A smart control method for emergency events

Abstract

The present application discloses an intelligent emergency control method, which relates to the technical field of traffic control, including establishing a safe evacuation time model for a comprehensive transportation hub, decomposing the pedestrian evacuation process of the comprehensive transportation hub based on the safe evacuation time model of the comprehensive transportation hub, and obtaining a pedestrian evacuation time series; further decomposing the pedestrian evacuation time series according to the fluctuation of vehicle flow and the speed and density variation law of pedestrian flow, and obtaining a pedestrian evacuation time subsequence group; selecting a pedestrian evacuation path for the comprehensive transportation hub based on an improved ant colony algorithm; and scheduling resources according to the selected optimal evacuation path and the pedestrian evacuation time subsequence group using a public transportation emergency collaborative scheduling recommendation method based on deep imitation learning, and establishing an emergency response plan library integrating an expert decision rule library. The present invention can effectively assist in the control of emergencies or emergency situations in transportation hubs and ensure the travel safety of passengers.

Description

Technical Field

[0001] The present application relates to the field of traffic control technology, and specifically to a method for intelligent control of emergency events. Background Art

[0002] In the management and control of emergency activities and sudden incidents in comprehensive transportation hubs, the passenger flow is complex, requiring detailed planning and plans, strengthening of safety management, optimization of traffic organization, strengthening of information release and guidance, and establishment of sound emergency plans and cross-departmental coordination mechanisms.

[0003] However, the current response to large-scale events or emergencies mostly relies on experience and manual judgment, resulting in problems such as inaccurate predictions, untimely control, inadequate response, high trial and error costs, a single control mechanism, and low response efficiency. In addition, when faced with complex situations such as high-density and rapid increases in passenger flow, it is more likely to cause public opinion and accidents due to misjudgment of the situation or lack of response plans, which is contrary to the direction of modern smart city construction. Summary of the invention

[0004] In view of this, the present application provides an intelligent management and control method for emergency events, which can solve technical problems such as inaccurate predictions, untimely management and control, inadequate response, high trial and error costs, and the possibility of causing public opinion and accidents due to misjudgment of the situation or lack of response plans when facing complex situations such as high-density and rapid increase in passenger flow.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A smart emergency management method, comprising:

[0007] Establishing a safe evacuation time model for a comprehensive transportation hub, and decomposing the pedestrian evacuation process of the comprehensive transportation hub based on the safe evacuation time model for the comprehensive transportation hub to obtain a pedestrian evacuation time series;

[0008] According to the fluctuation of vehicle flow and the speed and density variation of pedestrian flow, the pedestrian evacuation time series is further decomposed to obtain a pedestrian evacuation time subsequence group;

[0009] An improved ant colony algorithm is used to select the optimal path for pedestrian evacuation in a comprehensive transportation hub;

[0010] A public transportation emergency collaborative dispatch infrastructure resource pool and an emergency management decision-making knowledge resource pool are constructed. According to the selected optimal evacuation path and the pedestrian evacuation time subsequence group, a public transportation emergency collaborative dispatch recommendation method based on deep imitation learning is used to perform resource scheduling, and an emergency response plan library that integrates the expert decision-making rule library is established.

[0011] Furthermore, the establishing of a safe evacuation time model for a comprehensive transportation hub and the decomposition of the pedestrian evacuation process of the comprehensive transportation hub based on the safe evacuation time model for the comprehensive transportation hub include:

[0012] The total pedestrian evacuation time T is decomposed into three parts. The first part is the time for pedestrians to get off the bus. The second part is the time it takes for pedestrians to evacuate from the platform to the passage, recorded as the platform evacuation time The third part is the time it takes for pedestrians to pass through the passage, gate, and stairs, which is recorded as the passage evacuation time. .

[0013] Furthermore, the time and number of pedestrians getting off the bus in the integrated transportation hub meet the following requirements: ,in, is the maximum number of pedestrians getting off each door in the integrated transportation hub, .

[0014] Furthermore, the further decomposition of the pedestrian evacuation time series according to the traffic flow fluctuation and the speed and density variation of the pedestrian flow includes:

[0015] Calculate platform evacuation time based on traffic fluctuation theory , the platform evacuation time Including the time it takes for pedestrians to dissipate on the stairs , pedestrian passage time at the stairs , ;

[0016] Calculate the channel evacuation time according to the speed and density change rules of pedestrian flow , = ,in, is the channel length, The density of pedestrians in the passage or stairs.

