Emergency evacuation path planning method and system and storage medium

Abstract

The invention relates to the technical field of path planning, in particular to an emergency evacuation path planning method and system and a storage medium. The method comprises the following steps: obtaining building layout data; performing building structure topology analysis on the building layout data to generate building structure layout data; arranging monitoring equipment according to the building structure layout data to obtain monitoring equipment deployment data; performing environment perception on the monitoring equipment based on the monitoring equipment deployment data so as to generate environment perception data; performing static image acquisition on the environment sensing data to obtain a static environment image; performing channel connection on the static environment image to generate building channel distribution data; and performing potential dangerous channel area identification on the building channel distribution data through the static environment image to generate potential dangerous channel area data. According to the invention, by integrating environment perception, dynamic video stream analysis and intelligent path scheduling, the flexibility and accuracy of emergency evacuation path planning are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to an emergency evacuation path planning method, system and storage medium. Background Art

[0002] Early evacuation planning mainly relied on manual design and empirical judgment to develop simple escape routes for buildings or public places. This method is effective in small-scale events, but with the increase in population density and the complexity of buildings, traditional methods are difficult to cope with the diverse dangers that arise in emergencies. Entering the 21st century, the advancement of computer technology has driven the intelligent development of emergency evacuation path planning. Models based on graph theory and shortest path algorithms have begun to be applied to evacuation path optimization, which can dynamically generate effective escape routes in complex buildings. With the development of sensor networks and Internet of Things technologies, real-time data collection and processing capabilities have been greatly improved, and path planning algorithms can be combined with real-time environmental information for more accurate planning. In addition, the introduction of simulation technology has made emergency drills closer to actual scenarios and improved the reliability of planning schemes. However, traditional methods are usually based on preset building layouts and simple shortest path algorithms, lacking dynamic adjustment capabilities. At the same time, traditional path planning is difficult to flexibly respond to abnormal events during the evacuation process, such as fire spread or building damage, which leads to low flexibility and accuracy in emergency evacuation path planning. Summary of the invention

[0003] Based on this, it is necessary to provide an emergency evacuation route planning method, system and storage medium to solve at least one of the above technical problems.

[0004] To achieve the above object, a method for emergency evacuation route planning is provided, the method comprising the following steps: Step S1: Acquire building layout data; perform building structure topology analysis on the building layout data to generate building structure layout data; arrange monitoring equipment according to the building structure layout data to obtain monitoring equipment deployment data; perform environmental perception on the monitoring equipment based on the monitoring equipment deployment data to generate environmental perception data; Step S2: performing static image acquisition on the environmental perception data to obtain a static environmental image; performing channel connection on the static environmental image to generate building channel distribution data; performing potential dangerous channel area identification on the building channel distribution data through the static environmental image to generate potential dangerous channel area data; performing channel area path annotation on the building channel distribution data according to the potential dangerous channel area data to generate dangerous channel path annotation data; Step S3: Perform initial evacuation path planning on the building channel distribution data according to the dangerous channel path annotation data to generate initial emergency evacuation planning path data; perform dynamic video stream acquisition on the environmental perception data to obtain the environmental perception dynamic video stream; simulate the channel crowd flow situation on the environmental perception dynamic video stream to generate channel crowd flow simulation data; perform multi-dimensional real-time evacuation demand analysis on the channel crowd flow simulation data to generate real-time evacuation demand data; use the real-time evacuation demand data to sort the path priorities of the initial emergency evacuation planning path data to generate an initial evacuation path scheduling strategy; Step S4: Perform emergency path scheduling simulation on the initial emergency evacuation planning path data according to the initial evacuation path scheduling strategy to generate emergency route scheduling simulation data; perform abnormal event path scheduling adjustment on the emergency route scheduling simulation data to generate abnormal event dynamic path scheduling data; perform intelligent route scheduling instruction distribution on the initial emergency evacuation planning path data according to the emergency route scheduling simulation data and the abnormal event dynamic path scheduling data to generate distributed emergency evacuation instructions to execute emergency evacuation operations.

[0005] The present invention lays a foundation for subsequent analysis and planning by acquiring building layout data, ensures that subsequent work is carried out on accurate building information, generates building structure layout data, makes the layout of monitoring equipment more scientific and reasonable, and optimizes monitoring coverage and efficiency. The monitoring equipment is arranged based on the building structure layout data, which can ensure that all important areas are fully monitored, thereby improving the comprehensiveness and accuracy of environmental perception. Through the environmental perception function of the monitoring equipment, the environmental data inside the building can be obtained in real time, providing necessary information support for subsequent static and dynamic analysis. Static environmental image acquisition provides basic data for static environmental images, which are crucial for subsequent channel connection and potential danger identification. By connecting the static environmental images to channels, the generated building channel distribution data helps to understand the layout of the internal channels of the building and provides a structural basis for evacuation planning. By identifying the potential dangerous channel area, the area that threatens the evacuation can be discovered in advance, which helps to take preventive measures in an emergency. The path of the potential dangerous area is marked, and the generated dangerous channel path marking data provides key information for subsequent evacuation path planning and optimization, ensuring the effectiveness and safety of the evacuation plan. According to the path annotation data of dangerous passages, the initial evacuation path planning is carried out on the building channel distribution data, and the generated initial emergency evacuation planning path data provides the basic path for the actual evacuation operation. Through the acquisition of dynamic video streams, the density and dynamic changes of human flow can be obtained in real time, which is helpful to understand the actual evacuation situation and needs. The human flow situation is simulated and the channel human flow simulation data is generated, which is helpful to analyze the flow of personnel and optimize the evacuation strategy. By performing multi-dimensional real-time evacuation demand analysis on the channel human flow simulation data, real-time evacuation demand data is generated, so that the evacuation path can be dynamically adjusted according to actual needs. The initial evacuation path is prioritized by using the real-time evacuation demand data, and the initial evacuation path scheduling strategy is generated to ensure that the priority and order of evacuation in an emergency are optimized. By simulating the initial emergency evacuation planning path data, the effectiveness of different paths can be evaluated, possible problems can be predicted, and the evacuation path can be optimized. The path scheduling adjustment is carried out for abnormal events in the simulation data, and the abnormal event dynamic path scheduling data is generated, so that the evacuation path can be dynamically adjusted according to abnormal conditions, improving the ability to deal with emergencies. By performing intelligent path scheduling updates on the initial emergency evacuation planning path data and generating distributed emergency evacuation instructions, real-time path updates and rapid instruction distribution are achieved, ensuring that all participants can receive the latest instructions during the actual evacuation process, thereby improving evacuation efficiency and safety. Therefore, the present invention improves the flexibility and accuracy of emergency evacuation path planning by integrating environmental perception, dynamic video stream analysis, and intelligent path scheduling.

[0006] Preferably, step S1 comprises the following steps: Step S11: Acquire building layout data; Step S12: performing a building structure topology analysis on the building layout data to generate building structure layout data; performing a field of view width analysis on the building layout data according to the building structure layout data to generate building field of view width data; Step S13: arranging monitoring equipment for the building structure layout data by using the building field of view width data to obtain monitoring equipment deployment data; confirming the monitoring node position based on the monitoring equipment deployment data to obtain monitoring equipment node position data; Step S14: Perform environmental perception on the monitoring device based on the node location data of the monitoring device, thereby generating environmental perception data.

[0007] The present invention can ensure that the deployment of monitoring equipment takes into account the structural characteristics and spatial layout of the building through the building structure topology analysis and the field of view width analysis in step S12, thereby avoiding blind spots and improving monitoring coverage. Step S13 arranges monitoring equipment based on the field of view width data, so that the monitoring equipment can cover important areas more effectively, and the confirmation of node locations helps to improve the overall efficiency and reliability of the monitoring system. Step S14 can monitor environmental changes in real time, improve the system's ability to respond to external factors, and enhance safety management by performing environmental perception on the monitoring equipment. The logical design of the entire step chain helps to optimize the design of the monitoring system in the early stages, provide data support for the subsequent deployment and operation of monitoring equipment, and ensure that the entire system performs well in actual operation.

[0008] Preferably, step S2 comprises the following steps: Step S21: performing static image acquisition on the environmental perception data to obtain a static environmental image; performing image preprocessing on the static environmental image to generate a standard static environmental image, wherein the image preprocessing includes image filtering, image brightness enhancement and image grayscale value transformation; Step S22: performing channel contour segmentation on the static environment image to obtain a channel contour segmentation image; performing channel connection based on the channel contour segmentation image to generate building channel distribution data; Step S23: identifying potential dangerous passage areas on the building passage distribution data through a static environment image to generate potential dangerous passage area data; Step S24: annotating the building channel distribution data with channel area paths according to the potential dangerous channel area data to generate dangerous channel path annotation data.

