Guider layout method and device for open public place evacuation scene, and medium

Abstract

The invention relates to a guide person layout method and device for an open public place evacuation scene and a medium, and the method comprises the steps: collecting evacuation scene data, including road network data, exit position data, obstacle data, environmental noise data and crowd distribution data, of a target area; dividing the target area into a plurality of grids based on the road network data to form a grid set; calculating a reward value of the evacuation guide person layout position, wherein the reward value is comprehensively determined based on the distance from the current grid to the nearest exit and the number of effective evacuation persons guided by the guide person at the current grid position; calculating a visual function and an auditory function to obtain the number of guided evacuated people; and on the basis of the reward value of each grid, a specified number of grids are screened out from the grid set by adopting a particle swarm optimization algorithm, and an optimal layout scheme of the guiding person is formed. Compared with the prior art, the method has the advantages of high accuracy, high practicability, quick response and the like.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of emergency evacuation management, in particular to a guide person layout method for evacuation scenarios in open public places, a device and a medium. BACKGROUND

[0002] Open public places, such as urban parks, pedestrian blocks, and civic squares, have characteristics such as open spatial boundaries and multiple functions, and usually include ecological regulation, leisure and recreation, cultural display, and tourism services, thus becoming areas where people gather frequently. However, when large-scale activities are held, during holiday peaks, or in the event of an emergency, if the density of the crowd exceeds the carrying capacity of the place, it is easy to cause secondary safety risks such as crowding, trampling, and mass panic, which seriously threaten public safety and the order of urban operation. Therefore, developing a scientific and efficient evacuation guide plan is of great significance for ensuring the safety of public places and improving emergency response capabilities.

[0003] Currently, the evacuation guidance of such places mainly relies on safety personnel with rich experience, i.e., guide persons, to achieve. Guide persons play two key roles in the evacuation process: on the one hand, they maintain order on site, stabilize the emotions of the crowd, and reduce chaos caused by panic; on the other hand, they reasonably choose evacuation paths and exits to lead the crowd to safety. The reasonable layout of guide persons can significantly improve the efficiency and safety of evacuation. Whether the spatial layout of guide persons is reasonable directly affects the effectiveness of guidance. A reasonable layout not only affects the number of personnel that can be effectively guided, but also determines the efficiency and safety of the entire evacuation process. Currently, common guide person layout methods include uniform layout method, layout method based on maximum coverage model, and layout method based on K-means clustering algorithm.

[0004] The uniform layout method uniformly arranges guide persons at fixed intervals within the place, which is suitable for scenarios where the crowd is evenly distributed. If the evacuation area is irregular, Voronoi diagram is usually used to divide the responsibility area. This method is simple to operate, but it does not fully consider the spatial heterogeneity of crowd distribution density, and its applicability is poor when the crowd distribution is significantly different.

[0005] The maximum coverage model, as a classic site selection optimization model, determines the location of guide persons to cover as many evacuation personnel as possible given the number of guide persons. This model has a clear objective and controllable computational complexity, but its coverage standard is relatively single, and more practical factors need to be introduced by combining multi-objective optimization to improve its applicability.

[0006] The K-means clustering algorithm generates a guide person position and determines a guide relationship by performing clustering analysis on the spatial coordinates of the evacuees, and has the advantages of simple principle and high calculation efficiency. However, this method is difficult to effectively introduce real factors such as obstacles and exit distance, which limits its application effect in complex environments.

[0007] The prior art scheme found in practical application that due to the failure to fully consider the real factors such as obstacle shielding and environmental noise interference in a complex environment, it is easy to appear the following problems in a real evacuation scene: first, the visual line of sight is blocked by obstacles such as buildings and greenery, and even if the guide person is located in the preset theoretical coverage range, some evacuees still cannot observe the guide signal; second, the environmental noise causes a masking effect on sound propagation, making it difficult to effectively identify the voice instructions of the guide person, especially in a noisy open space, the sound guide effect is greatly reduced. These factors together cause the actual guide coverage to be lower than the theoretical expectation, resulting in a large number of visual and auditory coverage blind areas. Therefore, how to effectively operate the evacuation guide person layout method in a complex environment, while fully considering the influence of multiple real factors such as obstacle shielding, environmental noise and the like, and maintaining reasonable computational complexity, is a technical problem to be solved in the field of emergency evacuation management. SUMMARY

