Ruins protection area tourist diversion system and method based on dynamic bearing capacity

Abstract

The invention discloses a ruins protection area tourist diversion system and method based on dynamic bearing capacity. The diversion system comprises a data acquisition module, a bearing capacity calculation module, a diversion strategy optimization module, a tourist guide module and a feedback adjustment module. Real-time tourist data and environment information including tourist flow, residence time, meteorological conditions, site physical conditions and the like are collected; calculating the dynamic bearing capacity of the current ruin area, and comprehensively considering factors such as tourist load and environmental influence; a fuzzy logic reasoning method is adopted to evaluate tourist density and define a congestion degree grade: an IPSO algorithm is adopted to optimize tourist shunting paths, the shunting paths are generated and tourists are guided, and accurate shunting is carried out by adopting modes of intelligent identification, dynamic indication boards, mobile applications and the like; based on historical data and a real-time monitoring result, error correction is carried out on bearing capacity prediction, and the prediction accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of cultural heritage protection and tourism management, and particularly to a tourist diversion system and method for a heritage protection area based on dynamic carrying capacity. Background Art

[0002] Cultural tourism heritage sites are important carriers of human historical civilization and possess extremely high historical, cultural, and scientific research value. However, with the rapid development of the tourism industry, more and more tourists are flocking into heritage protection areas, resulting in huge artificial pressure on the heritage sites. These pressures are mainly reflected in several aspects: in terms of physical damage, the heritage site itself and its surrounding environment are exposed outdoors for a long time, affected by natural factors such as weathering and rain erosion, and at the same time, due to behaviors such as tourists trampling and touching, structural damage or even irreversible destruction is caused; in terms of the decline of environmental carrying capacity, large-scale tourist activities have a negative impact on the soil, vegetation, water resources, and air quality in the heritage site area, such as vegetation damage, soil hardening, aggravated water pollution and air pollution; in terms of the decline of tourist experience, high-density crowds lead to crowded roads in the heritage scenic area, affecting tourists' viewing experience, increasing management difficulties, and even posing safety hazards; in terms of backward management methods, at present, the tourist management in heritage protection areas mostly relies on manual regulation at fixed times and quantities, such as flow-limiting measures and fixed route planning. These methods lack the ability of dynamic adjustment and are difficult to accurately match the tourist flow with the heritage carrying capacity under different time periods and environmental conditions.

[0003] At present, the research on heritage protection and tourist management at home and abroad mainly focuses on several aspects, but there are still many limitations. In terms of carrying capacity assessment, many studies adopt fixed environmental carrying capacity standards, that is, the maximum tourist carrying capacity is preset according to the heritage site area, structural strength, etc., but ignore the dynamic impact of environmental changes (such as seasons, climate, tourist behavior patterns, etc.) on the carrying capacity, resulting in lagging management strategies; in terms of diversion methods, at present, most scenic areas adopt simple manual diversion or fixed route planning methods, which cannot adjust the diversion strategy according to the real-time tourist flow and environmental status, resulting in overcrowding in some areas and underutilization in other areas; in terms of management optimization, the existing tourist management systems mostly rely on manual decision-making and lack a data-driven intelligent optimization model, and cannot predict and adjust in combination with real-time monitoring data.

[0004] In addition, another significant shortcoming in the management of tourists in existing heritage protection areas is the lack of personalized tourist guidance. The management of tourist flow in most scenic spots does not fully consider individual differences among tourists, such as points of interest, itinerary preferences, etc., resulting in poor tourist experiences and making it difficult to achieve balanced diversion without affecting heritage protection. The existence of these problems has made the contradiction between heritage protection and tourism development increasingly prominent. There is an urgent need to develop a tourist diversion system for heritage protection areas based on dynamic carrying capacity, which can monitor the environmental status and tourist flow in real time, dynamically evaluate the carrying capacity of different areas of the heritage site, and optimize the tourist diversion plan through intelligent algorithms, improving the tourist experience while ensuring the safety of the heritage site and achieving sustainable and coordinated development of heritage protection and tourism development. Summary of the Invention

[0005] The purpose of the present invention is to provide a tourist diversion system and method for heritage protection areas based on dynamic carrying capacity, which can evaluate the carrying capacity in real time and intelligently regulate the distribution of tourist flow.