[0017] Furthermore, according to the traffic fluctuation theory, the calculation of platform evacuation time includes the following formula: Calculate the time it takes for pedestrians to disappear at the stairs ,in, , , The wave flow of pedestrians gathering after getting off the bus, is the wave flux of the pedestrian dissipation wave at the stairs, The normal walking speed of pedestrians after getting off the bus. is the pedestrian dissipation speed at the stairs; is the running speed of the escalator or the speed of pedestrians going up the stairs. is the pedestrian density at the platform, is the pedestrian density at the stairs, density of escalators or steps for pedestrians;

[0018] According to the formula = Calculate pedestrian passage time at stairs ,in, is the step length.

[0019] Furthermore, the use of the improved ant colony algorithm to select the optimal path for pedestrian evacuation in a comprehensive transportation hub includes analyzing influencing factors, which include psychological influencing parameters and environmental influencing parameters, and constructing a path selection model of the improved ant colony algorithm based on the influencing factors.

[0020] Furthermore, the calculation process of the path selection model of the improved ant colony algorithm includes:

[0021] The grid identification method is used to establish the hub evacuation map. Each grid is a grid. The grid environment is initialized, and the static and dynamic properties of the nodes are initialized to determine the obstacle location node B and the evacuation exit location E.

[0022] Establish an adjacency matrix of the grid, initialize relevant parameters that affect the evacuation of personnel in emergency activities and emergencies, the relevant parameters are related to psychological impact parameters and environmental impact parameters, and initialize model parameters and variables, the model parameters and variables include the maximum number of iterations Nmax, the number of evacuees m, the pheromone perception threshold of personnel to pheromones, information heuristic factor a, expected heuristic factor b, pheromone volatilization factor c and pheromone intensity Q, as well as pheromone matrix and taboo table;

[0023] Calculate the relevant parameters f1, f2 and f3 that affect the evacuation of personnel in emergency activities and emergencies, and then calculate the relevant parameters of the activity index M that affects the evacuation speed of personnel, M=f1×f2×f3, and the distance L between each adjacent node, and convert the distance into the equivalent length D between nodes, , ,v0 represents the normal walking speed of personnel in the passage, Indicates the speed at which people travel on a specific path;

[0024] Place m people on the starting node s respectively, add them to the taboo table, start iteration, and calculate the heuristic information matrix;

[0025] Search each path, find the free grid adjacent to the current grid in the adjacency matrix, select the next grid to pass through according to the pseudo-random proportional rule, record the route of this iteration, use the route to determine the walking route, select the point with the strongest pheromone as the target of the next walk, when the pheromone intensity Q> congestion factor r, the node is congested, reselect the key node, where r is the congestion factor of the key node of the comprehensive transportation hub, add the location point where the ant has passed to the taboo table, and determine whether the evacuees have found the exit. If they have found it, stop this iteration, record the walking route and length of the evacuees in this iteration, if the exit is not found, continue to search for each corresponding path;

[0026] After all passengers complete a walk, the pheromone value will be updated, the pheromone concentration on each path will be updated, the pheromone volatility factor will be dynamically and adaptively adjusted, and the taboo table Tabu will be cleared after each iteration to record the storage path in the next iteration;

[0027] Determine whether the maximum number of iterations is met. If so, output the route and length of the optimal evacuation path and the optimal route map. Otherwise, continue to iterate until the maximum number of iterations is met.

[0028] It can be seen from the above technical solution that the advantages of the present invention are:

[0029] 1. In this application, an intelligent management and control model is constructed by calculating and analyzing the pedestrian evacuation time and evacuation path, and a diversified emergency response plan library is integrated to improve emergency response capabilities and service quality, effectively handle emergencies or emergency situations, achieve the purpose of optimal path selection and reduce evacuation time, ensure the travel safety of passengers, make predictions more accurate, and control more timely. In addition, when facing complex situations such as high-density and rapid increase in passenger flow, control and guidance can be carried out according to the plan library. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application.

[0031] Figure 1 A schematic diagram of the steps of this application.

[0032] Figure 2 This is a schematic diagram of the structure of this application.

[0033] Figure 3 This is a schematic diagram of the specific steps of step S2 of this application.

[0034] Figure 4 This is a flowchart of the improved ant colony algorithm of this application. DETAILED DESCRIPTION

[0035] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the implementation modes and the accompanying drawings. Here, the illustrative implementation modes and descriptions of the present application are used to explain the present application, but are not intended to limit the present application.

