A pedestrian movement simulation system in a building

Abstract

The present invention discloses a pedestrian movement line simulation system in a building in the field of human flow simulation, including a building import module, a building equipment editing module and a pedestrian simulation module. The building import module is used to import building drawings, the building equipment editing module is used to edit and set equipment in the building, and the pedestrian simulation module is used to add pedestrian models and set behavior logic. The behavior logic includes process-based behavior and random behavior. The process-based behavior is used to simulate various behaviors of pedestrians in the building, such as receiving services, queuing, waiting, strolling, speed limits, etc., including node selection, path finding, facility interaction and leaving facility logic; pedestrian random behavior includes passive facility interaction logic, herd logic, idle time logic and companion logic. The technical solution of the present invention can improve the restoration degree of the initial human flow dispersion state by setting the pedestrian behavior logic.

Description

Technical Field

[0001] The invention belongs to the field of human flow simulation, in particular to a pedestrian movement line simulation system in a building. Background Art

[0002] In recent years, pedestrian simulation has become an indispensable tool to ensure that the layout, facility distribution / quantity, and evacuation safety in the design and operation of public buildings are in line with the characteristics of pedestrian behavior, prevent and resolve risks, optimize pedestrian flow, and ensure evacuation safety.

[0003] In order to solve the above problems, patent publication number CN108170995B discloses a pedestrian motion simulation method and system, the simulation method comprising: obtaining a social force model; the social force model is a circular pedestrian model; improving the social force model to establish a three-circle model; the three-circle model is composed of two circles with a first radius as a rotation radius and a circle with a second radius larger than the first radius as a rotation radius; the sum of the first radius and the second radius is the radius of the social force model; wherein, the central circle is a circle with the second radius as the rotation radius, and a circle with the first radius as the rotation radius is provided on both sides of the central circle, and the centers of the three circles are on the same horizontal plane; the overall shape of the three-circle model is an ellipse, and the major axis of the ellipse is the shoulder width of the pedestrian; the motion state of the pedestrian is simulated according to the three-circle model.

[0004] The above-mentioned pedestrian motion simulation method and system simulate the pedestrian model rotating and walking sideways in the same mode to restore the pedestrian motion state at the crowded exit. However, when simulating evacuation, there is an initial crowd dispersion state. The largest and most complex crowd change time point is between the initial crowd dispersion state and the transformation into the evacuation crowd queue. The initial crowd dispersion state will be affected by factors such as the area division, equipment layout and pedestrian interaction events in the building. The low degree of restoration of the initial crowd dispersion state will cause the simulation process to be distorted during the transformation of the crowd into the evacuation queue. Summary of the invention

[0005] In order to solve the problem of low restoration degree of the initial crowd dispersion state in the prior art, the purpose of the present invention is to provide a pedestrian movement line simulation system in a building, which improves the restoration degree of the initial crowd dispersion state by setting pedestrian behavior logic.

[0006] In order to achieve the above-mentioned object, the technical solution of the present invention is as follows: a pedestrian movement line simulation system in a building, a building import editing module: the building import editing module is used to import building drawings, and the types of building drawings include dxf and dwg format files;

[0007] Building equipment editing module: used to create equipment for pedestrian model interaction in the imported building drawings. The equipment has three interaction modes with the pedestrian model: point, line, and surface. The equipment has an attraction value for increasing the probability of pedestrian model approaching and a retention value for simulating operation time. The attraction value becomes invalid after the evacuation behavior is triggered;

[0008] Pedestrian simulation module: used to add pedestrian models to imported architectural drawings and set behavior logic. The pedestrian model is a two-dimensional image.

