Simulation method, device and electronic equipment for subway passenger behavior

Abstract

The application provides a simulation method and device for subway passenger behavior and electronic equipment, and belongs to the field of data processing. The method comprises the following steps: performing grid processing on a subway model scene to obtain a grid map; determining a target moving path in the grid map according to an initial position and a preset destination of a target passenger; obtaining a current state of the target passenger, wherein the current state is used to indicate a boarding process; determining a behavior decision of the target passenger through a preset behavior tree according to the current state, wherein the behavior decision is used to indicate a next state of the target passenger; and simulating the behavior of the target passenger according to the behavior decision, the target moving path and a social force model. The simulation accuracy and authenticity can be improved.

Description

Technical Field

[0001] This application belongs to the field of data processing, and specifically relates to a simulation method, device, and electronic device for subway passenger behavior. Background Technology

[0002] With the acceleration of global urbanization, subways, as the core carrier of urban rail transit, bear increasing passenger transport pressure. As highly densely populated areas, subway stations' operational efficiency, safety, and passenger experience directly affect the stability of the urban transportation system. Especially during peak hours, complex passenger behaviors, such as route selection, yielding, queuing, and congestion, can lead to safety hazards and operational bottlenecks. Therefore, accurately predicting and simulating passenger behavior through simulation technology is of great value for optimizing subway station design, developing emergency evacuation plans, and managing passenger flow.

[0003] Current simulation methods often focus on modeling single behavioral dimensions, while passenger behavior in subway scenarios is highly dynamic, multi-objective, and socially interactive, requiring consideration of both individual decision-making logic and group movement patterns. Traditional methods struggle to balance simulation scalability, behavioral diversity, and computational efficiency, leading to discrepancies between simulation results and real-world scenarios. For example, passengers cannot adjust their priority based on real-time congestion information, limiting their practical application in engineering. Furthermore, existing methods rely on fixed parameters or probability distributions to generate behavior, failing to reflect passenger heterogeneity. Group behavior coupling effects, such as herd mentality and panic propagation, are not adequately modeled, resulting in distorted simulation results for key phenomena like congestion propagation and bottleneck formation. Summary of the Invention

[0004] This application provides a simulation method, device, and electronic equipment for subway passenger behavior, offering a hybrid simulation framework that overcomes the limitations of a single model. While ensuring computational efficiency, it achieves high-fidelity simulation of the passenger's "decision-action-environment" closed loop. Simultaneously, it unifies intelligent decision-driven processes with group dynamics evolution to address the high-density, high-dynamic subway operation scenarios.

[0005] This application provides a simulation method for subway passenger behavior, including:

[0006] The subway model scene is processed into a grid to obtain a grid map;

[0007] The target passenger's movement path is determined in the grid map based on the passenger's initial location and preset destination;

[0008] Obtain the current status of the target passenger, which is used to indicate the boarding process;

[0009] determine a behavior decision of the target passenger according to the current state and a preset behavior tree, the behavior decision being used to indicate a next state of the target passenger;

[0010] simulate a behavior of the target passenger according to the behavior decision, the target moving path and a social force model.

[0011] According to the simulation method for subway passenger behaviors provided in the embodiments of the present application, the step of simulating the behavior of the target passenger according to the behavior decision, the target moving path and the social force model comprises the steps of: determining a plurality of arrival points from the grid map according to the target moving path; determining a target arrival point farthest from the preset destination among the plurality of arrival points; and simulating the behavior of the target passenger according to the behavior decision, the target arrival point and the social force model.

[0012] According to the simulation method for subway passenger behaviors provided in the embodiments of the present application, the step of simulating the behavior of the target passenger according to the behavior decision, the target arrival point and the social force model comprises the steps of: determining a moving process of the target passenger from a current position to the target arrival point by the social force model; determining a behavior process of the target passenger according to the behavior decision; simulating the behavior of the target passenger according to the moving process and the behavior process; determining a next arrival point of the target arrival point among the plurality of arrival points as the target arrival point, the plurality of arrival points being sorted according to distances from the preset destination, and the farther from the preset destination, the higher in the sorting; and repeating the above behaviors until the target passenger arrives at the preset destination.

