Public transport hub personnel path guiding method and equipment

Abstract

The invention provides a public transportation junction personnel path guiding method and equipment, and the method comprises the steps: dividing a space environment into regular grid units, calculating the accessibility factor and comfort factor of each grid unit, and achieving the refined quantitative evaluation of the internal passing conditions and riding experience of a transportation junction. On the basis, in combination with a weighted path planning algorithm, an optimal guide route can be provided for different crowds according to a real-time environment state, unfavorable areas such as congestion, noise and poor air quality can be effectively avoided, the passing efficiency and the passenger comfort are improved, and meanwhile, the dynamic adjustment and emergency response capability is achieved; reliable technical support is provided for intelligent operation and safety management of a large public space, the problems that an existing personnel path guiding scheme is poor in real-time performance, undefined in space constraint and lack of consideration on the comfort level of passengers are solved, and the service quality and the safety guarantee level of a hub in an urban traffic network are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to a public transport hub personnel path guidance method and device. BACKGROUND

[0002] Large public transport hubs have a wide area, complex spatial structure, highly concentrated passenger flow, and interwoven transfer routes, which make the traffic pressure high throughout the year. During holidays or large events, the passenger flow increases sharply, and the traffic pressure is further intensified. On the one hand, the sudden increase in passenger flow poses a severe challenge to emergency evacuation, which relates to the safety of passengers' lives and property; on the other hand, the large passenger flow and diversified transfer modes also test the fine management strategy of the guidance system. Unreasonable path guidance not only easily leads to congestion and even passenger retention, but also seriously affects the passenger transfer experience, thereby damaging the image of the hub and the city.

[0003] A scientific and dynamic guidance system can achieve reasonable allocation and dynamic control of passenger flow through diversified means, from static guide signs to real-time electronic screens, mobile navigation, and even intelligent sensing and shunting. In the event of an emergency, the system can quickly switch to an emergency mode to guide passengers to evacuate in an orderly manner, thereby maximizing the protection of their personal and property safety. During off-peak periods, personalized path recommendations and priority management of barrier-free channels can speed up passenger transfer and reduce the risk of retention. In the long term, the continuously optimized path guidance scheme not only helps the efficient coordination of internal resources of the hub, but also shapes the image of a smart hub and enhances the service value and brand influence of the hub in the city's transportation network.

[0004] Currently, the generation of personnel path guidance schemes mainly relies on three methods: experience rule-driven, simulation optimization, and data-driven prediction. Experience rule-driven relies on the manual analysis of traffic specifications and site floor plans by the operator, and manually sets transfer guidelines and flow limiting rules. Although this method has low deployment cost and simple maintenance, it is difficult to respond to sudden changes in passenger flow and temporary closed areas during peak periods due to its static rigidity. Simulation optimization collects crowd distribution data through cameras or other sensors and uses crowd behavior rules such as cellular automata and social force models for multiple experiments to find the scheme with the smallest congestion or fastest evacuation. However, since the simulation model often simplifies the spatial geometry and on-site details, it needs to be recalculated every time it is adjusted, making it difficult to respond in real time. Data-driven prediction uses historical passenger flow, passenger trajectories, and monitoring alerts to predict short-term passenger flow risks through time series models or graph neural networks, and then dynamically issues shunting strategies. It has adaptive ability in a big data environment, but lacks deep perception of BIM-level spatial constraints such as door and window clear height, passage width, and pipeline hub, and it is difficult to explain why the model recommends or closes a certain passage. SUMMARY

[0005] The application aims to provide a public transport hub personnel path guiding method and device.

[0006] To solve the above problems, the application provides a public transport hub personnel path guiding method, comprising:

[0007] Based on the overall scale and functional partition of the large public transport hub building, each grid unit of the large public transport hub building is divided, and the path edge between each grid unit and each adjacent grid unit is obtained;

[0008] Based on the BIM model of the public transport hub building, the static attribute element and the dynamic attribute element corresponding to each grid unit are obtained;

[0009] Based on the static attribute element and the dynamic attribute element of each grid unit, the reachability factor of each grid unit is calculated;

[0010] The comfort factor of each grid unit is calculated;

[0011] Based on the path edge between each grid unit and each adjacent grid unit, and the reachability factor A i (t) of each grid unit and the comfort factor C i (t), the path sequence with the minimum total cost is obtained.

[0012] Further, in the above method, based on the overall scale and functional partition of the large public transport hub building, each grid unit of the large public transport hub building is divided, and the path edge between each grid unit and each adjacent grid unit is obtained, comprising:

[0013] Based on the overall scale and each functional partition of the public transport hub building, the space of the public transport hub building is divided into a plurality of grid units to obtain the overall grid system composed of grid units, wherein each actual plot in the large public transport hub building corresponds to a grid unit;

[0014] Each grid unit in the overall grid system is assigned a unique ID, so that all grid units in the overall grid system are mapped to a node set {V i} of the graph;

[0015] Take the eight neighborhood grid units of each grid unit as the adjacent grid units V j of the grid unit, to obtain the undirected edge E i of the graph corresponding to each pair of adjacent units {V j , V ij}, that is, the path edge.

[0016] Furthermore, in the above method, based on the BIM model of the public transportation hub building, the static attribute features and dynamic attribute features corresponding to each grid cell are obtained, including:

[0017] Based on the BIM model of a large public transportation hub building, the static attribute elements S corresponding to each grid cell are obtained. i Including: Ground material G i Passage width W i Facility type F i and Functional Area Label Z i ;

[0018] Based on various types of sensor devices in large public transportation hubs, and combined with the BIM model of these hubs, the corresponding dynamic element attributes are continuously updated for each grid cell:

[0019] D i (t)={ρ i (t),T i (t),H i (t),N i (t),Aq i (t),L i (t),B i (t),A i (t)};

[0020] Where, ρ i (t) represents the actual pedestrian density of the grid cell i at time t;

[0021] T i (t) represents the air temperature of the actual plot where grid cell i is located at time t;

[0022] H i (t) represents the air humidity of the actual plot where grid cell i is located at time t;

[0023] L i (t) represents the actual light intensity of the plot where grid cell i is located at time t;

[0024] N i (t) represents the noise level of the actual plot where grid cell i is located at time t;

[0025] Aq i (t) represents the air quality of the actual plot where grid cell i is located at time t;

[0026] B i (t) represents the sudden obstruction event factor in the actual land parcel where grid cell i is located at time t, which is the obstruction state caused by certain accidental events;

[0027] A i (t) represents the availability status of the equipment in the actual plot where grid cell i is located at time t.