[0006] To achieve the above object, the present invention provides the following technical solution: A tourist diversion system for heritage protection areas based on dynamic carrying capacity, comprising a data acquisition module, a carrying capacity calculation module, a diversion strategy optimization module, a tourist guidance module, and a feedback adjustment module;

[0007] The data acquisition module is used to collect data on tourist flow, temperature and humidity, air quality, and the health status of the heritage site structure in real time, and transmit the collected data to the carrying capacity calculation module;

[0008] The carrying capacity calculation module receives the data transmitted by the data acquisition module and calculates the dynamic carrying capacity of the heritage site area based on the data. Among them, the temperature data collected by the data acquisition module corresponds to the temperature pressure factor, the humidity data corresponds to the humidity pressure factor, the air quality data corresponds to the air quality pressure factor, the structure health status data corresponds to the structure health status pressure factor, and the tourist flow data corresponds to the tourist density pressure factor. The calculation formula is as follows: Where C t is the current carrying capacity, C s is the theoretical maximum carrying capacity, P i is the i-th environmental pressure factor, a i is its weight coefficient, and the weight coefficient is determined through historical data analysis and expert evaluation;

[0009] The diversion strategy optimization module is connected to the carrying capacity calculation module, receives the dynamic carrying capacity calculation result, optimizes the tourist diversion strategy using the particle swarm optimization algorithm, and generates a diversion strategy, where the optimization includes allocating the number of tourists according to the carrying capacity of each area and determining the optimal tour route;

[0010] The tourist guidance module is connected to the flow diversion strategy optimization module, receives tourist guidance instructions according to the optimized flow diversion strategy, and guides tourists to tour along the optimized route through electronic map navigation or intelligent guidance signs;

[0011] The feedback adjustment module is connected to the tourist guidance module, collects tourist behavior data and environmental changes in real time, and transmits the feedback data to the flow diversion strategy optimization module for dynamically adjusting the flow diversion strategy.

[0012] (1) Data collection: Real-time collection of tourist flow data, temperature and humidity data, air quality data, and the structural health status data of the heritage protection area, and define the temperature data corresponding to the temperature pressure factor, the humidity data corresponding to the humidity pressure factor, the air quality data corresponding to the air quality pressure factor, the structural health status data corresponding to the structural health status pressure factor, and the tourist flow data corresponding to the tourist density pressure factor;

[0013] (2) Dynamic carrying capacity calculation: Calculate the current dynamic carrying capacity of the heritage area according to the collected data, and the calculation uses the formula where C t is the current carrying capacity, C s is the theoretical maximum carrying capacity, P i is the i-th environmental pressure factor, a i is its weight coefficient, and the weight coefficient is determined through historical data analysis and expert evaluation;

[0014] (3) Regional load assessment: According to the current tourist distribution and the dynamic carrying capacity calculated in step (2), calculate the load ratio R = N / C of each area of the heritage, where N is the number of tourists in the current area and C is the current dynamic carrying capacity of the area, and divide each area into a low-load area, a medium-load area, and a high-load area according to the load ratio. Among them, the low-load area (R ≤ 0.6) means free entry is allowed; the medium-load area (0.6 < R ≤ 0.9) means flow restriction and guidance; the high-load area (R > 0.9) means entry is prohibited and an alarm is triggered;

[0015] (4) Flow diversion strategy optimization: Based on the distribution of the low-load area, medium-load area, and high-load area determined in step (3), use the particle swarm optimization algorithm to generate a flow diversion strategy. The strategy includes the number of tourists transferred from the high-load area to the low-load area, the transfer path, and the control of tourist flow directions between areas. The optimization goal is to balance the load ratios of each area and ensure the tourist experience and the safety of the heritage;

[0016] (5) Tourist guidance execution: According to the flow diversion strategy optimized in step (4), push personalized tour route suggestions to tourists through an electronic tour map or an intelligent guidance sign system, and set prompt information at the entrance of the high-load area to guide tourists to flow to the low-load area;

[0017] (6) Feedback and adjustment: Collect data on the actual tour behaviors of tourists and environmental changes, evaluate the effect of flow diversion, and feedback the evaluation results to steps (2) and (4) to dynamically adjust the bearing capacity calculation parameters and the optimization weights of the flow diversion strategy, forming a closed-loop optimization mechanism.

[0018] The data collection in step (1) specifically includes:

[0019] (1.1) Collection of tourist flow data: Deploy infrared counters, depth cameras, and Wi-Fi probe sensors at the entrances, exits, main scenic spots, and key fork paths in the heritage protection area to count the number of tourists in each area in real time and record the changes in the flow density; among them, the infrared counter uses a two-way counting algorithm to accurately distinguish between incoming and outgoing tourists; the depth camera combines computer vision algorithms to generate a heat map of the flow density; the Wi-Fi probe estimates the number of people staying in the area by capturing the MAC addresses of mobile devices;

[0020] (1.2) Collection of temperature and humidity data: Deploy wireless temperature and humidity sensor nodes at a density of 3 - 5 meters per point in different functional areas of the heritage site, with a sampling frequency of once every 5 minutes, to record the temperature change range and humidity fluctuation values at each point in real time, and calculate the temperature and humidity anomaly index based on historical data for the same period;

[0021] (1.3) Collection of air quality data: Deploy sensors for detecting PM2.5, PM10, CO2 concentration, and volatile organic compounds to monitor the changes in air quality caused by tourist activities, with a sampling frequency of once every 10 minutes;

[0022] (1.4) Collection of data on the health status of the heritage site structure: Install micro-displacement sensors, vibration sensors, and stress-strain sensors at the key load-bearing structures, walls of historical buildings, and ground pavements of the heritage site to continuously collect structural response data for 24 hours, and perform preliminary processing through edge computing devices to extract the characteristic parameters of the structural health status.

