CN117610437B

CN117610437B - Prediction method and device for evacuation high-risk area of underground station in flood scene

Info

Publication number: CN117610437B
Application number: CN202410095337.9A
Authority: CN
Inventors: 杨晓霞; 郑倩倩; 董海荣; 魏金丽; 马浩; 黄帅; 韩超; 曲大义; 张永亮; 周敏; 康元磊
Original assignee: Qingdao University of Technology; China Railway Construction Electrification Bureau Group Co Ltd; Third Engineering Co Ltd of China Railway Construction Electrification Bureau Group Co Ltd; National Institute of Natural Hazards
Current assignee: Qingdao University of Technology; China Railway Construction Electrification Bureau Group Co Ltd; Third Engineering Co Ltd of China Railway Construction Electrification Bureau Group Co Ltd; National Institute of Natural Hazards
Priority date: 2024-01-24
Filing date: 2024-01-24
Publication date: 2024-06-21
Anticipated expiration: 2044-01-24
Also published as: CN117610437A

Abstract

The embodiment of the application discloses a method and a device for predicting an evacuation high-risk area of an underground station in a flood scene, and relates to the field of computer computing. One embodiment of the method comprises the following steps: acquiring passenger information and flood scene information of an underground station; inputting the acquired passenger information and flood scene information into a pre-trained evacuation prediction model, wherein the evacuation prediction model is used for representing the passenger information of the underground station and the corresponding relation between the flood scene information and the passenger density and/or flow in a subarea of the underground station in the flood scene; and determining a high risk area for evacuating passengers of the underground station in the flood scene according to the output of the evacuation prediction model. The embodiment can be used for reasonably guiding passengers to evacuate when floods occur, and passengers are prevented from gathering in a high-risk area, so that the safety of the whole underground station is improved.

Description

Prediction method and device for evacuation high-risk area of underground station in flood scene

Technical Field

The embodiment of the application relates to the technical field of computers, in particular to a method and a device for predicting an evacuation high-risk area of an underground station in a flood scene.

Background

Subway traffic systems are very important components of urban traffic and can provide efficient and rapid transit services in the event of urban traffic jams. However, because the underground station is narrow in space and large in personnel density and flow, when flood occurs, personnel are not easy to evacuate, and life safety of passengers is threatened. Therefore, predicting the high risk area in the underground station and evacuating people in the station to a safe place is a key problem.

Disclosure of Invention

The embodiment of the application provides a prediction method and a prediction device for an evacuation high-risk area of an underground station in a flood scene.

In a first aspect, some embodiments of the present application provide a prediction of a high risk area of an underground station, the method comprising: acquiring passenger information and flood scene information of an underground station; inputting the acquired passenger information and flood scene information into a pre-trained evacuation prediction model, wherein the evacuation prediction model is used for representing the passenger information of the underground station and the corresponding relation between the flood scene information and the passenger density and/or flow in a subarea of the underground station in the flood scene; and determining a high risk area for evacuating passengers of the underground station in the flood scene according to the output of the evacuation prediction model.

In some embodiments, the training data and/or test data of the evacuation prediction model is obtained by: constructing a hydrodynamic simulation system of the underground station based on fluid simulation software; individual motion simulation software based on a social force model is used for constructing a passenger evacuation simulation system, and the underground station is divided into at least two sub-areas in advance; and simulating based on the hydrodynamic simulation system and the passenger evacuation simulation system to obtain passenger density and/or flow in the subareas of the underground station corresponding to different passenger information and flood scene information.

In some embodiments, the sub-areas include a gate area, a stair area, and an exit area, the individuals in the passenger evacuation simulation system include a gate, passengers going up and down stairs, and waiting passengers at a platform floor, the passenger information includes a passenger's personality attributes including young and middle aged people, elderly people, young and middle aged people carrying children, the passenger locations include a platform floor and a hall floor, and the flood scene information includes water depth and water flow speed; and the simulating to obtain passenger information and passenger density and/or flow of subareas of the underground station corresponding to flood scene information based on the hydrodynamic simulation system and the passenger evacuation simulation system comprises the following steps: setting a flood invasion port and a flood invasion speed based on the hydrodynamic simulation system, and simulating to obtain the depth of water in the underground station in the flood scene; determining the travelling speed of the passenger under the influence of flood according to the water depth obtained by simulation; and setting the character attribute, the number of the passengers and the positions of the passengers based on the passenger evacuation simulation system, and combining the travelling speed of the passengers under the influence of flood to obtain the passenger density and/or the flow of the subareas of the underground station.

In some embodiments, the passenger's travel speed under the influence of a floodCalculated by the following formula:

Wherein, Is the speed of movement of the passenger under normal conditions,/>Is the rate of speed decrease due to fatigue,Is the time of the passenger walking,/>Is the rate of speed decrease due to water depth,/>Is a preset critical water depth which can not be walked by passengers,/>The flood depth with little or no influence on the passenger walking is set for the preset flood.

In some embodiments, the evacuation prediction model is built by: establishing an initial prediction model based on a random forest prediction model, wherein the number of decision trees in the initial prediction model is determined based on a classification regression decision tree CART of a coefficient selection feature; and optimizing the initial prediction model through a subtraction average optimizer algorithm to obtain the evacuation prediction model.

