution sampling rule S r to randomly select the next fence slot to visit. dsample represents the discrete distribution sampling operation.

[0133] Step 5.2, Processing of pheromone

[0134] In the subway station crowd transfer optimization problem, pheromone is distributed on the fence slots.

[0135] (1) Pheromone initialization

[0136] τ0 = τ max (14)

[0137] In the initialization stage, the initial values of all pheromones are set to the maximum value of pheromone.

[0138] (2) Local pheromone update

[0139]

[0140] Among them, is the local pheromone evaporation rate with a size in the interval (0, 1). After local pheromone update, the amount of pheromone at the key point i will decrease, which reduces the probability of this fence slot being selected by other ants. This mechanism can increase the local search ability of the algorithm, making subsequent ants tend to explore unused fence slots, thus avoiding the algorithm from repeating the construction of the same path and falling into a stagnant state.

[0141] (3) Global pheromone update

[0142]

[0143] In this route optimization scheme, we adopt the classic elite ant pheromone update method in ant colony algorithms. After all ants have completed path construction, the ant that has found the best historical solution so far will add extra pheromones to its corresponding route. Compared with traditional ant colony algorithms, this global pheromone update strategy can both enhance the search guidance of the algorithm through excellent ants and effectively reduce the complexity of the algorithm.

[0144] In summary, this embodiment has at least the following advantages and beneficial effects compared to the prior art:

[0145] (1) The embodiments of the present invention construct a subway scene simulation model by collecting historical passenger flow data and virtual crowd simulation model from subway stations. By encoding the facility nodes in the subway scene, the problem is transformed into a problem of solving the optimal subset. The congestion of different candidate transfer routes is evaluated, which can provide a better and more effective design scheme for passenger transfer routes.

[0146] (2) This embodiment of the invention addresses the characteristic of spatial congestion as the optimization objective in the problem of pedestrian transfer path planning. The method designs a novel pheromone calculation strategy that considers the pheromone information of the fenced slots already visited by the ants. By adjusting the weights of different visited fenced slots, the pheromone on fenced slots with higher congestion has a smaller impact on the current path planning direction, while the pheromone on fenced slots with lower congestion has a larger impact. When constructing a solution, the ants are guided by the congestion information implicit in the pheromones.

[0147] (3) In this embodiment of the invention, which addresses the characteristic of spatial congestion as the optimization objective in the problem of pedestrian transfer path planning, a new heuristic computation strategy is designed. This strategy considers the historical information of the fence slots already visited by the ants and takes into account the impact of choosing the next fence slot on the future path planning direction. When constructing a solution, the ants are guided by the congestion information implicit in the heuristic information.

[0148] This embodiment also provides a subway station passenger transfer route optimization device, including:

[0149] At least one processor;

[0150] At least one memory for storing at least one program;

[0151] When the at least one program is executed by the at least one processor, the at least one processor implements the method shown in FIG1.

[0152] This embodiment of a subway station passenger transfer route optimization device can execute a subway station passenger transfer route optimization method provided in the method embodiment of the present invention. It can execute any combination of implementation steps of the method embodiment and has the corresponding functions and beneficial effects of the method.

[0153] This application also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the method shown in FIG1.

[0154] This embodiment also provides a storage medium storing instructions or programs that can execute the subway passenger transfer route optimization method provided in the method embodiment of the present invention. When the instructions or programs are run, any combination of implementation steps of the method embodiment can be executed, and the method has the corresponding functions and beneficial effects.

[0155] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and sub-operations described as part of a larger operation are executed independently.

[0156] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the described functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0157] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0158] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0159] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0160] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0161] In the foregoing description of this specification, references to terms such as "one embodiment," "another embodiment," or "some embodiments" indicate that a specific feature, structure, material, or characteristic described in connection with an embodiment or example is included in at least one embodiment or example of the present invention. In this specification, illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0162] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0163] The above is a detailed description of the preferred embodiments of the present invention. However, the present invention is not limited to the above embodiments. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention. All such equivalent modifications or substitutions are included within the scope defined by the claims of this application.