[0013] According to the simulation method for subway passenger behaviors provided in the embodiments of the present application, the step of determining the moving process of the target passenger from the current position to the target arrival point by the social force model comprises the steps of: determining a first interaction force between the target passenger and other passengers at the target arrival point; determining a second interaction force between the target passenger and an obstacle at the target arrival point; determining a self-driving force of the target passenger moving to the target arrival point; and determining the moving process of the target passenger from the current position to the target arrival point according to the self-driving force, the first interaction force and the second interaction force.

[0014] According to the simulation method for subway passenger behaviors provided in the embodiments of the present application, the step of determining a plurality of arrival points from the grid map according to the target moving path comprises the steps of: taking a centroid of each grid in the grid map as a moving node; determining a target grid corresponding to the target moving path; and determining a moving node corresponding to the target grid as the plurality of arrival points.

[0015] According to the simulation method for subway passenger behavior provided in the embodiments of the present application, the mobile node corresponding to the target grid is determined as the plurality of arrival points, including: determining whether the target grid is an edge grid of the grid map; if the target grid is the edge grid, determining a point along a normal direction of the mobile node corresponding to the edge grid by a preset distance as an arrival point corresponding to the edge grid.

[0016] The present application also provides an electronic device, including a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the simulation method for subway passenger behavior according to any one of the above embodiments when executing the computer program.

[0017] The present application also provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program is executable by a processor to implement the simulation method for subway passenger behavior according to any one of the above embodiments.

[0018] The present application also provides a computer program product, including a computer program, wherein the computer program is executable by a processor to implement the simulation method for subway passenger behavior according to any one of the above embodiments.

[0019] The simulation method for subway passenger behavior, device and electronic device provided by the present application first perform grid processing on a subway model scene to obtain a grid map, then determine a target moving path in the grid map according to an initial position and a preset destination of a target passenger, then acquire a current state of the target passenger, the current state being used to indicate a boarding process, then determine a behavior decision of the target passenger through a preset behavior tree according to the current state, the behavior decision being used to indicate a next state of the target passenger, and finally simulate the behavior of the target passenger according to the behavior decision, the target moving path and a social force model. The scheme fuses a hybrid simulation framework of a behavior tree and a social force model, breaks through the limitation of a single model, ensures the calculation efficiency, and realizes high-fidelity simulation of a passenger "decision-action-environment" closed loop. Meanwhile, the scheme realizes the unification of intelligent decision driving and group dynamics evolution to cope with high-density and high-dynamic subway operation scenes. BRIEF DESCRIPTION OF DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the present application or prior art, the following will briefly introduce the drawings needed in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor.

[0021] Figure 1is one of flow diagrams of a simulation method for subway passenger behavior provided by the present application.

[0022] Figure 2 is an architecture diagram of a behavior tree provided by the present application.

[0023] Figure 3 is another one of flow diagrams of a simulation method for subway passenger behavior provided by the present application.

[0024] Figure 4 is a functional unit composition block diagram of a simulation device for subway passenger behavior provided by the present application.

[0025] Figure 5 is a structural diagram of an electronic device provided by the present application. DETAILED DESCRIPTION

[0026] In order to make the objectives, technical solutions and advantages of the present application clearer, the technical solutions in the present application will be described clearly and completely below with reference to the drawings in the present application. Obviously, the described embodiments are some embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0027] The terms "first", "second", and the like in the specification of the present application and the above-described drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed or can optionally include other steps or units inherent to the process, method, product or device.

[0028] Reference to "an embodiment" in this document means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present application. The phrase appears at various places in the specification does not necessarily all refer to the same embodiment, nor is it necessarily mutually exclusive of other embodiments. It is explicitly and implicitly understood that the embodiments described herein can be combined with other embodiments.

[0029] Current simulation methods focus on modeling a single behavior dimension, while passenger behavior in a subway scenario has high dynamicity, multi-target and social interaction. Traditional methods are difficult to balance between simulation scale expandability, behavior diversity and computing efficiency, resulting in deviations between simulation results and actual scenarios.