[0028] Furthermore, in the above method, based on the static and dynamic attribute features of each grid cell, the reachability factor of each grid cell is calculated, including:

[0029] Construct the reachability factor A of grid cell i at time t. i The computational matrix of (t);

[0030] Based on the reachability factor A i The computation matrix of (t) is used to obtain the weighted fusion reachability factor A. i (t)'.

[0031] Furthermore, in the above method, the reachability factor A of grid cell i at time t is constructed. i The computational matrix of (t) includes:

[0032] A i (t)=f1(W i ',E i (t),O i (t),S i (t),M i (t),V i (t));

[0033] Among them, W i ' is the passage width factor of grid cell i, taken as...

[0034]

[0035] Among them, W max It is the maximum passageway width within the grid cell of the entire large public transport hub building;

[0036] E i (t) is the congestion index of grid cell i at time t, taking...

[0037]

[0038] O i (t) is the obstacle factor of grid cell i at time t, used to represent physical or administrative obstacles; S i (t) represents the safety factor of the grid area, indicating whether the area is close to a hazard source; O i (t) and S i (t) The values ​​of these two parameters come from the functional area label Z. i Facility type F iAnd sudden obstruction event factor B i (t).

[0039] For the barrier factor O of grid cell i at time t i (t), we divide the degree of obstacle impact into three levels, and introduce a distance attenuation function and an occlusion intensity score to establish an obstacle factor O. i (t) model:

[0040]

[0041] Barrier Factor O i In the (t) model, n is the number of obstacles detected in the grid cells, and d ij S is the distance from the center of the grid cell to the obstacle. j Let α be the occlusion strength of the j-th obstacle; if it is completely occluded, this value is 1. j This is the obstacle weighting factor for the obstacle;

[0042] S i (t) is the safety factor of grid cell i at time t; for safety factor S i (t), setting the safety passage level of the highest-level risk source in the entire area to 0, the closer this value is to 0, the greater the risk and the weaker the willingness to pass; introducing an interpolated safety attenuation function to construct the following calculation method:

[0043]

[0044] Where m is the number of risk sources, γ k The weight of a risk source is determined by factors such as the power supply; for example, a fire would have a greater weight than an electricity problem. k Indicates the radius of influence of the risk source; ρ k (t) represents the risk level of the k-th risk source at time t, which is a value between 0 and 1; d ik λ represents the distance from grid cell i to the k-th risk source; k This represents the distance attenuation coefficient; e is the natural constant, approximately equal to 2.71828.

[0045] M i (t) is the facility availability factor of grid cell i at time t, calculated as follows:

[0046]

[0047] Where n represents the number of facilities within grid cell i; α j ω represents the current operational availability status value of the j-th facility, commonly defined as: 1 for normal operation, 0.5 for minor anomalies or partial disruption, and 0 for malfunction or complete unavailability; jThis represents the access weight or functional importance of the j-th facility, which is determined by the facility type and its corresponding configuration.

[0048] V i (t) is the visibility factor of grid cell i at time t, and its value depends on three important parameters: the visible solid angle Ω. i Illuminance (L) i (t) and the identifier recognition reliability S i Ω i The field of view of grid cell i is positively correlated with the accessibility factor; the sign recognition reliability S i This indicates the identifiability of the guide marker in grid cell i, and its value depends on whether the guide marker appears in the visible area and whether the marker is clear; the calculation formula is as follows:

[0049]

[0050] Wherein, λ1, λ2, and λ3 are weight coefficients, obtained from multiple sets of training data;

[0051] Furthermore, in the above method, based on the reachability factor A i The computation matrix of (t) is used to obtain the weighted fusion reachability factor A. i (t)', including:

[0052] The weighted fusion method is used to obtain the weighted fusion reachability factor A. i Formula (t):

[0053] A i (t)'=ω1W i ,+ω2E i (t)+ω3O i (t)+ω4S i (t),+ω5M i (t),+ω6V i (t));

[0054] The reachability factor A is solved using the Analytic Hierarchy Process (AHP). i In the formula (t), each factor W i E i (t), O i (t), S i (t), M i (t), V i The weight values ​​of (t)); according to the 1-9 proportional scaling method, the reachability factor A i In formula (t), all factors are compared pairwise for importance, and a 6th-order judgment matrix A is constructed, where a ij Let represent the importance of criterion i relative to criterion j, and satisfy a.ij =1 / a ji ,a ii =1; In the proportional scale, 1 indicates equal importance, 3 indicates slightly important, 5 indicates significantly important, 7 indicates strongly important, 9 indicates extremely important, and other values ​​are supplementary to intermediate values;

[0055] After normalizing each column of the judgment matrix A, the average value of each row is calculated to obtain the weight of each item.

[0056] Calculate the largest eigenvalue λ of the judgment matrix A. max ;

[0057] Based on the maximum eigenvalue λ max Calculate the consistency index CI = (λ) max -n) / (n-1), where n is the matrix dimension 6;

[0058] Based on the consistency index CI, the consistency ratio CR = CI / RI is calculated, where RI is the random consistency index, and its value is determined by n, here taken as 1.24. If the consistency ratio CR is less than or equal to 0.1, then the judgment matrix A has acceptable consistency, and the reachability factor A is obtained based on the judgment matrix A. i In the formula (t), each factor W i E i (t), O i (t), S i (t), M i (t), V i The weight values ​​of (t) and their corresponding weighted fusion reachability factor A i (t)'; otherwise, the score needs to be re-scored and the judgment matrix A needs to be adjusted.

[0059] Furthermore, in the above method, the comfort factor for each grid cell is calculated, including:

[0060] The comfort factor C of grid cell i at time t i The formula for calculating (t) is as follows:

[0061] C i (t)=f2(T i (t),H i (t),N i (t),Aq i (t),L i (t))

[0062] Among them, T i (t),H i (t) represents the ambient temperature and humidity, N i (t) represents the ambient noise level, Aq i(t) represents the air mass, L i (t) represents the illuminance level;

[0063] Among them, ambient temperature and humidity T i (t),H i (t), calculated using the temperature and humidity index DI:

[0064] DI = T i (t)-0.55(1-0.01H i (t))(T i (t)-14.5);

[0065] The air quality Aq was calculated using the weighted average method. i (t):

[0066]

[0067] Among them, the weight coefficients λ1', λ2', and λ3' are all greater than or equal to 0 and their sum is 1. The values ​​of the weight coefficients λ1', λ2', and λ3' depend on the different scenarios of the spatial grid cells.

