Intelligent evacuation path automatic generation system and method based on artificial intelligence

Abstract

The invention belongs to the technical field of intelligent evacuation, and discloses an intelligent evacuation path automatic generation system and method based on artificial intelligence. The method comprises the following steps: collecting building modeling data, wherein the building modeling data comprises building key parameters and equipment resource parameters; modeling according to the building modeling data to obtain a building simulation model; defining personnel characteristic parameters and disaster characteristic parameters on the building simulation model to obtain an intelligent evacuation simulation model; self-adaptively generating an evacuation path according to the intelligent evacuation simulation model; according to the scheme, the congestion state can be quickly responded in the dynamic environment, the high efficiency and safety of evacuation are guaranteed to the maximum extent through the mode of combining shunting optimization and priority setting, and the method is suitable for various complex buildings and disaster scenes and has remarkable practical value.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent evacuation, and more specifically, to an intelligent evacuation path automatic generation system and method based on artificial intelligence. Background Art

[0002] In sudden disaster events such as fires, earthquakes, floods, etc., how to quickly and safely evacuate the people in the affected area is the core issue of ensuring life safety. However, traditional evacuation plans mostly rely on fixed route designs, failing to fully consider the real-time changes in the disaster environment and the characteristics of human behavior, resulting in problems such as congestion, blocked paths, and excessive evacuation times during actual evacuations. In addition, traditional methods lack efficient dynamic adjustment capabilities when dealing with complex building environments, unable to comprehensively optimize evacuation paths and allocate priorities, thus reducing the evacuation efficiency. Therefore, an intelligent evacuation path automatic generation system is designed to automatically simulate and evaluate evacuation paths in various disaster scenarios such as fires, earthquakes, floods, etc.

[0003] The existing Chinese patent application with the publication number CN109992876A proposes a method, device, and computer equipment for processing fire evacuation paths in buildings. The method includes: obtaining the room structure parameters of the building, determining the evacuation points and evacuation space exits of the evacuation space according to the room structure parameters of the building, generating evacuation paths from each evacuation point to the evacuation space exits according to the room structure parameters, and obtaining the detection result of whether the generated evacuation paths of the evacuation space meet the regulations according to the lengths of the evacuation paths. This method realizes the automatic drawing of the evacuation route map during the three-dimensional design process and automatically detects whether it meets the relevant requirements of fire protection specifications, enabling the building information model to meet the needs of fire protection design.

[0004] Although the above method can meet most scenarios, through research and practical application of the above method and the existing technology, it is found that the above method and the existing technology have at least the following partial defects:

[0005] Traditional evacuation plans usually rely on fixed route designs, making it difficult to cope with the dynamic changes in the real-time disaster environment and the complexity of human behavior, often resulting in problems such as congestion, blocked paths, and evacuation delays. For example, the people on some floors may evacuate smoothly due to priority evacuation, while the people on other floors are detained because the passages are occupied, significantly increasing the difficulty of escape. In addition, this method lacks dynamic adjustment capabilities in complex building environments, unable to optimize evacuation paths and priorities, and also difficult to provide targeted evacuation guidance for special groups (such as the disabled, the elderly, and children), further delaying the overall evacuation time and even endangering life safety.

[0006] In view of this, the present invention proposes an intelligent evacuation path automatic generation system and method based on artificial intelligence to solve the above problems. Summary of the Invention

[0007] To overcome the above defects of the prior art and to achieve the above object, the present invention provides the following technical solutions: An intelligent evacuation path automatic generation method based on artificial intelligence, including:

[0008] Collect building modeling data, where the building modeling data includes building key parameters and equipment resource parameters;

[0009] Model according to the building modeling data to obtain a building simulation model;

[0010] Define personnel characteristic parameters and disaster characteristic parameters on the building simulation model to obtain an intelligent evacuation simulation model;

[0011] Adaptive generate an evacuation path according to the intelligent evacuation simulation model.

[0012] Further, the method for adaptively generating an evacuation path according to the intelligent evacuation simulation model includes:

[0013] Step 1: Preset the total evacuation duration and time step; divide the total evacuation duration by the time step, and round up the result of the division to obtain H time steps; preset the initial value of h as 1, and the value range of h is from 1 to H; add all evacuation network edges to the set of edges to be processed; the evacuation network edges are the channels in the building simulation model;

[0014] Step 2: Start judging the evacuation status from the highest floor of the building structure in sequence. If all the personnel on the current floor have completed evacuation, remove the evacuation network edges connected to the evacuation network nodes corresponding to the current floor from the set of edges to be processed; continuously judge layer by layer downward until encountering a floor where the evacuation has not been completed, then terminate the judgment operation to obtain the set of edges to be processed at the h-th time step;

[0015] Step 3: Preset a congestion weight threshold 1 and a congestion weight threshold 2, where the congestion weight threshold 1 is greater than the congestion weight threshold 2; analyze and process the evacuation network edges in the set of edges to be processed in combination with the congestion weight threshold 1 and the congestion weight threshold 2 to obtain the congestion edge set, risk edge set, and unobstructed edge set at the h-th time step;

[0016] Step 4: Plan the evacuation path for the evacuation network edges according to the congestion edge set, risk edge set, and unobstructed edge set at the h-th time step;

[0017] Step 5: Let h = h + 1. If h is less than or equal to H, continue to execute Step 2 to Step 4. If h is greater than H, end the current process.