[0030] To solve the above problems, the application provides a simulation method, device and electronic equipment for subway passenger behavior. The embodiments of the application are described in detail below with reference to the drawings.

[0031] Please refer to Figure 1 , Figure 1 is one of the flowcharts of the simulation method for subway passenger behavior provided by the application. The simulation method for subway passenger behavior includes the following steps.

[0032] S101, grid processing is performed on a subway model scene to obtain a grid map.

[0033] Among them, the model scene can be scanned first, and then the reachable part of the model scene is gridded. In particular, triangular meshing or quadrilateral meshing can be used. That is, these reachable areas are divided into a plurality of small planar areas by triangles or quadrilaterals, so as to accurately describe the shape and spatial position of the object.

[0034] S102, determining a target moving path in the grid map according to the initial position and the preset destination of the target passenger.

[0035] Among them, the destination of the target passenger (i.e. pedestrian in the following) can be determined by setting hyperparameters when simulating. Or the preset destination can also be determined automatically according to the initial position of the target passenger. For example, if the initial position of the target passenger is in the subway, the preset destination of the target passenger is the subway entrance, and if the initial position of the target passenger is the subway entrance, the preset destination is the subway waiting area. The target path can be obtained by A algorithm.

[0036] S103, obtaining the current state of the target passenger.

[0037] Among them, the current state is used to indicate the boarding process, including ticket purchase, passing through the security check machine, swiping the gate machine card, waiting for the subway, etc.

[0038] S104, determining the behavior decision of the target passenger according to the current state through a preset behavior tree.

[0039] Among them, the behavior decision is used to indicate the next state of the target passenger. Please refer to Figure 2 Based on the judgment of the state of the pedestrian, the next behavior of the pedestrian can be determined. For example, the next behavior is moving, or getting off, or buying a ticket, or passing through the gate, or waiting for the train, etc. The behavior tree can realize hierarchical modeling of complex passenger intentions (such as target priority adjustment and environmental feedback response) through modular and expandable decision logic.

[0040] S105, simulate the behavior of the target passenger according to the behavior decision, the target moving path and the social force model.

[0041] Wherein, the behavior process of the target passenger can be determined according to the behavior decision, the moving process of the target passenger can be determined through the social force model according to the target moving path, and the behavior of the target passenger can be simulated based on the behavior process and the moving process. After simulating the behavior of the target passenger, a corresponding simulation animation can be generated.

[0042] It can be seen that in the embodiment, firstly, the subway model scene is subjected to grid processing to obtain a grid map, then the target moving path is determined in the grid map according to the initial position and the preset destination of the target passenger, then the current state of the target passenger is acquired, the current state is used to indicate the boarding process, then the behavior decision of the target passenger is determined through the preset behavior tree according to the current state, the behavior decision is used to indicate the next state of the target passenger, and finally the behavior of the target passenger is simulated according to the behavior decision, the target moving path and the social force model. The scheme combines the mixed simulation framework of the behavior tree and the social force model, breaks through the limitation of a single model, ensures the calculation efficiency, and realizes high-fidelity simulation of the passenger “decision-action-environment” closed loop. Meanwhile, the unification of intelligent decision driving and group dynamics evolution is realized to cope with the high-density and high-dynamic subway operation scene.

[0043] In one possible embodiment, the simulation of the behavior of the target passenger according to the behavior decision and the target moving path through the social force model comprises: determining a plurality of arrival points from the grid map according to the target moving path; determining the arrival point farthest from the preset destination in the plurality of arrival points as a target arrival point; and simulating the behavior of the target passenger through the social force model according to the behavior decision and the target arrival point.

[0044] Wherein, each grid can correspond to an arrival point. Since the general social force model adopts the “shortest path” principle, that is, the driving force directly points to the target point, which makes the pedestrian not “intelligent” to bypass the obstacles, and when facing “L” type and similar obstacles, the pedestrian will be “captured” by the concave surface and cannot reach the destination. Therefore, the navigation algorithm is used to calculate the path of the divided grid map, the start point and the end point, obtain the reachable key points on the start point and the end point path, that is, a plurality of arrival points, and then simulate the moving process through the social force model according to the arrival points in turn.