[0036] refer to Figures 1 to 4 ,like Figure 1 As shown, this embodiment provides an intelligent control method for emergency events, which can effectively assist in handling traffic problems caused by emergencies such as fire, harmful gas emission, and commercial activities, and ensure the travel safety of passengers, and can also control and guide complex situations such as high-density and rapid increase in passenger flow. The intelligent control method for emergency events includes:

[0037] Step S1: Establish a safe evacuation time model for a comprehensive transportation hub, and decompose the pedestrian evacuation process of the comprehensive transportation hub based on the safe evacuation time model for the comprehensive transportation hub to obtain a pedestrian evacuation time series.

[0038] The step of establishing a safe evacuation time model for a comprehensive transportation hub and decomposing the pedestrian evacuation process of the comprehensive transportation hub based on the safe evacuation time model for the comprehensive transportation hub includes:

[0039] The total pedestrian evacuation time T is decomposed into three parts. The first part is the time for pedestrians to get off the bus. The second part is the time it takes for pedestrians to evacuate from the platform to the passage, recorded as the platform evacuation time The third part is the time it takes for pedestrians to pass through the passage, gate, and stairs, which is recorded as the passage evacuation time. .

[0040] Specifically, the time and number of pedestrians getting off the bus in the integrated transportation hub meet the following requirements: ,in, is the maximum number of pedestrians getting off each door in the integrated transportation hub, and is a constant parameter. In this embodiment, , The number of passengers entering the station can be predicted using a passenger flow prediction model for emergency activities and emergencies.

[0041] Step S2: further decompose the pedestrian evacuation time series according to the fluctuation of vehicle flow and the speed and density variation of pedestrian flow to obtain a pedestrian evacuation time subsequence group.

[0042] Step S2 is specifically as follows: according to the fluctuation of vehicle flow and the speed and density variation law of pedestrian flow, the pedestrian evacuation time series is further decomposed to obtain a pedestrian evacuation time subsequence group including:

[0043] Step S20: Calculate the platform evacuation time based on the traffic fluctuation theory , the platform evacuation time Including the time it takes for pedestrians to dissipate on the stairs , pedestrian passage time at the stairs , ;

[0044] Step S21: Calculate the channel evacuation time according to the speed and density change law of pedestrian flow , = ,in, is the channel length, The density of pedestrians in the passage or stairs.

[0045] Specifically, step S201: according to the formula Calculate the time it takes for pedestrians to disappear at the stairs ,in, , , The wave flow of pedestrians gathering after getting off the bus, is the wave flux of the pedestrian dissipation wave at the stairs, The normal walking speed of pedestrians after getting off the bus. is the pedestrian dissipation speed at the stairs; is the running speed of the escalator or the speed of pedestrians going up the stairs. is the pedestrian density at the platform, is the pedestrian density at the stairs, density of escalators or steps for pedestrians;

[0046] Step S202: According to the formula = Calculate pedestrian passage time at stairs ,in, is the step length.

[0047] Step S3: Use the improved ant colony algorithm to select the optimal path for pedestrian evacuation in the integrated transportation hub.

[0048] Traditional optimization algorithms often have problems such as high computational complexity and low search accuracy, making it difficult to accurately calculate the optimal evacuation strategy. By simulating the search process of multiple ants, the optimal solution can be obtained, which can reduce the algorithm's computing time.

[0049] The optimal path selection of pedestrian evacuation paths in comprehensive transportation hubs using the improved ant colony algorithm includes analyzing influencing factors, which include psychological influencing parameters and environmental influencing parameters, and constructing a path selection model of the improved ant colony algorithm based on the influencing factors.

[0050] In comprehensive transportation hubs, the main subjects of emergency activities and emergency event management are usually large-scale evacuation of people. The ultimate goal is to dynamically search for the path with the shortest evacuation time. However, due to abnormal emotions such as impatience and panic of the evacuees, crowd detention or congestion, changes in the event environment, etc. will affect the mobility of people. Therefore, there is a need for an evacuation path optimization method for the evacuation of people in large-scale buildings that takes into account the impact of the environment and the impact of crowd detention and congestion.