[0009] Behavioral logic includes process-based behavior and random behavior;

[0010] Process-based behaviors include selection logic, path-finding logic, and device interaction logic;

[0011] The selection logic is that the pedestrian model selects the next behavior according to a preset selection procedure, and the selection method of the preset selection procedure is one of specified, probabilistic or conditional selection;

[0012] Pathfinding logic generates a route to the next behavior based on the selection logic;

[0013] Pedestrian random behaviors include passive facility interaction logic, herd logic, leisure time logic and companion logic;

[0014] The device interaction logic is that when the pedestrian model interacts with the device, it stays at the point position or at a random position within a circle with a preset radius value centered on the point; when the pedestrian model interacts with a line object, the path of the pedestrian model is replaced by a path of a multi-segment line; when the pedestrian interacts with a surface object, the pedestrian stays in the polygonal area formed by the surface or triggers the idle time logic; the stay time value is one of the interval random values ​​or distributed random values ​​based on the temporary retention value;

[0015] The passive device interaction logic is that pedestrians are affected by preset probabilities and interact with device points, lines, surface objects and their combinations;

[0016] The herd logic presets a visual range value for the pedestrian model, and increases the probability of the pedestrian model performing the same behavior according to the number of other pedestrian model behaviors within the visual range value of the pedestrian model;

[0017] The idle time logic is that the pedestrian model waits or wanders around when there is no behavior trigger; when pedestrians are waiting, they avoid other moving pedestrians;

[0018] The companion logic is that there are multiple pedestrian models in the architectural drawings to form a companion group. The companion group is set with a relative activity range value, and the distance between the pedestrian models in the companion group is within the relative activity range value.

[0019] The following beneficial effects are achieved by adopting the above scheme: users can import architectural drawings to simulate building structures, add pedestrian models to architectural drawings to simulate real environments, and the pedestrian models will imitate the activities of pedestrians in the building according to their behavioral logic.

[0020] Behavior logic is divided into process-based behavior and random behavior. Users can set process-based behavior, and then change the behavior execution steps of the pedestrian model in a macro sense, which is convenient for users to formulate special simulation scenarios or customize pedestrian models with unique behaviors. Random behavior is the behavioral basis of the pedestrian model, and pedestrians will perform various behaviors and interactions based on random behavior.

[0021] The generation and disappearance logic can simulate the flow of people in the architectural drawings, and at the same time update the character models in the architectural drawings or reduce the computing resource expenditure used by the character models.

[0022] The device interaction logic is used to simulate the interaction between pedestrians and devices in the building, such as ticket machines, receiving machines, chairs, and notice boards. Because the devices have certain functions, they will attract pedestrians to use them to fit the pedestrian density distribution in actual conditions. The devices have three interaction modes with pedestrian models: point, line, and surface, so that different devices can improve the realism according to different interaction modes, so that the simulation can be further restored to reality.

[0023] The selection logic is used to set the selection of the behavior node so that the pedestrian model can perform the selection of the device or movement direction according to the preset selection.

[0024] The interaction logic of passive facilities echoes the interaction logic of equipment, simulating the activities of pedestrians in various equipment.

[0025] The herd logic is a simulation of psychological logic. During the evacuation process, a large number of people will spontaneously follow due to the herd effect, rather than independently analyzing and judging the route. At the same time, more people will gather at attractive equipment or events due to the herd effect. By setting the field of view range value, the range of the herd effect can be simulated, making the distribution and evacuation process of pedestrians more in line with group psychology.

[0026] The idle time logic supplements the logic of pedestrians' idle state and enriches pedestrian behavior. At the same time, the pedestrian model under the idle time logic has no interactive target, so it will avoid pedestrian models under other behavior logics. The companion logic simulates companion activities, and there are interpersonal relationships between pedestrians, which makes them concentrate in a certain area without external influences. By setting up companion groups, the pedestrian density distribution and evacuation movement process of pedestrians walking together are simulated, which further fits the pedestrian density distribution in actual conditions.

[0027] Under the behavioral logic, the pedestrian model will simulate the normal flow pattern of people in the building in the architectural drawings, so that when evacuating in simulation, the initial state of the flow of people can better fit the actual situation and the simulation results are more accurate.

