BIM model-based building dynamic evacuation road network generation method and system

Abstract

The invention discloses a building dynamic evacuation road network generation method and system based on a BIM model, and the method comprises the steps: obtaining spatial layout data and multilayer connection information from a building BIM model, and constructing an initial road network frame; generating corrected road network data according to the initial road network framework and the traffic restriction information; according to the corrected road network data and safety specification requirements, an evacuation route meeting the standard is calculated, and a preliminary evacuation road network is generated; acquiring real-time data of a sensor in the building, judging the influence of dynamic change on the preliminary evacuation road network, and updating impassable area information; and according to the updated impassable area information, recalculating an evacuation route, adjusting the preliminary evacuation road network, and generating an optimized evacuation road network. Therefore, according to the building dynamic evacuation road network generation method based on the BIM model, the efficiency and accuracy of building emergency evacuation are improved.

Description

Technical Field

[0001] The embodiments of the present invention relate to the technical field of emergency evacuation, and in particular, to a method and system for generating a dynamic evacuation road network of a building based on a BIM model. Background Art

[0002] In the process of automatically generating the passable road network of the whole building, based on the BIM model and the three-dimensional digital twin engine, it is first necessary to accurately extract the geometric structure and spatial layout information of the building. However, there are often complex structures inside the building, such as stairs, elevators, corridors, room partitions, etc. The diversity and irregularity of these elements increase the complexity of road network generation. Especially in multi-story buildings, the connection methods between different floors (such as stairs, elevators, ramps, etc.) need to be accurately identified and modeled to ensure that the generated road network has actual passability.

[0003] Secondly, the actual usage of the building needs to be considered during the road network generation process. For example, some areas may be impassable due to equipment installation, temporary obstacles, or specific functional requirements. These dynamic factors may not be fully reflected in the BIM model, resulting in a deviation between the generated road network and the actual situation. In addition, the design of the escape routes of the building usually needs to comply with specific safety specifications, such as the shortest path, the maximum evacuation time, etc. These requirements need to be fully considered during the road network generation.

[0004] Finally, after the road network is generated, how to effectively combine it with the emergency escape routes to generate the evacuation routes for any room or location is also a technical difficulty. It is necessary to ensure that the generated evacuation routes not only comply with safety specifications but also can be dynamically adjusted according to the real-time changes inside the building (such as fire, smoke diffusion, etc.) to ensure the timeliness and effectiveness of evacuation. This process involves complex algorithm design and real-time data processing capabilities, and requires high flexibility and accuracy in technical implementation. Summary of the Invention

[0005] The embodiments of the present invention provide a method and system for generating a dynamic evacuation road network of a building based on a BIM model. By extracting the spatial layout and multi-layer connection information from the BIM model of the building, combining the passage restrictions and real-time sensor data, dynamically generating and optimizing the evacuation road network, and finally generating the final evacuation plan that meets the safety specifications, so as to improve the efficiency and accuracy of building emergency evacuation.

[0006] To achieve the above object, in a first aspect, the present invention provides a method for generating a dynamic evacuation road network of a building based on a BIM model, including: obtaining spatial layout data and multi-layer connection information from the building BIM model to construct an initial road network framework. Generating corrected road network data according to the initial road network framework and traffic restriction information. Calculating evacuation routes that meet the standards according to the corrected road network data and safety code requirements to generate a preliminary evacuation road network. Obtaining real-time data of sensors inside the building, judging the influence of dynamic changes on the preliminary evacuation road network, and updating the information of impassable areas. Recalculating evacuation routes according to the updated information of impassable areas, adjusting the preliminary evacuation road network, and generating an optimized evacuation road network. Matching the optimized evacuation road network with the building BIM model through three-dimensional digital twin technology to generate a visual three-dimensional road network map. Dynamically updating evacuation paths according to the visual three-dimensional road network map and real-time data stream to generate a final evacuation plan.

[0007] In a second aspect, the present invention provides a system for generating a dynamic evacuation road network of a building based on a BIM model, including: an initial road network framework construction module, a road network data generation module, a preliminary evacuation road network generation module, an update module, an evacuation road network generation module, a visual three-dimensional road network map generation module, and an evacuation plan generation module. The initial road network framework construction module is used to obtain spatial layout data and multi-layer connection information from the building BIM model to construct an initial road network framework. The road network data generation module is used to generate corrected road network data according to the initial road network framework and traffic restriction information. The preliminary evacuation road network generation module is used to calculate evacuation routes that meet the standards according to the corrected road network data and safety code requirements to generate a preliminary evacuation road network. The update module is used to obtain real-time data of sensors inside the building, judge the influence of dynamic changes on the preliminary evacuation road network, and update the information of impassable areas. The evacuation road network generation module is used to recalculate evacuation routes according to the updated information of impassable areas, adjust the preliminary evacuation road network, and generate an optimized evacuation road network. The visual three-dimensional road network map generation module is used to match the optimized evacuation road network with the building BIM model through three-dimensional digital twin technology to generate a visual three-dimensional road network map. And the evacuation plan generation module is used to dynamically update evacuation paths according to the visual three-dimensional road network map and real-time data stream to generate a final evacuation plan.

[0008] In a third aspect, the present invention provides an electronic device, including:

[0009] At least one processor; and

[0010] A memory communicatively connected to the at least one processor;

[0011] The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the method for generating a dynamic evacuation road network of a building based on a BIM model as described above.

[0012] In a fourth aspect, the present invention provides a computer-readable storage medium, including a computer program and instructions. When the computer program or the instructions are run on a computer, the computer executes the method for generating a dynamic evacuation road network of a building based on a BIM model as described above.

[0013] Compared with the prior art, the method and system for generating a dynamic evacuation road network of a building based on a BIM model according to the present invention have the following beneficial effects:

[0014] 1. By accurately extracting geometric structure and spatial layout information from the building BIM model and combining multi-layer connection information, the present invention can construct an initial road network framework that is more in line with the actual building structure, thereby improving the accuracy of the evacuation road network;

[0015] 2. The present invention takes into account the actual use of buildings, such as access restriction information such as equipment installation, temporary obstacles, and dynamic change factors such as fire and smoke diffusion. It can update the information of inaccessible areas in real time and recalculate the evacuation routes, so that the evacuation road network has dynamic adaptability;

[0016] 3. In the process of generating the evacuation road network, the present invention combines the evacuation requirements in the safety specifications, such as the shortest path, the maximum evacuation time, etc., to ensure that the generated evacuation route meets the safety standards and improves the evacuation efficiency and safety;

[0017] 4. Through three-dimensional digital twin technology, the present invention matches the optimized evacuation road network with the building BIM model to generate a visual three-dimensional road network map, which is convenient for users to intuitively understand the evacuation route and spatial layout and improve the decision-making efficiency of emergency evacuation. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of a method for generating a dynamic evacuation road network of a building based on a BIM model in Embodiment 1 of the present invention;

[0019] Figure 2 It is a structural schematic diagram of a building dynamic evacuation road network generation system based on a BIM model in Embodiment 2 of the present invention;

[0020] Figure 3 It is a structural schematic diagram of an electronic device in Embodiment 3 of the present invention. DETAILED DESCRIPTION

[0021] The following further elaborates on the embodiments of the present invention in conjunction with the accompanying drawings and examples. It can be understood that the specific embodiments described herein are merely for explaining the embodiments of the present invention and do not limit the embodiments of the present invention. Additionally, it should be noted that for ease of description, only parts related to the embodiments of the present invention rather than all structures are shown in the accompanying drawings.

[0022] For ease of understanding, the main implementation concepts of the embodiments of the present invention are first briefly described.

[0023] During the process of generating a dynamic evacuation road network for a building based on a BIM model, there are multiple technical challenges. First, the complexity and diversity of the internal structure of the building increase the difficulty of road network generation. In multi-story buildings, connecting elements such as stairs, elevators, and corridors need to be accurately identified and modeled to ensure that the generated road network has actual passability. Second, the actual usage of the building, such as equipment installation areas and temporary obstacles, may result in certain areas being impassable, and these dynamic factors are difficult to fully reflect in the BIM model. In addition, the design of evacuation routes needs to comply with specific safety codes, such as requirements for the shortest path and maximum evacuation time, and these factors need to be fully considered during the road network generation process. Finally, how to effectively combine the generated road network with emergency escape routes and dynamically adjust the evacuation routes according to the real-time changes inside the building is a technical problem involving complex algorithm design and real-time data processing.

[0024] Consider a specific technical application scenario: a 30-story large commercial complex that includes a shopping mall, an office area, and a hotel. The building uses an advanced BIM system for management, but still faces challenges in the formulation and implementation of emergency evacuation plans. The internal structure of the building is complex, including multiple atriums, skybridges connecting different areas, multiple elevator groups, and multiple emergency escape stairs. In addition, the store layout in the shopping mall area often changes, and there are irregular renovations and partition adjustments in the office area. In such a scenario, the evacuation road network generated based on the static BIM model is difficult to adapt to the dynamic changes of the building. For example, a large-scale renovation is carried out on a certain floor of the shopping mall, resulting in the temporary blockage of the original evacuation route, and this information is not timely reflected in the evacuation system. At the same time, a large number of sensors are installed inside the building, including smoke detectors, temperature sensors, and human flow monitoring devices, which can collect data in real time, but how to effectively use this data to dynamically update the evacuation road network becomes a key technical challenge.