[0068] Ambient noise level N i (t) is calculated as follows:

[0069]

[0070] Each sensor samples at 10Hz, according to a time window ΔT. eq The equivalent sound level L is calculated over a period of 10 seconds. eq,i (t), where L p (T) represents the instantaneous sound level (dB):

[0071]

[0072] Let E be the nominal luminous flux of the k-th light source at time t. k (t), the distance from the center of grid cell i to the light source k is d. ik The light transmission transmittance is τ ik (t), to obtain the illuminance level L i The formula for calculating (t) is as follows:

[0073]

[0074] Furthermore, in the above method, based on the path edges between each grid cell and each adjacent grid cell, and the reachability factor A of each grid cell... i (t)' and comfort factor C i (t), yielding the path sequence with the minimum total cost, including:

[0075] Each grid cell i has an reachability factor A at time t. i (t)' and comfort factor C i (t), all are normalized to the interval 0 to 1;

[0076] Define the comprehensive weight of grid cell i at time t as:

[0077] W i (t)=β1(1-A i (t)')+β2(1-C i (t));

[0078] Where β1 represents the importance weight of accessibility and β2 represents the importance weight of comfort, and β1+β2=1;

[0079] For the path edge connecting mesh cells i and j, the cost of the path edge between mesh cells i and j at time t is calculated using an average weighted average of the edge weights. ij (t):

[0080]

[0081] Where, d ij W is the actual spatial distance between two grid cells. i (t) represents the comprehensive weight of grid cell i at time t; W j (t) represents the comprehensive weight of grid cell j at time t;

[0082] Based on each pair of adjacent units {V i V j The undirected edge E of the corresponding graph ij and undirected edge E ij The corresponding edge weights are used to search for the shortest path from the starting grid cell s to the ending grid cell g, and output as a path sequence; where the "shortest" path is defined as the minimum total cost, that is, the minimum total edge weight.

[0083] Furthermore, in the above method, after obtaining the path sequence with the minimum total cost, the following steps are also included:

[0084] Based on the output path sequence, calculate the overall path metrics:

[0085] Total path cost:

[0086]

[0087] Average path reachability:

[0088]

[0089] Average route comfort:

[0090]

[0091] Where N is the number of grid cells contained in the path;

[0092] By comprehensively judging the safety and comfort of a route using total route cost, average route reachability, and average route comfort indicators, the weights β1 and β2 are adjusted to meet the guidance needs of passengers in different scenarios.

[0093] According to another aspect of the present invention, a calculator device is also provided, comprising:

[0094] Processor; and

[0095] A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method described in any of the preceding descriptions.

[0096] Compared to existing technologies, this invention achieves a refined and quantitative assessment of the internal traffic conditions and passenger experience of transportation hubs by dividing the spatial environment into regular grid units and calculating the accessibility and comfort factors for each grid unit. Based on this, combined with a weighted path planning algorithm, optimal guidance routes can be provided to different groups of people according to real-time environmental conditions. This method effectively avoids unfavorable areas such as congestion, noise, and poor air quality, improving traffic efficiency and passenger comfort. It also possesses dynamic adjustment and emergency response capabilities, providing reliable technical support for the intelligent operation and safety management of large public spaces.

[0097] This invention addresses the problems of poor real-time performance, unclear spatial constraints, and lack of consideration for passenger comfort in existing passenger route guidance schemes by studying a method for guiding passenger routes in large public transportation hubs based on digital twin models. It helps to efficiently coordinate internal resources of the hub, create a smart hub image, and improve the service quality and safety of the hub in the urban transportation network. Attached Figure Description

[0098] Figure 1 This is a flowchart of a public transportation hub pedestrian path guidance method according to an embodiment of the present invention. Detailed Implementation

[0099] The present invention will now be described in further detail with reference to the accompanying drawings.

[0100] In a typical configuration of this application, the terminal, the device of the service network, and the trusted party all include one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0101] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0102] Computer-readable media include both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include non-transitory computer-readable media, such as modulated data signals and carrier waves.

[0103] To overcome the limitations of existing methods in geometric accuracy, semantic fusion, and real-time response, digital twin technology based on BIM models can provide corresponding support:

[0104] On the one hand, BIM models integrate the three-dimensional geometry and attribute data of multiple disciplines such as architecture, structure and MEP into the same digital twin. The dimensions, clearance and materials of each door, each section of pipe and even each staircase can be extracted from the model, providing geometric space constraints for path planning.

[0105] On the other hand, changes to the site, such as construction enclosures, equipment layout, and maintenance enclosures, can be updated to the BIM model in real time, and the algorithm can recalculate the optimal route in real time based on the latest model.

[0106] In addition, BIM models can incorporate industry rules such as fire protection codes, accessibility design, and load limits, and automatically perform compliance checks during the path generation process;

[0107] Ultimately, the path results can be written back into the BIM model, providing accurate, dynamic, and standardized guidance services for the operation management system and passengers through 3D visualization, AR navigation, or mobile interface.

[0108] Digital twin technology based on BIM models deeply integrates three paradigms: experience rules, simulation, and data prediction, giving path guidance solutions a new dimension of refinement, dynamism, and compliance.

[0109] like Figure 1 As shown, the present invention provides a method for guiding pedestrian routes in public transportation hubs, the method comprising:

[0110] Step 1: Based on the overall scale and functional zoning of the large public transportation hub building, divide the building into grid cells; and obtain the path edges between each grid cell and each adjacent grid cell.

[0111] Step 1.1: Based on the overall scale and functional zones of the large public transportation hub building, the space of the large public transportation hub building is divided into several grid units to obtain an overall grid system composed of grid units. Each actual plot of land within the large public transportation hub building corresponds to one grid unit. For a large public transportation hub, the overall scale OS of the building and the functional zones f... i These are the two most critical parameters determining the unit grid size. In a spacious waiting hall, a larger grid cell should be selected, while at key transfer points such as passageways, lobbies, and escalator entrances, the grid cell size needs to be reduced to improve the accuracy of the analysis. Therefore, the size R of the grid cell i in the constructed space is crucial. i Relationship with the overall scale and functional zoning of the building (R) i ={OS,f i}

[0112] Specifically, the overall scale (OS) of a building mainly refers to its overall spatial size characteristics:

[0113] From a physical perspective, the overall scale (OS) of a building encompasses its basic dimensions such as height, length, and width, reflecting its macroscopic size. For example, the waiting hall of a large public transportation hub may have a significant scale in terms of area and height, which is a manifestation of its overall scale.