In some embodiments, the optimizing the initial prediction model by a subtractive average optimizer algorithm to obtain the evacuation prediction model includes: setting an objective function, and training the initial prediction model by using training data; initializing a subtraction average optimizer population, and setting a value range of a decision tree; optimizing the number of decision trees in the initial prediction model by using a subtractive average optimizer algorithm, and updating the optimal search agent position by taking the number of decision trees and the number of leaves as a group of candidate solutions of the subtractive average optimizer algorithm; and obtaining a candidate solution corresponding to an optimal value in an objective function of a subtraction average optimizer algorithm through iterative calculation, and taking the candidate solution as the number and the number of leaves of a decision tree in the evacuation prediction model to finish training the model.

In some embodiments, the objective function includes:

Wherein, For combined classification model,/>Classification model for a single decision tree,/>For inputting variables,/>For output variables,/>To indicate a function, leave represents the number of leaf nodes.

In some embodiments, the setting an objective function, training the initial predictive model with training data, comprises: constructing decision tree by training dataTraining, namely starting from the root, dividing the tree layer by layer according to the classification attribute of the decision tree until the tree leaves to obtain a concept classification result; Introducing an evaluation function of a decision tree:

Wherein, Entropy for all samples within the current leaf node,/>For the weight number of the leaf node in all leaves (number of samples of the leaf node)/>Entropy value accumulated for all leaves; by creating the number of decision trees and the number of leaves, a random forest is constructed.

In some embodiments, the optimizing the initial prediction model by a subtractive average optimizer algorithm to obtain the evacuation prediction model includes: randomly generating particles within the range of the upper limit value and the lower limit value by adopting a rand function, and initializing the position of a search agent, wherein the search agent is used for determining the value of a decision variable, and the set of the search agents forms an algorithm overall, and the algorithm overall is represented by the following equation:

Wherein, Is a subtractive average optimizer algorithm SABO population matrix,/>Is/>Each search agent, x _i,d is its/>, in the search spaceDimension decision variable,/>Is the number of search agents,/>Is the number of decision variables,/>Is a random number within interval [0,1 ]/>And/>Respectively is the/>Lower and upper bounds for the individual decision variables; evaluating an objective function based on each search agent, an evaluation value of the objective function being expressed by the following formula;

Wherein, Is a vector of objective function values,/>Is based on the/>Evaluation values of objective functions of the individual search agents;

the location of the search agent is updated by the following formula:

Wherein, Is the newly calculated/>A search agent; /(I)Based on the newly calculated/>Evaluation value of objective function of each search agent,/>Is the total number of particles,/>Is a random value obeying normal distribution, "/>, and is a random value obeying normal distribution"Is the/>, search agent B and search agent AThe formula of the subtraction is as follows:

Wherein, Is a vector of dimension m, is a random number generated by [1,2], F (A) and F (B) are values of the objective functions of search agents A and B, respectively, and sign is signum functions.

In a second aspect, some embodiments of the present application provide a prediction apparatus for an evacuation high risk area of an underground station in a flood scene, the apparatus comprising: an acquisition unit configured to acquire passenger information of an underground station and flood scene information; the prediction unit is configured to input the acquired passenger information and flood scene information into a pre-trained evacuation prediction model, wherein the evacuation prediction model is used for representing the corresponding relation between the passenger information of the underground station and the flood scene information and the passenger density and/or flow in a subarea of the underground station in the flood scene; and the determining unit is configured to determine a high risk area for evacuating passengers of the underground station in the flood scene according to the output of the evacuation prediction model.

In some embodiments, the apparatus further comprises a simulation unit configured to obtain training sample data and/or test sample data of the evacuation prediction model by: constructing a hydrodynamic simulation system of the underground station based on fluid simulation software; individual motion simulation software based on a social force model is used for constructing a passenger evacuation simulation system, and the underground station is divided into at least two sub-areas in advance; and simulating based on the hydrodynamic simulation system and the passenger evacuation simulation system to obtain passenger density and/or flow in the subareas of the underground station corresponding to different passenger information and flood scene information.

In some embodiments, the sub-areas include a gate area, a stair area, and an exit area, the individuals in the passenger evacuation simulation system include a gate, passengers going up and down stairs, and waiting passengers at a platform floor, the passenger information includes a passenger's personality attributes including young and middle aged people, elderly people, young and middle aged people carrying children, the passenger locations include a platform floor and a hall floor, and the flood scene information includes water depth and water flow speed; and the simulation unit is further configured to: setting a flood invasion port and a flood invasion speed based on the hydrodynamic simulation system, and simulating to obtain the depth of water in the underground station in the flood scene; determining the travelling speed of the passenger under the influence of flood according to the water depth obtained by simulation; and setting the character attribute, the number of the passengers and the positions of the passengers based on the passenger evacuation simulation system, and combining the travelling speed of the passengers under the influence of flood to obtain the passenger density and/or the flow of the subareas of the underground station.

In some embodiments, the method further comprises a model building unit configured to build the evacuation prediction model by: establishing an initial prediction model based on a random forest prediction model, wherein the number of decision trees in the initial prediction model is determined based on a classification regression decision tree CART of a coefficient selection feature; and optimizing the initial prediction model through a subtraction average optimizer algorithm to obtain the evacuation prediction model.

In some embodiments, the model building unit is further configured to: setting an objective function, and training the initial prediction model by using training data; initializing a subtraction average optimizer population, and setting a value range of a decision tree; optimizing the number of decision trees in the initial prediction model by using a subtractive average optimizer algorithm, and updating the optimal search agent position by taking the number of decision trees and the number of leaves as a group of candidate solutions of the subtractive average optimizer algorithm; and obtaining a candidate solution corresponding to an optimal value in an objective function of a subtraction average optimizer algorithm through iterative calculation, and taking the candidate solution as the number and the number of leaves of a decision tree in the evacuation prediction model to finish training the model.