[0023] The dynamic calculation of the bearing capacity in step (2) specifically includes:

[0024] (2.1) Calculation of environmental pressure factors:

[0025] Calculation formula for the temperature pressure factor: where T is the current temperature, T opt is the optimal tour temperature, and T max is the acceptable maximum temperature;

[0026] Calculation formula for the humidity pressure factor: where H is the current humidity, H opt is the optimal tour humidity, and H max is the acceptable maximum humidity deviation;

[0027] Calculation formula for air quality stress factor: where AQI is the air quality index, and AQI max is the maximum acceptable air quality index;

[0028] Calculation formula for structural health status stress factor: where S i is the structural stress or displacement value at the i-th monitoring point, and S i,max is the safety valve threshold, and n is the total number of monitoring points;

[0029] (2.2) Determination of weight coefficients: Determine the weight coefficients of each stress factor through the analytic hierarchy process (AHP) combined with the principal component analysis (PCA) of historical monitoring data, and establish a season-time period adjustment matrix to dynamically adjust the weights in different seasons and time periods;

[0030] (2.3) Calculation of dynamic bearing capacity: Calculate the current bearing capacity through the formula where C0 is the theoretical maximum bearing capacity, and w’ i is the adjusted weight coefficient, and p i is the i-th environmental stress factor; Perform spatial interpolation on the discrete monitoring point data through the cubic spline interpolation method to generate a heat map of the bearing capacity distribution in the entire site area, and update it every 15 minutes.

[0031] The regional load assessment in step (3) specifically includes:

[0032] (3.1) Site area division: Based on the site cultural relic protection level, historical value assessment, and tourist behavior patterns, divide the site protection area into three functional areas: the core protection area, the general display area, and the edge service area, and further divide them into n management units, and configure independent pedestrian flow monitoring devices for each management unit;

[0033] (3.2) Calculation of load ratio: For each management unit i, calculate the current load ratio where N i is the number of tourists in the current unit, and C i is the current dynamic bearing capacity of this unit;

[0034] (3.3) Load rating: According to the load ratio R value, combined with the results of the site vulnerability assessment, establish a multi-level load rating standard, specifically as follows:

[0035] Core protection area: Low load area (R ≤ 0.5), medium load area (0.5 < R ≤ 0.8), high load area (R > 0.8);

[0036] General display area: Low load area (R ≤ 0.6), medium load area (0.6 < R ≤ 0.9), high load area (R > 0.9);

[0037] Edge service area: low load area (R≤0.7), medium load area (0.7<R≤0.95), high load area (R>0.95);

[0038] (3.4) Analysis of regional linkage relationship: Establish a tourist flow relationship map between adjacent management units, analyze the linkage effect of the load state change of each unit, and predict the change of the load distribution after tourist diversion.

[0039] The optimization of the diversion strategy in step (4) specifically includes:

[0040] (4.1) Problem modeling: Model the tourist diversion problem as a multi-objective optimization problem, and define the objective function as:

[0041]

[0042] where, R i is the load ratio of the i-th area, R avg is the target average load ratio, T i is the average tour time of tourists in each area, D i is the walking distance of tourists, E is the comprehensive tour experience score, and w1 to w4 are weight coefficients;

[0043] (4.2) Parameter setting of particle swarm optimization algorithm: Set the number of particles to 50, the maximum number of iterations to 200, the inertia weight w linearly decreases from 0.9 to 0.4, the acceleration constants c1 = c2 = 2.0, and adopt the local optimal particle swarm optimization algorithm with a V-shaped topology structure to improve the convergence speed;

[0044] (4.3) Encoding of diversion strategy: Each particle represents a possible diversion strategy, encoded as X = (p1, p2,...., p n , r1, r2,..., r m ), where P i represents the proportion of tourists transferred from the i-th high load area to other areas, and r j represents the recommended weight of the j-th path;

[0045] (4.4) Setting of constraint conditions:

[0046] The load ratio of any area shall not exceed the safety threshold of this area: R i ≤R i,max ,

[0047] The load ratio of the core cultural relics area shall not exceed 0.8: R i ≤0.8,

[0048] The one-way walking distance of tourists shall not exceed the preset maximum value: D k ≤D nax ,

[0049] The flow volume of tourists between regions shall not exceed the channel capacity: F ij ≤F ij,max ,

[0050] (4.5) Strategy generation and verification: Generate the optimal diversion strategy through iterative optimization, including the number of tourists to be transferred in each high-load area, the number of tourists that can be received in each low-load area, the weight allocation of recommended routes, and the control of tourist flow between regions; Use historical data for Monte Carlo simulation to verify the effectiveness of the strategy, ensuring that the load ratio in the high-load area can be reduced to a safe level in more than 90% of the scenarios.