[0051] like Figure 2 As shown, the evacuation path analysis based on the improved ant colony includes two parts: brittleness analysis and path solving. Brittleness is an inherent property of complex systems. Brittleness refers to the property that under certain specific conditions, due to the influence of internal or external factors, the system may experience sudden, unpredictable and far-reaching failures or failures. This brittleness is determined by the high degree of interdependence and interactivity between the various components in the complex system. Once a key part of the system has a problem, it may trigger a chain reaction and lead to the collapse of the entire system. For example, a complex system may cause some subsystems to collapse under the interference of certain external factors, which may in turn cause the collapse of the entire system. Suppose the input of a complex system is xi (i=1, 2,…, m), and the output is yj (j=1, 2,…, n). When 1≤j≤n, when yj=0, it means the system is in a safe state and the system output function is normal, where: It means that for any j greater than or equal to 1 and less than or equal to n, when When yj=1, 1≤j≤n, it means the system is in a crash state, where Indicates that yj=1 exists, and the system output function is abnormal. xi[(xi)min,(xi)max], the state of the system is stable; as long as xi [(xi)min,(xi)max], the system will show a tendency to collapse. The emergency evacuation system of the comprehensive transportation hub is mainly composed of the passenger subsystem, evacuation road subsystem, ground transportation subsystem and management and control subsystem. Each subsystem is independent and interconnected and interacts with each other. The emergency evacuation system of the comprehensive transportation hub is a complex system and is also brittle. It contains multiple subsystems, each of which contains multiple elements. The subsystems influence each other and have strong interactivity. There are also complex relationships between the elements of each subsystem. When a subsystem is disturbed by uncertain factors, other subsystems will also be affected due to the interaction between subsystems. The continuous increase of interference factors leads to the collapse of subsystems one after another, which may lead to the collapse of the entire system. The collapse of the evacuation system is manifested in overcrowding in the hub, long queuing time, and disruptive behavior of passengers. The evacuation efficiency and congestion level of each subsystem are the core factors that determine whether the entire evacuation system can operate efficiently.

[0052] This application uses an improved ant colony algorithm to consider the impact of the event environment on the speed of personnel movement, and selects the optimal path for the pedestrian evacuation path of the comprehensive transportation hub. According to the characteristics of passenger evacuation in the comprehensive transportation hub, nodes that are prone to congestion are listed as obstacle points, such as the exit door, platform passage and the last traffic evacuation exit. These nodes are key nodes. The subsystem where each key node is located will not be congested within a certain capacity. Once the capacity is exceeded, the congestion will be prominent. The capacity of each key node is expressed by the congestion factor. When one of them is congested, it will affect the operation of the entire system, and it is necessary to effectively evacuate the passengers gathered in the hub. Therefore, it is particularly important to find a suitable and efficient evacuation path.

[0053] Specifically, the calculation process of the path selection model of the improved ant colony algorithm includes:

[0054] Step S30: Use the grid identification method to establish a hub evacuation map. Each grid is a grid. Initialize the grid environment, initialize the static attributes and dynamic attributes of the node, determine the obstacle location node B and the evacuation exit location E, where the static attributes include the two-dimensional spatial coordinates of the node, and the dynamic attributes include the time t, the number of people at the node at the tth time, the node type (normal node or obstacle node), the node temperature, the concentration of harmful gases, and the light source brightness coefficient, etc.

[0055] Step S31: Establishing the adjacency matrix of the grid, initializing the relevant parameters affecting the evacuation of personnel in emergency activities and emergencies, the relevant parameters are related to the psychological impact parameters and the environmental impact parameters, and initializing the model parameters and variables, the model parameters and variables include the maximum number of iterations Nmax, the number of evacuees m, the pheromone perception threshold of personnel to pheromones, the information heuristic factor a, the expected heuristic factor b, the pheromone volatilization factor c and the pheromone intensity Q, as well as the pheromone matrix and the taboo table;

[0056] like Figure 2 As shown in the figure, a safe evacuation time model is established to analyze the micro traffic characteristics. The analysis process includes influencing factors and evacuation time. The influencing factors include environmental factors and psychological factors caused by the incident. The evacuation time includes pedestrian alighting time, platform evacuation time and channel evacuation time.

[0057] Specifically, step S32: calculate the relevant parameters f1, f2 and f3 that affect the evacuation of personnel in emergency activities and emergencies, and then calculate the relevant parameters of the activity index M that affects the evacuation speed of personnel, M=f1×f2×f3, and the distance L between each adjacent node, and convert the distance into the equivalent length D between nodes, , ,v0 represents the normal walking speed of personnel in the passage, Indicates the speed at which people travel on a specific path, including narrow roads.

[0058] In this embodiment, the relevant parameters f1, f2 and f3 affecting the evacuation of personnel respectively represent the influence coefficient of temperature on the movement speed of personnel, the influence coefficient of harmful gas on the movement speed of personnel and the influence coefficient of light source brightness on the movement speed of personnel.