[0009] The present invention can effectively improve the quality of static environmental images through image preprocessing (including filtering, brightness enhancement and grayscale value conversion) in step S21, provide a more accurate data basis for subsequent analysis, and ensure the accuracy of environmental perception. Through channel contour segmentation and channel connection, the distribution data of the building channel is generated, which provides a clear channel structure for the subsequent identification of dangerous areas and ensures the accurate expression of the building channel layout. By identifying the potential dangerous channel area through static environmental images, areas with safety hazards can be discovered in advance, thereby providing early warning information for building safety management and improving the overall safety level. The channel path is marked according to the identified potential dangerous area data to generate dangerous channel path marking data. This helps to quickly identify and avoid dangerous areas in emergency situations and ensure the safety of personnel evacuation paths. The design of the entire step chain is intended to improve the safety management capabilities within the building through refined data analysis and marking, so that preventive measures can be taken before potential dangers occur to reduce accident risks.

[0010] Preferably, step S23 includes the following steps: Step S231: extracting the channel space structure of the static environment image to generate channel space structure data; analyzing the channel obstacle distribution of the static environment image to generate channel obstacle distribution data; Step S232: performing a channel narrow distance variation analysis on the channel spatial structure data to generate channel narrow distance variation data; performing an obstacle multi-dimensional risk factor analysis on the channel obstacle distribution data to generate obstacle risk factor data, wherein the obstacle multi-dimensional risk factor analysis includes an obstruction risk factor analysis and an obstacle component risk factor analysis; Step S233: calculating the passage difficulty index for the building passage distribution data by using the obstacle risk factor data and the passage narrow distance variation data to obtain the passage difficulty index; Step S234: Based on the comparison between the passage difficulty index and the preset passage difficulty index threshold, when the passage difficulty index is greater than or equal to the preset passage difficulty index threshold, the corresponding building passage is marked as a potentially dangerous passage, thereby generating potentially dangerous passage area data.

[0011] By extracting the spatial structure of the channel and analyzing the distribution of obstacles, the present invention can fully understand the physical layout of the channel and the obstacles it has, thereby providing detailed basic data for subsequent risk assessment and index calculation. The analysis of the narrow distance change of the channel can identify the narrow areas in the channel that cause difficulty in passing; the multi-dimensional risk factor analysis of obstacles (including obstruction risk and component risk) can accurately assess the potential danger of obstacles. These analyses provide multi-level assessment dimensions for channel safety and ensure the comprehensiveness of risk assessment. By integrating the narrow distance change data and the obstacle risk factor data, the difficulty index of the channel is calculated to quantify the difficulty of passing the channel. This quantitative method helps to more clearly identify the potential risks in the channel. By comparing with the preset difficulty index threshold, the channels that are difficult to pass or have high risks are marked to generate data on potential dangerous channel areas. This process ensures that only channels that reach a certain risk level will be marked as dangerous areas, avoiding excessive marking and misjudgment. The entire step chain is reasonably designed and the data analysis is comprehensive, which can provide a scientific decision-making basis for the safety management of building channels and improve management efficiency. By marking and warning of potentially dangerous passages, preventive measures can be taken in advance to reduce safety hazards.

[0012] Preferably, step S3 comprises the following steps: Step S31: Performing initial evacuation path planning on the building channel distribution data according to the dangerous channel path annotation data to generate initial emergency evacuation planning path data; Step S32: performing dynamic video stream acquisition on the environment perception data to obtain an environment perception dynamic video stream; performing crowd density change analysis on the environment perception dynamic video stream to generate crowd density change data; Step S33: simulating the channel crowd flow situation of the building channel distribution data through the crowd density change data to generate channel crowd flow simulation data; performing channel capacity analysis on the building channel distribution data according to the channel crowd flow simulation data to generate channel capacity analysis data; Step S34: Use the channel capacity analysis data to perform multi-dimensional real-time evacuation demand analysis on the crowd density change data to generate real-time evacuation demand data; use the real-time evacuation demand data to sort the path priorities of the initial emergency evacuation planning path data to generate an initial evacuation path scheduling strategy.

[0013] The present invention performs initial evacuation path planning based on the path marking data of dangerous channels, and can reasonably plan a preliminary emergency evacuation path on the basis of the marking of dangerous areas. This provides a basic and operational framework for the entire evacuation process, ensuring the scientific nature of the evacuation planning. Through the dynamic video stream acquisition of environmental perception data and the analysis of crowd density changes, the distribution and changes of the crowd in the building can be understood in real time. This enables the evacuation planning to adapt to the actual situation in a timely manner and avoid crowd congestion and chaos during the evacuation process. Through the simulation of the flow of people, the load conditions of different channels during the evacuation process can be predicted, and the channel capacity analysis can be performed. This process ensures an accurate assessment of the channel load capacity, thereby avoiding exceeding the channel load limit during the evacuation process. Using the channel capacity analysis data and the real-time evacuation demand data, the initial evacuation path is prioritized and the scheduling strategy is optimized. This process ensures that in an emergency, the evacuation path can be adjusted according to the real-time situation, giving priority to evacuating crowded areas, and ensuring the safety of the crowd to the greatest extent. Through the dynamic adjustment and optimization of the evacuation path, step S3 ensures that the evacuation process in an emergency is both safe and efficient, and can effectively reduce casualties and property losses.

[0014] Preferably, step S34 includes the following steps: Step S341: using an infrared camera to collect temperature change data on crowd density change data to obtain crowd temperature change data; performing fast Fourier transform on the crowd temperature change data to generate crowd temperature change frequency data; performing dynamic psychological stress assessment based on the crowd temperature change frequency data to generate crowd psychological stress assessment data; Step S342: using environmental sensors to monitor environmental variables on the channel capacity analysis data to obtain environmental variable monitoring data, wherein the environmental variable monitoring includes temperature monitoring, humidity monitoring, and smoke concentration monitoring; performing evacuation channel feasibility analysis on the channel capacity analysis data using the environmental variable monitoring data to generate channel feasibility scoring data; Step S343: dynamically calculating the evacuation demand based on the crowd psychological stress assessment data and the channel feasibility score data based on the Bayesian network algorithm to generate real-time evacuation demand data; Step S344: using the real-time evacuation demand data to sort the path priority of the initial emergency evacuation planning path data, and generating evacuation priority sorting data; using the evacuation priority sorting data to sort the path priority of the initial emergency evacuation planning path data, and generating an initial evacuation path scheduling strategy.

[0015] The present invention collects temperature change data of the crowd through an infrared camera, and combines fast Fourier transform to perform frequency analysis, thereby evaluating the psychological pressure of the crowd. This process helps to identify the psychological stress response that occurs in an emergency situation, and is helpful to formulate a more humane evacuation strategy. Environmental sensors are used to monitor environmental variables such as temperature, humidity and smoke concentration, and the feasibility analysis of channel capacity is performed through these data. This process ensures that the channel environment is suitable for evacuation during the evacuation process, avoiding evacuation failure or casualties due to environmental discomfort. Based on the Bayesian network algorithm, the crowd psychological pressure assessment data is combined with the channel feasibility score data to perform dynamic calculation of evacuation needs. Through this process, the evacuation strategy can be adjusted in real time to ensure that personnel are evacuated under optimal conditions and to maximize personnel safety. The initial evacuation path is prioritized using real-time evacuation demand data, and the generated evacuation priority ranking data ensures that in an emergency situation, people in high-risk or high-density areas are evacuated with the highest priority. By dynamically adjusting the evacuation path, the blindness and irrationality of path selection are avoided, and the evacuation efficiency is improved. The entire process generates a more intelligent and optimized evacuation route scheduling strategy through multi-dimensional data analysis and dynamic adjustment, which can meet the evacuation needs in different situations. The implementation of this strategy helps to respond quickly in emergency situations, improve overall evacuation efficiency, and reduce casualties.

[0016] Preferably, step S4 comprises the following steps: Step S41: performing emergency path scheduling simulation on the initial emergency evacuation planning path data according to the initial evacuation path scheduling strategy to generate emergency route scheduling simulation data; Step S42: performing abnormal event analysis on the emergency route scheduling simulation data to generate abnormal scheduling event data; performing path scheduling adjustment on the emergency route scheduling simulation data according to the abnormal scheduling event data to generate abnormal event dynamic path scheduling data; Step S43: Integrate the abnormal event dynamic path scheduling data and the emergency route scheduling simulation data to generate route scheduling simulation comprehensive data; divide the route scheduling simulation comprehensive data into data sets to generate a model training set and a model test set; use a decision tree algorithm to perform model training on the model training set to generate a route scheduling decision pre-model; Step S44: performing model optimization iteration on the route scheduling decision pre-model through the model test set, thereby generating a route scheduling decision model; using the route scheduling decision model to perform intelligent emergency path scheduling update on the initial emergency evacuation planning path data, and generating dynamic emergency evacuation path update data; Step S45: Distribute the dynamic emergency evacuation path update data through the distributed network to generate distributed emergency evacuation instructions to execute emergency evacuation operations.