[0025] If this technical problem cannot be effectively solved, it may lead to serious consequences. First of all, the static evacuation road network cannot adapt to the dynamic changes of buildings, which may cause people to be guided into blocked or dangerous areas in case of emergencies. Secondly, the failure to make full use of real-time data may result in missing the opportunity to adjust the evacuation route in a timely manner, increasing the evacuation time and risk. In addition, if the evacuation road network cannot be synchronized with the actual situation of the building, it may lead to a large deviation between the results of evacuation drills and the actual situation, reducing the effectiveness of the emergency plan. From a technical perspective, this problem highlights the limitations of existing BIM systems in a dynamic environment, as well as the importance of real-time data processing and decision-making systems in complex building environments. Solving this problem can not only improve the safety performance of buildings, but also promote the development of BIM technology towards a more intelligent and dynamic direction.

[0026] When solving the technical problem of generating a dynamic evacuation road network for a building based on a BIM model, the present invention first considered how to accurately obtain the spatial layout and multi-layer connection information of the building. Since the internal structure of the building is complex, including diverse connection elements such as stairs, elevators, and corridors, directly extracting this information from the BIM model is a challenge. For this reason, the present invention proposes a method of obtaining spatial layout data and multi-layer connection information from the building BIM model to construct an initial road network framework. This method can effectively transform the complex building structure into basic data available for road network generation. However, only the initial road network framework is not sufficient to cope with the actual usage situation of the building. For example, certain areas may be impassable due to equipment installation or temporary obstacles. To solve this problem, the present invention proposes a step of generating revised road network data based on the initial road network framework and traffic restriction information. This step takes into account the actual traffic restrictions, making the generated road network more in line with the actual situation. Next, the present invention considered how to ensure that the generated evacuation routes meet the requirements of safety codes. For this reason, a method of calculating standard-compliant evacuation routes based on the revised road network data and safety code requirements to generate a preliminary evacuation road network is proposed. This step ensures that the generated road network not only considers the actual traffic situation but also complies with relevant safety standards.

[0027] Considering the dynamic changes in the internal environment of a building, such as fires or other emergencies, static evacuation road networks may not be able to respond in a timely manner. Therefore, the present invention proposes a method of obtaining real-time data from sensors inside the building, judging the impact of dynamic changes on the preliminary evacuation road network, and updating the information on impassable areas. This innovative step enables the evacuation road network to be dynamically adjusted according to real-time situations. Based on the updated information on impassable areas, the present invention further proposes a method of recalculating evacuation routes, adjusting the preliminary evacuation road network, and generating an optimized evacuation road network. This ensures that the evacuation road network can be continuously optimized to adapt to the real-time changes inside the building. To improve the visualization effect and practicality of the evacuation road network, the present invention introduces three-dimensional digital twin technology, matches the optimized evacuation road network with the building BIM model, and generates a visualized three-dimensional road network map. This step not only improves the visualization effect of the road network but also lays a foundation for subsequent dynamic updates. Finally, to achieve real-time dynamic updates of the evacuation plan, the present invention proposes a method of dynamically updating evacuation paths according to the visualized three-dimensional road network map and real-time data streams, and generating a final evacuation plan. This step enables the evacuation system to adjust evacuation strategies in real time according to the latest building status and environmental changes.

[0028] Embodiment 1

[0029] Figure 1 is a schematic flowchart of a method for generating a dynamic evacuation road network of a building based on a BIM model in Embodiment 1 of the present invention, as Figure 1 shown, Embodiment 1 provides a method for generating a dynamic evacuation road network of a building based on a BIM model, including: Step S100, obtaining spatial layout data and multi-layer connection information from the building BIM model, and constructing an initial road network framework; Step S200, generating corrected road network data according to the initial road network framework and traffic restriction information; Step S300, calculating evacuation routes that meet the standards according to the corrected road network data and safety code requirements, and generating a preliminary evacuation road network; Step S400, obtaining real-time data from sensors inside the building, judging the impact of dynamic changes on the preliminary evacuation road network, and updating the information on impassable areas; Step S500, recalculating evacuation routes according to the updated information on impassable areas, adjusting the preliminary evacuation road network, and generating an optimized evacuation road network; Step S600, matching the optimized evacuation road network with the building BIM model through three-dimensional digital twin technology, and generating a visualized three-dimensional road network map; Step S700, dynamically updating evacuation paths according to the visualized three-dimensional road network map and real-time data streams, and generating a final evacuation plan.

[0030] Among them, the BIM model refers to the Building Information Model, which is a digital representation containing data such as the geometry of the building, spatial relationships, geographical information, the attributes and quantities of each component, and can be specifically implemented using software such as Autodesk Revit and Bentley AECOsim Building Designer. Among them, the dynamic evacuation road network refers to an evacuation path network that can automatically adjust according to the real-time conditions inside the building, and can be specifically implemented using graph theory algorithms and real-time data processing technologies. Among them, the three-dimensional digital twin technology refers to creating a virtual replica of a physical entity to achieve the mapping from the physical world to the digital world, and can be specifically implemented using three-dimensional engines such as Unity3D and Unreal Engine.

[0031] The present invention combines the BIM model, real-time sensor data, and three-dimensional digital twin technology to achieve the automatic generation and real-time optimization of the dynamic evacuation road network of a building. Through this method, the evacuation road network can be dynamically adjusted according to the real-time changes inside the building, improving the evacuation efficiency and safety.

[0032] The working principle of the present invention can be divided into the following key steps:

[0033] First, extract the spatial layout data and multi - layer connection information from the building BIM model. This step obtains the positions and connection relationships of key elements such as walls, partitions, stairs, elevators, and corridors by parsing the geometric structure of the BIM model. This information is used to construct an initial road network framework, providing a basis for subsequent road network generation. Next, generate the revised road network data based on the initial road network framework and traffic restriction information. This step takes into account actual traffic restrictions, such as equipment installation areas and temporary obstacles, and excludes non - passable areas through geometric analysis and path - planning tools to ensure that the generated road network conforms to the actual situation. Then, calculate the evacuation routes that meet the standards according to the revised road network data and safety code requirements, and generate a preliminary evacuation road network. This step uses the Dijkstra algorithm, combined with the shortest - path and maximum evacuation - time threshold requirements in the safety code, to ensure that the generated evacuation routes meet the safety standards. Next, obtain the real - time data of the internal sensors of the building, judge the impact of dynamic changes on the preliminary evacuation road network, and update the information of non - passable areas. This step dynamically marks the affected areas as non - passable areas by analyzing sensor data, such as the spread of fire or smoke, to achieve real - time update of the road network. Based on the updated information of non - passable areas, recalculate the evacuation routes, adjust the preliminary evacuation road network, and generate an optimized evacuation road network. This step recalculates the evacuation routes through the Dijkstra algorithm and optimizes the node positions using the K - means clustering algorithm to ensure real - time optimization of the road network. Subsequently, through three - dimensional digital twin technology, match the optimized evacuation road network with the building BIM model to generate a visual three - dimensional road network map. This step uses tools such as Three.js to generate a three - dimensional road network map and dynamically adjusts the evacuation routes through the A* algorithm to improve the visualization effect and practicality of the road network. Finally, according to the visual three - dimensional road network map and real - time data stream, dynamically update the evacuation paths to generate the final evacuation plan. This step continuously analyzes real - time data, dynamically updates non - passable areas, and recalculates the evacuation paths using the A* algorithm to ensure the real - time nature and effectiveness of the evacuation plan. These steps work together to achieve the conversion from a static BIM model to a dynamic evacuation road network and can continuously optimize the evacuation plan according to real - time data. The reasons for choosing these technical features are that they can effectively solve problems such as the complex internal structure of buildings, dynamic changes in usage conditions, and the need to comply with safety codes, thus significantly improving evacuation efficiency and safety.

[0034] As a preferred implementation, the present invention can be applied to a 30 - story large - scale commercial complex. The building includes a shopping mall, an office area, and a hotel, with a complex internal structure, including multiple atriums, skybridges connecting different areas, multiple elevator groups, and multiple emergency escape stairs.

[0035] First, the BIM model of the building was created using Autodesk Revit software. The spatial layout data and multi-layer connection information of the building were extracted through Revit's API. For example, the floor plan of each floor was obtained, including the location and size of walls, doors, windows, and corridors; the location of stairs and elevators and the floor information connected to them were extracted. Then, the path planning algorithm written in Python was used to build the initial road network framework based on the extracted data. Considering that the store layout in the shopping mall area often changes, and the office area has irregular decoration and partition adjustments, the system will regularly update the access restriction information. For example, if a large-scale renovation of a shopping mall on a certain floor causes the original evacuation route to be temporarily blocked, this information will be entered into the system to correct the road network data. Then, based on the corrected road network data and local building safety regulations, the Dijkstra algorithm is used to calculate the evacuation route that meets the standards. For example, if the distance from any point to the nearest safe exit is not more than 50 meters, the system will generate a preliminary evacuation road network based on this. A large number of sensors are installed inside the building, including smoke detectors, temperature sensors, and pedestrian flow monitoring equipment. These sensors transmit data to the central processing system in real time through the MQTT protocol. The system uses machine learning algorithms (such as random forests) to analyze this data to determine whether any area has become inaccessible. For example, if the temperature in an area suddenly rises and the smoke concentration increases, the system will mark the area as inaccessible. Based on the updated information about inaccessible areas, the system uses the A-star algorithm to recalculate the evacuation route and adjust the preliminary evacuation network. For example, if a fire is detected in an area on the 3rd floor, the system will immediately replan the evacuation routes on that floor and adjacent floors to avoid the dangerous area. Next, the Unity3D engine is used to create a 3D digital twin model of the building. The optimized evacuation network is mapped to this 3D model to generate a visual 3D network map. This 3D model can display the conditions inside the building in real time, including inaccessible areas and recommended evacuation routes. Finally, the system continuously receives and analyzes real-time data streams and dynamically updates the evacuation path. For example, if a sudden increase in the flow of people in a certain evacuation channel is detected, the system will automatically adjust the evacuation plan and guide some of the people to other relatively idle channels to avoid congestion.