Claims

1. A method for optimizing passenger transfer routes in subway stations, characterized in that, Includes the following steps: The process involves obtaining the layout information of a subway station and abstracting the subway station scene into a complete graph based on this information. Obstacles in the subway station scene are represented as vertices of the complete graph, and edges between any two vertices represent fences prohibiting pedestrian traffic. Edges in the complete graph are filtered according to preset criteria to remove those that do not meet the conditions. A mathematical model is constructed based on the filtered complete graph, and the optimization objective of the model is determined. Based on the optimization objective, an ant colony optimization algorithm is used to optimize the model to obtain the final transfer route scheme. The obstacles in the subway station scene include entities with obstacle attributes such as ticket machines, elevators, support columns, and others. The abstraction of the subway station scene into a complete graph based on the layout information includes: obtaining a node set based on the obstacles in the subway station scene. According to the node set Connect any two nodes to construct a complete graph. ;in, Represents the complete graph edge set, edge set elements in Representing a complete graph An edge in the node represents an edge in the node. and nodes A fence between them; for elements have: The step of filtering edges in the complete graph according to preset filtering conditions includes: setting an upper limit for edge length. , will complete the map The length of the middle section exceeds the upper limit of the side length. By deleting edges, we obtain the optimized edge set. ： in, Represents a node and nodes The Eulerian distance between them; the construction of a mathematical model based on the filtered complete graph, and the determination of the model's optimization objective, including: the edge set The elements in the array are represented in lexicographical order of the node pairs. The problem involves determining whether or not to place fences at the locations of these node pairs, transforming the optimization problem of subway station passenger transfer routes into a problem of solving... The optimal subset is found, and the optimization objective is to minimize the congestion within the subway station. in, For maximum simulation time, The number of passengers in the subway station; ， ， For simulation Passengers at all times and Angle of direction of travel, passengers and The radius of the radii and the Euler distance between them; The exponent represents the difference between the radius and the Eulerian distance; the optimization of the model using the ant colony algorithm according to the optimization objective to obtain the final transfer route scheme includes: A1, initializing pheromones; wherein, the pheromones are distributed on the fences; A2, initializing the ant colony, at the beginning of each round of the cycle, each ant is assigned a fixed starting point; after each ant is assigned a starting point, the ant will select the next fence to traverse based on the heuristic information and pheromone information of the subway station scene; A3, the ant selects the next fence to visit according to preset rules; A4, when the ant obtains the next fence to visit, it analyzes the information on the fences it has passed. A5. Decode the path into a layout scheme for the scene, evaluate the congestion of the scheme, and calculate the fitness value of the layout scheme; A6. Global pheromone update: In this transfer route optimization scheme, the elite ant pheromone update method is adopted; after all ants have completed path construction, the ants that have searched for the historical best solution will add extra pheromone to their corresponding routes; A7. If the evolution has reached the maximum number of evaluations, proceed to step A8, otherwise return to step A2 to enter the next round of evolution; A8. Decode the path with the minimum fitness value to obtain the optimal layout of the subway station passenger transfer route.

2. The method for optimizing subway passenger transfer routes according to claim 1, characterized in that, Step A3 specifically includes: in the first... Step, its next access fence The rules are as follows: (1) Among them, fence The pheromone content on the surface Indicates the current random number. Represents a predefined number; fence The inspirational information above for: (2) Among them, Represents a discrete distribution sampling operation; Indicates the pheromone influence factor. Indicates the influence factor of heuristic information. Indicates whether the fence has been selected. As shown in formula (2), the heuristic information is a one-dimensional vector, which is calculated as follows: (3) Among them It is a path The candidate solutions obtained after decoding.

3. The method for optimizing subway passenger transfer routes according to claim 1, characterized in that, In step A4, the pheromones are locally updated using the following formula: in, It is a local volatile factor of pheromones. This is the initial value for pheromones.

4. The method for optimizing subway passenger transfer routes according to claim 1, characterized in that, In step A6, the following formula is used for global pheromone updates: in, The optimal path among the current generation of candidate solutions The fence on the top, Indicates the optimal fence On the pheromones, Indicates the maximum pheromone content. This represents the minimum pheromone value. This refers to the local volatile factor of pheromones.

5. A subway station passenger transfer route optimization device, characterized in that, include: At least one processor; At least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the method of any one of claims 1-4.

6. A computer-readable storage medium storing a processor-executable program, characterized in that, The processor-executable program, when executed by the processor, is used to perform the method as described in any one of claims 1-4.

Images