[0008] The purpose of the present application is to overcome the defects of the prior art and provide a guide person layout method, device and medium for an evacuation scene in an open public place, which synchronously introduces a visual visibility function based on line segment intersection detection and an auditory perception function based on an outdoor sound propagation attenuation model in an evacuation guide person layout model, quantifies the influence of obstacle shielding and environmental noise masking on information transmission, reduces visual and auditory coverage blind areas in a complex environment, and improves the reliability of guide information transmission and the actual effectiveness of the evacuation scheme.

[0009] The purpose of the present application can be achieved by the following technical solutions: According to one aspect of the present application, a guide person layout method for an evacuation scene in an open public place is provided, characterized in that the specific steps include: S1, collecting evacuation scene data of a target area, the evacuation scene data including road network data, exit position data, obstacle data, environmental noise data and crowd distribution data; S2, dividing the target area into a plurality of grids based on the road network data to form a grid set; S3, for each grid in the grid set, calculate the reward value of the evacuation guide person layout position, the reward value is based on the distance from the current grid to the nearest exit, and the number of evacuation personnel effectively guided by the guide person at the current grid position is comprehensively determined; wherein, the number of evacuation personnel is obtained by calculating the occlusion effect of obstacles on visual visibility, that is, the visual function, and the masking effect of environmental noise on auditory perception, that is, the auditory function; S4, based on the reward value of each grid, a particle swarm optimization algorithm is used to select a specified number of grids from the grid set to form an optimal layout scheme of the guide person.

[0010] Further, the reward value of the evacuation guide person layout position The expression is: , Wherein, is the distance reward value of the grid ; is the maximum distance reward value in the grid ; is the guide evacuation personnel number reward value of the grid ; is the maximum guide evacuation personnel number reward value in the grid ; is a constant weight that adjusts the guide evacuation personnel number reward value and the distance reward value.

[0011] Further, the distance reward value is calculated in the path search network by A * algorithm, the path search network is composed of nodes and edges representing road passing positions, and the distance reward value is the shortest path distance from the center point of the current grid to the nearest exit.

[0012] Further, the guide evacuation personnel number reward value is used to measure the ability of the guide person to effectively guide the number of evacuation personnel, and the expression is: , Wherein, S is the set of evacuation personnel, is the visual function between the guide person and the evacuation personnel at the grid ; is the auditory function between the guide person and the evacuation personnel at the grid .

[0013] Further, the visual function is judged by line segment intersection detection, when the line between the guide person position and the evacuation personnel position is not blocked by any obstacle, and the distance between the two is less than the preset visual field radius, the function value is 1, otherwise it is 0; the expression of the visual function is: , , , , wherein, is the grid and the distance between the guide and the evacuee; is the radius of the field of view; is the intersection detection function, i.e. to determine whether there is an obstacle between the guide and the evacuee; and represent the coordinates of the grid and the evacuee respectively; is the boundary coordinate of the obstacle; and are the line segment intersection detection functions; and are the direction vectors of the line segment and the line segment respectively.

[0014] Further, the hearing function is determined by an outdoor sound propagation attenuation model, and when the sound pressure level of the guide signal received by the evacuee from the grid is higher than the sound pressure level of the ambient noise by a predetermined threshold, the function value is 1, otherwise it is 0; the expression of the hearing function is: , , , , wherein, is the sound pressure level of the guide signal received by the evacuee; is the distance between the grid and the evacuee ; is the sound pressure level of the ambient noise; is the initial sound pressure level of the guide signal; is the directivity correction value of the guide signal in the propagation process, including the directivity index of point sound source , the sound propagation index of solid angle and the shielding attenuation index ; is the attenuation value of the guide signal in the propagation process, including geometric attenuation , atmospheric attenuation , ground effect attenuation , obstacle attenuation and other attenuations​ .