[0036] In this way, the present invention can provide a dynamic, real-time, and visual evacuation system for the large commercial complex, greatly improving the evacuation efficiency and safety in emergency situations.

[0037] In this embodiment, the step S100 includes: step S101, parsing the geometric structure from the building BIM model to obtain the spatial layout data of the walls and partitions; step S102, determining the positional relationship between the walls and partitions according to the spatial layout data; step S103, extracting the multi-layer connection information of the stairs, elevators and corridors from the building BIM model; step S104, determining the connection point data according to the positional relationship and the multi-layer connection information; step S105, constructing a multi-layer road network structure through the connection point data; step S106, optimizing the multi-layer road network structure by using a genetic algorithm to generate the initial road network framework.

[0038] Specifically, parse the geometric structure from the BIM model: This step can be achieved by using the API interface of BIM software or specialized geometric data extraction tools. For example, the API of Autodesk Revit can be used to extract the geometric information of structural elements such as walls, floors, and ceilings. This information usually includes parameters such as coordinate points, length, width, and height. Obtain the spatial layout data of walls and partitions: Based on the parsed geometric structure, spatial analysis algorithms can be used to identify and classify walls and partitions. For example, the plane sweep algorithm can be used to detect planar structures perpendicular to the ground and classify them as walls or partitions. The output of this step can be a data structure containing the positions, dimensions, and orientations of walls and partitions. Determine the positional relationship between walls and partitions: Using the obtained spatial layout data, graph theory algorithms can be applied to establish the topological relationship between walls and partitions. For example, an adjacency matrix can be used to represent the connection relationship between walls, or a quadtree structure can be used to quickly query the walls and partitions within a specific area. Extract multi-level connection information: This step requires special attention to vertical connection elements such as stairs, elevators, and corridors. The attribute information in the BIM model can be used to identify these elements. For example, look for objects with the attributes of "Stairs", "Elevator", or "Corridor". For stairs, information such as the starting and ending floors, width, and inclination angle can be extracted; for elevators, information such as the floor range served and capacity can be extracted. Determine the connection point data: Based on the wall positional relationship and multi-level connection information, spatial interpolation algorithms can be used to generate connection points. For example, connection points are set at the intersection points of corridors, entrances and exits of rooms, starting and ending points of stairs, etc. These connection points will become the nodes of the road network. Construct a multi-level road network structure: Using the minimum spanning tree algorithm in graph theory, such as Kruskal's algorithm or Prim's algorithm, construct a preliminary road network structure based on the connection point data. This structure should include all the connection points on all floors and their connection relationships. Optimize the road network structure using a genetic algorithm: A genetic algorithm can be used to optimize the connection method and path selection of the road network. For example, a fitness function can be defined to evaluate the efficiency of the road network (such as average path length, congestion level, etc.), and then through crossover and mutation operations, a better road network structure can be generated and selected.

[0039] There are close associations and interactions between these steps. For example, the positional relationship between walls and partitions directly affects the determination of connection points, while the multi-level connection information determines the road network connection method between different floors. Through this systematic method, the present invention can effectively extract the necessary spatial information from the BIM model and transform this information into an initial road network framework that can be used for evacuation path planning.

[0040] In particular, the extraction of multi-layer connection information and the application of genetic algorithms can effectively handle vertical connection problems in complex building structures and optimize the road network structure. This not only improves the accuracy and practicality of the road network, but also lays a solid foundation for subsequent dynamic evacuation route planning.

[0041] For example, in a specific embodiment, consider the BIM model of a five-story office building. First, use the Autodesk Revit API to extract the geometric structure of the building, including the floor plan, wall positions, and dimensions of each floor. Then, use spatial analysis algorithms to identify the room layout on each floor and determine the positions of corridors, office areas, and public areas. For multi-layer connections, the system identifies two stairwells (located on the east and west sides of the building) and a central elevator shaft. The geometric information of the stairs includes the height (18 cm) and width (30 cm) of each step, as well as the total width of the stairs (1.5 m). The information of the elevator includes its load capacity (1000 kg) and speed (2 m / s). When determining the connection points, the system sets nodes at the entrances and exits of each room, intersections of corridors, starting and ending points of stairs, and elevator doors. For example, on the main corridor of each floor, a connection point is set every 5 meters. Use the Kruskal algorithm to construct the initial multi-layer road network structure and connect all the nodes. Then, apply the genetic algorithm for optimization, and define the fitness function as: f = 1 / (average path length + α * congestion coefficient), where α is a weight coefficient set to 0.5. Through multiple generations of iteration (such as 100 generations), continuously adjust the connection method, and finally obtain an optimized road network structure that balances the path length and congestion level. This optimized road network structure becomes the initial road network framework, providing a basis for subsequent dynamic evacuation route planning. It not only considers the actual spatial layout of the building, but also improves the efficiency of the road network through algorithm optimization, thus being able to better support evacuation needs in case of emergencies.

[0042] In this embodiment, the step S200 includes: step S201, extracting the spatial position relationship between walls and partitions according to the initial road network framework; step S202, identifying passage restriction information through geometric analysis, and marking the equipment installation area and the position of temporary obstacles; step S203, if there are impassable areas, excluding the impassable areas through a path planning tool to generate a corrected road network structure; step S204, extracting multi-layer connection information from the corrected road network structure to determine connection point data; step S205, constructing a corrected multi-layer road network framework through a network modeling tool; step S206, adjusting the corrected multi-layer road network framework using a path optimization algorithm to generate the corrected road network data.

[0043] Specifically, first, extract the spatial position relationship between walls and partitions based on the initial road network framework. This step can be achieved in various ways. For example, use spatial analysis algorithms to identify and locate the walls and partitions in the BIM model, or adopt image processing techniques to analyze the building floor plan. The extracted spatial position relationship can include parameters such as the coordinates, length, width, and height of the walls and partitions. Secondly, identify the traffic restriction information through geometric analysis, and mark the equipment installation areas and the positions of temporary obstacles. Geometric analysis can adopt various algorithms, such as the convex hull algorithm, the minimum bounding rectangle algorithm, etc., to identify irregularly shaped obstacles. The traffic restriction information can include fixed obstacles (such as columns, equipment) and temporary obstacles (such as construction areas, temporary isolation belts). These information can be distinguished by setting different weights or marks. Next, if there are impassable areas, exclude these areas through a path planning tool to generate a corrected road network structure. The path planning tool can adopt algorithms such as the A* algorithm, the Dijkstra algorithm, or the RRT (Rapidly-exploring Random Tree) algorithm, etc. This step ensures that the generated road network structure avoids all impassable areas and improves the practicality of the road network. Then, extract the multi-layer connection information from the corrected road network structure to determine the connection point data. The multi-layer connection information includes the positions and connection relationships of vertical transportation facilities such as stairs, elevators, and ramps. The connection point data can include information such as the coordinates of each connection point, the floor to which it belongs, and the connection type. This step solves the connection problem between different floors in a complex building and ensures the connectivity of the generated road network in the vertical direction. Next, construct the corrected multi-layer road network framework through a network modeling tool. The network modeling tool can use the adjacency matrix or adjacency list in graph theory to represent the road network structure, or use specialized road network modeling software. The constructed multi-layer road network framework should contain information about nodes (representing passable points) and edges (representing passable paths). Finally, adopt a path optimization algorithm to adjust the corrected multi-layer road network framework to generate corrected road network data. The path optimization algorithm can include genetic algorithms, ant colony algorithms, or simulated annealing algorithms, etc. The optimization goal can be to minimize the total path length, maximize the traffic efficiency, or balance the load of each path, etc.

[0044] Through this series of steps, the technical solution of the present invention can effectively solve the problem that the initial road network does not conform to the actual traffic situation. This solution comprehensively considers static structure information and dynamic traffic restriction information, and through multi-step analysis and optimization, generates road network data that not only conforms to the actual structure of the building but also takes into account the real-time traffic situation.

[0045] As a preferred implementation manner, the technical solution of the present invention can be specifically implemented as follows:

[0046] First, use a BIM model parsing tool to extract the geometric data of walls and partitions from the building information model. For example, a wall may be represented as a series of line segments or polygons, and each wall contains information such as the coordinates of its starting and ending points, thickness, etc. A partition may be represented as a thinner wall or a specific obstacle object. Next, adopt computational geometry algorithms for spatial analysis. For example, use the plane sweep line algorithm to identify openings (such as doors) between adjacent walls, and use polygon boolean operations to determine the passable areas. For equipment installation areas and temporary obstacles, the minimum bounding rectangle algorithm can be used for quick positioning and marking. After identifying the impassable areas, apply an improved A* algorithm for path planning. This algorithm can set obstacle weights to avoid impassable areas. For example, the weight of a fixed obstacle can be set to infinity, and the weight of a temporary obstacle can be set to a large but finite value (such as 1000). For the extraction of multi-story connection information, a depth-first search algorithm can be used. Starting from the entrance point of each floor, search for all possible paths until a connection point (such as a staircase or elevator) to other floors is found. Each connection point records its coordinates, the floor it belongs to, and the connection type. In the network modeling stage, a graph data structure can be used. Each passable point serves as a node of the graph, and the passable paths between nodes serve as edges. For multi-story buildings, a multi-layer graph structure can be used, and different layers are connected through the previously identified connection points. Finally, genetic algorithms can be used for path optimization. The initial population can be multiple different road network structures, and new road network structures are generated through crossover and mutation operations. The fitness function can comprehensively consider factors such as path length, congestion, and safety. For example, the fitness function can be set as: F = w1*L + w2*C + w3*S, where L is the total path length, C is the congestion index, S is the safety index, and w1, w2, w3 are weight coefficients. Through multiple generations of iteration, finally select the road network structure with the highest fitness as the optimization result.