[0017] The present invention can pre-rehearse the evacuation scenario in advance by simulating the emergency path scheduling of the initial emergency evacuation planning path data, and the generated simulation data provides an accurate basis for subsequent scheduling optimization and exception handling. This simulation process helps identify potential problems, thereby ensuring that the implementation of the evacuation plan is more reliable. By analyzing the simulation data for abnormal events, various emergencies that occur during the evacuation process can be discovered and handled in a timely manner, and the path scheduling can be adjusted according to these abnormal events. This process ensures the flexibility of the evacuation plan and the ability to deal with emergencies, greatly reducing the uncertainty in the evacuation process. The abnormal event data and the simulation data are integrated, and the training set is model trained through the decision tree algorithm to generate a route scheduling decision pre-model. This data-driven model training method improves the intelligence of evacuation path decision-making and can better adapt to complex evacuation needs. The decision pre-model is optimized and iterated through the model test set to generate a final route scheduling decision model, and the evacuation path is intelligently scheduled and updated using the model. This process realizes real-time optimization of path planning, ensuring that the evacuation path can be adjusted in time with changes in actual conditions, thereby improving evacuation efficiency. The updated evacuation route is distributed through the distributed network to ensure that each evacuation node can quickly respond and execute the updated evacuation instructions. The use of this distributed network improves the speed and efficiency of instruction transmission and ensures the smooth progress of evacuation operations.

[0018] Preferably, step S42 includes the following steps: Step S421: performing abnormal event analysis on the emergency route scheduling simulation data to generate scheduling abnormal event data, wherein the scheduling abnormal event data includes personnel abnormal event data and channel abnormal event data; Step S422: when it is confirmed that the abnormal scheduling event data is abnormal personnel event data, human behavior analysis is performed on the abnormal personnel event data to generate abnormal personnel behavior analysis data; emergency evacuation speed assessment is performed on the abnormal personnel event data through the abnormal personnel behavior analysis data to obtain abnormal personnel evacuation assessment data; Step S423: When it is confirmed that the scheduling abnormal event data is channel abnormal event data, an abnormal event impact analysis is performed on the channel abnormal event data to generate channel abnormal impact analysis data; emergency evacuation safety assessment is performed on the channel abnormal event data through the channel abnormal impact analysis data to obtain abnormal channel evacuation safety assessment data; Step S424: Based on the abnormal personnel evacuation assessment data and the abnormal channel evacuation safety assessment data, the emergency route scheduling simulation data is reallocated to adjacent shortest paths to generate abnormal event dynamic path scheduling data.

[0019] The present invention subdivides abnormal event data into personnel abnormal event data and channel abnormal event data, and performs targeted analysis respectively. This classification processing method improves the accuracy of abnormal event analysis and ensures that different types of abnormal events can be processed accordingly. By performing human behavior analysis on personnel abnormal events, personnel abnormal behavior analysis data is generated. This in-depth analysis can identify abnormal situations of personnel behavior during evacuation, such as panic, hysteresis, etc., and provides accurate data support for emergency decision-making by evaluating the evacuation speed of abnormal personnel. Impact analysis is performed on channel abnormal event data to generate channel abnormal impact analysis data, and safety assessment is performed through the data. This process helps identify the potential threat of channel abnormality to the evacuation path, and provides safety assessment results to ensure that the feasibility and safety of the channel are fully considered under abnormal circumstances. Based on abnormal personnel evacuation assessment data and abnormal channel evacuation safety assessment data, adjacent shortest paths are redistributed for emergency route scheduling simulation data to generate abnormal event dynamic path scheduling data. This process not only ensures the flexible adjustment of the evacuation path under abnormal circumstances, but also optimizes the efficiency and safety of the evacuation path through the redistribution of adjacent shortest paths. Through detailed analysis and evaluation of abnormal events, step S42 ensures the accuracy and real-time nature of emergency evacuation decisions. The generation and application of abnormal event dynamic path scheduling data enables the evacuation path to respond to changes in on-site conditions in a timely manner, thereby ensuring personnel safety to the greatest extent possible.

[0020] In this specification, an emergency evacuation path planning system is provided, which is used to execute the above-mentioned emergency evacuation path planning method, and the emergency evacuation path planning system includes: The monitoring module is used to obtain building layout data; perform building structure topology analysis on the building layout data to generate building structure layout data; arrange monitoring equipment according to the building structure layout data to obtain monitoring equipment deployment data; perform environmental perception on the monitoring equipment based on the monitoring equipment deployment data to generate environmental perception data; The dangerous area identification module is used to collect static images of environmental perception data to obtain static environmental images; connect channels of the static environmental images to generate building channel distribution data; identify potential dangerous channel areas of the building channel distribution data through the static environmental images to generate potential dangerous channel area data; annotate the channel area paths of the building channel distribution data according to the potential dangerous channel area data to generate dangerous channel path annotation data; The path scheduling module is used to perform initial evacuation path planning on the building channel distribution data according to the dangerous channel path annotation data, and generate initial emergency evacuation planning path data; perform dynamic video stream acquisition on the environmental perception data to obtain the environmental perception dynamic video stream; simulate the channel crowd flow situation on the environmental perception dynamic video stream to generate channel crowd flow simulation data; perform multi-dimensional real-time evacuation demand analysis on the channel crowd flow simulation data to generate real-time evacuation demand data; use the real-time evacuation demand data to sort the path priority of the initial emergency evacuation planning path data, and generate the initial evacuation path scheduling strategy; The scheduling decision module is used to perform emergency path scheduling simulation on the initial emergency evacuation planning path data according to the initial evacuation path scheduling strategy to generate emergency route scheduling simulation data; perform abnormal event path scheduling adjustment on the emergency route scheduling simulation data to generate abnormal event dynamic path scheduling data; perform intelligent route scheduling instruction distribution on the initial emergency evacuation planning path data according to the emergency route scheduling simulation data and the abnormal event dynamic path scheduling data to generate distributed emergency evacuation instructions to execute emergency evacuation operations.

[0021] A computer-readable storage medium stores a computer program, which, when executed, implements any one of the emergency evacuation route planning methods described above.

[0022] The beneficial effect of the present invention is that by analyzing the building layout data and deploying monitoring equipment, the structure and potential dangerous areas inside the building can be fully understood. This detailed monitoring data helps to identify and mark dangerous passages, thereby improving the safety of the building. The combination of static and dynamic environmental perception data can generate more accurate evacuation path planning. This path planning takes into account the actual channel flow and potential dangerous areas, so that people can be more effectively guided to evacuate. The analysis of dynamic video streams and the generation of real-time evacuation demand data make emergency response more flexible and timely. The evacuation path can be adjusted according to real-time data to improve the effect of emergency handling. Based on emergency path scheduling simulation and abnormal event path adjustment, the generated intelligent route scheduling instructions can optimize the distribution of emergency evacuation instructions, thereby making the entire evacuation process more efficient and orderly. Through environmental perception data and simulation analysis, data-driven decisions can be generated to help improve the emergency management level of buildings in emergencies and reduce potential safety hazards. This process improves the ability of buildings to respond to emergencies and enhances the safety of personnel through multi-dimensional analysis and optimization of emergency evacuation paths. Therefore, the present invention improves the flexibility and accuracy of emergency evacuation route planning by integrating environmental perception, dynamic video stream analysis and intelligent route scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 A schematic diagram of the steps of an emergency evacuation route planning method; Figure 2 for Figure 1 Detailed implementation steps of step S2 in the flowchart; Figure 3 for Figure 1 Detailed implementation steps of step S3 in FIG. The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0024] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0025] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0026] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0027] To achieve this, please refer to Figures 1 to 3 , an emergency evacuation path planning method, the method comprising the following steps: Step S1: Acquire building layout data; perform building structure topology analysis on the building layout data to generate building structure layout data; arrange monitoring equipment according to the building structure layout data to obtain monitoring equipment deployment data; perform environmental perception on the monitoring equipment based on the monitoring equipment deployment data to generate environmental perception data; Step S2: performing static image acquisition on the environmental perception data to obtain a static environmental image; performing channel connection on the static environmental image to generate building channel distribution data; performing potential dangerous channel area identification on the building channel distribution data through the static environmental image to generate potential dangerous channel area data; performing channel area path annotation on the building channel distribution data according to the potential dangerous channel area data to generate dangerous channel path annotation data; Step S3: Perform initial evacuation path planning on the building channel distribution data according to the dangerous channel path annotation data to generate initial emergency evacuation planning path data; perform dynamic video stream acquisition on the environmental perception data to obtain the environmental perception dynamic video stream; simulate the channel crowd flow situation on the environmental perception dynamic video stream to generate channel crowd flow simulation data; perform multi-dimensional real-time evacuation demand analysis on the channel crowd flow simulation data to generate real-time evacuation demand data; use the real-time evacuation demand data to sort the path priorities of the initial emergency evacuation planning path data to generate an initial evacuation path scheduling strategy; Step S4: Perform emergency path scheduling simulation on the initial emergency evacuation planning path data according to the initial evacuation path scheduling strategy to generate emergency route scheduling simulation data; perform abnormal event path scheduling adjustment on the emergency route scheduling simulation data to generate abnormal event dynamic path scheduling data; perform intelligent route scheduling instruction distribution on the initial emergency evacuation planning path data according to the emergency route scheduling simulation data and the abnormal event dynamic path scheduling data to generate distributed emergency evacuation instructions to execute emergency evacuation operations.