[0018] Further, the method for planning the evacuation path for the evacuation network edges according to the congestion edge set, risk edge set, and unobstructed edge set includes:

[0019] Perform the first flow rate diversion for the evacuation network edges in the congestion edge set according to the preset evacuation method;

[0020] Analyze and process the evacuation network edges in the risk edge set according to the preset processing method to obtain a secondary congestion edge set. If the number of evacuation network edges in the secondary congestion edge set is greater than zero, perform the second flow rate diversion for the evacuation network edges in the secondary congestion edge set in the same way as the first flow rate diversion. If the number of evacuation network edges in the secondary congestion edge set is equal to zero, end the current process;

[0021] In the same way as the method for obtaining the secondary congestion edge set, obtain a tertiary congestion edge set. If the number of evacuation network edges in the tertiary congestion edge set is greater than zero, perform the third flow rate diversion for the evacuation network edges in the tertiary congestion edge set in the same way as the first flow rate diversion. If the number of evacuation network edges in the tertiary congestion edge set is equal to zero, end the current process;

[0022] Input the current number of evacuated persons, individual attributes, maximum passing capacity, and disaster characteristic parameters corresponding to each evacuation network edge in the congestion edge set, risk edge set, and unobstructed edge set into the channel weight model respectively to obtain the evacuation network edge weights corresponding to each evacuation network edge in the congestion edge set, risk edge set, and unobstructed edge set;

[0023] Evacuate the evacuated persons in the evacuation network edges according to the evacuation network edge weights.

[0024] Furthermore, the method for evacuating the evacuated persons in the evacuation network edges according to the evacuation network edge weights includes:

[0025] If there is an evacuation network edge with an evacuation network edge weight greater than or equal to the first congestion weight threshold, add the evacuation network edge with an evacuation network edge weight greater than or equal to the first congestion weight threshold to the weight setting set, and set the evacuation priority for the individual attributes of the evacuated persons corresponding to the evacuation network edges in the weight setting set; Evacuate the evacuated persons with a third-level evacuation level from the evacuation network edges in the weight setting set. The evacuated persons with a first-level evacuation level and a second-level evacuation level enter the floor buffer area to wait. After the evacuated persons with a third-level evacuation level are evacuated, the evacuated persons with a first-level evacuation level and a second-level evacuation level are evacuated;

[0026] If there is no evacuation network edge with an evacuation network edge weight greater than or equal to the first congestion weight threshold, end the current process.

[0027] Furthermore, the method for setting the evacuation priority for the individual attributes of the evacuated persons corresponding to the evacuation network edges in the weight setting set includes:

[0028] S140: Denote the number of evacuation network edges in the weight setting set as QZ, set the initial value of the preset qz to 1, and the value range of qz is from 1 to QZ;

[0029] S141: Obtain the qz-th evacuation network edge from the weight setting set, and obtain the current number of evacuees in the qz-th evacuation network edge, denoted as P; input the current number of evacuees, the maximum passing capacity, and the individual attributes of the P evacuees into the weight setting model respectively to obtain the evacuation priorities of the P evacuees corresponding to the qz-th evacuation network edge;

[0030] S142: Let qz = qz + 1. If qz is less than or equal to QZ, continue to execute S141. If qz is greater than QZ, end the current process.

[0031] Further, the method for obtaining the congested edge set, the risky edge set, and the unobstructed edge set includes:

[0032] S110: Denote the number of evacuation network edges in the edge set to be processed as TD, set the initial value of the preset td to 1, and the value range of td is from 1 to TD;

[0033] S111: Obtain the current number of evacuees and individual attributes in the td-th evacuation network edge;

[0034] S112: Input the current number of evacuees, individual attributes, the maximum passing capacity, and the disaster characteristic parameters into the channel weight model to obtain the evacuation network edge weight of the td-th evacuation network edge;

[0035] S113: If the evacuation network edge weight of the td-th evacuation network edge is greater than or equal to the first congestion weight threshold, add the td-th evacuation network edge to the congested edge set; if the evacuation network edge weight of the td-th evacuation network edge is greater than or equal to the second congestion weight threshold and less than the first congestion weight threshold, add the td-th evacuation network edge to the risky edge set; if the evacuation network edge weight of the td-th evacuation network edge is less than the second congestion weight threshold, add the td-th evacuation network edge to the unobstructed edge set;

[0036] S114: Let td = td + 1. If td is less than or equal to TD, continue to execute S111 to S113; if td is greater than TD, end the current process.

[0037] Further, the method for performing the first flow rate diversion on the evacuation network edges in the congested edge set according to the preset evacuation method includes:

[0038] S120: If the number of evacuation network edges in the congestion edge set is not zero, record the number of evacuation network edges in the congestion edge set as YD, set the initial value of the preset yd to 1, and the value range of yd is from 1 to YD; if the number of evacuation network edges in the congestion edge set is zero, end the current process;

[0039] S121: Obtain the yd-th evacuation network edge from the congestion edge set, and add the evacuation network edges adjacent to the yd-th evacuation network edge and not in the congestion edge set to the evacuation diversion set corresponding to the yd-th evacuation network edge; if the number of evacuation network edges in the evacuation diversion set corresponding to the yd-th evacuation network edge is not zero, calculate the evacuation traffic flow borne by each evacuation network edge in the evacuation diversion set, and calculate the latest current number of evacuated people for each evacuation network edge in the evacuation diversion set according to the evacuation traffic flow borne by each evacuation network edge; update the current number of evacuated people for each evacuation network edge in the evacuation diversion set to the corresponding latest current number of evacuated people;

[0040] S122: Calculate the latest current number of evacuated people for the yd-th evacuation network edge in the congestion edge set according to the evacuation traffic flow borne by each evacuation network edge in the evacuation diversion set, and update the current number of evacuated people for the yd-th evacuation network edge in the congestion edge set to the latest current number of evacuated people;

[0041] S123: Let yd = yd + 1. If yd is less than or equal to YD, continue to execute S121 to S122; if yd is greater than YD, end the current process.