[0047] Based on the above analysis, it can be seen that the technical solution of the present invention effectively solves the technical problem of generating corrected road network data according to the initial road network framework and traffic restriction information by comprehensively considering static structures and dynamic factors and adopting a variety of advanced algorithms, providing more accurate and practical basic data for building evacuation route planning.

[0048] In this embodiment, the step S300 includes: step S301, based on the corrected road network data, combining the evacuation requirements in the safety specifications, to determine the shortest path and the maximum evacuation time threshold; step S302, using the Dijkstra algorithm, according to the corrected road network data and the maximum evacuation time threshold, to calculate the evacuation routes that meet the standards; step S303, according to the evacuation routes, to generate the preliminary evacuation road network, and extract the key nodes and connection relationships; step S304, if there are areas in the preliminary evacuation road network that do not meet the standards, then adjust the Dijkstra algorithm parameters and recalculate the evacuation routes; step S305, through iterative optimization, to determine the final preliminary evacuation road network.

[0049] Specifically, determining the shortest path and the maximum evacuation time threshold based on the corrected road network data and safety specification requirements is a key step. This step can be achieved in various ways. For example: 1. Use the Floyd-Warshall algorithm to calculate the shortest paths between all node pairs and set the maximum evacuation time threshold according to the evacuation requirements in the safety specification; 2. Adopt the A* algorithm combined with a heuristic function to quickly find the shortest paths between key nodes, taking into account the geometric features of buildings and safety specification requirements; 3. Combine the genetic algorithm and the simulated annealing algorithm to optimize path selection and time threshold setting to adapt to complex building structures and evacuation requirements. Calculating the evacuation routes that meet the standards using the Dijkstra algorithm is the core step of the present invention. The implementation of the Dijkstra algorithm can consider the following aspects: 1. Use a priority queue (such as a Fibonacci heap) to optimize the algorithm performance and improve the calculation efficiency of large-scale road networks; 2. Introduce an edge weight dynamic adjustment mechanism to update the path weights according to real-time evacuation situations and building states; 3. Combine parallel computing technologies, such as CUDA or OpenCL, to accelerate the path calculation process for large buildings. In the process of generating the preliminary evacuation road network and extracting key nodes and connection relationships, the following implementation methods can be considered: 1. Use the minimum spanning tree algorithm in graph theory (such as the Kruskal algorithm or the Prim algorithm) to construct the skeleton of the preliminary evacuation road network; 2. Adopt a clustering algorithm (such as K-means or DBSCAN) to identify and extract key nodes; 3. Utilize spatial indexing technologies (such as R-trees or quadtrees) to optimize the storage and query efficiency of nodes and connection relationships. If there are areas in the preliminary evacuation road network that do not meet the standards, the present invention proposes a method of adjusting the parameters of the Dijkstra algorithm and recalculating the evacuation routes. This process can be achieved in the following ways: 1. Use machine learning algorithms (such as random forests or support vector machines) to predict areas that do not meet the standards and adjust the algorithm parameters accordingly; 2. Introduce a multi-objective optimization algorithm that simultaneously considers multiple factors such as path length, evacuation time, and safety, and dynamically adjusts the weight parameters of the Dijkstra algorithm; 3. Adopt reinforcement learning techniques to adaptively optimize the algorithm performance by continuously trying and evaluating different parameter combinations. Determining the final preliminary evacuation road network through iterative optimization is an important feature of the present invention. This process can consider the following implementation methods: 1. Use the Monte Carlo simulation method to run the optimization process multiple times and statistically analyze the distribution characteristics of the optimal solutions; 2. Adopt the genetic algorithm or the particle swarm optimization algorithm to find the globally optimal evacuation road network solution through multiple generations of evolution; 3. Combine an expert system and fuzzy logic to introduce human experience and judgment to improve the practicality and reliability of the optimization results.

[0050] As a preferred implementation manner, the technical solution of the present invention can be implemented according to the following steps:

[0051] 1. Data Preparation: Extract the information of nodes and edges from the corrected road network data to construct a graph structure G(V, E), where V is the set of nodes and E is the set of edges. Each edge e ∈ E contains information such as length l(e) and travel time t(e).

[0052] 2. Parameter Setting: According to the requirements of safety specifications, set the maximum evacuation time threshold Tmax. Initialize the weight parameter w of the Dijkstra algorithm, and usually w can be set to 0.7.

[0053] 3. Shortest Path Calculation: Use the Dijkstra algorithm to calculate the shortest path from each node to the nearest exit. For each edge e, define its weight as w * l(e)+(1 - w) * t(e).

[0054] 4. Preliminary Evacuation Road Network Generation: Merge all the shortest paths to form a preliminary evacuation road network N. Extract the key nodes (such as intersections and turning points) and connection relationships in N.

[0055] 5. Compliance Check: Check whether the total evacuation time of each path in N is less than or equal to Tmax. If there are paths that do not meet the requirements, go to step 6; otherwise, go to step 7.

[0056] 6. Parameter Adjustment and Recalculation: Adjust the weight parameter w, for example, w = w - 0.1. Return to step 3 for recalculation.

[0057] 7. Road Network Optimization: Use the K - means algorithm to cluster the key nodes and merge the nodes with relatively close distances. Use the minimum spanning tree algorithm to optimize the connection relationships between nodes.

[0058] 8. Output Result: Generate the final preliminary evacuation road network, including the optimized node positions and connection relationships.

[0059] Through this implementation method, the present invention can generate an evacuation road network that meets safety standards in a complex building environment. For example, in a multi - storey office building, this method can effectively handle vertical connection structures such as stairs and elevators, and at the same time consider the special requirements of different floors (such as the safety doors on some floors being locked). Through iterative optimization, the finally generated evacuation road network can ensure the shortest path while ensuring that the evacuation time of all locations is within the safe range. Compared with the prior art, the technical solution of the present invention has significant advantages. Traditional evacuation route generation methods usually only consider the shortest path and ignore the requirements of evacuation time and safety specifications. The present invention can ensure that the evacuation time meets safety standards while ensuring the shortest path by introducing the maximum evacuation time threshold and the iterative optimization process. In addition, the method of the present invention can dynamically adapt to changes in the internal environment of the building, and quickly generate an updated evacuation road network through parameter adjustment and recalculation, which has important significance in practical applications.

[0060] In this embodiment, the step S400 includes: step S401, obtaining real-time data of sensors inside the building, cleaning and standardizing the real-time data; step S402, calculating the range and speed of fire or smoke spread according to the standardized real-time data; step S403, judging whether the spread range exceeds the traffic capacity threshold according to a preset threshold rule; step S404, if it exceeds the traffic capacity threshold, marking the affected area as an impassable area; step S405, updating the traffic status of the preliminary evacuation road network according to the impassable area to generate updated impassable area information.

[0061] Specifically, the technical solution proposed by the present invention dynamically identifies dangerous areas inside a building through real-time data collection, processing, and analysis, and updates the evacuation road network in a timely manner. This method can effectively respond to the rapid changes in the internal environment of the building, such as fires or smoke spread, and ensure the real-time effectiveness of the evacuation route. By setting a traffic capacity threshold, the system can objectively determine whether an area is safe and passable, avoiding errors and delays that may be caused by human judgment. At the same time, by continuously updating the information on impassable areas, accurate basic data is provided for subsequent recalculation and optimization of the evacuation route, thereby improving the reliability and adaptability of the entire evacuation system. The technical solution of the present invention includes multiple key features, and each feature has multiple possible implementation methods: Obtaining real-time data from sensors inside the building: Data can be obtained through various types of sensors such as temperature sensors, smoke sensors, and gas concentration sensors. These sensors can be connected to the central processing system through wired or wireless networks. Data cleaning and standardization: Various data processing algorithms can be used, such as outlier detection, data interpolation, and data normalization. For example, the Z-score method can be used for data standardization, or the moving average method can be used to filter out noise. Calculating fire or smoke spread: Computational Fluid Dynamics (CFD) models or simplified zone models can be used to simulate fire or smoke spread. For example, the FDS (Fire Dynamics Simulator) software can be used for accurate simulation, or CFAST (Consolidated Model of Fire and Smoke Transport) can be used for rapid estimation. Judging thresholds: Threshold rules can be set based on multiple parameters, such as temperature, smoke concentration, and toxic gas concentration. The threshold can be a fixed value or a value dynamically adjusted according to the characteristics of the building. Marking impassable areas: Graphical algorithms such as flood fill algorithms can be used to mark continuous impassable areas, or the building can be divided into small units using a grid method, and the affected units can be marked one by one. Updating traffic status: Graph theory algorithms such as Depth-First Search (DFS) or Breadth-First Search (BFS) can be used to update the connectivity of the road network, or dynamic programming algorithms can be used to recalculate the shortest path. There is a close association and interaction between these features. The acquisition of real-time data provides the basis for subsequent data processing and analysis. Data cleaning and standardization ensure the accuracy of subsequent analysis. The calculation results of fire or smoke spread directly affect the threshold judgment, which in turn determines the marking of impassable areas. Finally, the information on impassable areas is used to update the traffic status of the evacuation road network, forming a complete dynamic update cycle.