[0028] The present invention lays a foundation for subsequent analysis and planning by acquiring building layout data, ensures that subsequent work is carried out on accurate building information, generates building structure layout data, makes the layout of monitoring equipment more scientific and reasonable, and optimizes monitoring coverage and efficiency. The monitoring equipment is arranged based on the building structure layout data, which can ensure that all important areas are fully monitored, thereby improving the comprehensiveness and accuracy of environmental perception. Through the environmental perception function of the monitoring equipment, the environmental data inside the building can be obtained in real time, providing necessary information support for subsequent static and dynamic analysis. Static environmental image acquisition provides basic data for static environmental images, which are crucial for subsequent channel connection and potential danger identification. By connecting the static environmental images to channels, the generated building channel distribution data helps to understand the layout of the internal channels of the building and provides a structural basis for evacuation planning. By identifying the potential dangerous channel area, the area that threatens the evacuation can be discovered in advance, which helps to take preventive measures in an emergency. The path of the potential dangerous area is marked, and the generated dangerous channel path marking data provides key information for subsequent evacuation path planning and optimization, ensuring the effectiveness and safety of the evacuation plan. According to the path annotation data of dangerous passages, the initial evacuation path planning is carried out on the building channel distribution data, and the generated initial emergency evacuation planning path data provides the basic path for the actual evacuation operation. Through the acquisition of dynamic video streams, the density and dynamic changes of human flow can be obtained in real time, which is helpful to understand the actual evacuation situation and needs. The human flow situation is simulated and the channel human flow simulation data is generated, which is helpful to analyze the flow of personnel and optimize the evacuation strategy. By performing multi-dimensional real-time evacuation demand analysis on the channel human flow simulation data, real-time evacuation demand data is generated, so that the evacuation path can be dynamically adjusted according to actual needs. The initial evacuation path is prioritized by using the real-time evacuation demand data, and the initial evacuation path scheduling strategy is generated to ensure that the priority and order of evacuation in an emergency are optimized. By simulating the initial emergency evacuation planning path data, the effectiveness of different paths can be evaluated, possible problems can be predicted, and the evacuation path can be optimized. The path scheduling adjustment is carried out for abnormal events in the simulation data, and the abnormal event dynamic path scheduling data is generated, so that the evacuation path can be dynamically adjusted according to abnormal conditions, improving the ability to deal with emergencies. By performing intelligent path scheduling updates on the initial emergency evacuation planning path data and generating distributed emergency evacuation instructions, real-time path updates and rapid instruction distribution are achieved, ensuring that all participants can receive the latest instructions during the actual evacuation process, thereby improving evacuation efficiency and safety. Therefore, the present invention improves the flexibility and accuracy of emergency evacuation path planning by integrating environmental perception, dynamic video stream analysis, and intelligent path scheduling.

[0029] In the embodiment of the present invention, reference Figure 1The above is a schematic diagram of the steps of an emergency evacuation path planning method of the present invention. In this example, the emergency evacuation path planning method includes the following steps: Step S1: Acquire building layout data; perform building structure topology analysis on the building layout data to generate building structure layout data; arrange monitoring equipment according to the building structure layout data to obtain monitoring equipment deployment data; perform environmental perception on the monitoring equipment based on the monitoring equipment deployment data to generate environmental perception data; In an embodiment of the present invention, building layout data is obtained through architectural design drawings, laser scanning, photogrammetry or BIM (Building Information Model) system, including information such as the floor plan, elevation, structural hierarchy, room function distribution, entrance and exit locations, etc. of the building. The building layout data is analyzed using a topological analysis algorithm to construct a topological structure model of the building. This model describes the connection relationship between the various spaces in the building, such as the interconnection between rooms, floors, and corridors. The topological structure model is converted into a graphical representation, such as a graph of nodes (representing rooms) and edges (representing channels). Based on the topological analysis results, the building structure layout data is generated, covering the spatial relationship of the building, path connection and other information, which is used for subsequent monitoring equipment layout and environmental perception analysis. According to the building structure layout data, an appropriate type of monitoring equipment, such as a camera, sensor, etc., is selected, considering its coverage, resolution, functional requirements, etc. Design the layout of monitoring equipment to ensure that key areas (such as entrances and exits, large open areas, and hidden spaces) are within the monitoring range, and optimize the equipment layout to minimize blind spots. Generate monitoring equipment deployment data, record the location, type, viewing angle, and other information of each device, and form a detailed monitoring equipment layout diagram. Install monitoring equipment according to the equipment layout data and debug it to ensure its normal operation. Perform environmental perception through installed monitoring equipment and collect real-time environmental data, such as video monitoring, temperature and humidity sensor data, smoke detection data, etc. Fusion and processing of perception data from different devices, remove noise, perform data cleaning and format conversion, and generate environmental perception data, including real-time monitoring information and environmental parameters in the building, for applications such as security management and automated control.

[0030] Step S2: performing static image acquisition on the environmental perception data to obtain a static environmental image; performing channel connection on the static environmental image to generate building channel distribution data; performing potential dangerous channel area identification on the building channel distribution data through the static environmental image to generate potential dangerous channel area data; performing channel area path annotation on the building channel distribution data according to the potential dangerous channel area data to generate dangerous channel path annotation data; In the embodiment of the present invention, a static image of the interior of a building is collected by using a fixed camera or a high-resolution camera. Ensure that the camera layout covers key areas of the building, such as corridors, room entrances, etc. Adjust the camera parameters to obtain high-quality images to avoid image blur or insufficient lighting. Set an appropriate acquisition frequency. Usually, the acquisition interval of static images is longer, but the image should be clear enough. The obtained image is used for subsequent channel connection and potential danger area identification. Image processing is performed on the static environment image, including edge detection, image segmentation and feature extraction, to identify the channels and corridors in the building. Based on the image processing results, the channels inside the building are modeled to determine the connection relationship between the channels. The distribution of each channel in the building is recorded and visualized, including the layout and connection mode of the channels. By analyzing the static environment image and combining the building channel distribution data, the channel area with potential danger is identified. This step includes obstacle detection, narrow channel identification, etc. Use a machine learning algorithm (such as a target detection model) or a rule engine to perform risk assessment on the channel and identify the dangerous area. Identify the potential danger channel area in the building to provide a basis for subsequent path annotation. According to the potential danger channel area data, the building channel distribution data is path-annotated. The marking should include the specific location of the dangerous area and the safe passage path. Use graphic marking tools or GIS (geographic information system) software to mark the passage area to ensure the accuracy and completeness of the marking information, including the identification of dangerous areas and path planning in the passages within the building to help effectively evacuate people in an emergency.

[0031] Step S3: Perform initial evacuation path planning on the building channel distribution data according to the dangerous channel path annotation data to generate initial emergency evacuation planning path data; perform dynamic video stream acquisition on the environmental perception data to obtain the environmental perception dynamic video stream; simulate the channel crowd flow situation on the environmental perception dynamic video stream to generate channel crowd flow simulation data; perform multi-dimensional real-time evacuation demand analysis on the channel crowd flow simulation data to generate real-time evacuation demand data; use the real-time evacuation demand data to sort the path priorities of the initial emergency evacuation planning path data to generate an initial evacuation path scheduling strategy; In an embodiment of the present invention, by using the aforementioned dangerous passage path annotation data, the location and characteristics of the dangerous area in the building are understood. According to the building passage distribution data, the layout and connection mode of all passages in the building are mastered. An algorithm (such as the Dijkstra algorithm) is applied to perform initial evacuation path planning on the building passage distribution data. Taking into account the marked dangerous areas, a safe evacuation route is selected. In the planning process, a path that avoids the dangerous area is given priority, and the connectivity and effectiveness of the path are ensured. The generated evacuation path is recorded, including the starting point, end point, passages passed through, and strategies for avoiding dangerous areas of each path. A dynamic video stream acquisition device (such as a camera) is installed to monitor the flow of people in the building in real time. Video stream data is collected in real time to ensure that the video stream covers key areas to capture changes in the flow of people. The dynamic video stream is processed, including crowd detection, tracking, and density calculation. Computer vision technology and crowd flow analysis algorithms are used to simulate crowd flow conditions. Channel crowd flow simulation data is generated based on the processing results, reflecting the density and flow of people in different channels, including simulated crowd flow data for each channel for further analysis and decision-making. Use data analysis tools (such as statistical analysis and machine learning models) to conduct multi-dimensional analysis of channel crowd flow simulation data, including changes in crowd density and channel congestion. Calculate real-time evacuation demand, including evaluating the demand priority and capacity requirements of each evacuation path based on the crowd flow. Record and analyze the real-time demand data of each evacuation path, including the demand priority and adjustment suggestions for each path. Prioritize the initial emergency evacuation planning path data based on the real-time evacuation demand data. Use a sorting algorithm (such as a priority queue algorithm) to determine the priority of each path and generate an initial evacuation path scheduling strategy.

[0032] Step S4: Perform emergency path scheduling simulation on the initial emergency evacuation planning path data according to the initial evacuation path scheduling strategy to generate emergency route scheduling simulation data; perform abnormal event path scheduling adjustment on the emergency route scheduling simulation data to generate abnormal event dynamic path scheduling data; perform intelligent route scheduling instruction distribution on the initial emergency evacuation planning path data according to the emergency route scheduling simulation data and the abnormal event dynamic path scheduling data to generate distributed emergency evacuation instructions to execute emergency evacuation operations.