[0114] From a spatial perspective, the overall scale (OS) of a building also involves the proportional relationship between its various components (such as the main structure and ancillary facilities) and the scale relationship between the building and its surrounding environment (such as urban space and transportation network).

[0115] Functional partition f i This refers to dividing the building space into several areas with specific uses based on the different functions of the building.

[0116] Taking large public transportation hubs as an example, functional zoning fi This can be specifically manifested as:

[0117] Waiting hall (the area for passengers to wait for their trains);

[0118] • Transfer passage (the area connecting different transportation lines);

[0119] • Lobby (building entrance area);

[0120] • Escalator area (the space in front of and behind the escalator);

[0121] • Commercial service area (area with shops and restaurants), etc.

[0122] Different functional zones have different processing strategies in terms of spatial grid division, facility layout, and pedestrian flow analysis due to differences in usage scenarios, pedestrian density, and spatial importance. For example, different unit grid sizes may be set.

[0123] Step 1.2: Each grid cell needs to know its position index within the overall grid system, as well as its adjacent accessible cells. Therefore, after dividing the space into basic grid cells in Step 1.1, the "grid cell adjacency relationship" is constructed. First, a unique ID is assigned to each grid cell in the overall grid system, so that all grid cells in the overall grid system can be mapped to the node set {V} of the graph. i Considering that people can pass diagonally, the eight neighboring grid cells (top, bottom, left, right, and four diagonal cells) of each grid cell are taken as the adjacent grid cells V of that grid cell. j To obtain each pair of adjacent units {V i V j The undirected edge E of the corresponding graph ij That is, the path edge.

[0124] Step 2: Based on the BIM model of the public transportation hub building, obtain the static attribute features and dynamic attribute features corresponding to each grid cell;

[0125] Step 2.1: Based on the BIM model of the large public transportation hub building, bind each grid cell to its corresponding static attribute feature. The static attribute feature S corresponding to each grid cell... i Including: Ground material G i Passage width W i Facility type F i and Functional Area Label Z i .

[0126] S i ={G i W i ,F i Zi}

[0127] Among them, ground material G i Passage width W i Facility type F i and Functional Area Label Z i For each static element attribute vector;

[0128] Ground material G i This refers to the material properties of the ground surface of the actual plot where the grid unit is located, and the ground surface material affects the comfort of passage.

[0129] Passage width W i This refers to the maximum passage width of the actual plot where the grid cell is located, which is used to constrain the maximum pedestrian traffic capacity.

[0130] Facility type F i This refers to common static facilities on the actual plot where the grid unit is located, such as "elevators", "seats", "vending machines", etc. The type of facilities affects the accessibility and speed limits of the plot.

[0131] Functional area label Z i This refers to the functional area corresponding to the actual plot of land where the grid unit is located, such as "waiting area", "public service area", "security checkpoint area", etc. The functional area label is used for decision-making logic judgments such as target matching for passenger guidance.

[0132] Here, the "static information" of each grid unit in the building, such as the ground material, passage width, surrounding facilities, and functional zoning, is compiled into a set and bound to the grid unit to provide basic data support for subsequent analysis, such as pedestrian flow simulation and passenger guidance.

[0133] Step 2.2: Based on the various types of sensor devices in the large public transportation hub building, and combined with the BIM model of the large public transportation hub building, continuously update the corresponding dynamic element attributes for each grid cell:

[0134] D i (t)={ρ i (t),T i (t),H i (t),N i (t),Aq i (t),L i (t),B i (t),A i (t)}

[0135] Where, ρ i(t) represents the actual pedestrian density of grid cell i at time t, calculated by analyzing real-time monitoring video using the built-in algorithm of the binocular camera.

[0136] T i (t) represents the air temperature (H) of the actual plot where grid cell i is located at time t. i (t) represents the air humidity of the actual plot where grid cell i is located at time t, L i (t) represents the actual light intensity of the plot where grid cell i is located at time t, N i (t) represents the noise level of the actual plot where grid cell i is located at time t, Aq i (t) represents the air quality of the actual plot where grid cell i is located at time t, which is obtained by collecting data from temperature, humidity, light, sound and air quality sensors deployed on site.

[0137] B i (t) represents the obstruction state caused by certain accidental events in the actual plot where grid cell i is located at time t, generated from relevant information in the multimodal work order data;

[0138] A i (t) represents the availability status of equipment in the actual plot where grid cell i is located at time t, such as whether the elevator is operating normally, whether the vending machine has sufficient supplies, etc.

[0139] Through this multimodal data, on the one hand, a grid-based dynamic element influence matrix covering the entire field can be constructed to quantify the accessibility of different areas at a specific time; on the other hand, the above multimodal data can be associated and integrated with the on-site BIM model to further support the construction of a digital twin system, so that the accessibility status, environmental parameters and facility availability of each grid unit change dynamically over time, and are presented in real time in a three-dimensional visualization environment to drive the intelligent decision-making of the path guidance model.

[0140] Step 3: Based on the static and dynamic attribute features of each grid cell obtained in Step 2, calculate the reachability factor of each grid cell;

[0141] Step 3.1: The accessibility of spatial grid cells, as a fundamental element to be considered in personnel path guidance planning, directly affects whether personnel can pass through normally. From the static and dynamic attribute elements of the grid cells constructed in Step 2, elements affecting physical accessibility are selected to construct the accessibility factor A of grid cell i at time t as follows. i The computational matrix of (t):

[0142] A i (t)=f1(W i ',E i (t),Oi (t),S i (t),M i (t),V i (t))

[0143] Among them, W i ' is the passage width factor of grid cell i. The larger the value, the more people can pass through per unit time. A normalized processing method is used, taking...

[0144]

[0145] Among them, W max It is the maximum passageway width within the grid cell of the entire large public transport hub building;

[0146] E i (t) represents the congestion index of grid cell i at time t. Based on the regulations for personnel density safety thresholds for different levels of transportation hubs and the requirements in relevant standard documents, the corresponding personnel density safety threshold E is obtained. th ,Pick

[0147]

[0148] The more severe the congestion, the more E i The smaller the value of (t);

[0149] O i (t) is the obstacle factor of grid cell i at time t, used to represent physical or administrative obstacles; S i (t) represents the safety factor of the grid area, indicating whether the area is close to a hazard source, such as equipment rooms, power equipment, or violent emergencies; the values ​​of these two parameters are derived from the functional area label Z in step 2. i Facility type F i And sudden obstruction event factor B i (t).