[0028] Compared with the existing technology, the behavior logic is divided into process-based behavior and random behavior. The process-based behavior can be used to make macro adjustments to the behavior execution of the pedestrian model, which is convenient for users to formulate special scenarios or special pedestrian models. The normal crowd flow simulation in the building is constructed through the pedestrian behavior logic. It can not only test the crowd carrying capacity in the building, but also build a more restored initial evacuation state. The largest and most complex crowd change time point is when the initial crowd dispersion state is transformed into the evacuation crowd queue. The more restored initial evacuation state can reflect a more realistic emergency action situation in the process, and through the herd logic, the technical solution can simulate the driven evacuation scenario that occurs in local emergencies.

[0029] Furthermore, the pedestrian model is provided with random character parameters, including gender, interest, age, weight and height. The probability of the device's pedestrian model approaching is calculated by gender, interest, age and attractiveness value. The two-dimensional image size and moving speed of the pedestrian model vary according to weight and height.

[0030] Beneficial effects: Different groups of people are simulated by random character parameters, and the behavior logic of pedestrians is changed according to the character parameters. Different devices have different effects on different groups of people. For example, children are more likely to be attracted to arcades or toddler areas. Therefore, when calculating the probability of pedestrian models approaching, gender, interests and age are added for calculation. Weight and height have a greater impact on mobility, so the size and movement speed of the two-dimensional image of the pedestrian model are changed by weight and height to make the simulated scene more in line with real life.

[0031] Furthermore, the pedestrian model movement is simulated using a linear acceleration algorithm and a steering acceleration algorithm.

[0032] Beneficial effect: There are acceleration and deceleration processes when the human body moves, so the movement simulation through linear acceleration algorithm and steering acceleration algorithm is more realistic.

[0033] Furthermore, the building import module is also used to import or add obstacles and edit building patterns in architectural drawings in real time.

[0034] Beneficial effects: Users can simulate building planning by adding obstacles or building patterns in real time, and the building planning will produce a plan that is more suitable for the flow of pedestrian models.

[0035] Furthermore, the behavior logic also includes regional behavior logic, and the behavior logic includes dividing the action area in the architectural drawing, and the action area is provided with an environmental impact value for simulating the impact of the environment on the movement of the pedestrian model.

[0036] Beneficial effects: Different areas within a building have different impacts on pedestrians, such as dark areas, slippery areas, and steep slopes, so by dividing the action area within the building drawings, set environmental impact values ​​to simulate the movement of pedestrians in this area.

[0037] Furthermore, the environmental impact value includes a light brightness value, and the field of view value of the pedestrian model is affected by the light brightness value.

[0038] Beneficial effects: In dark areas, pedestrians not only move slower, but their vision is also affected, making it more difficult for them to follow distant targets and reducing the effect of herd logic.

[0039] Furthermore, the behavior logic also includes crowding logic, which detects the number of pedestrian models within the surrounding area of ​​the pedestrian model and makes corrections based on the number of pedestrian models combined with a preset pedestrian density and speed relationship function.

[0040] Beneficial effect: It is difficult for pedestrians to maintain normal movement in crowded conditions. Therefore, by detecting the number of pedestrian models within the surrounding area of ​​the pedestrian model, it is determined whether it is in a crowded environment and its speed is corrected.

[0041] Furthermore, the behavior logic is implemented based on behavior trees and finite state machines. The behavior tree is a unidirectional multi-branch tree structure data. The nodes in the behavior tree are one of generating pedestrian models, interacting with pedestrian models and equipment, or pedestrian disappearance. Some nodes are associated with coordinates in architectural drawings.

[0042] Beneficial effects: The behavior logic is executed through the behavior tree. Different behaviors are triggered by entering different branch points. The stacked nodes are selected according to the tree structure, so that the pedestrian model can produce different behaviors on the same tree, and it is convenient to set a fixed behavior mode for the pedestrian model.