[0033] In an embodiment of the present invention, initial emergency evacuation planning path data and initial evacuation path scheduling strategy are received. Based on the initial evacuation path scheduling strategy, the initial emergency evacuation planning path data is simulated. The evacuation process is simulated using simulation tools and algorithms (such as discrete event simulation or agent-based models), taking into account crowd behavior, path congestion and obstacles. Emergency route scheduling simulation data is output to describe the evacuation path effect under different scenarios, including expected evacuation time, personnel flow and potential bottlenecks. Emergency route scheduling simulation data and abnormal event dynamic path scheduling data are received. Abnormal event analysis is performed on the emergency route scheduling simulation data to identify abnormal situations (such as congestion, equipment failure, etc.). Path scheduling is adjusted for abnormal events, and the evacuation path is replanned to respond to emergencies. Abnormal event dynamic path scheduling data is output, including adjusted evacuation paths and response measures. The emergency route scheduling simulation data and the abnormal event dynamic path scheduling data are integrated to generate a comprehensive data set, including emergency path scheduling strategies, abnormal event response plans and adjusted path planning. The comprehensive data is analyzed using intelligent algorithms (such as machine learning or optimization algorithms) to generate final route scheduling instructions. Generate optimal evacuation instructions taking into account real-time crowd dynamics, environmental changes, and the impact of abnormal events. Distribute the generated intelligent evacuation instructions to relevant emergency response systems and on-site personnel through a distributed network. Ensure that the instructions are accurately communicated and executed, and adjust the evacuation strategy to respond to real-time situations. Output distributed emergency evacuation instructions, including specific evacuation paths, priority adjustments, and emergency response steps to support effective emergency evacuation operations.

[0034] Preferably, step S1 comprises the following steps: Step S11: Acquire building layout data; Step S12: performing a building structure topology analysis on the building layout data to generate building structure layout data; performing a field of view width analysis on the building layout data according to the building structure layout data to generate building field of view width data; Step S13: arranging monitoring equipment for the building structure layout data by using the building field of view width data to obtain monitoring equipment deployment data; confirming the monitoring node position based on the monitoring equipment deployment data to obtain monitoring equipment node position data; Step S14: Perform environmental perception on the monitoring device based on the node location data of the monitoring device, thereby generating environmental perception data.

[0035] In an embodiment of the present invention, detailed building layout information is obtained from a building plan, BIM (Building Information Modeling) data or on-site survey data. These data include the room distribution, floor structure, wall position, door and window layout, etc. of the building. The obtained building layout data is topologically analyzed to determine the connection relationship and spatial structure between the various parts of the building. By analyzing the generated building structure layout data, the distribution of the internal space of the building and the connection relationship between the various rooms, passages, stairs, etc. can be accurately described. The field of view width analysis is performed to evaluate the field of view coverage of each area of ​​the building. By calculating the field of view width of each monitoring point or camera position inside the building, the corresponding building field of view width data is generated. These data are used for the reasonable arrangement of subsequent monitoring equipment to ensure effective coverage of all key areas of the building. Using the building field of view width data, the monitoring equipment is reasonably arranged, and the optimal camera installation position is selected to ensure the maximum coverage and the least blind area. The specific installation position and angle of each monitoring device are confirmed, and the monitoring device node position data is generated to ensure the rationality and coverage effect of each node in the building structure. After the equipment is installed, the monitoring equipment is used to perceive the surrounding environment, including external conditions such as ambient light, temperature, and noise. The generated environmental perception data can be used to optimize and adjust the monitoring equipment, such as changing the aperture setting of the camera, adding night vision function, etc., to adapt to different environmental conditions and ensure the stability and reliability of the monitoring effect.

[0036] As an example of the present invention, refer to Figure 2 As shown, in this example, step S2 includes: Step S21: performing static image acquisition on the environmental perception data to obtain a static environmental image; performing image preprocessing on the static environmental image to generate a standard static environmental image, wherein the image preprocessing includes image filtering, image brightness enhancement and image grayscale value transformation; Step S22: performing channel contour segmentation on the static environment image to obtain a channel contour segmentation image; performing channel connection based on the channel contour segmentation image to generate building channel distribution data; Step S23: identifying potential dangerous passage areas on the building passage distribution data through a static environment image to generate potential dangerous passage area data; Step S24: annotating the building channel distribution data with channel area paths according to the potential dangerous channel area data to generate dangerous channel path annotation data.

[0037] In an embodiment of the present invention, a static image of the environment of the building is collected by a high-resolution camera or other imaging device to obtain a clear static environment image. Ensure that the collection is carried out under good lighting conditions to ensure the clarity and accuracy of the image. The static environment image is subjected to noise filtering to eliminate random noise in the image. Common filtering methods such as Gaussian filtering and median filtering can be used. The brightness of the image is optimized by histogram equalization or adaptive brightness enhancement algorithm to improve the overall brightness and contrast of the image. The color image is converted into a grayscale image, or the grayscale value of the grayscale image is adjusted to make the contrast of the image more prominent, and a standard static environment image is generated. The standard static environment image is segmented by channel contour using an edge detection algorithm (such as Canny edge detection) or a threshold segmentation method to extract the contour information of the channel in the building. By analyzing the lines and edges in the static environment image, the contour of the channel is identified and segmented to obtain a channel contour segmentation image. Based on the channel contour obtained by segmentation, the fragmented contour of the channel is connected and repaired using morphological operations (such as dilation, corrosion) or connected component analysis. The connected channel contour data are integrated to generate complete building channel distribution data to describe the layout structure of the channel inside the building. By analyzing the building channel distribution data in the static environment image, the dangerous channel area is identified. Dangerous features include narrow channels, curved channels, and channels that are too close to obstacles. The channel area is further analyzed using a deep learning-based image recognition model or rule algorithm to identify potential dangerous channel areas. The identified potential dangerous channel areas are marked, and their corresponding geographic coordinates and feature information are recorded to generate potential dangerous channel area data. According to the layout of the channels in the building and the location of the potential dangerous areas, marking rules are formulated, such as marking the starting point, end point, and path type (main channel, secondary channel, etc.) of the dangerous path. Using the potential dangerous channel area data, the building channel distribution data is marked to generate clear dangerous channel path marking data. The marked dangerous channel path data is integrated with the channel distribution data to form a complete building channel layout and dangerous path marking data, providing data support for subsequent building safety management and emergency planning.

[0038] Preferably, step S23 includes the following steps: Step S231: extracting the channel space structure of the static environment image to generate channel space structure data; analyzing the channel obstacle distribution of the static environment image to generate channel obstacle distribution data; Step S232: performing a channel narrow distance variation analysis on the channel spatial structure data to generate channel narrow distance variation data; performing an obstacle multi-dimensional risk factor analysis on the channel obstacle distribution data to generate obstacle risk factor data, wherein the obstacle multi-dimensional risk factor analysis includes an obstruction risk factor analysis and an obstacle component risk factor analysis; Step S233: calculating the passage difficulty index for the building passage distribution data by using the obstacle risk factor data and the passage narrow distance variation data to obtain the passage difficulty index; Step S234: Based on the comparison between the passage difficulty index and the preset passage difficulty index threshold, when the passage difficulty index is greater than or equal to the preset passage difficulty index threshold, the corresponding building passage is marked as a potentially dangerous passage, thereby generating potentially dangerous passage area data.

[0039] The present invention uses computer vision technology to extract the spatial structure of the building channel in the static environment image, identify the spatial geometric features of the channel (such as width, height, inclination, etc.), and generate channel spatial structure data. Edge detection, morphological analysis, deep learning model and other methods can be used to ensure that the extracted channel structure data can accurately reflect the actual spatial layout of the channel. Obstacles in the channel (such as columns, equipment, furniture, etc.) are identified and segmented through static environment images to generate preliminary obstacle distribution data. The identified obstacles are further classified, and the obstacles are refined and analyzed based on features such as shape, size and material to generate detailed channel obstacle distribution data. The extracted channel spatial structure data is analyzed to identify the narrow distance change area in the channel (such as the sharply narrowed part of the channel), calculate the specific narrow distance change values ​​of these areas, and generate channel narrow distance change data. The continuity and mutation points of the channel narrow distance change are evaluated to identify the key positions that affect traffic safety. The degree of influence of obstacles on traffic is evaluated, such as the relative relationship between the size and position of the obstacles and the channel, and the obstruction risk factor data is generated. Analyze the material and physical properties of obstacles, such as whether they are flammable, fragile, or have sharp edges, evaluate their potential threats to safety, and generate component risk factor data. Combine the obstacle risk factor data with the channel narrowness change data to conduct a comprehensive analysis of the building channel distribution data. Use a weighted model or other mathematical model to calculate the difficulty index of each channel. The difficulty index reflects the difficulty of passing through the channel. Its calculation takes into account the narrowness of the channel, the degree of obstruction of the obstacle, and other relevant factors. According to the design standards and safety regulations of the building, set a threshold for the channel difficulty index to identify dangerous channels. Compare the calculated channel difficulty index with the preset threshold. When the difficulty index is greater than or equal to the threshold, the channel is considered to be a potentially dangerous channel. Mark the channels identified as potentially dangerous, record their location, channel number, and related risk factors, and generate potentially dangerous channel area data. Store the marked potentially dangerous channel area data in the system for subsequent risk management and emergency planning.