In some embodiments, the objective function includes:

Wherein, For combined classification model,/>Classification model for a single decision tree,/>For inputting variables,/>For output variables,/>To indicate a function.

In some embodiments, the model building unit is further configured to:

Constructing decision tree by training data Training, namely starting from the root, dividing the tree layer by layer according to the classification attribute of the decision tree until the tree leaves to obtain a concept classification result; Introducing an evaluation function of a decision tree:

In some embodiments, the model building unit is further configured to:

Randomly generating particles within the range of the upper limit value and the lower limit value by adopting a rand function, and initializing the position of a search agent, wherein the search agent is used for determining the value of a decision variable, and the set of the search agents forms an algorithm overall, and the algorithm overall is represented by the following equation:

the location of the search agent is updated by the following formula:

In a third aspect, some embodiments of the present application provide an apparatus comprising: one or more processors; and a storage device having one or more programs stored thereon, which when executed by the one or more processors cause the one or more processors to implement the method as described in the first aspect.

In a fourth aspect, some embodiments of the application provide a computer readable medium having stored thereon a computer program which when executed by a processor implements a method as described in the first aspect.

In order to solve the technical problem of how to determine an evacuation high risk area of an underground station in a flood scene, the method and the device for predicting the evacuation high risk area of the underground station in the flood scene provided by the embodiment of the application acquire passenger information of the underground station and flood scene information; inputting the acquired passenger information and flood scene information into a pre-trained evacuation prediction model, wherein the evacuation prediction model is used for representing the passenger information of the underground station and the corresponding relation between the flood scene information and the passenger density and/or flow in a subarea of the underground station in the flood scene; the high risk area for evacuating passengers of the underground station in the flood scene is determined according to the output of the evacuation prediction model, so that passengers can be reasonably guided to evacuate when the flood occurs, the passengers are prevented from being gathered in the high risk area, and the safety of the whole underground station is improved.

Drawings

Other features, objects and advantages of the present application will become more apparent upon reading of the detailed description of non-limiting embodiments, made with reference to the accompanying drawings in which:

FIG. 1 is a diagram of some exemplary system architecture in which the present application may be used;

FIG. 2 is a flow chart of one embodiment of a method for predicting an evacuation high risk area of an underground station in a flood scenario according to the present application;

FIG. 3 is a schematic diagram of a simulation model of an underground station sub-region in an application scenario of an embodiment of the present application;

FIG. 4 is a flowchart of a subtractive mean optimizer algorithm optimizing a random forest classification prediction model in an application scenario of an embodiment of the present application;

FIG. 5 is a schematic structural view of one embodiment of an underground station evacuation high risk area prediction apparatus in a flood scenario according to the present application;

Fig. 6 is a schematic diagram of a computer system suitable for use in implementing some embodiments of the application.

Detailed Description

In order to enable those skilled in the art to better understand the prediction method, the prediction of the high risk area of the underground station is clearly described below with reference to the specific implementation method and the attached drawings. It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

It should be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations. In addition, in the description of the present specification and the appended claims, the terms "first," "second," and "third," etc. are used merely to distinguish between descriptions, and are not to be construed as indicating or implying relative importance. It should be noted that, without conflict, the embodiments of the present application and features of the embodiments may be combined with each other. The application will be described in detail below with reference to the drawings in connection with embodiments.

Fig. 1 shows an exemplary system architecture 100 of an embodiment of a method for predicting an evacuation high risk area of an underground station in a flood scenario or an apparatus for predicting an evacuation high risk area of an underground station in a flood scenario, to which the present application may be applied.

As shown in fig. 1, a system architecture 100 may include terminal devices 101, 102, 103, a network 104, and a server 105. The network 104 is used as a medium to provide communication links between the terminal devices 101, 102, 103 and the server 105. The network 104 may include various connection types, such as wired, wireless communication links, or fiber optic cables, among others.

The user may interact with the server 105 via the network 104 using the terminal devices 101, 102, 103 to receive or send messages or the like. Various client applications, such as a data processing class application, a simulation modeling class application, etc., may be installed on the terminal devices 101, 102, 103.

The terminal devices 101, 102, 103 may be hardware or software. When the terminal devices 101, 102, 103 are hardware, they may be various electronic devices with display screens, including but not limited to smartphones, tablets, laptop and desktop computers, and the like. When the terminal devices 101, 102, 103 are software, they can be installed in the above-listed electronic devices. Which may be implemented as a plurality of software or software modules, or as a single software or software module. The present invention is not particularly limited herein.

The server 105 may be a server providing various services, for example, a background server providing support for applications installed on the terminal devices 101, 102, 103, and the server 105 may acquire passenger information of underground stops and flood scene information; inputting the acquired passenger information and flood scene information into a pre-trained evacuation prediction model, wherein the evacuation prediction model is used for representing the passenger information of the underground station and the corresponding relation between the flood scene information and the passenger density and/or flow in a subarea of the underground station in the flood scene; and determining a high risk area for evacuating passengers of the underground station in the flood scene according to the output of the evacuation prediction model.

It should be noted that, the method for predicting the evacuation high risk area of the underground station in the flood scene provided by the embodiment of the application may be executed by the server 105, or may be executed by the terminal devices 101, 102 and 103, and correspondingly, the apparatus for predicting the evacuation high risk area of the underground station in the flood scene may be set in the server 105, or may be set in the terminal devices 101, 102 and 103.

The server may be hardware or software. When the server is hardware, the server may be implemented as a distributed server cluster formed by a plurality of servers, or may be implemented as a single server. When the server is software, it may be implemented as a plurality of software or software modules (e.g., to provide distributed services), or as a single software or software module. The present invention is not particularly limited herein.