[0042] Further, the calculation method for the evacuation traffic flow borne by each evacuation network edge in the evacuation diversion set includes:

[0043] Calculate the evacuation traffic flow borne by each evacuation network edge according to the remaining capacity of each evacuation network edge in proportion; the remaining capacity of each evacuation network edge is the maximum number of people that can pass through the corresponding evacuation network edge minus the current number of evacuated people.

[0044] Further, the method for analyzing and processing the evacuation network edges in the risk edge set according to the preset processing method to obtain the secondary congestion edge set includes:

[0045] S130: If the number of evacuation network edges in the risk edge set is not zero, record the number of evacuation network edges in the risk edge set as FX, set the initial value of the preset fx to 1, and the value range of fx is from 1 to FX; if the number of evacuation network edges in the risk edge set is zero, end the current process;

[0046] S131: Obtain the fx-th evacuation network edge from the risk edge set, and input the current number of evacuated persons, individual attributes, maximum passing capacity, and disaster characteristic parameters of the fx-th evacuation network edge into the channel weight model to obtain the evacuation network edge weight of the fx-th evacuation network edge;

[0047] S132: If the evacuation network edge weight of the fx-th evacuation network edge is greater than or equal to the congestion weight threshold one, add the fx-th evacuation network edge to the secondary congestion edge set;

[0048] S133: Let fx = fx + 1. If fx is less than or equal to FX, continue to execute S131 to S132; if fx is greater than FX, end the current process.

[0049] An intelligent evacuation path automatic generation system based on artificial intelligence, implementing the intelligent evacuation path automatic generation method based on artificial intelligence, includes:

[0050] The first acquisition module is used to acquire building modeling data, and the building modeling data includes building key parameters and equipment resource parameters;

[0051] The data modeling module is used to perform modeling according to the building modeling data to obtain a building simulation model;

[0052] The parameter definition module is used to define personnel characteristic parameters and disaster characteristic parameters on the building simulation model to obtain an intelligent evacuation simulation model;

[0053] The intelligent evacuation module is used to adaptively generate an evacuation path according to the intelligent evacuation simulation model;

[0054] The evacuation evaluation module is used to summarize and output the evacuation simulation results after the evacuation simulation is completed.

[0055] The technical effects and advantages of the intelligent evacuation path automatic generation system and method based on artificial intelligence of the present invention:

[0056] By real-time collection and analysis of the congestion status, risk status and smooth status of the evacuation network edge, combined with the three-iteration diversion mechanism, a rapid response to the dynamic environment is achieved, effectively alleviating the local congestion problem caused by high-density human flow. The individual attributes of the evacuees (such as age, gender, special population classification, etc.) are analyzed through the weight setting model, and the evacuation priority is accurately set to provide targeted evacuation guidance for special populations, reflecting the high attention to safety and fairness. The floor buffer mechanism is introduced to temporarily accommodate people with lower evacuation priorities, avoiding overload and congestion, while further ensuring the orderliness and continuity of the evacuation process. By real-time collection and accurate summary of data during the evacuation process, an intuitive and usable evacuation report is generated to support users to comprehensively evaluate the advantages and disadvantages of the evacuation plan; at the same time, the data-driven feedback mechanism promotes the continuous optimization of path planning.

[0057] This solution can quickly respond to congestion in a dynamic environment. By combining diversion optimization and priority setting, it maximizes the efficiency and safety of evacuation. It is suitable for a variety of complex buildings and disaster scenarios and has significant practical value and innovation. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a schematic diagram of an intelligent evacuation path automatic generation system based on artificial intelligence according to Embodiment 1 of the present invention;

[0059] Figure 2 This is a flow chart of a method for automatically generating an intelligent evacuation path based on artificial intelligence according to Embodiment 2 of the present invention;

[0060] Figure 3 A flow chart of a method for adaptively generating an evacuation route according to an intelligent evacuation simulation model;

[0061] Figure 4 The present invention is a flow chart of a method for planning evacuation paths for evacuation network edges according to a congested edge set, a risk edge set and a smooth edge set. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0063] Example 1

[0064] See also Figure 1As shown in the figure, the intelligent evacuation path automatic generation system based on artificial intelligence in this embodiment includes a first acquisition module, a data modeling module, a parameter definition module, an intelligent evacuation module, and an evacuation evaluation module. Each module is connected by wire and / or wirelessly to achieve data transmission.

[0065] The first acquisition module is used to acquire building modeling data, and the building modeling data includes building key parameters and equipment resource parameters; the building key parameters include floor height, structural layout, number of passages, and exit positions; the equipment resource parameters include alarm layout, emergency lighting equipment layout, and fire fighting equipment layout.

[0066] The data modeling module is used to model according to the building modeling data to obtain a building simulation model.

[0067] The method for obtaining the building simulation model includes:

[0068] Import the building key parameters into the building floor plan, identify walls, rooms, corridors, stairs, passages, and exits in the building floor plan; assign the building key parameters to the corresponding building areas, set the maximum number of people that can pass through each passage, and obtain a floor plan with physical meaning.

[0069] Import the equipment resource parameters into the floor plan, and mark the positions of alarms, emergency lighting equipment, and fire fighting equipment in the floor plan.

[0070] On the basis of the floor plan, use building information modeling technology (BIM) to connect the floors to form a complete building three-dimensional space; import the marked alarms, emergency lighting equipment, and fire fighting equipment into the building three-dimensional space, define the coverage range and function trigger conditions of alarms, emergency lighting equipment, and fire fighting equipment, and obtain a building simulation model.

[0071] The parameter definition module is used to define personnel characteristic parameters and disaster characteristic parameters on the building simulation model to obtain an intelligent evacuation simulation model.