[0062] When the technical solution of the present invention solves the problem of the impact of internal dynamic changes in a building on the preliminary evacuation road network, it follows the following process: First, environmental data is obtained in real time through a sensor network inside the building. This data may include multiple parameters such as temperature, smoke concentration, and toxic gas concentration. The data collection frequency can be adjusted according to the characteristics of the building and safety requirements, for example, collecting data every 5 seconds or every 10 seconds. Next, the collected data is cleaned and standardized. This step can remove outliers, fill in missing data, and convert different types of data into a unified standard format. For example, the median filtering method can be used to remove outliers, the linear interpolation method can be used to fill in missing data, and then all data is mapped to the range of 0-1 through Min-Max normalization. Then, based on the processed data, a pre-established model is used to calculate the spread range and speed of fire or smoke. This may involve complex physical models, such as considering factors such as the geometric structure of the building, material properties, and ventilation conditions. The calculation result can be a three-dimensional diffusion field, showing the degree of danger at each spatial point. According to the calculation result, the system will judge whether each area exceeds a preset traffic capacity threshold. These thresholds may be set based on safety standards. For example, when the smoke concentration exceeds 0.1 m^-1 or the temperature exceeds 60 °C, the area is considered unsuitable for passage. For areas that exceed the threshold, the system will mark them as non-passable areas. This may involve updating the status flag of each spatial unit in the digital model of the building. The marking process needs to consider the continuity of space to ensure that there are no isolated passable areas. Finally, the system re-evaluates the effectiveness of the preliminary evacuation road network based on the updated non-passable area information. This may include deleting paths that pass through non-passable areas or adjusting the paths to bypass these areas. The updated road network information will be used for subsequent evacuation planning and guidance.

[0063] Through this series of steps, the technical solution of the present invention can timely reflect the internal dynamic changes of the building, ensuring that the evacuation road network always maintains the latest and safest state. This dynamic update mechanism greatly improves the reliability and adaptability of the evacuation system, providing a safer evacuation guarantee for the building users.

[0064] As a preferred implementation manner, the technical solution of the present invention can be implemented in a large commercial complex. The complex includes multiple floors of shopping areas, office areas, and dining areas, with a total building area of approximately 100,000 square meters and a daily footfall of up to 50,000 person-times. In this complex, a total of 5,000 various sensors are installed, including 2,000 temperature sensors, 2,000 smoke sensors, and 1,000 carbon monoxide sensors. These sensors are evenly distributed in various areas of the building, with an average of one sensor installed per 20 square meters. All sensors are connected to the central processing system via a wireless network, and the data acquisition frequency is once every 5 seconds. The data cleaning and standardization process uses a sliding window median filtering algorithm to remove outliers, and the window size is set to 11 data points. For possible missing data, linear interpolation is used for filling. Then, the Z-score method is used to standardize all the data. The calculation of fire or smoke spread uses a simplified zone model, which divides the entire building into 5,000 cubic units, each with a side length of 5 meters. The model takes into account the building's ventilation system and fire compartment settings, and uses the finite difference method to solve the diffusion equation to calculate the temperature and smoke concentration changes in each unit. The passage capacity thresholds are set as follows: when the temperature in a certain unit exceeds 50 °C, or the smoke concentration exceeds 0.08 m^-1, or the carbon monoxide concentration exceeds 100 ppm, that unit is marked as impassable. These thresholds are formulated based on international safety standards and local fire regulations. The marking of impassable areas uses a three-dimensional flood filling algorithm, starting from the identified hazard sources and spreading to mark the impassable areas around. The algorithm takes into account the connectivity in both vertical and horizontal directions to ensure the continuity and integrity of the marking. Finally, the update of the evacuation road network uses the A* algorithm to recalculate the shortest safe path from each possible starting point to the nearest exit. The heuristic function of the algorithm takes into account the distance factor and the safety factor, and preferentially selects paths far from dangerous areas. Through this implementation manner, the technical solution of the present invention can quickly respond to dynamic changes in a complex large building, update the evacuation road network in a timely manner, and provide safe and reliable evacuation guidance for a large number of people. The reaction time of the system from sensing danger to updating the evacuation road network does not exceed 30 seconds, greatly improving the evacuation efficiency in emergency situations.

[0065] In this embodiment, the step S500 includes: step S501, according to the updated impassable area information, recalculate the evacuation route using the Dijkstra algorithm; step S502, adjust the preliminary evacuation road network according to the recalculated evacuation route to generate a new road network layout; step S503, extract the node position information from the new road network layout; step S504, optimize the node position information through the K-means clustering algorithm and adjust the road network spatial layout; step S505, generate an optimized evacuation road network according to the adjusted road network spatial layout.

[0066] Specifically, first, according to the updated information of impassable areas, the Dijkstra algorithm is used to recalculate the evacuation routes. The Dijkstra algorithm is a classic shortest path algorithm and is used in the present invention to calculate the optimal evacuation routes. This algorithm can quickly find the shortest path from any starting point to the safety exit according to the latest information of impassable areas. For example, when a certain area becomes impassable due to a fire or other emergencies, the Dijkstra algorithm can quickly replan the route to avoid these dangerous areas. Secondly, according to the recalculated evacuation routes, the preliminary evacuation road network is adjusted to generate a new road network layout. This step integrates the latest evacuation routes calculated by the Dijkstra algorithm into the existing road network to form an updated road network layout. This process may involve operations such as adding new paths, deleting no-longer-safe paths, and adjusting the weights of existing paths. Next, the node position information is extracted from the new road network layout. Nodes usually represent key positions in the road network, such as intersections, corners, or safety exits. Accurate node position information is crucial for subsequent optimization. Then, the node position information is optimized by the K-means clustering algorithm to adjust the spatial layout of the road network. The K-means clustering algorithm is a commonly used data analysis method and is innovatively applied to road network optimization in the present invention. This algorithm can group similar nodes and find the center point of each group, thereby optimizing the distribution of nodes. This step helps to simplify the road network structure, reduce redundant nodes, and improve the evacuation efficiency. For example, in a large open space, the K-means clustering can help determine the best intermediate assembly point to make the evacuation of people more orderly and efficient. Finally, according to the adjusted spatial layout of the road network, an optimized evacuation road network is generated. This final evacuation road network integrates the dynamically updated information of impassable areas, the shortest paths calculated by the Dijkstra algorithm, and the node distribution optimized by the K-means clustering to form a comprehensively optimized evacuation plan.

[0067] For example, in a multi-story office building, when a fire breaks out on a certain floor, the technical solution of the present invention can quickly update the information of impassable areas and use the Dijkstra algorithm to recalculate the shortest paths from each office to the safety exit. At the same time, the K-means clustering algorithm can optimize the location of the assembly points on each floor to ensure that there will be no congestion in certain areas during the evacuation of people. This ability of dynamic adjustment and optimization enables the evacuation plan to adapt to the changing environment at any time, greatly improving the efficiency and safety of evacuation.

[0068] As a preferred implementation manner, the technical solution of the present invention can be implemented as follows: First, the system receives the updated information on non-passable areas. These information may come from various sensors within the building, such as smoke detectors, heat sensors, etc. For example, the system may receive the information that there is thick smoke in the corridor on the 3rd floor and mark this area as non-passable. Then, the system uses the Dijkstra algorithm to recalculate the evacuation route. The algorithm regards each passable area in the building as a node in the graph, and the connections between the nodes represent passable paths. Each path is assigned a weight, representing the time or difficulty required to pass through this path. For example, the weight of a normal corridor may be 1, while the weight of a narrow or crowded passage may be 2 or 3. The weight of a non-passable area is set to infinity to ensure that the algorithm does not select these paths. The Dijkstra algorithm starts from each starting point (such as each office) and calculates the shortest path to the nearest safe exit. Then, the system adjusts the preliminary evacuation road network according to the calculation results of the Dijkstra algorithm to generate a new road network layout. This may involve deleting the paths passing through non-passable areas, adding new alternative paths, or adjusting the directions and flow allocations of existing paths. Next, the system extracts the node position information from the new road network layout. These nodes may include key positions such as the intersections of corridors, stairwells, and safe exits. Each node is assigned specific coordinate values, such as (x, y, z), where z represents the floor. Subsequently, the system uses the K-means clustering algorithm to optimize the node position information. Assuming K = 5 is selected, the algorithm divides all nodes into 5 clusters. The center point of each cluster is considered to be the best assembly point in this area. For example, in a large open office area, the algorithm may determine several assembly points near the main exit, near the stairs, etc. Finally, the system generates the final optimized evacuation road network according to the optimized node positions and path information. This road network not only includes the latest passable paths but also optimizes the distribution of personnel flow and assembly points, thereby improving the overall evacuation efficiency.

[0069] Based on the above analysis, it can be seen that through this method, the technical solution of the present invention can quickly respond to environmental changes in case of emergencies, provide the optimal evacuation route, and improve the overall evacuation efficiency by optimizing the node distribution. This ability of dynamic optimization significantly enhances the adaptability and effectiveness of the evacuation plan, providing a safer and more reliable evacuation guarantee for the building users. Compared with the prior art, the technical solution of the present invention has significant advantages. The traditional evacuation road network is usually static and cannot respond to sudden environmental changes in a timely manner. However, the present invention greatly improves the flexibility and adaptability of the evacuation plan by updating the information of impassable areas in real time and recalculating the evacuation route. In addition, traditional methods often only focus on the calculation of the shortest path and ignore the optimization of the overall road network layout. By introducing the K-means clustering algorithm, the present invention not only optimizes a single path but also improves the spatial distribution of the entire road network, thereby improving the evacuation efficiency at the macroscopic level. This method of dynamic optimization and global consideration makes the technical solution of the present invention show obvious superiority when dealing with complex and changeable emergencies.