It should be understood that the number of terminal devices, networks and servers in fig. 1 is merely illustrative. There may be any number of terminal devices, networks, and servers, as desired for implementation.

With continued reference to fig. 2, a flow 200 of one embodiment of a method for predicting an evacuation high risk area of an underground station in a flood scenario according to the present application is shown. The method for predicting the evacuation high-risk area of the underground station in the flood scene comprises the following steps:

Step 201, passenger information of an underground station and flood scene information are acquired.

In this embodiment, the execution subject (e.g., the server or the terminal shown in fig. 1) of the method for predicting the evacuation high risk area of the underground station in the flood scene may first acquire the passenger information of the target underground station and the flood scene information. The underground station may be any underground station whose high risk area is to be predicted, for example, an underground station in an area where water disaster is likely to occur, including a subway station located underground. The passenger information may include data affecting the moving speed of the passenger, such as the passenger's character attribute, the passenger type, the passenger's age, the passenger's health degree, etc., and may include data affecting the evacuation of the passenger, such as the number of passengers and the passenger's location. Flood scenario information may include data that may affect passenger movement speed, such as water depth, water flow speed, precipitation, underground station drainage speed, etc. Passenger information and flood scene information of the underground station can be input through staff, also can be obtained through municipal big data, and as an example, the staff can obtain the data through on-site investigation, and also can obtain by referring to the data similar to the underground station. After the passenger information and the flood scene information are acquired, the relation between the data and the passenger moving speed can be obtained through fitting or simulation.

Step 202, inputting the acquired passenger information and flood scene information into a pre-trained evacuation prediction model.

In this embodiment, the evacuation prediction model is used to characterize the passenger information of the underground station and the correspondence between flood scene information and the passenger density and/or flow in the sub-area of the underground station in the flood scene, and the evacuation prediction model can be obtained by training the initial prediction model through training samples. The training sample can be obtained by simulation through simulation software, can be obtained through historical evacuation data of the underground station, and can also be obtained through experiments. The initial prediction model can be established based on a random forest algorithm or other deep learning models, and the final evacuation prediction model can be obtained by further training and adjusting the initial prediction model through a gradient descent algorithm, a Newton method and other algorithms.

In some alternative implementations of the present embodiment, the training data and/or the test data of the evacuation prediction model are obtained by: constructing a hydrodynamic simulation system of the underground station based on fluid simulation software; individual motion simulation software based on a social force model is used for constructing a passenger evacuation simulation system, and an underground station is divided into at least two sub-areas in advance; and simulating based on the hydrodynamic simulation system and the passenger evacuation simulation system to obtain passenger density and/or flow in the subareas of the underground station corresponding to different passenger information and flood scene information.

In the implementation mode, individual motion simulation software based on a social force model is adopted to correspond to an on-site scene, multiple scenes in an underground station are modeled, as an example, a three-dimensional simulation model of a high risk area for evacuating passengers in a flood scene of the underground station can be constructed by utilizing MassMotion software, and MassMotion software simulates the motions of pedestrians based on the social force model so as to adapt to the conditions (such as avoiding obstacles and other pedestrians) of dynamic changes in a physical environment, and a route cost method is used for finding a route, so that the motion rule of the passengers can be truly simulated. Adopting individual motion simulation software MassMotion based on a social force model, corresponding to an on-site Scene, constructing a model through a Scene module, and modeling an underground station; setting an activity event through an 'Activities' module, and setting the character attribute of an individual; and simulating pedestrian movement by a Simulation module to obtain the people flow density and the number of the sub-areas of the crowd in the evacuation process.

In some optional implementations of this embodiment, the sub-areas include a gate area, a stair area, and an exit area, the individuals in the passenger evacuation simulation system include a gate, passengers going up and down stairs, and waiting passengers at a platform floor, the passenger information includes a person attribute of the passengers, the number of the passengers, and a passenger position, the person attribute of the passengers includes young and middle-aged, elderly, young and middle-aged carrying children, the passenger position includes the platform floor and a landing floor, and the flood scene information includes a water depth and a water flow speed; and simulating based on the hydrodynamics simulation system and the passenger evacuation simulation system to obtain passenger density and/or flow of different passenger information and sub-areas of the underground station corresponding to the flood scene information, comprising: setting a flood intrusion port and a flood intrusion speed based on a hydrodynamic simulation system, and simulating to obtain the depth of water in an underground station in a flood scene; determining the travelling speed of the passenger under the influence of flood according to the water depth obtained by simulation; based on the passenger evacuation simulation system, the character attribute, the number of passengers and the positions of the passengers are set, and the passenger density and/or the flow of the subareas of the underground station are obtained by combining the travelling speed of the passengers under the influence of flood.

In this implementation, the character attributes of the passengers may also include middle-aged and non-middle-aged passengers, adult males, adult females, elderly people, whether or not to carry a child, and so forth. The water flow speed and the water depth updating speed can be calculated according to a formula or can be determined by simulation software. The training set and the testing set can be obtained by changing the data such as the number of passengers, the attributes of the passengers, the distribution of the passengers, the depth and the speed of water flow and the like in the simulation experiment for many times, the method can be used for simulating a three-dimensional simulation model of a scene identified by a high risk area of passenger evacuation under the flood scene of the underground station constructed based on a social force model, and the social force model can simulate individual motions more accurately, so that the reliability of the obtained data is high.