[0040] As an example of the present invention, refer to Figure 3 As shown, in this example, step S3 includes: Step S31: Performing initial evacuation path planning on the building channel distribution data according to the dangerous channel path annotation data to generate initial emergency evacuation planning path data; Step S32: performing dynamic video stream acquisition on the environment perception data to obtain an environment perception dynamic video stream; performing crowd density change analysis on the environment perception dynamic video stream to generate crowd density change data; Step S33: simulating the channel crowd flow situation of the building channel distribution data through the crowd density change data to generate channel crowd flow simulation data; performing channel capacity analysis on the building channel distribution data according to the channel crowd flow simulation data to generate channel capacity analysis data; Step S34: Use the channel capacity analysis data to perform multi-dimensional real-time evacuation demand analysis on the crowd density change data to generate real-time evacuation demand data; use the real-time evacuation demand data to sort the path priorities of the initial emergency evacuation planning path data to generate an initial evacuation path scheduling strategy.

[0041] In an embodiment of the present invention, the safety level and risk area of ​​the internal passage of the building are identified based on the path annotation data of the dangerous passage. A path planning algorithm (such as the Dijkstra algorithm, etc.) is used to perform preliminary evacuation path planning on the building passage distribution data to generate initial emergency evacuation planning path data. The path planning takes into account the principle of the shortest path and avoiding dangerous areas. The dynamic video stream in the building is collected in real time by monitoring equipment to generate environmental perception dynamic video stream data. These video streams can capture the real-time distribution and movement of people inside the current building. Computer vision technology (such as motion detection, target tracking, etc.) is used to analyze the crowd movement and density changes in the environmental perception dynamic video stream to generate crowd density change data for each area inside the building. By detecting the crowd density changes at different time points, the areas where the crowd gathers and the potential congestion locations are identified, providing data support for the subsequent optimization of the evacuation path. Using the crowd density change data, the building passage distribution data is simulated by a simulation algorithm (such as a cellular automaton or an agent-based model) to perform a dynamic simulation of the flow of people on the building passage distribution data to generate channel flow simulation data. The simulation results are analyzed to evaluate the carrying capacity of each channel during the peak flow period and the congestion that occurs. Based on the channel crowd flow simulation data, the actual traffic capacity of each channel is calculated to generate channel capacity analysis data. This data reflects the maximum traffic volume of each channel in different time periods and the utilization efficiency under the current crowd distribution. Combined with the channel capacity analysis data and the crowd density change data, a multi-dimensional real-time evacuation demand analysis is performed. Factors including crowd density, channel capacity, channel safety, etc. are considered to generate real-time evacuation demand data. Predict the evacuation needs of various areas in an emergency and identify bottlenecks and high-risk areas. According to the real-time evacuation demand data, the initial emergency evacuation planning path data is dynamically adjusted to optimize the priority sorting of the paths to ensure the safety and efficiency of the evacuation paths. The initial evacuation path scheduling strategy is generated, covering the priority of each path, the recommended use time period, and the path switching plan in emergency situations, so as to guide people to evacuate quickly and safely in actual evacuation.

[0042] Preferably, step S34 includes the following steps: Step S341: using an infrared camera to collect temperature change data on crowd density change data to obtain crowd temperature change data; performing fast Fourier transform on the crowd temperature change data to generate crowd temperature change frequency data; performing dynamic psychological stress assessment based on the crowd temperature change frequency data to generate crowd psychological stress assessment data; Step S342: using environmental sensors to monitor environmental variables on the channel capacity analysis data to obtain environmental variable monitoring data, wherein the environmental variable monitoring includes temperature monitoring, humidity monitoring, and smoke concentration monitoring; performing evacuation channel feasibility analysis on the channel capacity analysis data using the environmental variable monitoring data to generate channel feasibility scoring data; Step S343: dynamically calculating the evacuation demand based on the crowd psychological stress assessment data and the channel feasibility score data based on the Bayesian network algorithm to generate real-time evacuation demand data; Step S344: using the real-time evacuation demand data to sort the path priority of the initial emergency evacuation planning path data, and generating evacuation priority sorting data; using the evacuation priority sorting data to sort the path priority of the initial emergency evacuation planning path data, and generating an initial evacuation path scheduling strategy.

[0043] In the embodiment of the present invention, the temperature change of the area with changing crowd density is monitored by using an infrared camera, and the real-time temperature data of each area is collected to generate accurate crowd temperature change data. The collected crowd temperature change data is preprocessed, including noise filtering and data smoothing, to ensure the accuracy of subsequent analysis. The preprocessed crowd temperature change data is subjected to a fast Fourier transform (FFT), and the time domain data is converted into frequency domain data to generate crowd temperature change frequency data. This data reflects the periodicity and fluctuation of the crowd temperature change. Based on the crowd temperature change frequency data, combined with the established crowd psychological stress assessment model, a dynamic psychological stress assessment is performed. High temperature or frequent temperature changes mean higher psychological stress. Through the above assessment, crowd psychological stress assessment data reflecting the current psychological state of the crowd is generated, and the data will be used to adjust the priority of the evacuation path. The channel area is monitored in real time by using an environmental sensor, and environmental variables such as temperature, humidity and smoke concentration are collected to generate environmental variable monitoring data. These data provide environmental condition information of the evacuation channel. The environmental variable monitoring data is analyzed to determine whether there is fire, high humidity or other dangerous factors affecting the passage in the channel. Based on the environmental variable monitoring data, the feasibility of each channel in the current environment is analyzed. Using certain scoring criteria (such as low temperature, low humidity and no smoke, the scores are higher), the feasibility score data of each channel is calculated, and the generated channel feasibility score data will be used as an important reference indicator for evacuation path priority sorting. Using the Bayesian network algorithm, the psychological stress assessment data of the crowd is integrated with the channel feasibility score data to dynamically calculate the evacuation demand under the current situation. Through the reasoning ability of the Bayesian network, multi-dimensional factors such as psychological stress and environmental feasibility are comprehensively considered to generate real-time evacuation demand data to ensure that the selection of evacuation paths takes into account both the psychological stress of personnel and environmental safety. Using real-time evacuation demand data, the initial emergency evacuation planning paths are reordered. Paths with higher priority should avoid high-risk areas and try to choose channels with lower psychological stress and good environmental conditions to generate evacuation priority sorting data reflecting the path priority. Based on the evacuation priority sorting data, the initial emergency evacuation planning path data is optimized to generate the final initial evacuation path scheduling strategy. This strategy includes path selection and emergency plans under different circumstances to ensure that people can be guided to evacuate quickly and safely during the actual evacuation process.

[0044] Preferably, step S4 comprises the following steps: Step S41: performing emergency path scheduling simulation on the initial emergency evacuation planning path data according to the initial evacuation path scheduling strategy to generate emergency route scheduling simulation data; Step S42: performing abnormal event analysis on the emergency route scheduling simulation data to generate abnormal scheduling event data; performing path scheduling adjustment on the emergency route scheduling simulation data according to the abnormal scheduling event data to generate abnormal event dynamic path scheduling data; Step S43: Integrate the abnormal event dynamic path scheduling data and the emergency route scheduling simulation data to generate route scheduling simulation comprehensive data; divide the route scheduling simulation comprehensive data into data sets to generate a model training set and a model test set; use a decision tree algorithm to perform model training on the model training set to generate a route scheduling decision pre-model; Step S44: performing model optimization iteration on the route scheduling decision pre-model through the model test set, thereby generating a route scheduling decision model; using the route scheduling decision model to perform intelligent emergency path scheduling update on the initial emergency evacuation planning path data, and generating dynamic emergency evacuation path update data; Step S45: Distribute the dynamic emergency evacuation path update data through the distributed network to generate distributed emergency evacuation instructions to execute emergency evacuation operations.

[0045] In the embodiment of the present invention, the emergency path scheduling simulation is performed on the initial emergency evacuation planning path data according to the initial evacuation path scheduling strategy. During the simulation process, the flow of personnel, channel utilization and potential obstacles in an emergency situation are simulated to generate emergency route scheduling simulation data. During the simulation process, all path selection, personnel flow and system response are recorded to provide a data basis for subsequent analysis and optimization. The emergency route scheduling simulation data is analyzed to detect abnormal events that occur during the simulation process, such as path blockage, personnel retention, channel blocking, etc., to generate scheduling abnormal event data. The abnormal event data is deeply analyzed to identify the causes of abnormal events (such as excessive personnel density, insufficient channel capacity, etc.), providing a basis for path scheduling adjustment. According to the scheduling abnormal event data, the emergency route scheduling simulation data is dynamically adjusted, the path scheduling strategy is optimized, and the abnormal event dynamic path scheduling data is generated. The adjustment content includes changing the path priority, reallocating channel resources, etc., to reduce or avoid the occurrence of abnormal events. The abnormal event dynamic path scheduling data is integrated with the emergency route scheduling simulation data to generate more comprehensive route scheduling simulation data to ensure the diversity and richness required for decision model training. The integrated simulation data is divided to generate a model training set and a model test set, which are used for model training and testing respectively. The model training set is trained using the decision tree algorithm to generate a preliminary route scheduling decision pre-model. The model forms a preliminary decision basis for emergency route scheduling by learning the path selection rules in the simulation data. The route scheduling decision pre-model is tested using the model test set to evaluate its prediction accuracy and applicability in different emergency situations. According to the test results, the decision pre-model is optimized and iterated for multiple rounds to adjust the model parameters and decision rules, and finally a more accurate route scheduling decision model is generated. Using the optimized route scheduling decision model, the initial emergency evacuation planning path data is intelligently updated to generate dynamic emergency evacuation path update data. This data reflects the optimal emergency evacuation path plan based on the latest simulation and model optimization. The dynamic emergency evacuation path update data is distributed to each emergency evacuation execution terminal through a distributed network to generate a distributed emergency evacuation instruction. After receiving the instruction, each terminal performs the emergency evacuation operation according to the actual situation to ensure that the instruction can be executed in real time and effectively. In an emergency, the distributed command dispatch system can be used to quickly organize the evacuation of personnel, ensure the smooth and safe evacuation route, and achieve efficient emergency evacuation operations.