[0043] Furthermore, the pedestrian simulation module is provided with a UI interface for editing the pedestrian model. The UI interface is provided with a behavior logic control tree. The behavior logic control tree is used to edit the process behavior nodes of the pedestrian model. The logic control tree adopts a flow chart connection-type behavior node editor as the input mode.

[0044] Beneficial effects: Users can modify the logic of the pedestrian model. Through a visual interface, users can easily shape a pedestrian model with fixed behavior logic by editing behavior nodes. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 Schematic diagram of an embodiment of the present invention.

[0046] Figure 2 Schematic diagram of the device attracting pedestrian models to approach.

[0047] Figure 3 Schematic diagram of the relationship between pedestrian density and speed.

[0048] Figure 4 This is a flow-based behavior tree logic diagram. DETAILED DESCRIPTION

[0049] The following is further described in detail through specific implementation methods:

[0050] Embodiment 1

[0051] The embodiment is basically as shown in the attached Figure 1 To Attachment Figure 4 As shown:

[0052] In order to achieve the above-mentioned object, the technical solution of the present invention is as follows: a pedestrian movement line simulation system in a building, a building import editing module: the building import editing module is used to import building drawings, and the types of building drawings include dxf and dwg format files;

[0053] Building equipment editing module: used to create equipment for pedestrian model interaction in the imported building drawings. The equipment has three interaction modes with the pedestrian model: point, line, and surface. The equipment has an attraction value for increasing the probability of pedestrian model approaching and a retention value for simulating operation time. The attraction value becomes invalid after the evacuation behavior is triggered;

[0054] Pedestrian simulation module: used to add pedestrian models to imported architectural drawings and set behavior logic. The pedestrian model is a two-dimensional image.

[0055] Behavioral logic includes process-based behavior and random behavior;

[0056] Process-based behaviors include selection logic, path-finding logic, and device interaction logic;

[0057] The selection logic is that the pedestrian model selects the next behavior according to a preset selection procedure, and the selection method of the preset selection procedure is one of specified, probabilistic or conditional selection;

[0058] Pathfinding logic generates a route to the next behavior based on the selection logic;

[0059] Pedestrian random behaviors include passive facility interaction logic, herd logic, leisure time logic and companion logic;

[0060] The device interaction logic is that when the pedestrian model interacts with the device, it stays at the point position or at a random position within a circle with a preset radius value centered on the point; when the pedestrian model interacts with a line object, the path of the pedestrian model is replaced by a path of a multi-segment line; when the pedestrian interacts with a surface object, the pedestrian stays in the polygonal area formed by the surface or triggers the idle time logic; the stay time value is one of the interval random values ​​or distributed random values ​​based on the temporary retention value;

[0061] The passive device interaction logic is that pedestrians are affected by preset probabilities and interact with device points, lines, surface objects and their combinations;

[0062] The herd logic presets a visual range value for the pedestrian model, and increases the probability of the pedestrian model performing the same behavior according to the number of other pedestrian model behaviors within the visual range value of the pedestrian model;

[0063] The idle time logic is that the pedestrian model waits or wanders around when there is no behavior trigger; when pedestrians are waiting, they avoid other moving pedestrians;

[0064] The companion logic is that there are multiple pedestrian models in the architectural drawings to form a companion group. The companion group is set with a relative activity range value, and the distance between the pedestrian models in the companion group is within the relative activity range value.

[0065] The specific implementation process is as follows: users can import architectural drawings to simulate building structures, and add pedestrian models to architectural drawings to simulate real environments. The pedestrian models will imitate the activities of pedestrians in the building according to their behavioral logic.

[0066] Behavior logic is divided into process-based behavior and random behavior. Users can set process-based behavior, and then change the behavior execution steps of the pedestrian model in a macro sense, which is convenient for users to formulate special simulation scenarios or customize pedestrian models with unique behaviors. Random behavior is the behavioral basis of the pedestrian model, and pedestrians will perform various behaviors and interactions based on random behavior.