[0051] The implementation of tourist guidance in step (5) specifically includes:

[0052] (5.1) Personalized route generation: According to the characteristics such as interest preferences, expected tour time, and mobility ability in the tourist registration information, combined with the current diversion strategy, use the improved Dijkstra algorithm to generate 3-5 alternative tour routes for each tourist, and give priority to recommending routes passing through low-load areas;

[0053] (5.2) Implementation of multi-channel guidance: Push personalized tour maps and voice prompts through the mobile terminal APP; Install electronic display screens at key nodes in the heritage area to update the load status of each area and recommended routes in real time; Set up an intelligent tour guide identification system to visually display the congestion status of each area through LED color changes; Add tour guides at the entrances of high-load areas for guidance;

[0054] (5.3) Incentive mechanism design: Provide incentive measures such as extended visiting time, expert lectures, and discounts on cultural and creative products for tourists who follow the diversion suggestions and go to low-load areas to improve the diversion execution rate;

[0055] (5.4) Emergency evacuation plan: When the load ratio of a certain area exceeds the emergency threshold (R>1.1), start the emergency evacuation plan, suspend ticket sales at the entrance of this area, dispatch additional management personnel to guide on-site tourists to disperse, and issue emergency evacuation instructions through the broadcast system.

[0056] The feedback and adjustment in step (6) specifically include:

[0057] (6.1) Collection of tourist behavior data: By tracking the location of the mobile APP, analyzing video surveillance, and comparing the counts at entrances and exits, collect the actual movement trajectories of tourists, the distribution of their staying times, and their behavior of area conversion; collect evaluation data on tourists' perception of congestion, satisfaction with guidance, and overall experience through questionnaires within the APP and electronic evaluators at stations.

[0058] (6.2) Evaluation of the diversion effect: Calculate the following evaluation indicators:

[0059] Execution rate of the diversion strategy:

[0060] Degree of regional load balance: where σ is the standard deviation and μ is the mean;

[0061] Tourist satisfaction: where S i is the satisfaction score of the i-th tourist;

[0062] (6.3) Adjustment of the parameters of the carrying capacity model: Based on the collected environmental monitoring data and the response data of the site structure, apply multiple regression analysis to update the weight coefficients of each environmental stress factor, and adaptively adjust the parameters of the dynamic carrying capacity calculation model.

[0063] (6.4) Adjustment of the optimization parameters of the diversion strategy: According to the evaluation results, adjust the weight of the objective function, the threshold of the constraint conditions, and the convergence parameters in the particle swarm optimization algorithm to improve the efficiency of strategy generation.

[0064] (6.5) Closed-loop optimization mechanism: Establish a data-driven adaptive learning mechanism, and through the method of deep reinforcement learning, enable the system to continuously optimize the decision-making model according to the historical diversion effect.

[0065] Compared with the prior art, the advantages of the present invention are as follows:

[0066] 1. Dynamically calculate the carrying capacity of the site and improve the management accuracy

[0067] The present invention adopts a multi-source data fusion technology to collect information such as tourist flow, environmental factors (temperature, humidity, air quality, etc.), and the health status of the site in real time, and combines time series analysis to predict the future carrying capacity. Compared with the traditional static carrying capacity evaluation method, this system can dynamically adjust the tourist capacity threshold, making the calculation of the carrying capacity more accurate and more adaptable.

[0068] 2. Adopt an intelligent optimization algorithm to improve the diversion efficiency

[0069] This system integrates improved particle swarm optimization and deep reinforcement learning algorithms, and can generate optimal tourist diversion paths and strategies based on comprehensive consideration of tourist comfort, site protection needs and management costs. Compared with traditional fixed routes or empirical diversion methods, this system can dynamically adjust tourist flows based on real-time data, reduce congestion and improve management efficiency.

[0070] 3. Provide personalized tourist guidance to enhance tourist experience

[0071] The present invention supports personalized guided tours for tourists, and provides suggestions for the best tour routes based on tourists' points of interest, itinerary preferences and other information through smart mobile applications, wearable devices and electronic guide systems. This approach not only improves tourists' tour experience, but also effectively avoids excessive concentration in certain popular areas and optimizes the utilization rate of scenic area resources.