[0070] In this embodiment, the step S600 includes: step S601, obtaining the real-time data of the sensors inside the building through the MQTT protocol and parsing it into a format recognizable by the 3D engine; step S602, dynamically updating the impassable areas in the building BIM model according to the parsed data; step S603, matching the updated building BIM model with the optimized evacuation road network; step S604, generating a 3D road network map through Three.js; step S605, using the A* algorithm to adjust the evacuation route in the 3D road network map according to the real-time data; step S606, optimizing the spatial layout of the 3D road network map through the random forest algorithm to generate a visual 3D road network map.

[0071] Specifically, the implementation of the MQTT protocol can be achieved in various ways. For example, the Eclipse Paho MQTT client library can be used to implement MQTT communication. This library supports multiple programming languages, including Java, Python, C++, etc., and the appropriate version can be selected according to the specific development environment. In practical applications, parameters such as the MQTT server address, port, and topic can be set to ensure the correct reception of sensor data. There are also multiple possibilities for the selection of the 3D engine. In addition to Three.js, powerful 3D engines such as Unity3D or Unreal Engine can also be used. These engines have more powerful rendering capabilities and richer development tools, and can achieve more complex 3D scenes and interactive effects. In terms of data parsing, JSON or XML formats can be used to transmit sensor data, which can conveniently parse the data into a format recognizable by the 3D engine. For example, the JSON.parse() function can be used to parse JSON-formatted data, and then the parsed data can be mapped to the corresponding positions in the 3D scene. When implementing the A* algorithm, for example, heuristic functions are used to improve the search efficiency. For example, the Manhattan distance or Euclidean distance can be used as heuristic functions to find the optimal path more quickly. In addition, dynamic weight adjustment can be combined to dynamically adjust the path weights according to real-time data to adapt to different evacuation situations.

[0072] When the random forest algorithm optimizes the spatial layout of the 3D road network map, multiple features can be considered for training the model. For example, the spatial coordinates of nodes, connection relationships, pedestrian flow density, etc. can be used as features, and the best spatial layout can be obtained through multiple iterative optimizations. There are close associations and interactions among these technical features. The real-time data obtained by the MQTT protocol directly affects the update of the BIM model, and the updated BIM model provides a basis for generating the 3D road network map by Three.js. The A* algorithm and the random forest algorithm then perform path optimization and spatial layout adjustment based on this updated data. This multi-level technical integration enables the present invention to solve the complex evacuation road network generation problem more accurately and efficiently.

[0073] In practical applications, the technical solution of the present invention can significantly improve the generation efficiency and accuracy of evacuation road networks. For example, in the design of an evacuation plan for a multi-story office building, it can be achieved through the following steps: First, use the MQTT protocol to connect temperature sensors, smoke sensors, and people flow density sensors in the building. Set the MQTT server address to "mqtt.example.com", the port to 1883, and the subscription topic to "building / sensors / #". Then, use Three.js to create a basic 3D scene and load a pre-prepared BIM model. The GLTF format BIM model file can be loaded using the GLTFLoader of Three.js. Next, receive and parse MQTT data in real time. For example, the received JSON format data may be as follows: {"temperature":35,"smoke":200,"density":0.8,"location":{"x":10,"y":5,"z":20}}. According to this data, dynamically update the impassable areas in the BIM model. For example, when the smoke concentration exceeds 150, mark the corresponding area as impassable. Use the A* algorithm to calculate the optimal evacuation route. Set the starting point as the current location (10, 5, 20) and the ending point as the nearest safe exit. Use the Euclidean distance as the heuristic function and consider the people flow density as the path weight. Finally, use the random forest algorithm to optimize the spatial layout of the 3D road network map. When training the model, use node coordinates, connection relationships, and people flow density as features, and train through 500 decision trees to obtain the optimized spatial layout.

[0074] In this way, the present invention can generate and update a visual 3D evacuation road network map in real time, providing intuitive and accurate evacuation guidance for building managers and users. Compared with the prior art, the technical solution of the present invention has significant advantages. Traditional evacuation road network generation methods are usually based on static building models and are difficult to adapt to real-time changes. The present invention can dynamically adjust the evacuation road network by introducing 3D digital twin technology and real-time data analysis, better coping with emergencies. In addition, the A* algorithm and random forest algorithm used in the present invention can generate the optimal evacuation route more quickly and accurately compared with traditional path planning methods, taking into account various complex factors such as people flow density and obstacle distribution. This dynamic and intelligent evacuation road network generation method greatly improves the evacuation efficiency and safety, providing more reliable technical support for building emergency management.

[0075] In this embodiment, the step S700 includes: step S701, obtaining real-time data of sensors inside the building and analyzing the fire and smoke diffusion situation; step S702, determining the range of impassable areas according to the analysis result; step S703, dynamically updating the impassable areas in the visualized three-dimensional road network map through Three.js; step S704, using the A* algorithm to recalculate the evacuation route according to the updated visualized three-dimensional road network map; step S705, updating the evacuation lines inside the building according to the recalculated evacuation route; step S706, matching the updated evacuation lines with the building BIM model through GIS tools to generate a dynamic road network map; step S707, generating a final evacuation plan according to the dynamic road network map.

[0076] Specifically, obtaining real-time data from sensors inside a building can be achieved in various ways. For example, a distributed sensor network can be used, including temperature sensors, smoke sensors, infrared sensors, etc. These sensors transmit data to a central processing system in real time through wireless communication technologies such as ZigBee or Wi-Fi. Another way is to utilize Internet of Things (IoT) technology to connect various sensors to a cloud platform for real-time data collection and analysis. Analyzing fire and smoke spread situations can employ multiple algorithms. Among them, the Computational Fluid Dynamics (CFD) model can be used to simulate the spread process of fire and smoke, taking into account factors such as the building's geometric structure and ventilation conditions. Machine learning algorithms, such as Support Vector Machines (SVM) or deep learning networks, can also be used to predict the spread trend of fire and smoke, improving the prediction accuracy by training historical data. When determining the range of impassable areas, multiple thresholds can be set to define the danger levels. For example, when the temperature exceeds 60°C or the smoke concentration exceeds a certain threshold, the area is marked as impassable. These thresholds can be adjusted according to the characteristics and safety standards of different buildings. Three.js is a powerful JavaScript 3D library for dynamically updating the visualized 3D road network map. Through Three.js, real-time rendering and interactive 3D scenes can be achieved. When updating impassable areas, different colors or textures can be used to mark dangerous areas. For example, red can be used to indicate high-risk areas, and yellow can be used to indicate potentially dangerous areas. In addition, animation effects such as flashing or fading can be added to highlight the latest changes. The A* algorithm is an efficient path planning algorithm, especially suitable for path recalculation in dynamic environments. During implementation, the algorithm performance can be optimized according to different heuristic functions. For example, heuristic functions can be designed by combining multiple factors such as distance, crowding degree, and danger level to find the safest and fastest evacuation route. When updating the evacuation lines inside the building, a segmented update strategy can be adopted. That is, only the evacuation lines in the affected areas are updated instead of recalculating the entire building's evacuation route, which can significantly improve the update efficiency. At the same time, multiple alternative routes can be set to handle the situation where some routes suddenly become unavailable. The use of GIS tools can improve the accuracy of the matching between evacuation lines and BIM models. For example, spatial analysis functions can be used to ensure that the evacuation lines match the actual structure of the building, avoiding unreasonable paths such as passing through walls. In addition, GIS can also provide a geographic coordinate system, which helps to accurately locate and navigate in large or complex buildings. When generating a dynamic road network map, factors such as pedestrian flow density and movement speed can be considered. For example, the cellular automaton model can be used to simulate pedestrian movement, thus more accurately predicting congestion points and optimizing evacuation routes. The generation of the final evacuation plan can adopt a multi-objective optimization algorithm, considering multiple objectives such as evacuation time, path safety, and crowd distribution.

[0077] As a preferred implementation, the technical solution of the present invention can be implemented in a large commercial complex. The complex includes multiple floors of shopping areas, office areas, and an underground parking lot, with a total building area of approximately 100,000 square meters and a daily footfall of up to 50,000 person-times. First, approximately 1,000 sensors are installed in the building, including temperature sensors, smoke sensors, and infrared sensors. These sensors transmit data to the central processing system in real time via a 5G network, with a data update frequency of once per second. The central processing system uses deep learning algorithms to analyze the sensor data and predict fire and smoke spread. When a fire is detected, the system immediately activates the dynamic evacuation plan generation program. Three.js is used to create a 3D visualization model of the entire building. In the event of a fire, the system updates the 3D model in real time, marking the impassable areas in red and the potentially dangerous areas in yellow. The delay in this update process is no more than 100 milliseconds, ensuring the real-time nature of the information. The A* algorithm is used to recalculate the evacuation routes. The algorithm takes into account three main factors: distance, crowd density, and danger level, with weights of 0.4, 0.3, and 0.3 respectively. The system recalculates the global evacuation routes every 5 seconds to ensure the real-time optimization of the routes. The updated evacuation lines are matched with the BIM model through a GIS tool. The GIS system uses ESRI's ArcGIS platform, with an accuracy that can reach the centimeter level. This ensures a high degree of coincidence between the evacuation lines and the actual building structure. The final generated dynamic road network map contains multiple levels of information: main evacuation routes, alternative routes, danger area markings, and estimated congestion points. The system also generates specific evacuation instructions for different areas, such as "Please use the No. 1 safety staircase for evacuation in the north area of the 3rd floor", etc. Traditional evacuation systems usually rely on preset static routes and cannot adapt to the dynamic changes in emergency situations. In contrast, the present invention can adjust the evacuation strategy in a timely manner according to the actual situation through real-time data analysis and dynamic path planning. For example, some traditional systems may guide the crowd to an exit that has been blocked by the fire, while the system of the present invention can identify this situation in real time and re-plan a safe route.