[0046] Preferably, step S42 includes the following steps: Step S421: performing abnormal event analysis on the emergency route scheduling simulation data to generate scheduling abnormal event data, wherein the scheduling abnormal event data includes personnel abnormal event data and channel abnormal event data; Step S422: when it is confirmed that the abnormal scheduling event data is abnormal personnel event data, human behavior analysis is performed on the abnormal personnel event data to generate abnormal personnel behavior analysis data; emergency evacuation speed assessment is performed on the abnormal personnel event data through the abnormal personnel behavior analysis data to obtain abnormal personnel evacuation assessment data; Step S423: When it is confirmed that the scheduling abnormal event data is channel abnormal event data, an abnormal event impact analysis is performed on the channel abnormal event data to generate channel abnormal impact analysis data; emergency evacuation safety assessment is performed on the channel abnormal event data through the channel abnormal impact analysis data to obtain abnormal channel evacuation safety assessment data; Step S424: Based on the abnormal personnel evacuation assessment data and the abnormal channel evacuation safety assessment data, the emergency route scheduling simulation data is reallocated to adjacent shortest paths to generate abnormal event dynamic path scheduling data.

[0047] In an embodiment of the present invention, by performing abnormal event analysis on the emergency route scheduling simulation data, the detected abnormal event data is classified into personnel abnormal event data and channel abnormal event data. According to the analysis results, personnel abnormal event data and channel abnormal event data are generated respectively to facilitate subsequent in-depth analysis. When the abnormal event data is confirmed to be personnel abnormal event data, the behavior of the personnel is analyzed using computer vision technology to generate personnel abnormal behavior analysis data. This analysis includes the identification of abnormal actions, stagnation, retrograde and other behaviors. Through the behavior analysis data, abnormal behaviors that affect the evacuation speed can be identified, providing a basis for further evacuation speed evaluation. Based on the personnel abnormal behavior analysis data, the speed of the personnel during the evacuation process is evaluated using a dynamic evaluation model to generate abnormal personnel evacuation evaluation data. The evaluation takes into account the impact of different types of abnormal behaviors on the speed of personnel movement to ensure the accuracy of the evaluation. When the abnormal event data is confirmed to be channel abnormal event data, the impact analysis of channel abnormal events is performed. The analysis content includes channel blockage, structural damage, fire smoke diffusion, etc., and channel abnormal impact analysis data is generated. The analysis results can be used to evaluate the potential impact of channel abnormalities on evacuation safety, especially the threat level to the passage capacity and personnel safety of the channel. Based on the channel abnormal impact analysis data, the safety assessment model is used to evaluate the evacuation safety of the channel and generate abnormal channel evacuation safety assessment data. The assessment result is used to determine whether the channel is still suitable as an emergency evacuation path under the current conditions. Based on the abnormal personnel evacuation assessment data and the abnormal channel evacuation safety assessment data, the emergency route scheduling simulation data is redistributed to adjacent shortest paths. This process uses the path optimization algorithm to recalculate the optimal evacuation path to ensure a balance between evacuation speed and safety. During the redistribution process, new abnormal event dynamic path scheduling data is generated, and the evacuation path is updated in real time to avoid evacuation delays and safety hazards caused by abnormal events to the greatest extent.

[0048] In this specification, an emergency evacuation path planning system is provided, which is used to execute the above-mentioned emergency evacuation path planning method, and the emergency evacuation path planning system includes: The monitoring module is used to obtain building layout data; perform building structure topology analysis on the building layout data to generate building structure layout data; arrange monitoring equipment according to the building structure layout data to obtain monitoring equipment deployment data; perform environmental perception on the monitoring equipment based on the monitoring equipment deployment data to generate environmental perception data; The dangerous area identification module is used to collect static images of environmental perception data to obtain static environmental images; connect channels of the static environmental images to generate building channel distribution data; identify potential dangerous channel areas of the building channel distribution data through the static environmental images to generate potential dangerous channel area data; annotate the channel area paths of the building channel distribution data according to the potential dangerous channel area data to generate dangerous channel path annotation data; The path scheduling module is used to perform initial evacuation path planning on the building channel distribution data according to the dangerous channel path annotation data, and generate initial emergency evacuation planning path data; perform dynamic video stream acquisition on the environmental perception data to obtain the environmental perception dynamic video stream; simulate the channel crowd flow situation on the environmental perception dynamic video stream to generate channel crowd flow simulation data; perform multi-dimensional real-time evacuation demand analysis on the channel crowd flow simulation data to generate real-time evacuation demand data; use the real-time evacuation demand data to sort the path priority of the initial emergency evacuation planning path data, and generate the initial evacuation path scheduling strategy; The scheduling decision module is used to perform emergency path scheduling simulation on the initial emergency evacuation planning path data according to the initial evacuation path scheduling strategy to generate emergency route scheduling simulation data; perform abnormal event path scheduling adjustment on the emergency route scheduling simulation data to generate abnormal event dynamic path scheduling data; perform intelligent route scheduling instruction distribution on the initial emergency evacuation planning path data according to the emergency route scheduling simulation data and the abnormal event dynamic path scheduling data to generate distributed emergency evacuation instructions to execute emergency evacuation operations.

[0049] A computer-readable storage medium stores a computer program, which, when executed, implements any one of the emergency evacuation route planning methods described above.

[0050] The beneficial effect of the present invention is that by analyzing the building layout data and deploying monitoring equipment, the structure and potential dangerous areas inside the building can be fully understood. This detailed monitoring data helps to identify and mark dangerous passages, thereby improving the safety of the building. The combination of static and dynamic environmental perception data can generate more accurate evacuation path planning. This path planning takes into account the actual channel flow and potential dangerous areas, so that people can be more effectively guided to evacuate. The analysis of dynamic video streams and the generation of real-time evacuation demand data make emergency response more flexible and timely. The evacuation path can be adjusted according to real-time data to improve the effect of emergency handling. Based on emergency path scheduling simulation and abnormal event path adjustment, the generated intelligent route scheduling instructions can optimize the distribution of emergency evacuation instructions, thereby making the entire evacuation process more efficient and orderly. Through environmental perception data and simulation analysis, data-driven decisions can be generated to help improve the emergency management level of buildings in emergencies and reduce potential safety hazards. This process improves the ability of buildings to respond to emergencies and enhances the safety of personnel through multi-dimensional analysis and optimization of emergency evacuation paths. Therefore, the present invention improves the flexibility and accuracy of emergency evacuation route planning by integrating environmental perception, dynamic video stream analysis and intelligent route scheduling.

[0051] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0052] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but should conform to the widest scope consistent with the principles and novel features invented herein.

Claims

1. A method for emergency evacuation route planning, characterized in that: The following steps are involved: Step S1: Acquire building layout data; perform building structure topology analysis on the building layout data to generate building structure layout data; Arrange monitoring equipment according to the building structure layout data to obtain monitoring equipment deployment data; perform environmental perception on the monitoring equipment based on the monitoring equipment deployment data to generate environmental perception data; Step S2: performing static image acquisition on the environmental perception data to obtain a static environmental image; performing channel connection on the static environmental image to generate building channel distribution data; performing potential dangerous channel area identification on the building channel distribution data through the static environmental image to generate potential dangerous channel area data; performing channel area path annotation on the building channel distribution data according to the potential dangerous channel area data to generate dangerous channel path annotation data; Step S3: Performing initial evacuation path planning on the building channel distribution data according to the dangerous channel path annotation data to generate initial emergency evacuation planning path data; performing dynamic video stream acquisition on the environmental perception data to obtain an environmental perception dynamic video stream; Simulate the channel crowd flow situation of the environmental perception dynamic video stream to generate channel crowd flow simulation data; perform multi-dimensional real-time evacuation demand analysis on the channel crowd flow simulation data to generate real-time evacuation demand data; use the real-time evacuation demand data to sort the path priority of the initial emergency evacuation planning path data to generate the initial evacuation path scheduling strategy; Step S4: performing emergency path scheduling simulation on the initial emergency evacuation planning path data according to the initial evacuation path scheduling strategy to generate emergency route scheduling simulation data; performing abnormal event path scheduling adjustment on the emergency route scheduling simulation data to generate abnormal event dynamic path scheduling data; According to the emergency route scheduling simulation data and the abnormal event dynamic path scheduling data, the initial emergency evacuation planning path data is intelligently distributed with route scheduling instructions to generate distributed emergency evacuation instructions to execute emergency evacuation operations.