[0045] It can be seen that in the embodiment, the target arrival point is determined based on the navigation algorithm, and then simulated through the social force model, which can improve the accuracy and realizability of the simulation.

[0046] In a possible embodiment, the simulation of the behavior of the target passenger according to the behavior decision, the target arrival point and the social force model comprises: determining, by the social force model, a movement process of the target passenger from the current position to the target arrival point; determining a behavior process of the target passenger according to the behavior decision; simulating the behavior of the target passenger according to the movement process and the behavior process; determining that a next arrival point of the target arrival point in the plurality of arrival points is the target arrival point, the plurality of arrival points being sorted according to distances to the preset destination, and the farther the distance to the preset destination, the higher the sorting; and repeating the above behaviors until the target passenger arrives at the preset destination.

[0047] The behavior process may, for example, be a queuing process, a ticket purchasing process, a security check process and the like of the target passenger. When the movement process is obtained, the distance of each arrival point in the target path to the preset destination can be sorted based on the determined target path, and then the arrival point farthest from the preset destination is sequentially taken as the target arrival point, and the movement process is determined based on the target arrival point by the social force model.

[0048] In a specific implementation, when the social force model determines the movement process of the user from the current position to the target arrival point, a temporary arrival point in the process from the current position to the target arrival point can be generated, that is, the dynamic avoidance and following of pedestrians and the like can be simulated according to the social force model. Since the walking direction of the passenger is determined by the target point attraction, the repulsion of surrounding pedestrians and the obstacle avoidance force and the like, the passenger may not move completely according to the movement trajectory in the target path in the movement process. For example, the current determined behavior decision of the user is to queue out of the gate machine, and the corresponding target arrival point is the gate machine in the subway. At this time, the social force model determines the movement process of the target passenger when queuing, for example, the target passenger queues to the end of the current queue, or the target passenger moves to another gate machine to queue and the like.

[0049] It can be seen that, in the embodiment, the behavior state of the subway passenger is determined by the behavior tree, and the navigation-social force queuing model is used to drive the passenger during movement, thereby improving the authenticity of the simulation result.

[0050] In a possible embodiment, a first interaction force between the target passenger and other passengers at the target arrival point is determined, a second interaction force between the target passenger and an obstacle at the target arrival point is determined, a self-driving force of the target passenger moving to the target arrival point is determined, and a movement process of the target passenger from the current position to the target arrival point is determined according to the self-driving force, the first interaction force and the second interaction force.

[0051] Wherein, the social force model is a force model for describing the interaction between the pedestrian and the surrounding pedestrians and the environment based on Newtonian dynamics, and the formula is as follows:

[0052]

[0053] Wherein, is a self-driving force, i.e., a self-driving force of the pedestrian to the destination; is the mass of the pedestrian; is the mass of the pedestrian; and are the interaction forces between the pedestrians and the interaction forces between the pedestrians and the obstacles, respectively.

[0054]

[0055] Wherein, is a desired speed vector of the pedestrian; is an actual speed of the pedestrian; is a relaxation time of the pedestrian from the actual speed to the desired speed.

[0056] It can be seen that, in the embodiment, the destination described by the self-driving force in the social force model is determined as the target arrival point, which can improve the accuracy and precision of the simulation.

[0057] In one possible embodiment, the determining a plurality of arrival points from the grid map according to the target movement path comprises: taking the centroid of each grid in the grid map as a movement node; determining a target grid corresponding to the target movement path; and determining the movement node corresponding to the target grid as the plurality of arrival points.

[0058] Wherein, after the triangulation is performed for the grid processing, the centroid of the triangulated triangular mesh can be calculated as a movement node. When the plurality of arrival points are determined, the movement nodes of all grids covered by the target movement path can be taken as the arrival points. Or the nodes on the path lines with the same movement direction and at a preset distance apart in the target movement path are determined as the arrival points. In particular, the plurality of arrival points include the nodes of the grids corresponding to the starting points and the ending points of each movement direction in the target movement path.