[0078] In addition, the visualization systems in the prior art often only provide limited 2D floor plans and are difficult to intuitively display the three-dimensional structure of complex buildings. The 3D visualization model created by the present invention using Three.js technology can not only more clearly display the evacuation routes but also intuitively show the spatial distribution of dangerous areas, helping managers make more accurate decisions. In terms of algorithms, many existing systems only consider the shortest path and ignore factors such as crowd density and danger level. The improved A* algorithm adopted by the present invention comprehensively considers multiple factors and can generate safer and more efficient evacuation routes. This is particularly important in buildings with high floors or complex structures, which can effectively avoid congestion in certain areas and thus improve the overall evacuation efficiency.

[0079] Finally, the present invention precisely matches the evacuation routes with the BIM model through a GIS tool, overcoming the problem in traditional systems where the evacuation routes do not match the actual building structure. This high-precision matching ensures the accuracy and enforceability of evacuation instructions, reducing the chaos and misguidance that may occur in emergency situations.

[0080] Generally speaking, the present invention realizes a full-process dynamic evacuation system from data collection, analysis and processing to visual display, significantly improving the response ability of buildings in emergency situations and the level of personnel safety protection.

[0081] Embodiment 2

[0082] Figure 2 is a schematic structural diagram of a building dynamic evacuation road network generation system in Embodiment 2 of the present invention. As Figure 2 shown, Embodiment 2 provides a building dynamic evacuation road network generation system based on a BIM model, including: a module for constructing an initial road network framework, a module for generating road network data, a module for generating a preliminary evacuation road network, an update module, a module for generating an evacuation road network, a module for generating a visual three-dimensional road network map, and a module for generating an evacuation plan. The module for constructing an initial road network framework is used to obtain spatial layout data and multi-layer connection information from the building BIM model and construct an initial road network framework. The module for generating road network data is used to generate corrected road network data according to the initial road network framework and traffic restriction information. The module for generating a preliminary evacuation road network is used to calculate evacuation routes that meet the standards and generate a preliminary evacuation road network according to the corrected road network data and safety code requirements. The update module is used to obtain real-time data from sensors inside the building, judge the impact of dynamic changes on the preliminary evacuation road network, and update the information on non-passable areas. The module for generating an evacuation road network is used to recalculate evacuation routes according to the updated information on non-passable areas, adjust the preliminary evacuation road network, and generate an optimized evacuation road network. The module for generating a visual three-dimensional road network map is used to match the optimized evacuation road network with the building BIM model through three-dimensional digital twin technology and generate a visual three-dimensional road network map. And the module for generating an evacuation plan is used to dynamically update evacuation paths according to the visual three-dimensional road network map and real-time data streams and generate a final evacuation plan.

[0083] In this embodiment, the module for constructing the initial road network framework includes: a spatial layout data acquisition unit, a position relationship determination unit, a connection information extraction unit, a connection point data determination unit, a multi-layer road network structure construction unit, and an initial road network framework generation unit. The spatial layout data acquisition unit is used to parse the geometric structure from the building BIM model and obtain the spatial layout data of the walls and partitions. The position relationship determination unit is used to determine the position relationship between the walls and partitions according to the spatial layout data. The connection information extraction unit is used to extract the multi-layer connection information of the stairs, elevators, and corridors from the building BIM model. The connection point data determination unit is used to determine the connection point data according to the position relationship and the multi-layer connection information. The multi-layer road network structure construction unit is used to construct a multi-layer road network structure through the connection point data. The initial road network framework generation unit is used to optimize the multi-layer road network structure by using a genetic algorithm and generate the initial road network framework.

[0084] In this embodiment, the module for generating road network data includes: a spatial position relationship extraction unit, a marking unit, a road network structure generation unit, a connection point determination unit, a multi-layer road network framework construction unit, and a road network data generation unit. The spatial position relationship extraction unit is used to extract the spatial position relationship between the walls and partitions according to the initial road network framework. The marking unit is used to identify the passage restriction information through geometric analysis and mark the equipment installation area and the position of temporary obstacles. The road network structure generation unit is used to exclude the impassable area through a path planning tool and generate a corrected road network structure if there is an impassable area. The connection point determination unit is used to extract the multi-layer connection information from the corrected road network structure and determine the connection point data. The multi-layer road network framework construction unit is used to construct a corrected multi-layer road network framework through a network modeling tool. The road network data generation unit is used to adjust the corrected multi-layer road network framework by using a path optimization algorithm and generate the corrected road network data.

[0085] In this embodiment, the module for generating a preliminary evacuation road network includes: a determination unit, a calculation unit for evacuation routes, an extraction unit, a recalculation unit, and a determination unit for the preliminary evacuation road network. The determination unit is configured to determine the shortest path and the maximum evacuation time threshold based on the corrected road network data in combination with the evacuation requirements in safety specifications. The calculation unit for evacuation routes is configured to use the Dijkstra algorithm to calculate the evacuation routes that meet the standards according to the corrected road network data and the maximum evacuation time threshold. The extraction unit is configured to generate the preliminary evacuation road network according to the evacuation routes, and extract key nodes and connection relationships. The recalculation unit is configured to adjust the parameters of the Dijkstra algorithm and recalculate the evacuation routes if there are areas in the preliminary evacuation road network that do not meet the standards. The determination unit for the preliminary evacuation road network is configured to determine the final preliminary evacuation road network through iterative optimization.

[0086] In this embodiment, the update module includes: a real-time data acquisition unit, a calculation unit for the range and speed, a unit for judging the traffic capacity, a unit for marking impassable areas, and a unit for generating information on impassable areas. The real-time data acquisition unit is configured to acquire the real-time data of the sensors inside the building, and clean and standardize the real-time data. The calculation unit for the range and speed is configured to calculate the range and speed of the spread of fire or smoke according to the standardized real-time data. The unit for judging the traffic capacity is configured to judge whether the spread range exceeds the traffic capacity threshold according to the preset threshold rules. The unit for marking impassable areas is configured to mark the affected areas as impassable areas if the traffic capacity threshold is exceeded. The unit for generating information on impassable areas is configured to update the traffic status of the preliminary evacuation road network according to the impassable areas, and generate updated information on impassable areas.

[0087] In this embodiment, the module for generating an evacuation road network includes: a recalculation unit for evacuation routes, a unit for generating the road network layout, an information extraction unit, a layout adjustment unit, and a unit for generating the evacuation road network. The recalculation unit for evacuation routes is configured to recalculate the evacuation routes using the Dijkstra algorithm according to the updated information on impassable areas. The unit for generating the road network layout is configured to adjust the preliminary evacuation road network according to the recalculated evacuation routes, and generate a new road network layout. The information extraction unit is configured to extract the node position information from the new road network layout. The layout adjustment unit is configured to optimize the node position information through the K-means clustering algorithm and adjust the road network spatial layout. The unit for generating the evacuation road network is configured to generate an optimized evacuation road network according to the adjusted road network spatial layout.

[0088] In this embodiment, the generation of the visual three-dimensional road network map includes: a parsing unit, a dynamic update unit, a matching unit, a three-dimensional road network map generation unit, an adjustment unit, and a visual three-dimensional road network map generation unit. The parsing unit is used to obtain the real-time data of the sensors inside the building through the MQTT protocol and parse it into a format recognizable by the three-dimensional engine. The dynamic update unit is used to dynamically update the impassable areas in the building BIM model according to the parsed data. The matching unit is used to match the updated building BIM model with the optimized evacuation road network. The three-dimensional road network map generation unit is used to generate a three-dimensional road network map through Three.js. The adjustment unit is used to adopt the A* algorithm to adjust the evacuation routes in the three-dimensional road network map according to the real-time data. The visual three-dimensional road network map generation unit is used to optimize the spatial layout of the three-dimensional road network map through the random forest algorithm and generate a visual three-dimensional road network map.

[0089] In this embodiment, the evacuation plan generation module includes: an analysis unit, a range determination unit, a dynamic update area unit, a recalculation of evacuation routes unit, an evacuation line update unit, a dynamic road network map generation unit, and an evacuation plan generation unit. The analysis unit is used to obtain the real-time data of the sensors inside the building and analyze the fire and smoke diffusion situation. The range determination unit is used to determine the range of impassable areas according to the analysis result. The dynamic update area unit is used to dynamically update the impassable areas in the visual three-dimensional road network map through Three.js. The recalculation of evacuation routes unit is used to adopt the A* algorithm to recalculate the evacuation routes according to the updated visual three-dimensional road network map. The evacuation line update unit is used to update the evacuation lines inside the building according to the recalculated evacuation routes. The dynamic road network map generation unit is used to match the updated evacuation lines with the building BIM model through GIS tools and generate a dynamic road network map. The evacuation plan generation unit is used to generate a final evacuation plan according to the dynamic road network map.