[0015] Further, in the S4, when the particle swarm optimization algorithm is used to screen the optimal layout scheme, each particle is coded as a set of possible guide person positions, and the particle is iteratively evaluated and optimized based on a fitness function, and the fitness function expression is: , wherein, is the i-th particle, i is the total reward value of the layout scheme represented by the current particle, is a penalty term for the close distance between guide persons in the current particle, is an evaluation term for the proportion of evacuation personnel guided by the layout scheme represented by the current particle.

[0016] Further, the total reward value is obtained by calculating the sum of the reward values of the grid corresponding to all guide person positions in the current particle; the penalty term is obtained by counting the number of times that the distance between any two guide persons in the current particle is less than a predetermined threshold distance; and the evaluation term is obtained by calculating the difference between the total number of evacuation personnel that can be effectively guided by the layout scheme represented by the current particle and the total number of evacuation personnel.

[0017] According to a second aspect of the present application, an electronic device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the method when executing the program.

[0018] According to a third aspect of the present application, a computer readable storage medium is provided, which stores a computer program, and the program is executed by a processor to implement the method.

[0019] Compared with the prior art, the present application has the following beneficial effects: (1) By introducing a dual judgment mechanism of visual visibility and auditory perception, the reliability of guide information transmission is improved: when calculating the number of evacuation personnel effectively guided by the guide person, the present application introduces a visual function based on line intersection detection and an auditory function based on an outdoor sound propagation attenuation model, which accurately quantifies the obstruction of visual signals by obstacles and the masking effect of environmental noise on sound signals, ensuring that only those evacuation personnel who can effectively receive the guide signal in both vision and hearing are counted in the guide range during the layout evaluation stage, so that the generated layout scheme can significantly reduce the visual and auditory coverage blind area in the actual complex environment, thereby improving the overall reliability of guide information transmission.

[0020] ​(2) Construct a multi-factor integrated reward function to enhance the adaptability and rationality of the layout scheme in complex scenarios: The application constructs an improved reward function that comprehensively considers the number of guided people, exit distance, obstacles and environmental noise, and uses it as the optimization target of the particle swarm optimization algorithm. Multiple key factors that affect the evacuation guidance effect are integrated into a quantitative model, overcoming the limitations of existing methods that often focus on a single factor. The layout model can more comprehensively reflect the complexity of the real scene, and the generated guided people layout scheme in open public places such as parks and squares has stronger environmental adaptability and overall layout rationality.

[0021] (3) Use intelligent optimization algorithm to solve the optimal layout and improve the overall efficiency and safety of emergency evacuation: The application uses the particle swarm optimization algorithm to automatically solve the optimal guided person position set that meets multiple constraint conditions based on the integrated multi-factor reward value, converts the complex layout problem into a computable optimization problem, and efficiently solves it through iterative search to quickly obtain a high-quality layout that can cover as many evacuation personnel as possible while avoiding excessive concentration of guided person resources and meeting the coverage ratio requirements, reducing the response delay of the evacuation crowd, shortening the overall evacuation time, and reducing the risk of chaos caused by guided blind areas, thereby effectively improving the safety and efficiency of emergency evacuation. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 Layout method flowchart for open public place evacuation scenarios; Figure 2 Partial schematic diagram of the grid division result in this embodiment; Figure 3 Guided person layout result diagram in this embodiment. DETAILED DESCRIPTION

[0023] The technical solutions in the embodiments of the application will be described below in conjunction with the drawings in the embodiments of the application. Obviously, the described embodiments are part of the embodiments of the application, rather than all the embodiments. Based on the embodiments in the application, all other embodiments obtained by those of ordinary skill in the art without creative labor should fall within the scope of protection of the application.

[0024] Traditional guided person layout methods mostly focus on considering crowd density factors, resulting in a large number of visual and auditory coverage blind areas in evacuation guidance. This application comprehensively considers the influence of obstacles on the vision of evacuation personnel, the influence of environmental noise on the hearing of evacuation personnel, exit distance and other factors, uses an improved reward grid model that considers the number of guided people and exit distance, and combines a particle swarm optimization algorithm to solve the optimal guided person layout scheme, significantly improving the guided person's coverage rate of evacuation personnel.