[0072] 4. Early warning mechanism and dynamic adjustment to ensure the safety of the site

[0073] The present invention has an automatic early warning function. When the tourist density exceeds the set threshold or the environmental carrying capacity is close to the limit, the system will automatically trigger an alarm and take corresponding diversion measures, such as adjusting the tourist route, restricting entry into some areas, etc., thereby reducing the risk of physical damage to the site and ensuring the long-term safety of the site.

[0074] 5. Low-cost and efficient management to improve management level

[0075] Compared with the traditional manual flow control or fixed management method, the present invention can automatically calculate and optimize the flow of tourists, reduce the need for manual intervention, and thus reduce management costs. At the same time, the system is compatible with the existing scenic area management system, easy to promote and apply, and improve the intelligent management level of scenic spots.

[0076] 6. Promote the sustainable protection and development of cultural heritage

[0077] Through precise visitor management and intelligent diversion strategies, the present invention can effectively reduce the physical damage to the site caused by tourists without affecting the tourist experience, thereby extending the service life of the site. At the same time, intelligent management can improve the utilization efficiency of the site's carrying capacity, so that cultural heritage protection and tourism development can achieve a balanced and win-win goal. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are merely embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0079] Figure 1This is the process schematic diagram of the present invention. Detailed implementation manners

[0080] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0081] Embodiment 1: As shown in the figure, a tourist diversion system for a heritage protection area based on dynamic bearing capacity includes a data acquisition module, a bearing capacity calculation module, a diversion strategy optimization module, a tourist guidance module, and a feedback adjustment module;

[0082] The data acquisition module is used to collect data on tourist flow, temperature and humidity, air quality, and the health status of the heritage structure in real time, and transmit the collected data to the bearing capacity calculation module;

[0083] The bearing capacity calculation module receives the data transmitted by the data acquisition module and calculates the dynamic bearing capacity of the heritage area based on the data. Among them, the temperature data collected by the data acquisition module corresponds to the temperature pressure factor, the humidity data corresponds to the humidity pressure factor, the air quality data corresponds to the air quality pressure factor, the structure health status data corresponds to the structure health status pressure factor, and the tourist flow data corresponds to the tourist density pressure factor. The calculation formula is as follows: Among them, C t is the current bearing capacity, C s is the theoretical maximum bearing capacity, P i is the i-th environmental pressure factor, a i is its weight coefficient, and the weight coefficient is determined through historical data analysis and expert evaluation;

[0084] The diversion strategy optimization module is connected to the bearing capacity calculation module, receives the dynamic bearing capacity calculation result, optimizes the tourist diversion strategy using the particle swarm optimization algorithm, and generates a diversion strategy. The optimization includes allocating the number of tourists according to the bearing capacity of each area and determining the optimal tour route;

[0085] The tourist guidance module is connected to the diversion strategy optimization module, receives tourist guidance instructions according to the optimized diversion strategy, and guides tourists to tour according to the optimized route through electronic map navigation or intelligent guidance signs;

[0086] The feedback adjustment module is connected to the tourist guidance module, collects tourist behavior data and environmental change situations in real time, and transmits the feedback data to the diversion strategy optimization module for dynamically adjusting the diversion strategy.

[0087] Example 2: A method for diverting tourists in a heritage protection area based on dynamic carrying capacity, including the following steps:

[0088] (1) Data collection: Real-time collect the tourist flow data, temperature and humidity data, air quality data, and the structural health status data in the heritage protection area, and define the temperature data corresponding to the temperature pressure factor, the humidity data corresponding to the humidity pressure factor, the air quality data corresponding to the air quality pressure factor, the structural health status data corresponding to the structural health status pressure factor, and the tourist flow data corresponding to the tourist density pressure factor;

[0089] (2) Dynamic calculation of carrying capacity: Calculate the current dynamic carrying capacity of the heritage area according to the collected data. The calculation uses the formula where C t is the current carrying capacity, C s is the theoretical maximum carrying capacity, P i is the i-th environmental pressure factor, and a i is its weight coefficient, and the weight coefficient is determined through historical data analysis and expert evaluation;

[0090] (3) Regional load assessment: According to the current tourist distribution and the dynamic carrying capacity calculated in step (2), calculate the load ratio R = N / C of each area in the heritage area, where N is the number of tourists in the current area and C is the current dynamic carrying capacity of this area. And divide each area into a low-load area, a medium-load area, and a high-load area according to the load ratio. Among them, the low-load area (R ≤ 0.6) means free entry is allowed; the medium-load area (0.6 < R ≤ 0.9) means flow restriction and guidance; the high-load area (R > 0.9) means entry is prohibited and an alarm is triggered;