[0072] The method for obtaining the intelligent evacuation simulation model includes:

[0073] S100: Obtain the floor height in the building simulation model, denoted as LG; preset the initial value of lg to 1, and the value range of lg is from 1 to LG.

[0074] S101: Set the personnel characteristic parameters of the \(lg\)th floor on the building simulation model; the personnel characteristic parameters include the initial distribution positions and individual attributes of the evacuees on the \(lg\)th floor; the individual attributes include gender, age, movement speed, evacuation priority, and the crowd category to which the individual belongs; the evacuation priority includes the first-level evacuation level, the second-level evacuation level, and the third-level evacuation level. The higher the level of the evacuation priority, the higher the degree of evacuation priority.

[0075] It should be noted that the crowd category is used to distinguish ordinary people from special groups. The classification of special groups includes people with limited mobility (such as those using wheelchairs or crutches), the elderly (such as those over 65 years old), and children (such as those under 14 years old), etc. In addition, the movement characteristic parameters of special groups can be further refined. For example:

[0076] Movement ability: such as normal walking, slow movement, or complete dependence on assistive devices;

[0077] Evacuation priority: Define the priority degree of special groups in evacuation according to their physiological or psychological characteristics;

[0078] Auxiliary needs: such as whether they need human assistance or professional equipment support.

[0079] By comprehensively considering gender, age, the number of people, and the classification and proportion of special groups, the needs and behavior patterns of different types of people during evacuation can be more accurately reflected, so as to optimize the evacuation route design, improve the overall evacuation efficiency, and provide targeted solutions for the safe evacuation of special groups.

[0080] S102: Let \(lg = lg + 1\). If \(lg\) is less than or equal to \(LG\), continue to execute S101. If \(lg\) is greater than \(LG\), execute S103;

[0081] S103: Set the disaster characteristic parameters on the building simulation model. The disaster characteristic parameters include disaster type, disaster severity level, and disaster hazards; mark the exit positions in the building simulation model as evacuation network nodes, mark the channels in the building simulation model as evacuation network edges, construct all evacuation network nodes and evacuation network edges into an evacuation network, and connect the exit nodes through edges to obtain an intelligent evacuation simulation model.

[0082] It should be noted that the disaster types include fire, earthquake, flood, etc. The disaster severity levels include the first-level severity level, the second-level severity level, and the third-level severity level. The higher the level of the disaster severity, the higher the degree of disaster severity; the disaster hazards include high temperature, asphyxiation, and slipping, etc.

[0083] An intelligent evacuation module, used to adaptively generate evacuation paths according to the intelligent evacuation simulation model.

[0084] Such asFigure 3 As shown in Figure 3 , the method for adaptively generating evacuation routes according to the intelligent evacuation simulation model includes:

[0085] Step 1: Preset the total evacuation duration and the time step; divide the total evacuation duration by the time step, and round up the result of the division to obtain H time steps; preset the initial value of h as 1, where the value range of h is from 1 to H; add all the evacuation network edges to the set of edges to be processed; the evacuation network edges are the channels in the building simulation model.

[0086] The method for obtaining the H time steps includes:

[0087]

[0088] where Time max is the total evacuation duration, and Time step is the time step, represents rounding up.

[0089] Step 2: Start judging the evacuation status from the highest floor of the building structure in sequence. If all the people on the current floor have completed evacuation, remove the evacuation network edges connected to the evacuation network nodes corresponding to the current floor from the set of edges to be processed; this process continues to judge layer by layer downward until it encounters a floor where evacuation has not been completed, and then terminate the judgment operation to obtain the set of edges to be processed at the h-th time step.

[0090] Step 3: Preset a congestion weight threshold 1 and a congestion weight threshold 2, where the congestion weight threshold 1 is greater than the congestion weight threshold 2; analyze and process the evacuation network edges in the set of edges to be processed in combination with the congestion weight threshold 1 and the congestion weight threshold 2 to obtain the set of congested edges, the set of risky edges, and the set of unobstructed edges at the h-th time step.

[0091] Step 4: Plan the evacuation routes for the evacuation network edges according to the set of congested edges, the set of risky edges, and the set of unobstructed edges at the h-th time step.

[0092] Step 5: Let h = h + 1. If h is less than or equal to H, continue to execute Steps 2 to 4; if h is greater than H, end the current process.

[0093] The method for obtaining the set of congested edges, the set of risky edges, and the set of unobstructed edges includes:

[0094] S110: Denote the number of evacuation network edges in the set of edges to be processed as TD, preset the initial value of td as 1, where the value range of td is from 1 to TD;

[0095] S111: Obtain the current number of evacuated people and individual attributes in the td-th evacuation network edge.

[0096] S112: Input the current number of evacuees, individual attributes, maximum passing capacity, and disaster characteristic parameters into the passage weight model to obtain the evacuation network edge weight of the $t_d$-th evacuation network edge.

[0097] S113: If the evacuation network edge weight of the $t_d$-th evacuation network edge is greater than or equal to the first congestion weight threshold, add the $t_d$-th evacuation network edge to the congestion edge set; if the evacuation network edge weight of the $t_d$-th evacuation network edge is greater than or equal to the second congestion weight threshold and less than the first congestion weight threshold, add the $t_d$-th evacuation network edge to the risk edge set; if the evacuation network edge weight of the $t_d$-th evacuation network edge is less than the second congestion weight threshold, add the $t_d$-th evacuation network edge to the unobstructed edge set.

[0098] S114: Let $t_d=t_d + 1$. If $t_d$ is less than or equal to $TD$, continue to execute S111 to S113; if $t_d$ is greater than $TD$, end the current process.