[0025] The reward grid model is a grid model that divides the evacuation scene's road surface into grids according to a certain grid cell size. A reward function is used to calculate the value of each grid cell, called the reward value. Grids with higher reward values ​​are more likely to be used as placement locations for evacuation guides. Existing basic reward grid models only consider simple factors such as crowd density and distance. To generate effective and high-quality guide spatial layouts in complex environments, this method improves upon the reward grid model by adding realistic factors such as obstacles and environmental noise, and redesigning the reward function for calculating reward values. However, within the current technological framework, accurately quantifying the blocking effect of obstacles on visual visibility and the masking effect of environmental noise on auditory perception presents significant challenges. On the one hand, visibility analysis involves complex spatial geometric calculations, requiring the processing of a large amount of environmental data such as building outlines and terrain undulations, resulting in high computational complexity. On the other hand, the attenuation of sound waves in outdoor environments is affected by multiple physical factors such as distance, air absorption, ground effect, and obstacle shielding; establishing an accurate sound propagation model requires professional acoustic knowledge. The complexity of this multiphysics coupling exceeds the processing capabilities of traditional layout methods, making it difficult for existing technologies to effectively integrate these key environmental factors while ensuring computational efficiency.

[0026] This application incorporates realistic factors such as the number of guides, guidance distance, obstacles, and environmental noise into an improved reward grid model. It then designs a reward value calculation function to calculate the reward value of each grid. Finally, a particle swarm optimization algorithm is used to select effective and high-quality grids from the candidate grids for guide placement, resulting in a suitable layout scheme. Compared to previous guide placement methods, this approach reduces the number of visual and auditory guidance blind spots, decreases the delay time for evacuees, and improves evacuation safety and efficiency.

[0027] like Figure 1 As shown in this embodiment, a method for arranging guides in an open public place evacuation scenario is provided. The specific steps include: S1. Collect evacuation scene data of the target area. The evacuation scene data includes road network data, exit location data, obstacle data, environmental noise data, and crowd distribution data. S2. Based on road network data, the target area is divided into multiple grids to form a grid set; S3, for each grid in the grid set, calculate the reward value of the evacuation guide person layout position, the reward value is based on the distance from the current grid to the nearest exit, and the number of evacuation personnel effectively guided by the guide person at the current grid position is determined comprehensively; wherein, the number of evacuation personnel is obtained by calculating the shielding effect of obstacles on visual access, i.e. visual function, and the masking effect of environmental noise on auditory perception, i.e. auditory function; S4, based on the reward value of each grid, using particle swarm optimization algorithm, select a specified number of grids from the grid set to form the optimal layout scheme of the guide person.

[0028] In S1, the crowd distribution in the study area is obtained by monitoring equipment such as camera. The environmental noise data in the study area is obtained by sound pressure meter. The road data, obstacle data and exit information in the study area are obtained by vectorization and remote sensing interpretation combined with field investigation.

[0029] The crowd gathering place is divided into grid form, the length and width of the grid are set, the grid is divided by using the fishing net tool, the road grid data is obtained, and the grid set is represented as . Wherein, each grid represents a possible layout position of the guide person.

[0030] The crowd distribution data, obstacle data, environmental noise data, park exit data and road grid data obtained in the second step are loaded into the reward grid model, and the reward values of the grids are calculated according to the designed reward function, and the distance reward value grid and the guide number reward value grid are obtained.

[0031] For each grid in the set, the grid reward value calculated by the reward function is used to represent its adaptability as a guide person layout position. The reward value of the evacuation guide person layout position The expression of , Wherein, is the distance reward value of grid ; is the maximum distance reward value in grid ; is the guide evacuation personnel number reward value of grid ; is the maximum guide evacuation personnel number reward value in grid ; is a constant weight for adjusting the guide evacuation personnel number reward value and the distance reward value, and the value is between 0 and 1.

[0032] Wherein, the distance reward value is obtained by AThe algorithm is calculated in a path search network composed of nodes and edges representing the passing position of roads, and the distance reward value is the shortest path distance from the current grid center point to the nearest exit. The expression of the distance reward value is: , wherein, is the total path distance, is the cumulative actual distance from the grid to the node , and is the heuristic estimated distance from the node to the nearest exit.