[0059] It can be seen that, in the embodiment, the arrival points are determined based on the centroid, which can reduce the calculation amount and improve the accuracy and stability.

[0060] In one possible embodiment, the determining the movement node corresponding to the target grid as the plurality of arrival points comprises: determining whether the target grid is an edge grid of the grid map; and if the target grid is the edge grid, determining a point at a preset distance along the normal direction of the movement node corresponding to the edge grid as the arrival point corresponding to the edge grid.

[0061] wherein, for the arrival point at the edge of the map grid, the corresponding arrival point is determined as the extended point by extending the normal direction of the point by a preset distance.

[0062] It can be seen that, in the embodiment, the arrival point of the edge is moved, which can prevent the character from being out of the model, stuck in a corner, and the like, and improve the authenticity of the simulation.

[0063] The application will be described below. Figure 3 The application will be described below.

[0064] First, the first element in the current path point list is determined as the target point, that is, the arrival point farthest from the preset destination in the plurality of arrival points corresponding to the target moving path is determined as the target point. Then it is determined that the target passenger arrives at the target point, if not, it is determined that the user's behavior decision is to move to the target point, and the target passenger moves. If the target point is reached, it is determined whether queuing is needed, if not, the service is used, and the corresponding animation is played, that is, the animation content at this time is the user's behavior process. For example, the process of the user swiping the card to exit the gate machine. At the same time after the animation is played, the next element is set as the target point, and the above steps are executed. If queuing is needed, it is determined at this time whether there is a same type service point near the target point, for example, whether there is another gate machine near the target point. If there is a same type service point, it is determined whether the queue of the other service point is shorter, if yes, the same type service point is set as a temporary target point, and then moves to the temporary target point. If not, or there is no same type service point near the target point, the temporary target point is set as the tail of the service point queue. Then it is determined whether the temporary target point reaches the head of the queue, if yes, the service range of the service point is moved to, and the corresponding animation is played. If not, the temporary target point is set as the position behind the front one in the queue.

[0065] The application makes decisions on the behavior state of the subway passenger through the behavior tree, drives the passenger to move using the navigation-social force queuing model, and integrates the social force model into the navigation and queuing algorithm, so that the pedestrian behavior is more consistent with the real simulation situation. Through the dynamic coupling of the behavior tree and the social force model, the unity of intelligent decision driving and group mechanics evolution is realized in the subway passenger simulation, which provides a new technical path for coping with high-density and high-dynamic subway operation scenarios.

[0066] A simulation device for subway passenger behavior provided by the application will be described below. The simulation device for subway passenger behavior described below corresponds to the simulation method for subway passenger behavior described above.

[0067] Please refer to Figure 4The simulation device 400 for subway passenger behavior includes: a processing unit 401 configured to grid a subway model scene to obtain a grid map; a first determination unit 402 configured to determine a target moving path in the grid map according to an initial position and a preset destination of a target passenger; an acquisition unit 403 configured to acquire a current state of the target passenger, the current state being used to indicate a boarding process; a second determination unit 404 configured to determine a behavior decision of the target passenger by a preset behavior tree according to the current state, the behavior decision being used to indicate a next state of the target passenger; and a simulation unit 405 configured to simulate behavior of the target passenger according to the behavior decision, the target moving path, and a social force model.

[0068] In one possible implementation, in the simulation of the behavior of the target passenger according to the behavior decision, the target moving path, and the social force model, the simulation unit 405 is specifically configured to: determine a plurality of arrival points from the grid map according to the target moving path; determine a target arrival point that is farthest from the preset destination among the plurality of arrival points; and simulate the behavior of the target passenger according to the behavior decision, the target arrival point, and the social force model.

[0069] In one possible implementation, in the simulation of the behavior of the target passenger according to the behavior decision, the target arrival point, and the social force model, the simulation unit 405 is specifically configured to: determine a moving process of the target passenger from a current position to the target arrival point by the social force model; determine a behavior process of the target passenger according to the behavior decision; simulate the behavior of the target passenger according to the moving process and the behavior process; determine a next arrival point of the target arrival point among the plurality of arrival points as the target arrival point, the plurality of arrival points being sorted according to distances from the preset destination, and the farther from the preset destination, the higher in the sorting; and repeat the above behavior until the target passenger arrives at the preset destination.