[0090] All the various change methods and specific examples of the method for generating a dynamic evacuation road network of a building based on a BIM model provided in the first embodiment are equally applicable to the system for generating a dynamic evacuation road network of a building based on a BIM model provided in this embodiment. Through the foregoing detailed description of a method for generating a dynamic evacuation road network of a building based on a BIM model, those skilled in the art can clearly know the implementation manner of a system for generating a dynamic evacuation road network of a building based on a BIM model in this embodiment. Therefore, for the sake of brevity of the specification, it will not be elaborated here.

[0091] Embodiment Three

[0092] Figure 3 is a schematic structural diagram of an electronic device in the third embodiment of the present invention, as Figure 3As shown in the figure, Embodiment 3 further provides an electronic device 300, which may include: a processor 301 and a memory 302.

[0093] The memory 302 is used to store programs; the memory 302 may include a volatile memory (English: volatile memory), such as a random access memory (English: random-access memory, abbreviation: RAM), such as a static random access memory (English: static random-access memory, abbreviation: SRAM), a double data rate synchronous dynamic random access memory (English: Double Data Rate Synchronous Dynamic Random Access Memory, abbreviation: DDR SDRAM), etc.; the memory may also include a non-volatile memory (English: non-volatile memory), such as a flash memory (English: flash memory). The memory 302 is used to store computer programs (such as application programs and functional modules for implementing the above method), computer instructions, etc. The above computer programs, computer instructions, etc. may be partitioned and stored in one or more memories 302. And the above computer programs, computer instructions, data, etc. may be called by the processor 301.

[0094] The above computer programs, computer instructions, etc. may be partitioned and stored in one or more memories 302. And the above computer programs, computer data, etc. may be called by the processor 301.

[0095] The processor 301 is used to execute the computer programs stored in the memory 302 to implement each step in the method involved in the above embodiment.

[0096] Specifically, reference may be made to the relevant descriptions in the foregoing method embodiments.

[0097] The processor 301 and the memory 302 may be independent structures or integrated structures integrated together. When the processor 301 and the memory 302 are independent structures, the memory 302 and the processor 301 may be coupled and connected through a bus 303.

[0098] The electronic device in this embodiment may execute the technical solutions in the above method, and the specific implementation process and technical principle are the same, which will not be elaborated here.

[0099] Embodiment 4

[0100] Embodiment 4 also provides a computer-readable storage medium, including a computer program and instructions. When the computer program or instructions run on a computer, the computer is enabled to execute the method for generating a dynamic evacuation road network of a building based on a BIM model according to any embodiment of the present invention.

[0101] The computer-readable storage medium includes: various media such as USB flash drives, mobile hard disks, ROM, RAM, magnetic disks or optical discs that can store program codes.

[0102] This embodiment also provides a computer program product. The computer program product includes: a computer program. The computer program is stored in a readable storage medium. At least one processor of an electronic device can read the computer program from the readable storage medium, and the at least one processor executes the computer program to enable the electronic device to execute the solution provided in any of the above embodiments.

[0103] It should be understood that various forms of the flow shown above can be used, with steps reordered, added or deleted. For example, the steps described in the disclosure of the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution disclosed in the present invention can be achieved. No limitation is imposed herein.

[0104] Note that the above is only a preferred embodiment of the present invention and the applied technical principle. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein. Various obvious changes, re-adjustments and substitutions can be made by those skilled in the art without departing from the protection scope of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments. Without departing from the concept of the present invention, more other equivalent embodiments can be included, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A method for generating a dynamic evacuation road network of a building based on a BIM model, characterized in that, Including: Obtain spatial layout data and multi - layer connection information from the building BIM model, and construct an initial road network framework; Generate revised road network data according to the initial road network framework and traffic restriction information; Calculate compliant evacuation routes according to the revised road network data and safety code requirements, and generate a preliminary evacuation road network; Obtain real - time data of internal sensors in the building, judge the impact of dynamic changes on the preliminary evacuation road network, and update the information of impassable areas; Recalculate the evacuation routes according to the updated information of impassable areas, adjust the preliminary evacuation road network, and generate an optimized evacuation road network; Match the optimized evacuation road network with the building BIM model through three - dimensional digital twin technology to generate a visualized three - dimensional road network map; Dynamically update the evacuation path according to the visualized three - dimensional road network map and real - time data stream to generate a final evacuation plan.

2. The method for generating a dynamic evacuation road network of a building based on a BIM model according to claim 1, wherein The obtaining spatial layout data and multi - layer connection information from the building BIM model and constructing an initial road network framework includes: Parse the geometric structure from the building BIM model to obtain the spatial layout data of walls and partitions; Determine the positional relationship of the walls and partitions according to the spatial layout data; Extract the multi - layer connection information of stairs, elevators and corridors from the building BIM model; Determine connection point data according to the positional relationship and the multi - layer connection information; Construct a multi - layer road network structure through the connection point data; Optimize the multi - layer road network structure by using a genetic algorithm to generate the initial road network framework.

3. The method for generating a dynamic evacuation road network of a building based on a BIM model according to claim 1, characterized in that, The generating revised road network data according to the initial road network framework and traffic restriction information includes: Extract the spatial positional relationship of walls and partitions according to the initial road network framework; Identify traffic restriction information through geometric analysis, and mark the equipment installation area and the location of temporary obstacles; If there are impassable areas, exclude the impassable areas through a path planning tool to generate a revised road network structure; Extract the multi - layer connection information from the revised road network structure to determine connection point data; Construct a revised multi - layer road network framework through a network modeling tool; Adjust the revised multi - layer road network framework by using a path optimization algorithm to generate the revised road network data.

4. The method for generating a dynamic evacuation road network of a building based on a BIM model according to claim 1, wherein The calculating compliant evacuation routes according to the revised road network data and safety code requirements and generating a preliminary evacuation road network includes: Based on the revised road network data, combined with the evacuation requirements in the safety code, determine the shortest path and the maximum evacuation time threshold; Use the Dijkstra algorithm to calculate compliant evacuation routes according to the revised road network data and the maximum evacuation time threshold; Generate the preliminary evacuation road network according to the evacuation routes, and extract key nodes and connection relationships; If there are areas in the preliminary evacuation road network that do not meet the standards, adjust the parameters of the Dijkstra algorithm and recalculate the evacuation routes; Determine the final preliminary evacuation road network through iterative optimization.

5. The method for generating a dynamic evacuation road network of a building based on a BIM model according to claim 1, characterized in that The obtaining real - time data of internal sensors in the building, judging the impact of dynamic changes on the preliminary evacuation road network, and updating the information of impassable areas includes: Obtain real-time data of sensors inside the building, clean and standardize the real-time data; Calculate the scope and speed of fire or smoke spread based on the standardized real-time data; Judge whether the spread scope exceeds the traffic capacity threshold according to the preset threshold rules; If it exceeds the traffic capacity threshold, mark the affected area as an impassable area; Update the traffic status of the preliminary evacuation road network according to the impassable area, and generate updated impassable area information.

6. The method for generating a dynamic evacuation road network of a building based on a BIM model according to claim 1, wherein, The generating an optimized evacuation road network by recalculating the evacuation route and adjusting the preliminary evacuation road network according to the updated impassable area information includes: Recalculate the evacuation route using the Dijkstra algorithm according to the updated impassable area information; Adjust the preliminary evacuation road network according to the recalculated evacuation route to generate a new road network layout; Extract node position information from the new road network layout; Optimize the node position information through the K-means clustering algorithm and adjust the road network spatial layout; Generate an optimized evacuation road network according to the adjusted road network spatial layout.

7. The method for generating a dynamic evacuation road network of a building based on a BIM model according to claim 1, wherein The generating a visual three-dimensional road network map by matching the optimized evacuation road network with the building BIM model through three-dimensional digital twin technology includes: Obtain real-time data of sensors inside the building through the MQTT protocol and parse it into a format recognizable by the three-dimensional engine; Dynamically update the impassable area in the building BIM model according to the parsed data; Match the updated building BIM model with the optimized evacuation road network; Generate a three-dimensional road network map through Three.js; Adjust the evacuation route in the three-dimensional road network map according to the real-time data using the A* algorithm; Optimize the spatial layout of the three-dimensional road network map through the random forest algorithm to generate a visual three-dimensional road network map.

8. A building dynamic evacuation road network generation system based on a BIM model, characterized in that, Includes: Construct an initial road network framework module for obtaining spatial layout data and multi-layer connection information from the building BIM model and constructing an initial road network framework; Generate road network data module for generating corrected road network data according to the initial road network framework and traffic restriction information; Generate a preliminary evacuation road network module for calculating evacuation routes that meet the standards and generating a preliminary evacuation road network according to the corrected road network data and safety code requirements; Update module for obtaining real-time data of sensors inside the building, judging the impact of dynamic changes on the preliminary evacuation road network, and updating the impassable area information; Generate an evacuation road network module for recalculating the evacuation route and adjusting the preliminary evacuation road network according to the updated impassable area information to generate an optimized evacuation road network; Generate a visual three-dimensional road network map for matching the optimized evacuation road network with the building BIM model through three-dimensional digital twin technology to generate a visual three-dimensional road network map; Generate an evacuation plan module for dynamically updating the evacuation path according to the visual three-dimensional road network map and real-time data stream to generate a final evacuation plan.

9. An electronic device, characterized in that, Includes: At least one processor; And A memory communicatively connected to the at least one processor; Among them, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method for generating a dynamic evacuation road network of a building based on a BIM model according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It includes a computer program and instructions, and when the computer program or the instructions run on a computer, the computer is caused to execute the method for generating a dynamic evacuation road network of a building based on a BIM model according to any one of claims 1-7.

Images