[0033] The guiding evacuation personnel number reward value is used to measure the ability of the guiding person to effectively guide the evacuation personnel, and the expression is: , wherein S is the set of evacuation personnel, is the visual function between the guiding person and the evacuation personnel at the grid , and is the auditory function between the guiding person and the evacuation personnel at the grid .

[0034] The visual function is judged by line segment intersection detection. When the line connecting the positions of the guiding person and the evacuation personnel is not blocked by any obstacle, and the distance between the two is less than the preset visual field radius, the function value is 1, otherwise it is 0; the expression of the visual function is: , , , , wherein, is the distance between the grid and the evacuation personnel ; is the visual field radius; is the intersection detection function, that is, to judge whether the guiding person and the evacuation personnel are blocked by any obstacle; and represent the coordinates of the grid and the evacuation personnel respectively; is the boundary coordinate of the obstacle; and are line segment intersection detection functions; and are line segment and line segment directional vector of the direction.

[0035] The auditory function is judged by an outdoor sound propagation attenuation model, and when the evacuation personnel receive the guide signal from the grid at a degree higher than the ambient noise sound pressure level by a preset threshold, the function value is 1, otherwise 0. When 1, it means that the sound guide signal transmitted by the guide person at the grid can be perceived by the evacuation personnel ; when 0, it cannot, that is, a masking effect is produced on the guide signal. In order to enable the evacuation personnel to clearly perceive the guide signal issued by the guide person, it is required that the received signal sound pressure level is at least 10dB higher than the ambient noise, so the judgment of the auditory function is calculated by using the propagation attenuation function of outdoor sound, and the expression is: , , , , wherein, is the guide signal sound pressure level received by the evacuation personnel; is the distance between the grid and the evacuation personnel ; is the ambient noise sound pressure level; is the initial sound pressure level of the guide signal; is the directivity correction value of the guide signal in the propagation process, including the point sound source directivity index , the sound propagation index of the solid angle and the shielding attenuation index ; is the attenuation value of the guide signal in the propagation process, including the geometric attenuation , the atmospheric attenuation , the ground effect attenuation , the obstacle attenuation and other attenuations .

[0036] The distance reward value grid and the guide quantity reward value grid are normalized to obtain normalized distance reward value grid data and normalized guide quantity reward value grid data. The normalized distance reward value grid data and the normalized guide quantity reward value grid data are loaded, the final reward value of the grid is calculated according to the formula, and reward grid result data is obtained.

[0037] In S4, the particle swarm optimization algorithm is used to screen the optimal layout scheme, each particle is coded as a set of possible guide person positions, the reward value is assigned to the center point of the grid, the center point of the grid is used as the candidate point of the guide person position, and the particle is iteratively evaluated and optimized based on the fitness function.

[0038] In order to ensure that the crowd can safely and efficiently complete the evacuation, the requirements for the layout of the guide person in this embodiment include: First, because the reward value of the center point of the grid represents the degree of suitability as a candidate point for the guide person position, the greater the reward value, the better the effect of selection, so the reward value of the selected candidate point should be as large as possible. Second, in order to ensure that the selected guide person combination can cover more evacuees and reduce the degree of overlap between the guide person coverage areas, the selected guide persons should maintain a certain distance from each other. Third, the total number of evacuees guided by the guide persons should be greater than or equal to a certain percentage threshold, so as to ensure that most or all evacuees can be guided by the guide persons.

[0039] The specific steps of the particle swarm algorithm in S4 include: Each particle is coded as a set of possible guide person positions. Assuming that n guide persons need to be laid out, a single particle is represented as , assuming that there are particles in a particle swarm, the th particle is represented by a vector , the dimension of the vector is , represents the two-dimensional coordinates of the j th guide person.

[0040] The particle mass is evaluated by the fitness function, including the objective function and the constraint penalty term, and the fitness function expression is: , , , , , wherein is the i th particle; represents the reward value of the grid to which the th guide person in the th particle is located.