[0150] For the barrier factor O i (t), we divide the degree of obstacle impact into three levels, and introduce a distance attenuation function and an occlusion intensity score to establish the following obstacle factor O. i (t) model:

[0151]

[0152] Barrier Factor O i In the (t) model, n is the number of obstacles detected in the grid cells, and d ij S is the distance from the center of the grid cell to the obstacle. j Let α be the occlusion strength of the j-th obstacle; if it is completely occluded, this value is 1.j This is the obstacle weighting factor for the obstacle.

[0153] S i (t) is the safety factor of grid cell i; for safety factor S i (t), we set the safety passage level of the highest-level risk source in the entire area to 0. The closer this value is to 0, the greater the risk and the weaker the willingness to pass. Considering that the safety factors of a grid cell area are affected by multiple hazard sources, the superposition adopts a product method to converge, avoiding the dominance of a single extreme value; the distance r between the risk source and grid cell i. k The larger the radius, the smaller the risk; the radius of influence r of the risk source k The larger the value, the greater the risk; based on the above analysis, an interpolated safety attenuation function is introduced to construct the following calculation method:

[0154]

[0155] Where m is the number of risk sources, γ k The weight of a risk source is determined by factors such as the power supply; for example, a fire would have a greater weight than an electricity problem. k Indicates the radius of influence of the risk source; ρ k (t) represents the risk level of the k-th risk source at time t, which is a value between 0 and 1; λ represents the distance from grid cell i to the k-th risk source; k This represents the distance attenuation coefficient; e is the natural constant, approximately equal to 2.71828.

[0156] M i (t) represents the facility availability factor of grid cell i at time t. When a grid cell i contains multiple facilities (such as escalators, elevators, turnstiles, etc.), the operating status of these facilities is converted into a quantifiable "availability score," and a weighted average is calculated by combining the scores with their access importance weights. The specific calculation formula is as follows:

[0157]

[0158] Where n represents the number of facilities within grid cell i; α j ω represents the current operational availability status value of the j-th facility, commonly defined as: 1 for normal operation, 0.5 for minor anomalies or partial disruption, and 0 for malfunction or complete unavailability; j This represents the access weight or functional importance of the j-th facility, which is determined by the facility type and its corresponding configuration.

[0159] V i (t) is the visibility factor of grid cell i, and its value depends on three important parameter values: the visible solid angle Ω. i Illuminance (L) i (t) and the identifier recognition reliability Si Ω i The field of view of grid cell i is positively correlated with the accessibility factor; the sign recognition reliability S i This indicates the identifiability of the guide marker in grid cell i, and its value depends on whether the guide marker appears in the visible area and whether the marker is clear. The final calculation formula is as follows:

[0160]

[0161] Among them, λ1, λ2, and λ3 are weight coefficients, which are obtained from multiple sets of training data.

[0162] Step 3.2: Based on the reachability factor A i The computation matrix of (t) is used to obtain the weighted fusion reachability factor A. i (t)'; Here, since the value ranges and physical meanings of the various original factors are different, a normalization method is used to ensure uniformity of dimensions. Then, a weighted fusion method is used to obtain the weighted fusion reachable factor A from these six types of indicators. i Formula (t):

[0163] A i (t)'=ω1W i ,+ω2E i (t)+ω3O i (t)+ω4S i (t),+ω5M i (t),+ω6V i (t))

[0164] Constructing a 6th-order decision matrix A: Solving for the reachability factor A using the AHP (Analytic Hierarchy Process). i In the formula (t), each factor W i E i (t), O i (t), S i (t), M i (t), V i The weight values ​​of (t)). According to the 1-9 proportional scaling method, the reachability factor A... i In formula (t), all factors are compared pairwise for importance, and a 6th-order judgment matrix A is constructed, where a ij Let represent the importance of criterion i relative to criterion j, and satisfy a. ij =1 / a ji ,a ii =1; In the proportional scale, 1 indicates equal importance, 3 indicates slightly important, 5 indicates significantly important, 7 indicates strongly important, 9 indicates extremely important, and other values ​​are supplementary to intermediate values;

[0165] Calculate the weights: After normalizing each column of the judgment matrix A, calculate the average value of each row to obtain the weights of each item.

[0166] To ensure logical consistency in the assignments during the scaling method, a consistency check is required: First, calculate the largest eigenvalue λ of the judgment matrix A. max Then, based on the largest eigenvalue λ max Calculate the consistency index CI = (λ) max -n) / (n-1), where n is the matrix dimension 6; finally, based on the consistency index CI, calculate the consistency ratio CR = CI / RI, where RI is the random consistency index, and the value is taken according to n, here it is taken as 1.24; if the consistency ratio CR is less than or equal to 0.1, then the judgment matrix A has acceptable consistency, otherwise it needs to be re-scored and the judgment matrix A needs to be adjusted.

[0167] In the Analytic Hierarchy Process (AHP), a consistency ratio (CR) of less than or equal to 0.1 is a crucial threshold for judging the logical consistency of the matrix. If this condition is met, it indicates that our pairwise comparisons of factor importance are logically consistent, and the factor weights calculated based on this judgment matrix A are reliable. These weights can then be used for subsequent weighted fusion calculations, such as the weighted fusion reachable factor A. i Calculation of (t)'.

[0168] If the consistency ratio CR is greater than 0.1, it indicates that the logical consistency of the judgment matrix is ​​insufficient, and the importance comparison between factors needs to be readjusted (i.e., the judgment matrix needs to be reconstructed) until the consistency ratio CR is less than or equal to 0.1.

[0169] Step 4: Calculate the comfort factor for each grid cell;

[0170] Step 4.1: In addition to accessibility, the comfort factor of a grid cell also needs to be considered. When the actual temperature and humidity of the actual site where some grid cells are located are unsuitable, the noise is too loud, or the air quality is poor, the attractiveness of the actual site where these grid cells are located to passengers will decrease. Even if the value of the accessibility factor is high, it is not suitable to use this site as an option in route guidance.