[0099] The training method of the passage weight model includes:

[0100] Pre-collect a weight evaluation data set, where the weight evaluation data set includes $G$ groups of weight evaluation data and the corresponding evacuation network edge weights. $G$ is a positive integer greater than 0. The weight evaluation data includes the current number of evacuees, individual attributes, maximum passing capacity, and disaster characteristic parameters. The evacuation network edge weights are evaluated by multiple technicians in the field according to the actual weight evaluation data and corresponding scores are given. After removing the maximum and minimum values, the average value is taken to obtain the evacuation network edge weights. Divide the weight evaluation data set into a training set and a test set. Use the weight evaluation data in the training set as the input of the passage weight model, and use the evacuation network edge weights in the training set as the output of the passage weight model. Take minimizing the sum of the prediction accuracies of all predicted evacuation network edge weights as the training objective. Stop training until the sum of the prediction accuracies reaches convergence. The passage weight model is a Naive Bayes model or a Support Vector Machine model.

[0101] As Figure 4 shown, the method for evacuating path planning for evacuation network edges according to the congestion edge set, risk edge set, and unobstructed edge set includes:

[0102] Perform the first flow rate diversion for the evacuation network edges in the congestion edge set according to the preset evacuation method.

[0103] Analyze and process the evacuation network edges in the risk edge set according to the preset processing method to obtain the secondary congestion edge set. If the number of evacuation network edges in the secondary congestion edge set is greater than zero, perform the second flow rate diversion for the evacuation network edges in the secondary congestion edge set in the same way as the first flow rate diversion of people. If the number of evacuation network edges in the secondary congestion edge set is equal to zero, end the current process;

[0104] In the same way as the method for obtaining the secondary congestion edge set, obtain the tertiary congestion edge set. If the number of evacuation network edges in the tertiary congestion edge set is greater than zero, perform the third flow rate diversion for the evacuation network edges in the tertiary congestion edge set in the same way as the first flow rate diversion of people. If the number of evacuation network edges in the tertiary congestion edge set is equal to zero, end the current process;

[0105] Input the current number of evacuated people, individual attributes, maximum passing capacity, and disaster characteristic parameters corresponding to each evacuation network edge in the congestion edge set, risk edge set, and unobstructed edge set into the channel weight model respectively to obtain the evacuation network edge weights corresponding to each evacuation network edge in the congestion edge set, risk edge set, and unobstructed edge set;

[0106] If there is an evacuation network edge with an edge weight greater than or equal to the first congestion weight threshold, indicating that there is still an evacuation network edge in a congested state after three diversions, then add the evacuation network edge with an edge weight greater than or equal to the first congestion weight threshold to the weight setting set, and set the evacuation priority for the individual attributes of the evacuated people corresponding to the evacuation network edge in the weight setting set; Evacuate the evacuated people with a third-level evacuation priority from the evacuation network edge in the weight setting set, and the evacuated people with non-third-level evacuation priorities enter the floor buffer area to wait. After the evacuated people with third-level evacuation priorities are evacuated, the evacuated people with non-third-level evacuation priorities are evacuated; If there is no evacuation network edge with an edge weight greater than or equal to the first congestion weight threshold, end the current process.

[0107] It should be noted that by gradually diverting the congestion edge set and risk edge set, the congestion problem caused by high-density crowds is effectively alleviated, ensuring the dynamic controllability of the evacuation process. The mechanism of three iterative diversions gradually reduces the congestion risk, avoids the local congestion problem caused by single diversion, dynamically adjusts the evacuation path, improves the overall evacuation efficiency, makes the path planning more adaptable, and can respond to dynamic environmental changes in real time. After the diversion is completed, the channel weight model is introduced to quantitatively evaluate the evacuation network edges, comprehensively considering the current number of evacuated people, individual attributes, maximum passing capacity, and disaster characteristic parameters, providing a reliable quantitative basis for subsequent evacuation path planning, and realizing the precise optimization of the evacuation path based on real-time data.

[0108] Setting evacuation priorities based on the individual attributes of the evacuees reflects care for special groups and helps improve evacuation safety and fairness. Implementing a priority evacuation strategy for people with high evacuation priorities at the edge of the evacuation network effectively reduces the pressure of people flow in high-density areas; temporarily placing people with low evacuation priorities in floor buffer zones to avoid channel overload and improve the controllability of evacuation order.

[0109] The method of performing the first flow diversion of the evacuation network edge in the congestion edge set according to the preset evacuation method includes:

[0110] S120: If the number of evacuation network edges in the congestion edge set is not zero, the number of evacuation network edges in the congestion edge set is recorded as YD, the initial value of yd is preset to 1, and the value range of yd is 1 to YD; if the number of evacuation network edges in the congestion edge set is zero, the current process is terminated;

[0111] S121: Obtain the ydth evacuation network edge from the congestion edge set, and add the evacuation network edges that are adjacent to the ydth evacuation network edge and are not in the congestion edge set to the evacuation diversion set corresponding to the ydth evacuation network edge; if the number of evacuation network edges in the evacuation diversion set corresponding to the ydth evacuation network edge is not zero, calculate the evacuation flow rate shared by each evacuation network edge in the evacuation diversion set, and calculate the latest current number of evacuated personnel for each evacuation network edge in the evacuation diversion set based on the evacuation flow rate shared by each evacuation network edge; update the current number of evacuated personnel for each evacuation network edge in the evacuation diversion set to the corresponding latest current number of evacuated personnel;

[0112] S122: Calculate the latest current number of evacuees on the yd-th evacuation network edge in the congestion edge set according to the evacuation flow shared by each evacuation network edge in the evacuation diversion set, and update the current number of evacuees on the yd-th evacuation network edge in the congestion edge set to the latest current number of evacuees;

[0113] S123: Let yd=yd+1. If yd is less than or equal to YD, continue to execute S121 to S122. If yd is greater than YD, end the current process.