[0041] The total reward value is obtained by summing the reward values ​​of all grids corresponding to the positions of all guides in the current particle; the penalty is obtained by counting the number of times the distance between any two guides in the current particle is less than a preset threshold distance; the evaluation is obtained by calculating the difference between the total number of evacuees effectively guided by the layout scheme represented by the current particle and the total number of evacuees. Specifically, The objective function is the total reward value of the layout scheme represented by the current particle. As a penalty term for when the distance between guides in the current particle is too close, the function value is any distance between two guides that is greater than a threshold distance. The cumulative number of times; This is an evaluation item for the proportion of evacuees guided by the current layout scheme represented by the particle, and is the sum of the number of people guided by all guides. To guide people and guide The distance between them; G is the total number of guides; S is the total number of evacuees; Indicates to the evacuation of personnel In other words, as long as any guide exists satisfy (That is, if the evacuees can be effectively guided), then the set is valid; set( ) represents each The valid set is denoted as 1 (otherwise 0), and then for all Summing yields a unique total number of evacuees, preventing duplicate counting. pct The percentage of guided evacuees out of the total evacuees; This represents the total number of people evacuated.

[0042] Based on the principle of particle swarm optimization, the velocity and position of each particle are updated. The particle's velocity represents the difference between its position in the next iteration and its position in the current iteration, i.e., the amount of movement the particle makes. Therefore, the particle's value in the next iteration equals its value in the current iteration plus its velocity. The particle's velocity is mainly calculated based on three factors: the particle's original velocity, the best position the particle has reached in previous iterations, and the best positions reached by other particles in the iterations.

[0043] The expression for updating the particle's velocity is: , In this equation, the left-hand side represents the particle's velocity in the next iteration. This is for the number of particle iterations; the first term on the right-hand side of the equation represents the number of times the particle has been in its iteration. The contribution of the wheel's speed to the speed of the next wheel. It is the inertia weight, used to control the continuity of speed; in the second term... called individual history best position, representing the position of the particle with the best fitness value in the iteration, called individual history best position, representing the position of the particle with the best fitness value in the iteration, called individual history best position, representing the position of the particle with the best fitness value in the iteration, is an individual learning factor, is a random number between (0, 1) used to adjust the contribution value of the second term to the particle movement amount; in the third term, called global history best position, representing the best position reached by the entire particle swarm in the iteration, is a global learning factor, is a random number between (0, 1) used to adjust the contribution value of the third term to the particle movement amount.

[0044] The expression for updating the position of the particle is: .

[0045] The particle updating and fitness evaluation process is repeatedly executed to update the individual and global optimal solutions. When the maximum number of iterations is reached or the quality of the solution no longer significantly improves over multiple generations, the algorithm is terminated and the global history best position is output as the final guide person layout scheme.

[0046] The method provided in the embodiment fully considers the influence of obstacles and environmental noise on the visual and auditory perception of evacuees in the construction of the guide person layout method in open public places, and further improves the rationality and reliability of the guide person layout. And a "guide person number-distance" reward grid function is constructed, a line segment intersection detection function and an outdoor sound propagation attenuation function are introduced into the reward grid function, and a particle swarm optimization algorithm is used to solve the optimal guide person layout result. Compared with the traditional evacuation guide person layout method, the guide person coverage rate in complex environments can be improved, the influence of obstacles and environmental noise on the reception of guide information by evacuees can be reduced, the evacuation time can be shortened, and the needs of actual emergency evacuation management work can be better met.

[0047] To verify the method provided in the embodiment, a certain park is selected as the research area for analysis. The selected research area has a large flow of people and a complex environment. According to the data obtained through field research, the daily number of people entering the park is about 3,000. The main park occupies an area of about 300,000 square meters, and the walking area only accounts for 21%. This spatial structure feature makes the space relatively limited for emergency evacuation in the case of a large number of people gathering, and the evacuation risk is relatively high.