[0059] Step S33: Place m people on the starting node s respectively, add them to the taboo table, start iteration, and calculate the heuristic information matrix.

[0060] For each node in the grid, the heuristic function is used to calculate the estimated cost to the target node, and the cost value is used as the value of the corresponding node in the heuristic information matrix. According to the grid size and the calculated heuristic value, the heuristic information matrix is ​​constructed, and the Manhattan distance can be used as the heuristic function. The rows and columns of the matrix correspond to the rows and columns in the grid, respectively, and the element value in the matrix is ​​the heuristic value of the corresponding node.

[0061] Step S34: Search each path, find the free grid adjacent to the current grid in the adjacency matrix, select the next grid to be passed according to the probability selection rule, record the route of this iteration, use the route to determine the walking route, select the point with the strongest pheromone as the target of the next walking step, when the pheromone intensity Q> congestion factor r, the node is congested, reselect the key node, where r is the congestion factor of the key node of the comprehensive transportation hub, add the location point where the ant has passed to the taboo table, and determine whether the evacuees have found the exit. If they have found it, stop this iteration, record the walking route and length of the evacuees in this iteration, if no exit is found, continue to search for each corresponding path;

[0062] Step S35: After all passengers have completed a walk, the pheromone value will be updated, the pheromone concentration on each path will be updated, the pheromone volatility factor will be dynamically and adaptively adjusted, and the taboo table Tabu will be cleared after each iteration to record the storage path in the next iteration;

[0063] Step S36: Determine whether the maximum number of iterations is met. If so, output the route and length of the optimal evacuation path and output the optimal route map. Otherwise, continue iterative calculation until the maximum number of iterations is met.

[0064] Step S4: Construct a public transportation emergency collaborative dispatch infrastructure resource pool and an emergency management decision-making knowledge resource pool, and select the optimal evacuation path and the pedestrian evacuation time subsequence group, use the public transportation emergency collaborative dispatch recommendation method based on deep imitation learning to perform resource dispatch, and establish an emergency response plan library that integrates the expert decision rule library. When dispatching resources within the hub, adjust the dispatch plan in real time according to the evacuation path and path evacuation time to ensure the smoothness and efficiency of traffic during the evacuation process. Establish an emergency response plan library that integrates the expert decision rule library, covering different types of emergency events, and can quickly select and start the corresponding emergency response plan according to the actual situation.

[0065] This application aims at the frequent occurrence of emergencies in comprehensive transportation hubs, analyzes the influencing factors of emergency activities and emergencies in the hub, and establishes a safe evacuation time model for comprehensive transportation hubs. Taking into account the changing rules of pedestrian flow, the pedestrian control process in the comprehensive transportation hub is decomposed. Based on the brittleness theory of complex methods, a comprehensive transportation hub pedestrian evacuation control path selection technology based on an improved ant colony algorithm is proposed to improve the efficiency of passenger evacuation. A public transportation emergency collaborative dispatching infrastructure resource pool and an emergency management decision-making knowledge resource pool are constructed, and a public transportation emergency collaborative dispatching recommendation technology based on deep imitation learning is proposed. An emergency response plan library integrating an expert decision rule library is established, wherein deep imitation learning is a method of learning by imitating expert behavior or strategies. In public transportation emergency dispatching, deep learning models can be used to imitate the decision-making process of experienced dispatchers in emergency situations, so as to quickly generate reasonable dispatching plans. In ensuring the travel safety of passengers, predictions are more accurate and control is more timely.