[0114] The calculation method of the evacuation flow rate shared by each evacuation network edge in the evacuation flow distribution set includes:

[0115]

[0116] Among them, Split(yd) i is the evacuation flow that the ith evacuation network edge in the evacuation diversion set corresponding to the ydth evacuation network edge should share, ED yd is the number of evacuation network edges in the evacuation diversion set corresponding to the yd-th evacuation network edge, NMAX(yd)i is the maximum number of people that can pass through the \(i\)-th evacuation network in the evacuation diversion set corresponding to the \(yd\)-th evacuation network edge, NNOW(yd) i is the current number of evacuated people in the \(i\)-th evacuation network in the evacuation diversion set corresponding to the \(yd\)-th evacuation network edge, YDRS yd is the current number of evacuated people on the \(yd\)-th evacuation network edge, YDMAX yd is the maximum number of people that can pass through the \(yd\)-th evacuation network edge, and \(\delta\) is the weight coefficient.

[0117] The calculation method for the latest current number of evacuated people for each evacuation network edge in the evacuation diversion set includes:[[]]

[0118] NNOW(yd) (i，new) = Split(yd) i + NNOW(yd) i ;

[0119] Among them, NNOW(yd) (i，new) is the latest current number of evacuated people on the \(i\)-th evacuation network edge in the evacuation diversion set corresponding to the \(yd\)-th evacuation network edge.

[0120] The calculation method for the latest current number of evacuated people on the \(yd\)-th evacuation network edge in the congestion edge set includes:[[]]

[0121]

[0122] Among them, YDCU (yd，new) is the latest current number of evacuated people on the \(yd\)-th evacuation network edge in the congestion edge set, and YDCU yd is the number of evacuated people on the \(yd\)-th evacuation network edge in the congestion edge set before the evacuation of people is diverted.

[0123] The method for analyzing and processing the evacuation network edges in the risk edge set according to a preset processing method to obtain a secondary congestion edge set includes:[[]]

[0124] S130: If the number of evacuation network edges in the risk edge set is not zero, then record the number of evacuation network edges in the risk edge set as FX, the initial value of the preset fx is 1, and the value range of fx is from 1 to FX; if the number of evacuation network edges in the risk edge set is zero, then end the current process;

[0125] S131: Obtain the \(fx\)-th evacuation network edge from the risk edge set, and input the current number of evacuated people, individual attributes, maximum number of people that can pass through, and disaster characteristic parameters of the \(fx\)-th evacuation network edge into the channel weight model to obtain the evacuation network edge weight of the \(fx\)-th evacuation network edge;

[0126] S132: If the evacuation network edge weight of the fx-th evacuation network edge is greater than or equal to the congestion weight threshold one, add the fx-th evacuation network edge to the secondary congestion edge set;

[0127] S133: Let fx = fx + 1. If fx is less than or equal to FX, continue to execute S131 to S132; if fx is greater than FX, end the current process.

[0128] The method for setting evacuation priorities for the individual attributes of the evacuees corresponding to the evacuation network edges in the weight setting set includes:

[0129] S140: Denote the number of evacuation network edges in the weight setting set as QZ. Preset the initial value of qz to 1, and the value range of qz is from 1 to QZ;

[0130] S141: Obtain the qz-th evacuation network edge from the weight setting set, and obtain the current number of evacuees in the qz-th evacuation network edge, denoted as P; input the current number of evacuees, the maximum number of people passing through, and the individual attributes of the P evacuees into the weight setting model respectively to obtain the evacuation priorities of the P evacuees corresponding to the qz-th evacuation network edge;

[0131] S142: Let qz = qz + 1. If qz is less than or equal to QZ, continue to execute S141; if qz is greater than QZ, end the current process.

[0132] The training method of the weight setting model includes:

[0133] Pre-collect a weight setting data set. The weight setting data set includes Y groups of weight setting data and the corresponding evacuation priorities for the Y groups of weight setting data. Y is a positive integer greater than 0. The weight setting data includes the current number of evacuees, individual attributes, and the maximum number of people passing through; divide the weight setting data set into a training set and a test set. Use the weight setting data in the training set as the input of the weight setting model, and use the evacuation priorities in the training set as the output of the weight setting model. Take minimizing the sum of the prediction accuracies of all predicted evacuation priorities as the training objective; stop training until the sum of the prediction accuracies reaches convergence; the weight setting model is a random forest model or a gradient boosting tree model.

[0134] The evacuation evaluation module is used to summarize and output the evacuation simulation results after the evacuation simulation is completed.

[0135] The method for evaluating the evacuation simulation results includes:

[0136] During the evacuation simulation process, dynamic record data for each time step is obtained. The dynamic record data includes the current positions of people, their movement speeds, and the status of passageways. People who have completed evacuation and those who have not are classified and marked, and their final status is recorded. For people who have not completed evacuation, the evacuation duration is continuously recorded, and for those who have completed evacuation, the recording of the evacuation duration is stopped. The evacuation distance is recorded in the same way as the recording method for the evacuation duration.

[0137] The number of people who have completed evacuation and the number of people who have not completed evacuation are counted. The people who have completed evacuation and those who have not are classified according to individual attributes, and the number of people who have completed evacuation and the number of people who have not completed evacuation corresponding to people with different attributes are obtained. The evacuation times are summarized to obtain the longest evacuation time, the shortest evacuation time, and the average evacuation time corresponding to people with different attributes. The evacuation distances are summarized to obtain the longest evacuation distance, the shortest evacuation distance, and the average evacuation distance corresponding to people with different attributes.