[0048] The park road network data, park exit data, crowd distribution data at a certain time, and noise distribution data at the time are collected. The park environmental noise data is obtained by inversely proportional distance weighted interpolation based on the environmental noise sound pressure level of the sampling points. The park road network data and the park exit position data are obtained based on high-definition remote sensing images and park map vectorization. The crowd distribution data is obtained by field investigation. The study area is divided into multiple regions, 2 to 4 investigation points are set in each region, and the crowd distribution of the study area from 8:00 to 18:00 is collected by recording videos at an interval of one hour. Through investigation data statistics, the crowd distribution at 16:00 with the largest number of people, 2883 people in total, is selected as the case data.

[0049] As shown in Figure 2 , the road is divided into square grids with a side length of 5 m. According to the reward value expression of the evacuation guide person layout position, it is assumed that any grid center point is the guide person position, and the road network distance from the position to the nearest exit is calculated, which is taken as the temporary reward value of the grid. All grids are traversed to calculate the distance reward value of all grids. After traversing and calculating the reward values of all grids, the temporary reward values are normalized, and the processing results are the final grid distance reward values.

[0050] It is assumed that any grid center point is the guide person position, and then a buffer zone is established with the position as the center and 50 m as the radius (the buffer radius is taken as the limit distance of the guide person that can guide the evacuation personnel), the number of evacuation personnel covered in the buffer zone is counted, and the number is taken as the temporary reward value of the grid. After traversing and calculating the reward values of all grids, the temporary reward values are normalized, and the processing results are the final grid guide person number reward values.

[0051] Due to the influence of obstacles (such as trees, mountains, house buildings, etc.) and environmental noise, the evacuation personnel falling within the 50 m guide range may not be able to receive the guide signal sent by the guide personnel, so it is necessary to judge whether the evacuation personnel can receive the guide information of the guide personnel, so as to determine whether a certain evacuation personnel is counted in the guide person number.

[0052] The parameter settings of the particle swarm algorithm in this embodiment are shown in Table 1.

[0053] Table 1 Parameter settings The layout result obtained is shown in Figure 3 .

[0054] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described modules can refer to the corresponding process in the foregoing method embodiments, which will not be described here.

[0055] The electronic device of the present application includes a central processing unit (CPU) that can perform various appropriate actions and processes in accordance with computer program instructions stored in a read only memory (ROM) or computer program instructions loaded from a storage unit into a random access memory (RAM). Various programs and data required for device operation can also be stored in the RAM. The CPU, the ROM, and the RAM are connected to each other by a bus. An input / output (I / O) interface is also connected to the bus.

[0056] Various components in the device are connected to the I / O interface, including: input units such as a keyboard, a mouse, etc.; output units such as various types of displays, a speaker, etc.; storage units such as a magnetic disk, an optical disk, etc.; and communication units such as a network card, a modem, a wireless communication transceiver, etc. The communication unit allows the device to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks. The processing unit performs the various methods and processes described above, such as the method of the present application. For example, in some embodiments, the method of the present application can be implemented as a computer software program that is tangibly embodied in a machine readable medium, such as the storage unit. In some embodiments, part or all of the computer program can be loaded and / or installed on the device via the ROM and / or the communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more steps of the method of the present application described above can be performed. Alternatively, in other embodiments, the CPU can be configured to perform the method of the present application by any other appropriate means, such as by means of firmware.

[0057] The functionality described herein above can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, example types of hardware logic components that can be used include field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), system on a chip (SOCs), complex programmable logic devices (CPLDs), etc.

[0058] Program code for carrying out the methods of the present application can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, causes the machine to perform the functions / acts specified in the flow diagrams and / or block diagrams. The program code can execute entirely on a machine, partly on a machine, as a stand-alone software package, partly on a machine and partly on a remote machine or entirely on a remote machine or server.

[0059] In the context of the present application, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable storage medium can include, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of machine-readable storage medium would include one or more lines of electrical wire, portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or Flash memory), optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the foregoing.