In some alternative implementations of the present embodiment, the speed of travel of the passenger under the influence of the floodCalculated by the following formula:

Wherein, Is the speed of movement of the passenger under normal conditions,/>Is the rate of speed decrease due to fatigue,Is the time of the passenger walking,/>Is the rate of speed decrease due to water depth,/>Is a preset critical water depth which can not be walked by passengers,/>For the flood depth with little or no influence on the passenger walking caused by the preset flood, the/> -can be determined according to the passenger informationFor example, when there are more middle-aged and young passengers,/>Can get higher, when more non-middle-aged and young passengers are, you can get-Can be taken lower, and when the health degree of the passengers is higher,/>Can be taken higher, and when the health degree of the passengers is lower,/>May be lower.

As an example, one can take=1.5 m/s，/>=70 cm，/>=10 cm。

In some alternative implementations of the present embodiment, the evacuation prediction model is built by: establishing an initial prediction model based on a random forest prediction model, wherein the number of decision trees in the initial prediction model is determined based on a classification regression decision tree CART of the feature of the coefficient selection of the foundation; and optimizing the initial prediction model through a subtraction average optimizer algorithm to obtain an evacuation prediction model. The subtractive Average Optimizer algorithm (sub-Average-Based Optimizer) was the evolutionary-Based meta-heuristic recently proposed in 2023 to update members in the overall location search space by using subtractive averaging of search agents. The algorithm updates the position of the population members in the search space by using the subtracted average of the individuals. The number of decision trees and the number of leaves are optimized based on a random forest classification prediction algorithm combined with a subtraction average optimizer, so that the prediction accuracy of the whole model can be improved.

In some optional implementations of the present embodiment, optimizing the initial prediction model by a subtractive mean optimizer algorithm, to obtain an evacuation prediction model, includes: setting an objective function, and training an initial prediction model by using training data; initializing a subtraction average optimizer population, and setting a value range of a decision tree; optimizing the number of decision trees in an initial prediction model by using a subtractive average optimizer algorithm, and updating the optimal search agent position by taking the number of decision trees and the number of leaves as a group of candidate solutions of the subtractive average optimizer algorithm; and obtaining a candidate solution corresponding to an optimal value in an objective function of the subtraction average optimizer algorithm through iterative calculation, and taking the candidate solution as the number and the number of leaves of a decision tree in the evacuation prediction model to finish training the model.

In some alternative implementations of the present embodiment, the objective function includes:

In some optional implementations of the present embodiment, setting an objective function, training an initial predictive model with training data includes: constructing decision tree by training dataTraining, namely starting from the root, dividing the tree layer by layer according to the classification attribute of the decision tree until the tree leaves to obtain a concept classification result; Introducing an evaluation function of a decision tree:

In some optional implementations of the present embodiment, optimizing the initial prediction model by a subtractive mean optimizer algorithm, to obtain an evacuation prediction model, includes: randomly generating particles within the range of the upper limit value and the lower limit value by adopting a rand function, and initializing the position of a search agent, wherein the search agent is used for determining the value of a decision variable, the collection of the search agent forms an algorithm overall, and the algorithm overall is expressed by the following equation:

the location of the search agent is updated by the following formula:

And 203, determining a high risk area for evacuating passengers of the underground station in the flood scene according to the output of the evacuation prediction model.

In this embodiment, the evacuation prediction model may directly output the passenger density and/or the flow rate of the corresponding sub-area, and determine, according to the output passenger density of the sub-area, whether the passenger density of the sub-area exceeds a preset density threshold, if so, determine the sub-area as a high risk area; according to the output flow of the subarea, whether the flow of the subarea exceeds a preset flow threshold value or not can be determined, and if so, the subarea is determined to be a high risk area. The sub-zone may also be determined to be a high risk zone based on the passenger density and flow rate of the outputted sub-zone if one of the passenger density and flow rate exceeds a preset threshold. The preset flow threshold and the preset density threshold may be determined through simulation, or may be determined according to historical data or experience of staff, and as an example, the flow threshold may be set to 6.2 people/m/s, and the density threshold may be set to 5.26 people/m ². In addition, the sequence output by the evacuation prediction model can be directly used for representing whether the subarea of the underground station is a high risk area or not, and training data and model structures can be adjusted according to different outputs.

The method provided by the embodiment of the application obtains the passenger information of the underground station and the flood scene information; inputting the acquired passenger information and flood scene information into a pre-trained evacuation prediction model, wherein the evacuation prediction model is used for representing the passenger information of the underground station and the corresponding relation between the flood scene information and the passenger density and/or flow in a subarea of the underground station in the flood scene; the high risk area for evacuating passengers of the underground station in the flood scene is determined according to the output of the evacuation prediction model, so that passengers can be reasonably guided to evacuate when the flood occurs, the passengers are prevented from being gathered in the high risk area, and the safety of the whole underground station is improved.

In some alternative implementations of the present embodiment, the subtractive mean optimizer algorithm optimizes a flow of random forest classification prediction models, comprising:

(1) Referring to fig. 4, data preprocessing, data set is divided into training samples and test samples;

(2) Determining the number of decision trees of a prediction model according to the number of input features and the number of prediction features, wherein the input features are the character attributes of passengers, the number of passengers, the distribution of the passengers and the depth and speed of water flow, and the prediction features are whether the density and the flow of passengers in subareas of underground stations exceed a threshold value or not;

(3) Setting the number of decision trees;

(4) Learning objective function of predictive model The classification prediction calculation formula of (c) is as follows:

(5) The particle initialization formula is to randomly generate a stack of particles within the range of the upper limit value and the lower limit value by adopting a rand function. Initializing the location of the search agent, the algorithm search agent determining the value of the decision variable. Thus, each search agent contains information on decision variables and uses vectors for mathematical modeling. The set of search agents together form an ensemble of algorithms that can be represented using a matrix according to the following equation:

Wherein, Is SABO population matrix,/>Is/>Each search agent (group member), x _i,d is its/>, in the search spaceDimension (decision variable)/>Is the number of search agents,/>Is the number of decision variables,/>Is a random number within interval [0,1 ]/>And/>Respectively is the/>Lower and upper bounds for the decision variables.