[0066] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A smart emergency management method, characterized in that: The steps include: Establishing a safe evacuation time model for a comprehensive transportation hub, and decomposing the pedestrian evacuation process of the comprehensive transportation hub based on the safe evacuation time model for the comprehensive transportation hub to obtain a pedestrian evacuation time series; According to the fluctuation of vehicle flow and the speed and density variation of pedestrian flow, the pedestrian evacuation time series is further decomposed to obtain a pedestrian evacuation time subsequence group; An improved ant colony algorithm is used to select the optimal path for pedestrian evacuation in a comprehensive transportation hub; Construct a public transportation emergency collaborative dispatch infrastructure resource pool and an emergency management decision-making knowledge resource pool, and according to the selected optimal evacuation path and the pedestrian evacuation time subsequence group, use the public transportation emergency collaborative dispatch recommendation method based on deep imitation learning to perform resource dispatch, and establish an emergency response plan library that integrates the expert decision rule library; The step of establishing a safe evacuation time model for a comprehensive transportation hub and decomposing the pedestrian evacuation process of the comprehensive transportation hub based on the safe evacuation time model for the comprehensive transportation hub includes: The total pedestrian evacuation time T is decomposed into three parts. The first part is the time for pedestrians to get off the bus. The second part is the time it takes for pedestrians to evacuate from the platform to the passage, recorded as the platform evacuation time The third part is the time it takes for pedestrians to pass through the passage, gate, and stairs, which is recorded as the passage evacuation time. ; The time and number of pedestrians getting off the bus in the integrated transportation hub meet the following requirements: ,in, is the maximum number of pedestrians getting off each door in the integrated transportation hub, and is a constant parameter; Further decomposing the pedestrian evacuation time series according to the traffic flow fluctuation and the speed and density variation law of the pedestrian flow includes: Calculate platform evacuation time based on traffic fluctuation theory , the platform evacuation time Including the time it takes for pedestrians to dissipate on the stairs , pedestrian passage time at the stairs , ; Calculate the channel evacuation time according to the speed and density change rules of pedestrian flow , = ,in, is the channel length, The density of pedestrians on the passage or stairs; According to the traffic fluctuation theory, the platform evacuation time is calculated include: According to the formula Calculate the time it takes for pedestrians to disappear at the stairs ,in, , , The wave flow of pedestrians gathering after getting off the bus, is the wave flux of the pedestrian dissipation wave at the stairs, The normal walking speed of pedestrians after getting off the bus. is the pedestrian dissipation speed at the stairs; is the running speed of the escalator or the speed of pedestrians going up the stairs. is the pedestrian density at the platform, is the pedestrian density at the stairs, density of escalators or steps for pedestrians; According to the formula = Calculate pedestrian passage time at stairs ,in, is the step length; The optimal path selection of pedestrian evacuation paths in integrated transportation hubs using the improved ant colony algorithm includes analyzing influencing factors, wherein the influencing factors include psychological influencing parameters and environmental influencing parameters, and constructing a path selection model of the improved ant colony algorithm based on the influencing factors; The calculation process of the path selection model of the improved ant colony algorithm includes: The grid identification method is used to establish the hub evacuation map. Each grid is a grid. The grid environment is initialized, and the static and dynamic properties of the nodes are initialized to determine the obstacle location node B and the evacuation exit location E. Establish an adjacency matrix of the grid, initialize relevant parameters that affect the evacuation of personnel in emergency activities and emergencies, the relevant parameters are related to psychological impact parameters and environmental impact parameters, and initialize model parameters and variables, the model parameters and variables include the maximum number of iterations Nmax, the number of evacuees m, the pheromone perception threshold of personnel to pheromones, information heuristic factor a, expected heuristic factor b, pheromone volatilization factor c and pheromone intensity Q, as well as pheromone matrix and taboo table; Calculate the relevant parameters f1, f2 and f3 that affect the evacuation of personnel in emergency activities and emergencies, and then calculate the relevant parameters of the activity index M that affects the evacuation speed of personnel, M=f1×f2×f3, and the distance L between each adjacent node, and convert the distance into the equivalent length D between nodes, , ,v0 represents the normal walking speed of personnel in the passage, Indicates the speed at which people travel on a specific path; Place m people on the starting node s respectively, add them to the taboo table, start iteration, and calculate the heuristic information matrix; Search each path, find the free grid adjacent to the current grid in the adjacency matrix, select the next grid to pass through according to the pseudo-random proportional rule, record the route of this iteration, use the route to determine the walking route, select the point with the strongest pheromone as the target of the next walk, when the pheromone intensity Q> congestion factor r, the node is congested, reselect the key node, where r is the congestion factor of the key node of the comprehensive transportation hub, add the location point where the ant has passed to the taboo table, and determine whether the evacuees have found the exit. If they have found it, stop this iteration, record the walking route and length of the evacuees in this iteration, if the exit is not found, continue to search for each corresponding path; After all passengers complete a walk, the pheromone value will be updated, the pheromone concentration on each path will be updated, the pheromone volatility factor will be dynamically and adaptively adjusted, and the taboo table will be cleared after each iteration to record the storage path in the next iteration; Determine whether the maximum number of iterations is met. If so, output the route and length of the optimal evacuation path and the optimal route map. Otherwise, continue to iterate until the maximum number of iterations is met.

Images