[0060] The above description is only specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of various equivalent modifications or replacements within the technical scope disclosed by the present application, and these modifications or replacements should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for arranging guides in an open public space evacuation scenario, characterized in that, The specific steps include: S1. Collect evacuation scene data of the target area, including road network data, exit location data, obstacle data, environmental noise data, and crowd distribution data; S2. Based on the road network data, the target area is divided into multiple grids to form a grid set; S3. For each grid in the grid set, calculate the reward value for the evacuation guide's placement position. The reward value is determined based on the distance from the current grid to the nearest exit and the number of evacuees effectively guided by the guide at the current grid position. The number of evacuees is obtained by calculating the visual function, which is the effect of obstacles on visual visibility, and the auditory function, which is the effect of environmental noise on auditory perception. S4. Based on the reward value of each grid, the particle swarm optimization algorithm is used to select a specified number of grids from the grid set to form the optimal layout scheme for the guide.

2. The method for arranging guides in an open public place evacuation scenario according to claim 1, characterized in that, The reward value for the placement of evacuation guides The expression is: ， in, For grid Distance bonus value; For grid The maximum distance reward value in; For grid The reward value for guiding and evacuating the number of people; For grid The maximum reward value for guiding and evacuating personnel; It is a constant weight that adjusts the reward value for the number of people guided to evacuate and the reward value for distance.

3. The method for arranging guides in an open public place evacuation scenario according to claim 2, characterized in that, The distance reward value is obtained through A The algorithm is calculated in a path search network, which consists of nodes and edges representing road access points. The distance reward value is the shortest path distance from the current grid center point to the nearest exit.

4. The method for arranging guides in an open public place evacuation scenario according to claim 2, characterized in that, The reward value for guiding the number of evacuees is used to measure the ability of a guide to effectively guide the number of evacuees, and its expression is: ， Where S represents the assembly of evacuees, For grid Guides and evacuation personnel at the site The visual function between, For grid The auditory function between the guide and the evacuees.

5. The method for arranging guides in an open public place evacuation scenario according to claim 4, characterized in that, The visual function is determined by line segment intersection detection. The function value is 1 when the line connecting the guide's position and the evacuee's position is not obstructed by any obstacles and the distance between them is less than a preset visual radius; otherwise, it is 0. The visual function expression is: ， ， ， ， in, For grid With evacuees The distance between them; The radius of the field of view; This is an intersection detection function, which determines whether there are obstacles obstructing the path between the guide and the evacuees; and Representing grids respectively and evacuation personnel The coordinates; The boundary coordinates of the obstacle; and This is a function for detecting line segment intersections. and Line segments and line segments The direction vector.

6. The method for arranging guides in an open public place evacuation scenario according to claim 4, characterized in that, The auditory function is determined using an outdoor sound propagation attenuation model. The function value is 1 when the sound pressure level of the guidance signal received from the grid at the evacuation site is higher than a preset threshold of the ambient noise sound pressure level; otherwise, it is 0. The auditory function expression is: ， ， ， ， in, The sound pressure level of the guidance signal received by evacuees; For grid With evacuees The distance between them; This refers to the ambient noise sound pressure level. The initial sound pressure level of the guide signal; Directivity correction values ​​for guiding signals during propagation, including point source directivity index. Sound propagation index at solid angle and shielding attenuation index ; To guide the attenuation value of the signal during propagation, including geometric attenuation. Atmospheric attenuation Ground effect attenuation Obstacle attenuation Other attenuations .

7. The method for arranging guides in an open public place evacuation scenario according to claim 1, characterized in that, In step S4, when using the particle swarm optimization algorithm to select the optimal layout scheme, each particle is encoded as a set of possible guide positions, and the particles are iteratively evaluated and optimized based on a fitness function, the expression of which is: ， in, For the first i One particle, The total reward value is the layout scheme represented by the current particle. As a penalty for guiding people to be too close together in the current particles, This is an evaluation item for guiding the coverage of the proportion of evacuees in the current layout scheme represented by the particles.

8. The method for arranging guides in an open public place evacuation scenario according to claim 7, characterized in that, The total reward value is obtained by summing the reward values ​​of all grids corresponding to the positions of all guides in the current particle; the penalty item is obtained by counting the number of times the distance between any two guides in the current particle is less than a preset threshold distance; the evaluation item is obtained by calculating the difference between the total number of evacuees that can be effectively guided by the layout scheme represented by the current particle and the total number of evacuees.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1 to 8.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1 to 8.

Images