[0138] The number of people who have completed evacuation, the number of people who have not completed evacuation, the longest evacuation time, the shortest evacuation time, the average evacuation time, the longest evacuation distance, the shortest evacuation distance, and the average evacuation distance corresponding to people with different attributes are output in a predetermined format.

[0139] Embodiment 2

[0140] Please refer to Figure 2 As shown, this embodiment provides an intelligent evacuation path automatic generation method based on artificial intelligence, which further includes:

[0141] Collect building modeling data, which includes building key parameters and equipment resource parameters.

[0142] Model based on the building modeling data to obtain a building simulation model.

[0143] Define personnel characteristic parameters and disaster characteristic parameters on the building simulation model to obtain an intelligent evacuation simulation model.

[0144] Adaptive generate an evacuation path according to the intelligent evacuation simulation model.

[0145] As described above, the above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art within the technical scope disclosed by the present invention can easily think of changes or substitutions, which should all be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

[0146] Finally: The above is only the preferred embodiment of the present invention and is not used to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should all be included within the protection scope of the present invention.

Claims

1. The method for automatically generating intelligent evacuation paths based on artificial intelligence is characterized in that: include: Collecting building modeling data, wherein the building modeling data includes key building parameters and equipment resource parameters; Modeling is performed according to the building modeling data to obtain a building simulation model; Defining personnel characteristic parameters and disaster characteristic parameters on the building simulation model to obtain an intelligent evacuation simulation model; The evacuation route is adaptively generated based on the intelligent evacuation simulation model.

2. The method for automatically generating an intelligent evacuation path based on artificial intelligence according to claim 1 is characterized in that: The method of adaptively generating an evacuation path according to an intelligent evacuation simulation model includes: Step 1: preset the total evacuation time and time step; take the total evacuation time as the quotient of the time step, and round up the result of the quotient to obtain H time steps; preset the initial value of h to be 1, and the value range of h is 1 to H; add all evacuation network edges to the set of edges to be processed; the evacuation network edges are channels in the building simulation model; Step 2: Start judging the evacuation status from the highest floor of the building structure. If all personnel on the current floor have been evacuated, remove the evacuation network edge connected to the evacuation network node corresponding to the current floor from the set of edges to be processed. Continue judging layer by layer until a floor that has not been evacuated is encountered, and terminate the judgment operation to obtain the set of edges to be processed for the hth time step. Step 3: preset congestion weight threshold 1 and congestion weight threshold 2, and congestion weight threshold 1 is greater than congestion weight threshold 2; analyze and process the evacuation network edges in the edge set to be processed by combining congestion weight threshold 1 and congestion weight threshold 2, and obtain the congestion edge set, risk edge set and smooth edge set of the hth time step; Step 4: Plan the evacuation path for the evacuation network edge according to the congestion edge set, risk edge set and smooth edge set of the hth time step; Step 5: Let h=h+1. If h is less than or equal to H, continue to execute steps 2 to 4. If h is greater than H, end the current process.

3. The method for automatically generating an intelligent evacuation path based on artificial intelligence according to claim 2 is characterized in that: The method of planning the evacuation path for the evacuation network edge according to the congestion edge set, risk edge set and smooth edge set includes: According to the preset evacuation method, the first flow of people is diverted to the evacuation network edge in the congested edge set; According to the preset processing method, the evacuation network edges in the risk edge set are analyzed and processed to obtain the secondary congestion edge set. If the number of evacuation network edges in the secondary congestion edge set is greater than zero, the evacuation network edges in the secondary congestion edge set are subjected to a second flow diversion using the same method as the first flow diversion. If the number of evacuation network edges in the secondary congestion edge set is equal to zero, the current process ends. The same method as the second congestion edge set is used to obtain the third congestion edge set. If the number of evacuation network edges in the third congestion edge set is greater than zero, the third flow diversion is performed on the evacuation network edges in the third congestion edge set in the same way as the first flow diversion. If the number of evacuation network edges in the third congestion edge set is equal to zero, the current process ends. The current number of evacuees, individual attributes, maximum number of passers-by and disaster characteristic parameters corresponding to each evacuation network edge in the congestion edge set, risk edge set and smooth edge set are respectively input into the channel weight model to obtain the evacuation network edge weight corresponding to each evacuation network edge in the congestion edge set, risk edge set and smooth edge set; Evacuate the evacuees on the evacuation network edges according to the evacuation network edge weights.

4. The method for automatically generating an intelligent evacuation path based on artificial intelligence according to claim 3 is characterized in that: The methods for evacuating the evacuees on the evacuation network edges according to the evacuation network edge weights include: If there is an evacuation network edge whose weight is greater than or equal to the congestion weight threshold 1, then the evacuation network edge whose weight is greater than or equal to the congestion weight threshold 1 is added to the weight setting set, and the evacuation priority is set for the individual attribute of the evacuees corresponding to the evacuation network edge in the weight setting set; the evacuees with the evacuation priority of the third evacuation level are evacuated from the evacuation network edge in the weight setting set, and the evacuees with the first evacuation level and the second evacuation level enter the floor buffer zone and wait. After the evacuees with the third evacuation level are evacuated, the evacuees with the first evacuation level and the second evacuation level are evacuated; If there is no evacuation network edge whose evacuation network edge weight is greater than or equal to the congestion weight threshold 1, the current process ends.