[0091] (4) Optimization of the diversion strategy: Based on the distribution of the low-load area, medium-load area, and high-load area determined in step (3), use the particle swarm optimization algorithm to generate a diversion strategy. The strategy includes the number of tourists transferred from the high-load area to the low-load area, the transfer path, and the control of the tourist flow direction between each area. The optimization goal is to balance the load ratio of each area and ensure the tourist experience and the safety of the heritage;

[0092] (5) Execution of tourist guidance: According to the diversion strategy optimized in step (4), push personalized tour route suggestions to tourists through an electronic guide map or an intelligent guidance sign system, and set prompt information at the entrance of the high-load area to guide tourists to flow to the low-load area;

[0093] (6) Feedback and adjustment: Collect the actual tourist behavior data and environmental change data, evaluate the diversion effect, and feedback the evaluation results to steps (2) and (4) to dynamically adjust the carrying capacity calculation parameters and the diversion strategy optimization weights to form a closed-loop optimization mechanism.

[0094] This method first collects key data such as tourist flow, temperature and humidity, air quality, and structural health status in the site area through multi-source sensors in real time, and converts this data into quantified environmental stress factors. Subsequently, based on the weight coefficients determined by expert experience and historical data, the actual carrying capacity of the current site area is dynamically calculated through a mathematical model, breaking through the limitations of traditional static carrying capacity assessment. Then, each area of the site is divided into low, medium, and high load areas according to the load ratio (the ratio of the current number of tourists to the dynamic carrying capacity), and a hierarchical control mechanism is established. Then, using the particle swarm optimization algorithm, considering the requirements of site protection and the needs of tourist experience, an optimal diversion strategy is generated to balance the distribution of tourists in each area. Personalized route suggestions are pushed to tourists through various means such as electronic guide maps and intelligent guiding signs to achieve precise guidance. Finally, by collecting tourist behavior data and environmental change data in real time, the diversion effect is evaluated and the system parameters are dynamically adjusted to form a feedback adjustment mechanism, enabling the entire system to continuously optimize itself, ensuring both the safety protection of the site and the improvement of tourists' visiting experience, and is particularly suitable for site protection areas with high cultural relic value, large tourist flow, and environmental sensitivity.

[0095] The data collection in step (1) specifically includes:

[0096] (1.1) Collection of tourist flow data: Deploy infrared counters, depth cameras, and Wi-Fi probe sensors at the entrances, exits, main viewing points, and key bifurcation paths in the site protection area to count the number of tourists in each area in real time and record the changes in pedestrian flow density. Among them, the infrared counter uses a two-way counting algorithm to accurately distinguish incoming and outgoing tourists; the depth camera combines computer vision algorithms to generate a heat map of pedestrian flow density; the Wi-Fi probe estimates the number of people staying in the area by capturing the MAC addresses of mobile devices.

[0097] (1.2) Collection of temperature and humidity data: Deploy wireless temperature and humidity sensor nodes at a density of 3 - 5 meters per point in different functional areas of the site, with a sampling frequency of once every 5 minutes, to record the temperature change range and humidity fluctuation values at each point in real time, and calculate the temperature and humidity anomaly index based on historical data for the same period.

[0098] (1.3) Collection of air quality data: Deploy sensors for detecting PM2.5, PM10, CO2 concentration, and volatile organic compounds to monitor the changes in air quality caused by tourist activities, with a sampling frequency of once every 10 minutes.

[0099] (1.4) Collection of data on the structural health status of the site: Install micro-displacement sensors, vibration sensors, and stress-strain sensors at the key load-bearing structures, historical building walls, and floor pavements of the site to continuously collect structural response data for 24 hours, and perform preliminary processing through edge computing devices to extract characteristic parameters of the structural health status.

[0100] In this step, a combined deployment of an infrared counter, a depth camera, and a Wi-Fi probe sensor is adopted for tourist flow monitoring, achieving precise differentiation of tourists entering and leaving, real-time generation of a heat map of the crowd density, and accurate estimation of the number of people staying in the area. For temperature and humidity data collection, wireless sensor nodes with a high-density distribution record environmental changes at a frequency of once every 5 minutes, and the anomaly index is calculated by combining historical data for the same period. The air quality monitoring system integrates sensors for detecting PM2.5, PM10, CO2 concentration, and volatile organic compounds, and samples once every 10 minutes to comprehensively evaluate the impact of tourist activities on the air environment. For the structural health status monitoring of the site, continuous 24-hour data collection is carried out through micro-displacement sensors, vibration sensors, and stress-strain sensors, and key characteristic parameters are extracted by combining edge computing technology.