[0067] The generation and disappearance logic can simulate the flow of people in the architectural drawings, and at the same time update the character models in the architectural drawings or reduce the computing resource expenditure used by the character models.

[0068] The device interaction logic is used to simulate the interaction between pedestrians and devices in the building, such as ticket machines, receiving machines, chairs, and notice boards. Because the devices have certain functions, they will attract pedestrians to use them to fit the pedestrian density distribution in actual conditions. The devices have three interaction modes with pedestrian models: point, line, and surface, so that different devices can improve the realism according to different interaction modes, so that the simulation can be further restored to reality.

[0069] The selection logic is used to set the selection of the behavior node so that the pedestrian model can perform the selection of the device or movement direction according to the preset selection.

[0070] The interaction logic of passive facilities echoes the interaction logic of equipment, simulating the activities of pedestrians in various equipment.

[0071] The herd logic is a simulation of psychological logic. During the evacuation process, a large number of people will spontaneously follow due to the herd effect, rather than independently analyzing and judging the route. At the same time, more people will gather at attractive equipment or events due to the herd effect. By setting the field of view range value, the range of the herd effect can be simulated, making the distribution and evacuation process of pedestrians more in line with group psychology.

[0072] The idle time logic supplements the logic of pedestrians' idle state and enriches pedestrian behavior. At the same time, the pedestrian model under the idle time logic has no interactive target, so it will avoid pedestrian models under other behavior logics. The companion logic simulates companion activities, and there are interpersonal relationships between pedestrians, which makes them concentrate in a certain area without external influences. By setting up companion groups, the pedestrian density distribution and evacuation movement process of pedestrians walking together are simulated, which further fits the pedestrian density distribution in actual conditions.

[0073] Under the behavioral logic, the pedestrian model will simulate the normal flow pattern of people in the building in the architectural drawings, so that when evacuating in simulation, the initial state of the flow of people can better fit the actual situation and the simulation results are more accurate.

[0074] The invention divides the behavior logic into process-based behavior and random behavior. Through the process-based behavior, it can make macro adjustments to the behavior execution of the pedestrian model, which is convenient for users to formulate special scenarios or special pedestrian models. Through the pedestrian behavior logic, it constructs a normal crowd flow simulation in the building, which can not only test the crowd carrying capacity in the building, but also build a more restored initial evacuation state. The largest and most complex crowd change time point is when the initial crowd dispersion state is transformed into the evacuation crowd queue. The more restored initial evacuation state can reflect a more realistic emergency action situation in the process, and through the herd logic, the technical solution can simulate the driven evacuation scenario that occurs in local emergencies.

[0075] Embodiment 2

[0076] The difference from the above embodiment is that the pedestrian model is provided with random character parameters, which include gender, interest, age, weight and height. The probability of the pedestrian model of the device approaching is calculated by gender, interest, age and attractiveness value. The two-dimensional image size and moving speed of the pedestrian model change according to weight and height.

[0077] The specific implementation process is as follows: simulate different groups of people through random character parameters, and change the behavior logic of pedestrians according to the character parameters. Different devices have different attraction effects on different groups of people. For example, children are more likely to be attracted to arcades or toddler areas. Therefore, when calculating the probability of pedestrian models approaching, gender, interests and age are added for calculation. Weight and height have a greater impact on mobility, so the size and movement speed of the two-dimensional image of the pedestrian model are changed by weight and height to make the simulated scene more in line with real life.

[0078] Embodiment 3

[0079] The difference from the above embodiment is that the pedestrian model movement adopts a linear acceleration algorithm and a steering acceleration algorithm to perform movement simulation.

[0080] The specific implementation process is as follows: when the human body moves, there are acceleration and deceleration processes, so the movement simulation through linear acceleration algorithm and steering acceleration algorithm is more realistic.

[0081] Embodiment 4

[0082] The difference from the above embodiment is that the building import module is also used to import or add obstacles and edit building patterns in real time in building drawings.