Each search agent is a candidate solution to the problem suggesting a value for the decision variable. Thus, the objective function of the problem can be evaluated on a per search agent basis. The evaluation value of the objective function may beTo represent. Based on the placement of each overall member's specified value for the problem decision variable, the objective function is evaluated and stored at/>Is a kind of medium. Thus,/>Is equal to the number of overall population members/>。

Is a vector of objective function values based on/>First/>Evaluation values of objective functions of the individual search agents. The evaluation value of the objective function is a suitable criterion for analyzing the quality of the solution proposed by the search agent. Thus, the best value calculated for the objective function corresponds to the best search agent. The process of identifying and saving the best search agent will continue until the last iteration of the algorithm, taking into account the search agent's location in the search space will be updated in each iteration.

The SABO algorithm introduces a new computational concept, ""Is called/>, search agent B and search agent aThe subtraction is defined as follows:

Is a vector of dimension m, is a random number generated by [1,2], F (A) and F (B) are values of the objective functions of search agents A and B, respectively, and sign is signum functions.

In SABO algorithm, any search agentThe displacement in the search space is through each search agent/>"/>"Arithmetic mean of subtraction. The location update is performed as follows:

Is the total number of particles,/> Is a random value subject to normal distribution.

The particle position substitution formula is as follows:

Referring to fig. 4, if the iteration number T is greater than the set total iteration number T, the iteration is ended, an optimal solution of the objective function value optimized by the subtraction average optimizer algorithm is obtained through iterative calculation, and the number of decision trees is optimized through the optimal solution, so that training of the model is completed. In addition, the trained model can be tested through test data, the matching degree between the predicted value and the true value is high, and the accuracy of the model is high. The accuracy of the model may also be analyzed by a confusion matrix.

With further reference to fig. 5, as an implementation of the method shown in the foregoing figures, the present application provides an embodiment of a prediction apparatus for an evacuation high risk area of an underground station in a flood scene, where the embodiment of the apparatus corresponds to the embodiment of the method shown in fig. 2, and the apparatus may be specifically applied to various electronic devices.

As shown in fig. 5, the prediction apparatus 500 for an evacuation high risk area of an underground station in a flood scene according to the present embodiment includes: an acquisition unit 501, a prediction unit 502, a determination unit 503. The system comprises an acquisition unit, a control unit and a control unit, wherein the acquisition unit is configured to acquire passenger information of an underground station and flood scene information; the prediction unit is configured to input the acquired passenger information and flood scene information into a pre-trained evacuation prediction model, wherein the evacuation prediction model is used for representing the passenger information of the underground station and the corresponding relation between the flood scene information and the passenger density and/or flow in the subarea of the underground station in the flood scene; and the determining unit is configured to determine a high risk area for evacuating passengers of the underground station in the flood scene according to the output of the evacuation prediction model.

In this embodiment, specific processing of the obtaining unit 501, the predicting unit 502, and the determining unit 503 of the apparatus 500 for predicting a high risk area for evacuation of an underground station in a flood scene may refer to step 201, step 202, and step 203 in the corresponding embodiment of fig. 2.

In some optional implementations of the present embodiment, the apparatus further comprises a simulation unit configured to obtain training sample data and/or test sample data of the evacuation prediction model by: constructing a hydrodynamic simulation system of the underground station based on fluid simulation software; individual motion simulation software based on a social force model is used for constructing a passenger evacuation simulation system, and an underground station is divided into at least two sub-areas in advance; and simulating based on the hydrodynamic simulation system and the passenger evacuation simulation system to obtain passenger density and/or flow in the subareas of the underground station corresponding to different passenger information and flood scene information.

In some optional implementations of this embodiment, the sub-areas include a gate area, a stair area, and an exit area, the individuals in the passenger evacuation simulation system include a gate, passengers going up and down stairs, and waiting passengers at a platform floor, the passenger information includes a passenger's character attribute, a number of passengers, and a passenger position, the passenger's character attribute includes young and middle-aged people, young and middle-aged people carry a child, the passenger position includes the platform floor and a landing floor, and the flood scene information includes a water depth and a water flow speed; and a simulation unit further configured to: setting a flood intrusion port and a flood intrusion speed based on a hydrodynamic simulation system, and simulating to obtain the depth of water in an underground station in a flood scene; determining the travelling speed of the passenger under the influence of flood according to the water depth obtained by simulation; based on the passenger evacuation simulation system, the character attribute, the number of passengers and the positions of the passengers are set, and the passenger density and/or the flow of the subareas of the underground station are obtained by combining the travelling speed of the passengers under the influence of flood.

In some optional implementations of the present embodiment, the method further comprises a model building unit configured to build an evacuation prediction model by: establishing an initial prediction model based on a random forest prediction model, wherein the number of decision trees in the initial prediction model is determined based on a classification regression decision tree CART of the feature of the coefficient selection of the foundation; and optimizing the initial prediction model through a subtraction average optimizer algorithm to obtain an evacuation prediction model.