[0171] Comfort Factor C i (t), as a subjective and objective comfort factor for people in grid cell i at a specific time, is essentially a multi-dimensional fusion evaluation of environmental physical conditions, human perception model, and real-time pedestrian flow. Therefore, the following relevant factors are mainly considered to calculate the comfort factor of grid cell i at time t: environmental temperature and humidity T. i (t),H i (t), environmental noise level N i (t), air quality Illuminance level L i (t):

[0172] C i (t)=f2(T i (t),H i (t),N i (t),Aq i (t),L i (t));

[0173] Step 4.2: Temperature and humidity are two closely related factors. While the human body perceives temperature, it is also affected by humidity. For example, at the same temperature of 30°C, a relative humidity of 30% feels significantly more comfortable than 80% humidity. Therefore, the Temperature and Humidity Index (DI) is used here for calculation:

[0174] DI = T i (t)-0.55(1-0.01H i (t))(T i (t)-14.5)

[0175] A lower DI value indicates greater comfort, while a value greater than 80 indicates significant discomfort and potential health risks.

[0176] Air quality Aq i (t) Air quality directly affects breathing comfort and human health. Its key pollutants are PM2.5, TVOC, and CO2. An AQI classification mapping method is used to convert these three types of pollutants into Air Quality Index (AQI) scores, ensuring consistency with national standards. For PM2.5, the corresponding AQI value can be obtained directly using the linear interpolation method. For TVOC and CO2 data, which lack a direct mapping table, a similar AQI mapping table is constructed based on the index ranges specified in national standards. Finally, a weighted average method is used to summarize and calculate the air quality index (AQI). i (t):

[0177]

[0178] Among them, the weighting coefficients λ1', λ2', and λ3' are all greater than or equal to 0 and their sum is 1. The values ​​of the weighting coefficients λ1', λ2', and λ3' depend on the different scenarios of the spatial grid unit. For general public spaces, external pollution is of greater concern, so the value of λ1 is the largest. For densely populated spaces, CO2 is used to reflect ventilation conditions, so the value of λ2 should be the largest. For finely decorated commercial spaces, TOVC is the main source of risk, so the value of λ3 should be the largest.

[0179] Ambient noise level N i (t) Affects auditory comfort and communication experience; ambient noise level Ni The measurement index of (t) is usually the equivalent continuous sound level, which can comprehensively reflect the average energy sound pressure level over a certain period of time. Therefore, each sensor samples at 10 Hz and according to the time window ΔT eq The equivalent sound level L is calculated over a period of 10 seconds. eq,i (t), where L p (T) represents the instantaneous sound level (dB):

[0180]

[0181] For humans, the ideal comfortable environmental condition is L ≤ 45dB, the acceptable upper limit is L ≤ 60dB, while the dangerous range is L ≥ 80dB. Therefore, the final environmental noise level N i (t) is calculated as follows:

[0182]

[0183] Excessive illumination intensity in the spatial grid may cause glare for passengers, while insufficient illumination may reduce their sense of security, ultimately affecting their travel comfort. Therefore, we take the nominal luminous flux of the k-th light source at time t as E. k (t), the distance from the center of grid cell i to the light source k is d. ik The light transmission transmittance is τ ik (t), to obtain the illuminance level L i The formula for calculating (t) is as follows:

[0184]

[0185] Step 5: Based on the path edges between each grid cell and its adjacent grid cells, and the reachability factor A of each grid cell. i (t)' and comfort factor C i (t), thus obtaining the path sequence with the minimum total cost;

[0186] Step 5.1: Assign an reachability factor A to each grid cell i at time t. i (t)' and comfort factor C i (t), all are normalized to the interval between 0 and 1.

[0187] To comprehensively reflect the traffic resistance and comfort loss of grid cell i, the comprehensive weight of grid cell i at time t is defined as:

[0188] W i (t)=β1(1-A i (t)')+β2(1-C i (t))

[0189] Here, β1 represents the importance weight of accessibility, and β2 represents the importance weight of comfort, satisfying β1 + β2 = 1. For example, in daily guidance, a higher weight can be given to comfort, while in emergency evacuation, the weight of accessibility can be increased.

[0190] The weight W i The larger the value of (t), the greater the difficulty or lower the comfort level of traversing the grid, and the more it should be avoided during path planning.

[0191] Step 5.2: For the path edge connecting mesh cells i and j, calculate the cost of the path edge between mesh cells i and j at time t. ij When (t), considering the physical distance and the combined weights of the grid cells at both ends, the average weighted form of the edge weights is adopted:

[0192]

[0193] Where, d ij W is the actual spatial distance (in meters) between two grid cells. i (t) represents the comprehensive weight of grid cell i at time t; W j (t) represents the overall weight of grid cell j at time t. This ensures that the cost of an edge is not only proportional to the distance but also affected by the accessibility and comfort of the grid cells at both ends.

[0194] Step 5.3: Based on each pair of adjacent units {V i V j The undirected edge E of the corresponding graph ij and undirected edge E ij The corresponding edge weights are determined using the classic path search algorithm, which searches for the shortest path from the starting node s to the ending node g. The "shortest" path is defined as having the minimum total cost, i.e., the minimum total edge weight.

[0195] Step 5.4: After the search is complete, output the path sequence and calculate the overall path index based on the output path sequence:

[0196] Total path cost:

[0197]

[0198] Average path reachability:

[0199]

[0200] Average route comfort:

[0201]

[0202] Where N is the number of grid cells contained in the path; by using the total cost of the path, the average reachability of the path, and the average comfort index of the path, the platform can comprehensively judge the safety and comfort of the path, and assist in adjusting the weights β1 and β2 to meet the guidance needs of passengers in different scenarios.

[0203] According to another aspect of the present invention, a calculator device is also provided, comprising:

[0204] Processor; and

[0205] A memory configured to store computer-executable instructions, which, when executed, cause the processor to perform the method described in any of the preceding descriptions.

[0206] For detailed descriptions of the various device embodiments of the present invention, please refer to the corresponding sections of the various method embodiments; they will not be repeated here.

[0207] In summary, this invention achieves a refined and quantitative assessment of traffic conditions and passenger experience within transportation hubs by dividing the spatial environment into regular grid units and calculating the accessibility and comfort factors for each unit. Based on this, and combined with a weighted path planning algorithm, optimal guidance routes can be provided to different groups of people according to real-time environmental conditions. This method effectively avoids unfavorable areas such as congestion, noise, and poor air quality, improving traffic efficiency and passenger comfort. It also possesses dynamic adjustment and emergency response capabilities, providing reliable technical support for the intelligent operation and safety management of large public spaces.