[0101] This comprehensive data collection scheme for multi-source heterogeneous data not only improves the accuracy of the assessment of the site environment status but also provides comprehensive and reliable data support for subsequent dynamic carrying capacity calculations, enabling tourist diversion decisions to be based on more refined and real-time site status information, thus effectively balancing the contradiction between site protection and tourist experience.

[0102] The specific dynamic calculation of the carrying capacity in step (2) includes:

[0103] (2.1) Calculation of environmental stress factors:

[0104] Calculation formula for the temperature stress factor: where T is the current temperature, T opt is the optimal tourist temperature, T max is the acceptable maximum temperature;

[0105] Calculation formula for the humidity stress factor: where H is the current humidity, H opt is the optimal tourist humidity, H max is the acceptable maximum humidity deviation;

[0106] Calculation formula for the air quality stress factor: where AQI is the air quality index, AQI max is the acceptable maximum air quality index;

[0107] Calculation formula for the structural health status stress factor: where S i is the structural stress or displacement value at the i-th monitoring point, S i,max is the safety valve threshold, and n is the total number of monitoring points;

[0108] (2.2) Determination of weight coefficients: The weight coefficients of each pressure factor are determined through the Analytic Hierarchy Process (AHP) combined with the Principal Component Analysis (PCA) of historical monitoring data, and a season - time period adjustment matrix is established to dynamically adjust the weights in different seasons and time periods;

[0109] (2.3) Calculation of dynamic carrying capacity: The current carrying capacity is calculated through the formula where \(C_0\) is the theoretical maximum carrying capacity, \(w'\) i is the adjusted weight coefficient, and \(p\) i is the \(i\) - th environmental pressure factor; The data of discrete monitoring points are spatially interpolated by the cubic spline interpolation method to generate a heat map of the carrying capacity distribution of the entire site area, and it is set to be updated every 15 minutes.

[0110] The above steps establish a complete calculation system for environmental pressure factors. For temperature pressure, it is calculated by the ratio of the square of the deviation from the optimal tour temperature, fully considering the dual impacts of temperature on tourist comfort and cultural relic safety; Humidity pressure is evaluated based on the ratio of the difference between the current humidity and the optimal humidity, effectively reflecting the impact of humidity on the stability of cultural relic materials; Air quality pressure directly reflects the degree of air pollution through the ratio of the air quality index to the maximum acceptable value; The structural health status pressure comprehensively considers the structural stress or displacement data of multiple monitoring points and calculates the overall structural risk through the ratio to the safety threshold.

[0111] The determination of weight coefficients combines the Analytic Hierarchy Process and the Principal Component Analysis method, and introduces a season - time period adjustment matrix to achieve dynamic weight adjustment, adapting to the sensitive changes of the site to environmental factors in different periods. Finally, the current carrying capacity is obtained through weighted calculation, and the cubic spline interpolation method is used to expand the data of discrete monitoring points into a heat map of the carrying capacity distribution of the entire area, which is updated every 15 minutes, ensuring the spatial continuity and time real - time of the carrying capacity assessment. This technology breaks through the limitations of traditional static carrying capacity models, enables the site management decision - making to be adjusted in a timely manner according to environmental changes, and provides a scientific basis for refined and differentiated tourist diversion strategies.

[0112] The regional load assessment in step (3) specifically includes:

[0113] (3.1) Site area division: Based on the cultural relic protection level, historical value assessment of the site and tourist behavior patterns, the site protection area is divided into three functional areas: the core protection area, the general display area and the edge service area, and further subdivided into \(n\) management units, and each management unit is equipped with independent passenger flow monitoring equipment;

[0114] (3.2) Calculation of load ratio: For each management unit \(i\), calculate the current load ratio where \(N\) i is the number of tourists in the current unit, and \(C\)i is the current dynamic bearing capacity of the unit;

[0115] (3.3) Load rating: According to the load ratio R value and combined with the results of the site vulnerability assessment, a multi-level load rating standard is established as follows:

[0116] Core protection area: low load area (R ≤ 0.5), medium load area (0.5 < R ≤ 0.8), high load area (R > 0.8);

[0117] General display area: low load area (R ≤ 0.6), medium load area (0.6 < R ≤ 0.9), high load area (R > 0.9);

[0118] Peripheral service area: low load area (R ≤ 0.7), medium load area (0.7 < R ≤ 0.95), high load area (R > 0.95);

[0119] (3.4) Analysis of regional linkage relationship: Establish a diagram of the tourist flow relationship between adjacent management units, analyze the linkage effect of the load status change of each unit, and predict the change of the load distribution after tourist diversion.

[0120] The above steps scientifically divide the entire area into three functional areas: the core protection area, the general display area, and the peripheral service area based on the protection level of the site cultural relics, historical value assessment, and tourist behavior patterns, and are further subdivided into several management units. Each unit is equipped with independent pedestrian flow monitoring equipment to ensure data accuracy.