[0070] In one possible implementation, in the determination of the moving process of the target passenger from the current position to the target arrival point by the social force model, the simulation unit 405 is specifically configured to: determine a first interaction force between the target passenger and other passengers at the target arrival point; determine a second interaction force between the target passenger and an obstacle at the target arrival point; determine a self-driving force of the target passenger moving to the target arrival point; and determine the moving process of the target passenger from the current position to the target arrival point according to the self-driving force, the first interaction force, and the second interaction force.

[0071] In a possible implementation, in the determining the plurality of arrival points from the target movement path according to the grid map, the simulation unit 405 is specifically configured to: take the centroid of each grid in the grid map as a movement node; determine a target grid corresponding to the target movement path; and determine the movement node corresponding to the target grid as the plurality of arrival points.

[0072] In a possible implementation, in the determining the movement node corresponding to the target grid as the plurality of arrival points, the simulation unit 405 is specifically configured to: determine whether the target grid is an edge grid of the grid map; and if the target grid is the edge grid, determine a point at a preset distance along the normal direction of the movement node corresponding to the edge grid as an arrival point corresponding to the edge grid.

[0073] Referring to Figure 5 , Figure 5 is a structural schematic diagram of an electronic device provided in the present application. As shown in Figure 5 , the electronic device can include a processor 510, a communications interface 520, a memory 530, and a communications bus 540, wherein the processor 510, the communications interface 520, and the memory 530 complete mutual communication through the communications bus 540. The processor 510 can invoke a logical instruction in the memory 530 to execute a simulation method for subway passenger behavior, the method including: performing grid processing on a subway model scene to obtain a grid map; determining a target movement path in the grid map according to an initial position and a preset destination of a target passenger; obtaining a current state of the target passenger, the current state being used to indicate a boarding process; determining a behavior decision of the target passenger through a preset behavior tree according to the current state, the behavior decision being used to indicate a next state of the target passenger; and simulating a behavior of the target passenger according to the behavior decision, the target movement path, and a social force model.

[0074] In addition, the logic instructions in the memory 530 described above can be implemented in the form of software functional units and sold or used as independent products, and can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, and includes several instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0075] In another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the simulation method for subway passenger behavior provided by the above method, the method comprising: performing grid processing on a subway model scene to obtain a grid map; determining a target moving path in the grid map according to an initial position and a preset destination of a target passenger; obtaining a current state of the target passenger, the current state being used to indicate a boarding process; determining a behavior decision of the target passenger according to the current state through a preset behavior tree, the behavior decision being used to indicate a next state of the target passenger; and simulating the behavior of the target passenger according to the behavior decision, the target moving path and a social force model.

[0076] In another aspect, the present application also provides a non-transitory computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the simulation method for subway passenger behavior provided by the above method, the method comprising: performing grid processing on a subway model scene to obtain a grid map; determining a target moving path in the grid map according to an initial position and a preset destination of a target passenger; obtaining a current state of the target passenger, the current state being used to indicate a boarding process; determining a behavior decision of the target passenger according to the current state through a preset behavior tree, the behavior decision being used to indicate a next state of the target passenger; and simulating the behavior of the target passenger according to the behavior decision, the target moving path and a social force model.

[0077] The device embodiments described above are merely illustrative, wherein the units described as separate components can or can not be physically separate, and the components displayed as units can or can not be physical units, i.e., can be located in one place, or can be distributed to multiple network units. Part or all of the modules can be selected to achieve the purposes of the embodiments according to actual needs. Those skilled in the art can understand and implement without creative labor.

[0078] Through the description of the above embodiments, those skilled in the art can clearly understand that the embodiments can be realized by means of software and the necessary general hardware platform, and of course can also be realized by hardware. Based on such understanding, the above technical solutions can be embodied in the form of a software product, which can be stored in a computer readable storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments.