[0083] The specific implementation process is as follows: users can simulate building planning by adding obstacles or building patterns in real time, and the building planning will produce a plan that is more suitable for the flow of pedestrian models.

[0084] Embodiment 5

[0085] The difference from the above embodiment is that the behavior logic also includes regional behavior logic, the behavior logic includes dividing the action areas in the architectural drawings, and the action areas are provided with environmental impact values ​​for simulating the impact of the environment on the movement of the pedestrian model.

[0086] The specific implementation process is as follows: Different areas within the building have different impacts on pedestrians, such as dark areas, slippery areas and steep slopes. Therefore, by dividing the action area within the building drawings, the environmental impact value is set to simulate the movement of pedestrians in the area.

[0087] Embodiment 6

[0088] The difference from the above embodiment is that the environmental impact value includes the light brightness value, and the visual field value of the pedestrian model is affected by the light brightness value.

[0089] The specific implementation process is as follows: In dark areas, pedestrians not only have a reduced movement speed, but their vision will also be affected, making it more difficult for them to follow distant targets and reducing the effect of herd logic.

[0090] Embodiment 7

[0091] The difference from the above embodiment is that the behavior logic also includes crowding logic, which detects the number of pedestrian models within the surrounding range of the pedestrian model, and makes corrections based on the number of pedestrian models combined with a preset pedestrian density and speed relationship function. The pedestrian density and speed relationship function is shown in the attached figure. Figure 3 shown.

[0092] The specific implementation process is as follows: It is difficult for pedestrians to maintain normal movement in a crowded environment. Therefore, by detecting the number of pedestrian models around the pedestrian model, it is determined whether it is in a crowded environment and its speed is corrected.

[0093] Embodiment 8

[0094] The difference from the above embodiment is that the behavior logic is implemented based on the behavior tree and the finite state machine; the behavior tree is a unidirectional multi-branch tree structure data, and the nodes in the behavior tree are one of generating a pedestrian model, interacting with the pedestrian model and the device, or disappearing the pedestrian, and some nodes are associated with the coordinates in the architectural drawings.

[0095] The specific implementation process is as follows: the behavior logic is executed through the behavior tree, different behaviors are triggered by entering different branch points, and the stacked nodes are selected according to the tree structure, so that the pedestrian model can produce different behaviors on the same tree, and it is convenient to set a fixed behavior mode for the pedestrian model.

[0096] Embodiment 9

[0097] The difference from the above embodiment is that the pedestrian simulation module is provided with a UI interface for editing the pedestrian model, and a behavior logic control tree is provided in the UI interface. The behavior logic control tree is used to edit the process-based behavior nodes of the pedestrian model, and the logic control tree adopts a flow chart-connected behavior node editor as the input mode.

[0098] The specific implementation process is as follows: users can modify the logic of the pedestrian model, and through a visual interface, it is convenient for users to shape a pedestrian model with fixed behavior logic by editing behavior nodes.