5. The method for automatically generating an intelligent evacuation path based on artificial intelligence according to claim 4 is characterized in that: The method of setting the evacuation priority for the individual attributes of the evacuees corresponding to the evacuation network edges in the weight setting set includes: S140: Record the number of evacuation network edges in the weight setting set as QZ, preset the initial value of qz to be 1, and the value range of qz is 1 to QZ; S141: Obtain the qzth evacuation network edge from the weight setting set, obtain the current number of evacuees in the qzth evacuation network edge, recorded as P; input the current number of evacuees, the maximum number of passers-by, and the individual attributes corresponding to the P evacuees into the weight setting model respectively, and obtain the evacuation priority corresponding to the P evacuees in the qzth evacuation network edge; S142: Let qz=qz+1. If qz is less than or equal to QZ, continue to execute S141. If qz is greater than QZ, end the current process.

6. The method for automatically generating an intelligent evacuation path based on artificial intelligence according to claim 5 is characterized in that: The method for obtaining the congested edge set, the risk edge set and the smooth edge set includes: S110: Record the number of evacuation network edges in the edge set to be processed as TD, preset the initial value of td to be 1, and the value range of td is 1 to TD; S111: Obtain the current number of evacuees and individual attributes in the tdth evacuation network edge; S112: Input the current number of evacuees, individual attributes, maximum number of passers-by and disaster characteristic parameters into the channel weight model to obtain the evacuation network edge weight of the td-th evacuation network edge; S113: If the evacuation network edge weight of the tdth evacuation network edge is greater than or equal to the congestion weight threshold 1, then the tdth evacuation network edge is added to the congestion edge set; if the evacuation network edge weight of the tdth evacuation network edge is greater than or equal to the congestion weight threshold 2, and less than the congestion weight threshold 1, then the tdth evacuation network edge is added to the risk edge set; if the evacuation network edge weight of the tdth evacuation network edge is less than the congestion weight threshold 2, then the tdth evacuation network edge is added to the unobstructed edge set; S114: Let td=td+1. If td is less than or equal to TD, continue to execute S111 to S113; if td is greater than TD, end the current process.

7. The method for automatically generating an intelligent evacuation path based on artificial intelligence according to claim 6, characterized in that: The method of performing the first flow diversion of the evacuation network edge in the congestion edge set according to the preset evacuation method includes: S120: If the number of evacuation network edges in the congestion edge set is not zero, the number of evacuation network edges in the congestion edge set is recorded as YD, the initial value of yd is preset to 1, and the value range of yd is 1 to YD; if the number of evacuation network edges in the congestion edge set is zero, the current process is terminated; S121: Obtain the ydth evacuation network edge from the congestion edge set, and add the evacuation network edges that are adjacent to the ydth evacuation network edge and are not in the congestion edge set to the evacuation diversion set corresponding to the ydth evacuation network edge; if the number of evacuation network edges in the evacuation diversion set corresponding to the ydth evacuation network edge is not zero, calculate the evacuation flow rate shared by each evacuation network edge in the evacuation diversion set, and calculate the latest current number of evacuated personnel for each evacuation network edge in the evacuation diversion set based on the evacuation flow rate shared by each evacuation network edge; update the current number of evacuated personnel for each evacuation network edge in the evacuation diversion set to the corresponding latest current number of evacuated personnel; S122: Calculate the latest current number of evacuees on the yd-th evacuation network edge in the congestion edge set according to the evacuation flow shared by each evacuation network edge in the evacuation diversion set, and update the current number of evacuees on the yd-th evacuation network edge in the congestion edge set to the latest current number of evacuees; S123: Let yd=yd+1. If yd is less than or equal to YD, continue to execute S121 to S122. If yd is greater than YD, end the current process.

8. The method for automatically generating an intelligent evacuation path based on artificial intelligence according to claim 7, characterized in that: The calculation method of the evacuation flow rate shared by each evacuation network edge in the evacuation flow distribution set includes: The evacuation flow rate shared by each evacuation network edge is calculated proportionally according to the remaining capacity of each evacuation network edge; the remaining capacity of each evacuation network edge is the maximum number of passers-by corresponding to each evacuation network edge minus the current number of evacuees.

9. The method for automatically generating an intelligent evacuation path based on artificial intelligence according to claim 8, characterized in that: The method of analyzing and processing the evacuation network edges in the risk edge set according to the preset processing method to obtain the secondary congestion edge set includes: S130: If the number of evacuation network edges in the risk edge set is not zero, the number of evacuation network edges in the risk edge set is recorded as FX, the initial value of fx is preset to 1, and the value range of fx is 1 to FX; if the number of evacuation network edges in the risk edge set is zero, the current process is terminated; S131: obtaining the fxth evacuation network edge from the risk edge set, inputting the current number of evacuees, individual attributes, maximum number of passers-by and disaster characteristic parameters of the fxth evacuation network edge into the channel weight model, and obtaining the evacuation network edge weight of the fxth evacuation network edge; S132: If the evacuation network edge weight of the fx-th evacuation network edge is greater than or equal to the congestion weight threshold 1, then add the fx-th evacuation network edge to the secondary congestion edge set; S133: Let fx=fx+1. If fx is less than or equal to FX, continue to execute S131 to S132; if fx is greater than FX, end the current process.

10. An intelligent evacuation path automatic generation system based on artificial intelligence, implementing the intelligent evacuation path automatic generation method based on artificial intelligence according to any one of claims 1 to 9, characterized in that: include: A first acquisition module is used to acquire building modeling data, wherein the building modeling data includes key building parameters and equipment resource parameters; A data modeling module is used to perform modeling according to the building modeling data to obtain a building simulation model; A parameter definition module is used to define personnel characteristic parameters and disaster characteristic parameters on the building simulation model to obtain an intelligent evacuation simulation model; An intelligent evacuation module, used to adaptively generate an evacuation route based on an intelligent evacuation simulation model; The evacuation assessment module is used to summarize and output the evacuation simulation results after the evacuation simulation is completed.

Images