[0208] This invention addresses the problems of poor real-time performance, unclear spatial constraints, and lack of consideration for passenger comfort in existing passenger route guidance schemes by studying a method for guiding passenger routes in large public transportation hubs based on digital twin models. It helps to efficiently coordinate internal resources of the hub, create a smart hub image, and improve the service quality and safety of the hub in the urban transportation network.

[0209] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

[0210] It should be noted that the present invention can be implemented in software and / or a combination of software and hardware, for example, using an application-specific integrated circuit (ASIC), a general-purpose computer, or any other similar hardware device. In one embodiment, the software program of the present invention can be executed by a processor to implement the steps or functions described above. Similarly, the software program of the present invention (including associated data structures) can be stored in a computer-readable recording medium, such as RAM memory, a magnetic or optical drive, a floppy disk, or similar devices. Furthermore, some steps or functions of the present invention can be implemented in hardware, for example, as circuitry that works with a processor to perform the various steps or functions.

[0211] Furthermore, a portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. The program instructions invoking the methods of the invention may be stored in a fixed or removable recording medium, and / or transmitted via a data stream in a broadcast or other signal-carrying medium, and / or stored in the working memory of a computer device operating according to the program instructions. Here, an embodiment of the invention includes an apparatus comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein, when the computer program instructions are executed by the processor, the apparatus is triggered to operate the methods and / or technical solutions based on the foregoing embodiments of the invention.

[0212] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered illustrative and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be embraced within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims. Furthermore, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices recited in the apparatus claims may also be implemented by a single unit or device in software or hardware. The terms "first," "second," etc., are used to indicate names and do not indicate any particular order.

Claims

1. A public transportation hub staff path guidance method characterized by, Comprising: Based on the overall scale and functional zoning of the large public transportation hub building, each grid unit of the large public transportation hub building is divided; And get the path edge between each grid unit and each adjacent grid unit; Based on the BIM model of the public transportation hub building, the static attribute elements and dynamic attribute elements corresponding to each grid unit are obtained; Based on the static attribute elements and dynamic attribute elements of each grid unit, the accessibility factor of each grid unit is calculated; The comfort factor of each grid unit is calculated; based on the path edges between each grid cell and each of its neighboring grid cells, and a reachability factor A for each grid cell i (t) a comfort factor C i (t), resulting in a sequence of paths with minimum total cost.

2. The public transportation hub staff path guiding method according to claim 1, characterized by, Based on the overall scale and functional zoning of the large public transportation hub building, each grid unit of the large public transportation hub building is divided; And get the path edge between each grid unit and each adjacent grid unit, including: Based on the overall scale and functional zoning of the public transportation hub building, the space of the public transportation hub building is divided into a plurality of grid units to obtain a whole grid system composed of grid units, wherein each actual plot in the large public transportation hub building corresponds to a grid unit; assigning a unique ID to each grid cell in the overall grid system such that all grid cells in the overall grid system map to a set of nodes {V i} of a graph; Take the eight neighboring grid cells of each grid cell as the adjacent grid cells V of that grid cell. j To obtain each pair of adjacent units {V i V j The undirected edge E of the corresponding graph ij That is, the path edge.

3. The public transportation hub staff path guiding method according to claim 1, characterized by, Based on the BIM model of the public transportation hub building, the static attribute elements and dynamic attribute elements corresponding to each grid unit are obtained, including: Based on the BIM model of the large public transportation hub building, the static attribute elements S corresponding to each grid unit are obtained i , including: ground material G i , passing width W i , facility type F i and function area label Z i ; Based on each type of sensor device in the large public transportation hub building, and combined with the BIM model of the large public transportation hub building, the dynamic attribute elements corresponding to each grid unit are continuously updated: D i (t) = {p i (t), T i (t), H i (t), N i (t), Aq i (t), L i (t), B i (t), A i (t)}; where, p i (t) is the actual land parcel where the grid cell i is located at time t. T i (t) is the air temperature of the actual plot where the grid cell i is located at time t; H i (t) is the air humidity of the actual plot where the grid cell i is located at time t; L i (t) is the light intensity of the actual plot where the grid cell i is located at time t; N i (t) is the noise level of the actual plot where the grid cell i is located at time t; Aq i (t) is the air quality of the actual plot where the grid cell i is located at time t; B i (t) is the factor of sudden hindering events in the actual plot where the grid cell i is located at time t, which is the hindering state caused by some accidental events; A i (t) is the available state of the device in the actual plot in which the grid cell i is located at time t.

4. The public transportation hub staff path guiding method according to claim 3, characterized by, Based on the static attribute elements and dynamic attribute elements of each grid unit, the accessibility factor of each grid unit is calculated, including: Constructing the reachability factor A of grid cell i at time t i the calculation matrix of (t) Based on the reachability factor A i (t) of the calculation matrix, the weighted fused reachability factor A i (t)' is obtained.

5. The public transportation hub staff path guiding method according to claim 4, characterized by, Constructing the reachability factor A of the grid cell i at time t i the calculation matrix of (t), comprising: A i (t) = f1(W i ’, E i (t), O i (t), S i (t), M i (t), V i (t)); where W i is the width of the passage of the grid cell i, taken as: where W max is the maximum aisle width in the grid cell of the entire large public transportation hub building range; E i (t) is the congestion index of the grid cell i at time t, taken as: O i (t) is the barrier factor of grid cell i at time t, which is used to represent physical or administrative barriers; S i (t) is the safety factor of grid zone, which is used to represent whether the grid cell i is close to the dangerous source; O i (t) and S i (t) are two parameters whose values come from the functional area label Z i , the facility type F i , and the sudden barrier event factor B i (t). The obstacle factor O of the grid cell i at time t i (t), we divide the obstacle influence degree into three levels, and introduce the distance attenuation function and the occlusion intensity score to establish the obstacle factor O i (t) model: Obstacle Factor O i (t) In the model, n is the number of obstacles detected in the grid cell; d ij is the distance from the grid cell to the center of the obstacle; S j is the occlusion strength of the jth obstacle, with a full occlusion having S j a value of 1; a j is the obstruction weight factor for that obstacle; S i (t) is the safety factor of grid cell i at time t; for the safety factor S i (t), the safety passing level of the highest level risk source in the entire area is set to 0, and the closer the value is to 0, the greater the risk and the weaker the willingness to pass; an interpolation type safety attenuation function is introduced to construct the following calculation method: where m is the number of risk sources, γ k is the weight of the risk source, for example, the weight of fire will be greater than power problems; r k represents the influence radius of the risk source; p k (t) represents the risk level of the kth risk source at time t, which is a value between 0 and 1; d ik represents the distance from grid unit i to the kth risk source; λ k represents the distance attenuation coefficient; e is the natural constant, which is approximately equal to 2.71828; M i (t) is the facility availability factor of grid cell i at time t, calculated as follows: where n represents the number of settings within grid cell i; a j represents the current operational availability state value of the jth facility, defined as 1 for normal operation, 0.5 for minor abnormality or partial disruption, and 0 for failure or complete unavailability; ω j represents the passage weight or functional importance of the jth facility, determined by the facility type and corresponding configuration; V i (t) is the visibility factor of grid cell i at time t, whose value depends on three important parameters: the visible solid angle Ω i , the illumination L i (t), and the sign recognition confidence S i ; Ω i represents the openness of the view of grid cell i, which is positively correlated with the reachability factor; the sign recognition confidence S i represents the recognizability of the guide sign of grid cell i, whose value depends on whether the guide sign appears in the visible area and whether the sign is clear; the calculation formula is as follows: Wherein, λ1, λ2, λ3 are weight coefficients, which are obtained through a plurality of training data.