[0099] The above is only an embodiment of the present invention. The common sense such as the known specific structure and characteristics in the scheme is not described in detail here. The ordinary technicians in the relevant field know all the common technical knowledge in the technical field of the invention before the application date or priority date, can obtain all the existing technologies in the field, and have the ability to apply the conventional experimental means before that date. The ordinary technicians in the relevant field can improve and implement this scheme in combination with their own abilities under the enlightenment given by this application. Some typical known structures or known methods should not become obstacles for ordinary technicians in the relevant field to implement this application. It should be pointed out that for those skilled in the art, without departing from the structure of the present invention, several deformations and improvements can be made, which should also be regarded as the protection scope of the present invention, which will not affect the effect of the implementation of the present invention and the practicality of the patent. The protection scope required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A pedestrian movement simulation system in a building, characterized by: Architectural import and editing module: used to import architectural drawings, including dxf and dwg format files; Building equipment editing module: used to create equipment for pedestrian model interaction in the imported building drawings. The equipment has three interaction modes with the pedestrian model: point, line, and surface. The equipment has an attraction value for increasing the probability of pedestrian model approaching and a retention value for simulating operation time. The attraction value becomes invalid after the evacuation behavior is triggered; Pedestrian simulation module: used to add pedestrian models to imported architectural drawings and set behavior logic. The pedestrian model is a two-dimensional image. Behavioral logic includes process-based behavior and random behavior; Process-based behaviors include selection logic, path-finding logic, and device interaction logic; The selection logic is that the pedestrian model selects the next behavior according to a preset selection procedure, and the selection method of the preset selection procedure is one of specified, probabilistic or conditional selection; Pathfinding logic generates a route to the next behavior based on the selection logic; Pedestrian random behaviors include passive facility interaction logic, herd logic, leisure time logic and companion logic; The device interaction logic is that when the pedestrian model interacts with the device, it stays at the point position or at a random position within a circle with a preset radius value centered on the point; when the pedestrian model interacts with a line object, the path of the pedestrian model is replaced by the path of a polyline; When pedestrians interact with surface objects, they stay in the polygonal area formed by the surface or trigger the idle time logic; the stay time value is one of the interval random values ​​or distributed random values ​​based on the temporary value; The passive device interaction logic is that pedestrians are affected by preset probabilities and interact with device points, lines, surface objects and their combinations; The herd logic presets a visual range value for the pedestrian model, and increases the probability of the pedestrian model performing the same behavior according to the number of other pedestrian model behaviors within the visual range value of the pedestrian model; The idle time logic is that the pedestrian model waits or wanders around when there is no behavior trigger; when pedestrians are waiting, they avoid other moving pedestrians; The companion logic is that there are multiple pedestrian models in the architectural drawings to form a companion group. The companion group is set with a relative activity range value, and the distance between the pedestrian models in the companion group is within the relative activity range value.

2. The pedestrian movement simulation system in a building according to claim 1, characterized in that: The pedestrian model is equipped with random character parameters, including gender, interest, age, weight and height. The device's pedestrian model approach probability is calculated based on gender, interest, age and attractiveness value. The two-dimensional image size and moving speed of the pedestrian model vary according to weight and height.

3. The pedestrian movement simulation system in a building according to claim 2, characterized in that: The pedestrian model movement is simulated using linear acceleration algorithm and steering acceleration algorithm.

4. The pedestrian movement simulation system in a building according to claim 3, characterized in that: The architectural import module is also used to import or add obstacles and edit architectural patterns in architectural drawings in real time.

5. The pedestrian movement simulation system in a building according to claim 4, characterized in that: The behavior logic also includes regional behavior logic, which includes dividing the action areas within the architectural drawings, and the action areas are provided with environmental impact values ​​for simulating the impact of the environment on the movement of the pedestrian model.

6. The pedestrian movement simulation system in a building according to claim 5, characterized in that: The environmental impact value includes the light brightness value, and the field of view value of the pedestrian model is affected by the light brightness value.

7. The pedestrian movement simulation system in a building according to claim 6, characterized in that: The behavior logic also includes crowding logic, which detects the number of pedestrian models within the surrounding area of ​​the pedestrian model and makes corrections based on the number of pedestrian models combined with a preset pedestrian density and speed relationship function.

8. The pedestrian movement simulation system in a building according to claim 7, characterized in that: The behavior logic is implemented based on behavior trees and finite state machines. The behavior tree is a unidirectional multi-branch tree structure data. The nodes in the behavior tree include generating pedestrian models, interaction between pedestrian models and equipment, and disappearance of pedestrians. Some nodes are associated with coordinates in architectural drawings.

9. The pedestrian movement simulation system in a building according to claim 7, characterized in that: The pedestrian simulation module is provided with a UI interface for editing the pedestrian model. The UI interface is provided with a behavior logic control tree. The behavior logic control tree is used to edit the process behavior nodes of the pedestrian model. The logic control tree adopts a flow chart connection-style behavior node editor as the input mode.

Images