2. The method for emergency evacuation route planning according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire building layout data; Step S12: performing a building structure topology analysis on the building layout data to generate building structure layout data; performing a field of view width analysis on the building layout data according to the building structure layout data to generate building field of view width data; Step S13: arranging monitoring equipment for the building structure layout data by using the building field of view width data to obtain monitoring equipment deployment data; confirming the monitoring node position based on the monitoring equipment deployment data to obtain monitoring equipment node position data; Step S14: Perform environmental perception on the monitoring device based on the node location data of the monitoring device, thereby generating environmental perception data.

3. The method for emergency evacuation route planning according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing static image acquisition on the environmental perception data to obtain a static environmental image; performing image preprocessing on the static environmental image to generate a standard static environmental image, wherein the image preprocessing includes image filtering, image brightness enhancement and image grayscale value transformation; Step S22: performing channel contour segmentation on the static environment image to obtain a channel contour segmentation image; performing channel connection based on the channel contour segmentation image to generate building channel distribution data; Step S23: identifying potential dangerous passage areas on the building passage distribution data through a static environment image to generate potential dangerous passage area data; Step S24: annotating the building channel distribution data with channel area paths according to the potential dangerous channel area data to generate dangerous channel path annotation data.

4. The method for emergency evacuation route planning according to claim 3, characterized in that: Step S23 includes the following steps: Step S231: extracting the channel space structure of the static environment image to generate channel space structure data; analyzing the channel obstacle distribution of the static environment image to generate channel obstacle distribution data; Step S232: performing a channel narrow distance variation analysis on the channel spatial structure data to generate channel narrow distance variation data; performing an obstacle multi-dimensional risk factor analysis on the channel obstacle distribution data to generate obstacle risk factor data, wherein the obstacle multi-dimensional risk factor analysis includes an obstruction risk factor analysis and an obstacle component risk factor analysis; Step S233: calculating the passage difficulty index for the building passage distribution data by using the obstacle risk factor data and the passage narrow distance variation data to obtain the passage difficulty index; Step S234: Based on the comparison between the passage difficulty index and the preset passage difficulty index threshold, when the passage difficulty index is greater than or equal to the preset passage difficulty index threshold, the corresponding building passage is marked as a potentially dangerous passage, thereby generating potentially dangerous passage area data.

5. The method for emergency evacuation route planning according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: Performing initial evacuation path planning on the building channel distribution data according to the dangerous channel path annotation data to generate initial emergency evacuation planning path data; Step S32: performing dynamic video stream acquisition on the environment perception data to obtain an environment perception dynamic video stream; performing crowd density change analysis on the environment perception dynamic video stream to generate crowd density change data; Step S33: simulating the channel crowd flow situation of the building channel distribution data through the crowd density change data to generate channel crowd flow simulation data; performing channel capacity analysis on the building channel distribution data according to the channel crowd flow simulation data to generate channel capacity analysis data; Step S34: Use the channel capacity analysis data to perform multi-dimensional real-time evacuation demand analysis on the crowd density change data to generate real-time evacuation demand data; use the real-time evacuation demand data to sort the path priorities of the initial emergency evacuation planning path data to generate an initial evacuation path scheduling strategy.

6. The method for emergency evacuation route planning according to claim 5, characterized in that: Step S34 includes the following steps: Step S341: using an infrared camera to collect temperature change data on crowd density change data to obtain crowd temperature change data; performing fast Fourier transform on the crowd temperature change data to generate crowd temperature change frequency data; performing dynamic psychological stress assessment based on the crowd temperature change frequency data to generate crowd psychological stress assessment data; Step S342: using environmental sensors to monitor environmental variables on the channel capacity analysis data to obtain environmental variable monitoring data, wherein the environmental variable monitoring includes temperature monitoring, humidity monitoring, and smoke concentration monitoring; performing evacuation channel feasibility analysis on the channel capacity analysis data using the environmental variable monitoring data to generate channel feasibility scoring data; Step S343: dynamically calculating the evacuation demand based on the crowd psychological stress assessment data and the channel feasibility score data based on the Bayesian network algorithm to generate real-time evacuation demand data; Step S344: using the real-time evacuation demand data to sort the path priority of the initial emergency evacuation planning path data, and generating evacuation priority sorting data; using the evacuation priority sorting data to sort the path priority of the initial emergency evacuation planning path data, and generating an initial evacuation path scheduling strategy.

7. The method for emergency evacuation route planning according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing emergency path scheduling simulation on the initial emergency evacuation planning path data according to the initial evacuation path scheduling strategy to generate emergency route scheduling simulation data; Step S42: performing abnormal event analysis on the emergency route scheduling simulation data to generate abnormal scheduling event data; performing path scheduling adjustment on the emergency route scheduling simulation data according to the abnormal scheduling event data to generate abnormal event dynamic path scheduling data; Step S43: Integrate the abnormal event dynamic path scheduling data and the emergency route scheduling simulation data to generate route scheduling simulation comprehensive data; divide the route scheduling simulation comprehensive data into data sets to generate a model training set and a model test set; use a decision tree algorithm to perform model training on the model training set to generate a route scheduling decision pre-model; Step S44: performing model optimization iteration on the route scheduling decision pre-model through the model test set, thereby generating a route scheduling decision model; using the route scheduling decision model to perform intelligent emergency path scheduling update on the initial emergency evacuation planning path data, and generating dynamic emergency evacuation path update data; Step S45: Distribute the dynamic emergency evacuation path update data through the distributed network to generate distributed emergency evacuation instructions to execute emergency evacuation operations.

8. The method for planning an emergency evacuation route according to claim 7, characterized in that: Step S42 includes the following steps: Step S421: performing abnormal event analysis on the emergency route scheduling simulation data to generate scheduling abnormal event data, wherein the scheduling abnormal event data includes personnel abnormal event data and channel abnormal event data; Step S422: when it is confirmed that the abnormal scheduling event data is abnormal personnel event data, human behavior analysis is performed on the abnormal personnel event data to generate abnormal personnel behavior analysis data; emergency evacuation speed assessment is performed on the abnormal personnel event data through the abnormal personnel behavior analysis data to obtain abnormal personnel evacuation assessment data; Step S423: When it is confirmed that the scheduling abnormal event data is channel abnormal event data, an abnormal event impact analysis is performed on the channel abnormal event data to generate channel abnormal impact analysis data; emergency evacuation safety assessment is performed on the channel abnormal event data through the channel abnormal impact analysis data to obtain abnormal channel evacuation safety assessment data; Step S424: Based on the abnormal personnel evacuation assessment data and the abnormal channel evacuation safety assessment data, the emergency route scheduling simulation data is reallocated to adjacent shortest paths to generate abnormal event dynamic path scheduling data.

9. An emergency evacuation route planning system, characterized in that: Used to execute the emergency evacuation path planning method according to claim 1, the emergency evacuation path planning system comprises: The monitoring module is used to obtain building layout data; perform building structure topology analysis on the building layout data to generate building structure layout data; arrange monitoring equipment according to the building structure layout data to obtain monitoring equipment deployment data; perform environmental perception on the monitoring equipment based on the monitoring equipment deployment data to generate environmental perception data; The dangerous area identification module is used to collect static images of environmental perception data to obtain static environmental images; connect channels of the static environmental images to generate building channel distribution data; identify potential dangerous channel areas of the building channel distribution data through the static environmental images to generate potential dangerous channel area data; annotate the channel area paths of the building channel distribution data according to the potential dangerous channel area data to generate dangerous channel path annotation data; The path scheduling module is used to perform initial evacuation path planning on the building channel distribution data according to the dangerous channel path annotation data, and generate initial emergency evacuation planning path data; perform dynamic video stream acquisition on the environmental perception data to obtain the environmental perception dynamic video stream; simulate the channel crowd flow situation on the environmental perception dynamic video stream to generate channel crowd flow simulation data; perform multi-dimensional real-time evacuation demand analysis on the channel crowd flow simulation data to generate real-time evacuation demand data; use the real-time evacuation demand data to sort the path priority of the initial emergency evacuation planning path data, and generate the initial evacuation path scheduling strategy; The scheduling decision module is used to perform emergency path scheduling simulation on the initial emergency evacuation planning path data according to the initial evacuation path scheduling strategy to generate emergency route scheduling simulation data; perform abnormal event path scheduling adjustment on the emergency route scheduling simulation data to generate abnormal event dynamic path scheduling data; perform intelligent route scheduling instruction distribution on the initial emergency evacuation planning path data according to the emergency route scheduling simulation data and the abnormal event dynamic path scheduling data to generate distributed emergency evacuation instructions to execute emergency evacuation operations.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed, the emergency evacuation route planning method according to any one of claims 1 to 8 is implemented.

Images