[0079] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement to part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A simulation method for subway passenger behavior, characterized by, The method comprises the following steps: grid processing is performed on a subway model scene to obtain a grid map; a target moving path is determined in the grid map according to an initial position and a preset destination of a target passenger; a current state of the target passenger is obtained, the current state being used to indicate a boarding process; a behavior decision of the target passenger is determined through a preset behavior tree according to the current state, the behavior decision being used to indicate a next state of the target passenger; a plurality of arrival points are determined from the grid map according to the target moving path, and a target arrival point is determined as an arrival point farthest from the preset destination among the plurality of arrival points; a moving process of the target passenger from a current position to the target arrival point is determined through a social force model, the moving process comprising a target moving path corresponding to the current position to the target arrival point, and a temporary arrival point indication generated according to simulated pedestrian dynamic avoidance and following phenomena; a behavior process of the target passenger is determined according to the behavior decision; behavior of the target passenger is simulated according to the moving process and the behavior process; the target arrival point is determined as a next arrival point of the target arrival point among the plurality of arrival points, the plurality of arrival points being sorted according to distances from the preset destination, and the farther from the preset destination, the higher in the sorting; and the above behavior is repeated until the target passenger arrives at the preset destination.

2. The method of claim 1, wherein, The moving process of the target passenger from the current position to the target arrival point through the social force model comprises: a first interaction force between the target passenger and other passengers at the target arrival point is determined; a second interaction force between the target passenger and an obstacle at the target arrival point is determined; a self-driving force of the target passenger moving to the target arrival point is determined; the moving process of the target passenger from the current position to the target arrival point is determined according to the self-driving force, the first interaction force and the second interaction force.

3. The method of claim 1, wherein, The plurality of arrival points determined from the grid map according to the target moving path comprises: a centroid of each grid in the grid map is determined as a moving node; a target grid corresponding to the target moving path is determined; a moving node corresponding to the target grid is determined as the plurality of arrival points.

4. The method of claim 3, wherein, The moving node corresponding to the target grid is determined as the plurality of arrival points, comprising: it is determined whether the target grid is an edge grid of the grid map; if the target grid is the edge grid, a point at a preset distance along a normal direction of the moving node corresponding to the edge grid is determined as an arrival point corresponding to the edge grid.

5. A simulation device for subway passenger behavior, characterized by, The device comprises: a processing unit configured to perform grid processing on a subway model scene to obtain a grid map; a first determining unit configured to determine a target moving path in the grid map according to an initial position and a preset destination of a target passenger; an obtaining unit configured to obtain a current state of the target passenger, the current state being used to indicate a boarding process; a second determining unit configured to determine a behavior decision of the target passenger through a preset behavior tree according to the current state, the behavior decision being used to indicate a next state of the target passenger; The simulation unit is configured to determine a plurality of arrival points from the grid map according to the target moving path; and determine a target arrival point as the arrival point farthest from the preset destination among the plurality of arrival points. The simulation unit is configured to determine a moving process of the target passenger from a current position to the target arrival point by a social force model, the moving process corresponding to a target moving path from the current position to the target arrival point, and temporary arrival point indications generated according to simulated pedestrian dynamic avoidance and following phenomena. The behavior decision is configured to determine a behavior process of the target passenger. The simulation unit is configured to simulate the behavior of the target passenger according to the moving process and the behavior process. The simulation unit is configured to determine a next arrival point of the target arrival point as the target arrival point among the plurality of arrival points, and sort the plurality of arrival points according to distances from the preset destination, and the farther the distance from the preset destination, the higher the sorting; and repeat the above behavior until the target passenger arrives at the preset destination.

6. An electronic device comprising a memory, a processor, and a computer program stored on the memory and running on the processor, characterized in that, The computer program is configured to enable the processor to implement the simulation method for the subway passenger behavior according to any one of claims 1 to 4 when the computer program is executed by the processor.

7. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is configured to enable the processor to implement the simulation method for the subway passenger behavior according to any one of claims 1 to 4 when the computer program is executed by the processor.

8. A computer program product comprising a computer program, characterized in that, The computer program is configured to enable the processor to implement the simulation method for the subway passenger behavior according to any one of claims 1 to 4 when the computer program is executed by the processor.

Images