In some optional implementations of the present embodiment, the model building unit is further configured to: setting an objective function, and training an initial prediction model by using training data; initializing a subtraction average optimizer population, and setting a value range of a decision tree; optimizing the number of decision trees in an initial prediction model by using a subtractive average optimizer algorithm, and updating the optimal search agent position by taking the number of decision trees and the number of leaves as a group of candidate solutions of the subtractive average optimizer algorithm; and obtaining a candidate solution corresponding to an optimal value in an objective function of the subtraction average optimizer algorithm through iterative calculation, and taking the candidate solution as the number and the number of leaves of a decision tree in the evacuation prediction model to finish training the model.

In some optional implementations of the present embodiment, the model building unit is further configured to:

Randomly generating particles within the range of the upper limit value and the lower limit value by adopting a rand function, and initializing the position of a search agent, wherein the search agent is used for determining the value of a decision variable, the collection of the search agent forms an algorithm overall, and the algorithm overall is expressed by the following equation:

Wherein, Is a subtractive average optimizer algorithm SABO population matrix,Is the firstEach search agent, x _i,d is its first in the search spaceThe dimensions of the decision variables are such that,Is the number of search agents that are to be selected,Is the number of decision variables that are to be made,Is a random number within interval 0,1,AndRespectively the firstLower and upper bounds for the individual decision variables; evaluating an objective function based on each search agent, an evaluation value of the objective function being expressed by the following formula;

the location of the search agent is updated by the following formula:

/>

Referring now to FIG. 6, there is illustrated a schematic diagram of a computer system 600 suitable for use in implementing a server or terminal of an embodiment of the present application. The server or terminal illustrated in fig. 6 is merely an example, and should not be construed as limiting the functionality and scope of use of embodiments of the present application.

As shown in fig. 6, the computer system 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes according to a program stored in a Read Only Memory (ROM) 602 or a program loaded from a storage section 608 into a Random Access Memory (RAM) 603. In the RAM 603, various programs and data required for the operation of the system 600 are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other through a bus 604. An input/output (I/O) interface 605 is also connected to bus 604.

The following components may be connected to the I/O interface 605: an input portion 606 including a keyboard, mouse, etc.; an output portion 607 including a Cathode Ray Tube (CRT), a Liquid Crystal Display (LCD), and the like, a speaker, and the like; a storage section 608 including a hard disk and the like; and a communication section 609 including a network interface card such as a LAN card, a modem, or the like. The communication section 609 performs communication processing via a network such as the internet. The drive 610 is also connected to the I/O interface 605 as needed. Removable media 611 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is installed as needed on drive 610 so that a computer program read therefrom is installed as needed into storage section 608.

In particular, according to embodiments of the present disclosure, the processes described above with reference to flowcharts may be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product comprising a computer program embodied on a computer readable medium, the computer program comprising program code for performing the method shown in the flowcharts. In such an embodiment, the computer program may be downloaded and installed from a network through the communication portion 609, and/or installed from the removable medium 611. The above-described functions defined in the method of the present application are performed when the computer program is executed by a Central Processing Unit (CPU) 601. It should be noted that the computer readable medium according to the present application may be a computer readable signal medium or a computer readable medium, or any combination of the two. The computer readable medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples of the computer-readable medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In the present application, however, the computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, with the computer-readable program code embodied therein. Such a propagated data signal may take any of a variety of forms, including, but not limited to, electro-magnetic, optical, or any suitable combination of the foregoing. A computer readable signal medium may also be any computer readable medium that is not a computer readable medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

Computer program code for carrying out operations of the present application may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, smalltalk, C ++ and conventional procedural programming languages, such as the C-language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any kind of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or may be connected to an external computer (for example, through the Internet using an Internet service provider).

The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

The units involved in the embodiments of the present application may be implemented in software or in hardware. The described units may also be provided in a processor, for example, described as: a processor includes an acquisition unit, a prediction unit, a determination unit. The names of these units do not constitute a limitation on the unit itself in some cases, and for example, the acquisition unit may also be described as "a unit configured to acquire passenger information of an underground station and flood scene information".

As another aspect, the present application also provides a computer-readable medium that may be contained in the apparatus described in the above embodiments; or may be present alone without being fitted into the device. The computer readable medium carries one or more programs which, when executed by the apparatus, cause the apparatus to: acquiring passenger information and flood scene information of an underground station; inputting the acquired passenger information and flood scene information into a pre-trained evacuation prediction model, wherein the evacuation prediction model is used for representing the passenger information of the underground station and the corresponding relation between the flood scene information and the passenger density and/or flow in a subarea of the underground station in the flood scene; and determining a high risk area for evacuating passengers of the underground station in the flood scene according to the output of the evacuation prediction model.

The above description is only illustrative of the preferred embodiments of the present application and of the principles of the technology employed. It will be appreciated by persons skilled in the art that the scope of the application referred to in the present application is not limited to the specific combinations of the technical features described above, but also covers other technical features formed by any combination of the technical features described above or their equivalents without departing from the inventive concept described above. Such as the above-mentioned features and the technical features disclosed in the present application (but not limited to) having similar functions are replaced with each other.