6. The public transportation hub staff path guiding method according to claim 5, characterized by, based on the reachability factor A i a calculation matrix of (t) to obtain a weighted fused reachability factor A i (t)', comprising: The reachable factor A after weighted fusion is obtained by using the method of weighted fusion i The formula of (t)' is: A i (t) = ω1W i (t) + ω2E i (t) + ω3O i (t) + ω4S i (t) + ω5M i (t) + ω6V i (t) Solving the reachable factor A by using AHP method i The weight value of each factor W i , E i , O i , S i , M i , V i in the formula of (t)';According to the 1-9 scale method, the importance of all factors in the formula of reachable factor A i (t)' is compared with each other, and a 6-order judgment matrix A is constructed, wherein a ij represents the importance of criterion i relative to criterion j, and satisfies a ij =1 / a ji , a ii =1;In the scale method, 1 represents equal importance, 3 represents slightly important, 5 represents obviously important, 7 represents strongly important, 9 represents extremely important, and other values are complementary to intermediate values. After normalizing each column of the judgment matrix A, the average value of each row is calculated, and finally the weight of each item is obtained; calculating the largest eigenvalue λ of the judgment matrix A max ; based on the largest eigenvalue λ max the consistency index CI = (λ max - n) / (n - 1), where n is the dimension of the matrix equal to 6; Based on the consistency index CI, the consistency ratio CR=CI / RI is calculated, RI is the random consistency index, which is taken as 1.24 according to n; if the consistency ratio CR is less than or equal to 0.1, it is judged that the judgment matrix A has acceptable consistency, and the reachable factor A is obtained based on the judgment matrix A i Each factor W i , E i , O i , S i , M i , V i in the formula (t)'and the corresponding weighted reachable factor A i after the weighted fusion of the weight values thereof; otherwise, the scoring needs to be re-adjusted, and the judgment matrix A is adjusted.

7. The public transportation hub staff path guiding method according to claim 1, characterized by, The comfort factor of each grid unit is calculated, including: Comfort factor C of grid cell i at time t i The calculation formula of (t) is as follows: C i (t) = f2(T i (t), H i (t), N i (t), Aq i (t), L i (t)) wherein T i (t) represents the temperature of the environment, H i (t) represents the humidity of the environment, N i (t) represents the noise level of the environment, Aq i (t) represents the air quality, L i (t) represents the level of illumination; wherein the environmental temperature and humidity T i (t), H i (t) is calculated using the temperature and humidity index DI: DI = T i (t) -0.55(1 - 0.01H i (t) (T i (t) -14.5); Aq is calculated using the weighted average method i (t): Wherein, the weight coefficients λ1', λ2', λ3' are all greater than or equal to 0 and satisfy the sum of 1, and the values of the weight coefficients λ1', λ2', λ3' depend on different scenarios of the space grid unit; Ambient noise level N i (t) is calculated as follows: where L eq,i (t) is the equivalent sound level, L p (T) is the instantaneous sound level; Let E k (t) be the nominal luminous flux of the kth light source at time t, the distance from the center of the grid cell i to the kth light source be d ik , and the light transmission transmittance be τ ik (t). The illumination level L i (t) is calculated as follows:

8. The public transportation hub staff path guiding method according to claim 2, characterized by, based on path edges between each grid cell and each adjacent grid cell, and a reachability factor A for each grid cell i (t) a comfort factor C i (t), to obtain a sequence of paths with minimum total cost, comprising: Each grid cell i has a reachability factor A at time t i (t)’ with a comfort factor C i (t), all normalized to the 0 to 1 interval; The comprehensive weight of grid unit i at time t is defined as: W i (t) = β1(1 - A i (t)') + β2(1 - C i (t)) Wherein, β1 represents the importance weight of accessibility, β2 represents the importance weight of comfort, and β1+β2=1 is satisfied; For the path edge connecting the grid cells i and j, the cost of the path edge of the grid cells i and j at time t is calculated in an average weighted form of the edge weight ij (t): wherein d ij is the actual spatial distance between two grid cells, W i (t) is the integrated weight of grid cell i at time t; W j (t) is the integrated weight of grid cell j at time t; Based on each pair of adjacent cells {V i , V j} corresponding to the undirected edge E ij and the edge weight corresponding to the undirected edge E ij , the shortest path from the starting grid cell s to the ending grid cell g is searched and output as a path sequence; wherein the "shortest" of the path is defined as the minimum total cost, i.e. the minimum total edge weight.

9. The public transportation hub staff path guiding method according to claim 8, characterized by, After obtaining the path sequence with the minimum total cost, it further includes: Based on the output path sequence, the path overall index is calculated: Path total cost: Path average accessibility: Path average comfort: Wherein, N is the number of grid units included in the path; Through the path total cost, the path average accessibility and the path average comfort index, the safety and comfort of the path are comprehensively judged, and the weights β1 and β2 are adjusted to meet the guiding needs of passengers in different scenarios.

10. A computing device, wherein, Comprising: A processor; And A memory arranged to store computer executable instructions that, when executed, cause the processor to perform the method of any one of claims 1 to 9.

Images