Claims

1. A prediction method for evacuation high risk areas of underground stations in flood scenes comprises the following steps:

acquiring passenger information and flood scene information of an underground station;

Inputting the acquired passenger information and flood scene information into a pre-trained evacuation prediction model, wherein the evacuation prediction model is used for representing the passenger information of the underground station and the corresponding relation between the flood scene information and the passenger density and/or flow in a subarea of the underground station in the flood scene;

Determining a high risk area for evacuating passengers of the underground station in the flood scene according to the output of the evacuation prediction model;

the evacuation prediction model is established through the following steps:

Establishing an initial prediction model based on a random forest prediction model, wherein the number of decision trees in the initial prediction model is determined based on a classification regression decision tree CART of a coefficient selection feature;

optimizing the initial prediction model through a subtraction average optimizer algorithm to obtain the evacuation prediction model;

The optimizing the initial prediction model through a subtraction average optimizer algorithm to obtain the evacuation prediction model includes:

Setting an objective function, and training the initial prediction model by using training data;

initializing a subtraction average optimizer population, and setting a value range of a decision tree;

optimizing the number of decision trees in the initial prediction model by using a subtractive average optimizer algorithm, and updating the optimal search agent position by taking the number of decision trees and the number of leaves as a group of candidate solutions of the subtractive average optimizer algorithm;

Obtaining a candidate solution corresponding to an optimal value in an objective function of a subtraction average optimizer algorithm through iterative computation, and taking the candidate solution as the number and the leaf number of decision trees in the evacuation prediction model to finish training the model;

Wherein the objective function includes:

H(x)＝argmax∑p(h_i(x))＝Y

Wherein H (x) is a combined classification model, H _i is a single decision tree classification model, x is an input variable, Y is an output variable, and p is an indicator function.

2. A method according to claim 1, wherein the training data and/or test data of the evacuation prediction model is obtained by:

constructing a hydrodynamic simulation system of the underground station based on fluid simulation software;

Individual motion simulation software based on a social force model is used for constructing a passenger evacuation simulation system, and the underground station is divided into at least two sub-areas in advance;

And simulating based on the hydrodynamic simulation system and the passenger evacuation simulation system to obtain passenger density and/or flow in the subareas of the underground station corresponding to different passenger information and flood scene information.

3. The method of claim 2, wherein the sub-areas include a gate area, a stair area, and an exit area, the individuals in the passenger evacuation simulation system include passengers entering and exiting a gate, going up and down stairs, and waiting passengers at a platform floor, the passenger information includes a passenger's personality attributes including young, elderly, young-middle-aged carrying children, and passenger positions including a platform floor and a landing floor, the flood scenario information includes water depth and water flow rate; and

The simulation based on the hydrodynamic simulation system and the passenger evacuation simulation system to obtain passenger density and/or flow of sub-areas of the underground station corresponding to different passenger information and flood scene information comprises the following steps:

Setting a flood invasion port and a flood invasion speed based on the hydrodynamic simulation system, and simulating to obtain the depth of water in the underground station in the flood scene;

determining the travelling speed of the passenger under the influence of flood according to the water depth obtained by simulation;

And setting the character attribute, the number of the passengers and the positions of the passengers based on the passenger evacuation simulation system, and combining the travelling speed of the passengers under the influence of flood to obtain the passenger density and/or the flow of the subareas of the underground station.

4. A method according to claim 3, wherein the travelling speed of the passenger under the influence of a flood disasterCalculated by the following formula:

B＝1-l/l_max

ω＝1.0/(0.982+exp(1.12t-4.0))

Wherein, Is the normal speed of the passenger movement, ω is the rate of speed drop due to fatigue, t is the time of passenger travel, B is the rate of speed drop due to water depth, l _max is the preset critical water depth where the passenger cannot travel, and l _little is the preset flood depth where the influence of the flood on the passenger travel is small or no.

5. The method of claim 1, wherein the setting an objective function, training the initial predictive model with training data, comprises:

Constructing a decision tree class= DecisionTree () through training data, training, and dividing the decision tree class= DecisionTree () from the root downwards layer by layer according to the classification attribute of the decision tree until the decision tree class is a leaf node, so as to obtain a conceptual classification result y= DecisionTree (x);

Introducing an evaluation function of a decision tree:

Wherein H (t) is the entropy of all samples in the current leaf node, N (t) is the weight number of the leaf node in all leaves, C (t) is the accumulated entropy of all leaves, and leave represents the number of leaf nodes;

by creating the number of decision trees and the number of leaves, a random forest is constructed.

6. The method of claim 1, wherein the optimizing the initial predictive model by a subtractive mean optimizer algorithm results in the evacuation predictive model, comprising:

x_i,d＝lb_d+r_i,d·(ub_d-lb_d)，i＝1，...，N，d＝1，...，m

Wherein X is the subtractive mean optimizer algorithm SABO population matrix, X _i is the ith search agent, X _i,d is its d-th dimensional decision variable in the search space, N is the number of search agents, m is the number of decision variables, r _i,d is the random number within the interval [0,1], lb _d and ub _d are the lower and upper bounds of the d-th decision variable, respectively;

Evaluating an objective function based on each search agent, an evaluation value of the objective function being expressed by the following formula;

Wherein, Is a vector of objective function values, and F _i is an evaluation value of an objective function based on the i-th search agent;

the location of the search agent is updated by the following formula:

Wherein, Is the i-th newly calculated search agent; /(I)Is based on the newly calculated evaluation value of the objective function of the ith search agent, N is the total number of particles, r _i is a random value subject to normal distribution, "-v" is the v-subtraction of search agent B and search agent a, and the formula is as follows:

7. An underground station evacuation high risk area prediction device under a flood scene, comprising:

an acquisition unit configured to acquire passenger information of an underground station and flood scene information;

The prediction unit is configured to input the acquired passenger information and flood scene information into a pre-trained evacuation prediction model, wherein the evacuation prediction model is used for representing the corresponding relation between the passenger information of the underground station and the flood scene information and the passenger density and/or flow in a subarea of the underground station in the flood scene;

a determining unit configured to determine a high risk area for evacuation of passengers of the underground station in a flood scene from an output of the evacuation prediction model;

the evacuation prediction model is established through the following steps:

Wherein the objective function includes:

H(x)＝argmax∑p(h_i(x))＝Y