[0121] The load assessment calculates the load ratio by the ratio of the current number of tourists to the dynamic bearing capacity, and sets different load rating standards for different functional areas: the core protection area adopts a more stringent standard (low load ≤ 0.5, medium load 0.5 - 0.8, high load > 0.8), the general display area adopts a relatively loose standard (low load ≤ 0.6, medium load 0.6 - 0.9, high load > 0.9), and the peripheral service area sets a larger tolerance range (low load ≤ 0.7, medium load 0.7 - 0.95, high load > 0.95).

[0122] This step also establishes a diagram of the tourist flow relationship between adjacent management units. By analyzing the regional linkage effect, it can accurately predict the change of the load distribution after the implementation of the diversion strategy. This differential load assessment method based on regional characteristics not only improves the refined management level of site protection but also provides a more practical decision-making basis for the subsequent optimization of the diversion strategy, effectively balancing the protection intensity and opening degree of different regions.

[0123] The optimization of the diversion strategy in step (4) specifically includes:

[0124] (4.1) Problem Modeling: Model the tourist diversion problem as a multi-objective optimization problem, and define the objective function as follows:

[0125]

[0126] Among them, R i is the load ratio of the i-th area, and R avg is the target average load ratio. T i is the average visiting time of tourists in each area, D i is the walking distance of tourists, E is the comprehensive tour experience score, and w1 to w4 are weight coefficients;

[0127] (4.2) Particle Swarm Optimization Algorithm Parameter Setting: Set the number of particles to 50, the maximum number of iterations to 200, the inertia weight w to linearly decrease from 0.9 to 0.4, the acceleration constants c1 = c2 = 2.0, and adopt the local optimal particle swarm optimization algorithm with a V-shaped topology structure to improve the convergence speed;

[0128] (4.3) Diversion Strategy Encoding: Each particle represents a possible diversion strategy, encoded as X = (p1, p2,...., p n , r1, r2,..., r m ), where P i represents the proportion of tourists transferred from the i-th high-load area to other areas, and r j represents the recommended weight of the j-th path;

[0129] (4.4) Constraint Condition Setting:

[0130] The load ratio of any area shall not exceed the safety threshold of this area: R i ≤R i,max ,

[0131] The load ratio of the core cultural relics area shall not exceed 0.8: R i ≤0.8,

[0132] The one-way walking distance of tourists shall not exceed the preset maximum value: D k ≤D nax ,

[0133] The tourist flow between areas shall not exceed the channel capacity: F ij ≤F ij,max ,

[0134] (4.5) Strategy Generation and Verification: Generate the optimal diversion strategy through iterative optimization, including the number of tourists to be transferred in each high-load area, the number of tourists that can be received in each low-load area, the weight allocation of recommended routes, and the control of tourist flow between regions; Use historical data for Monte Carlo simulation to verify the effectiveness of the strategy, ensuring that the load ratio in high-load areas can be reduced to a safe level in more than 90% of the scenarios.

[0135] The above steps model the tourist diversion problem as a multi-objective optimization problem, comprehensively consider various factors such as regional load balance, tour time, walking distance, and tour experience, construct a composite objective function with adjustable weights, and achieve a multi-dimensional balance between protection and experience.

[0136] In the algorithm implementation, the particle swarm optimization algorithm is adopted. The convergence speed of the algorithm is improved through carefully designed parameter configurations (50 particles, 200 iterations, linearly decreasing inertia weight) and a V-shaped topology structure. The coding of the diversion strategy adopts a two-layer structure, which includes both the transfer ratio of tourists from high-load areas to other areas and the recommended weights of each path, making the strategy more comprehensive. The design of constraint conditions comprehensively considers practical constraints such as the safety of the site (regional load does not exceed the safety threshold), tourist experience (walking distance limit), and channel capacity limit, ensuring the executability of the strategy. The Monte Carlo simulation verification mechanism is also introduced in the strategy generation process to ensure that the load in high-load areas can be effectively reduced in more than 90% of the scenarios, improving the robustness of the strategy, and thus realizing the scientific regulation of the tourist flow in the site protection area.

[0137] The specific implementation of tourist guidance in step (5) includes:

[0138] (5.1) Personalized Route Generation: According to the characteristics such as interest preferences, expected tour time, and mobility ability in the tourist registration information, combined with the current diversion strategy, use the improved Dijkstra algorithm to generate 3-5 alternative tour routes for each tourist, and give priority to recommending routes passing through low-load areas;

[0139] (5.2) Multi-channel Guidance Implementation: Push personalized navigation maps and voice prompts through the mobile terminal APP; Install electronic display screens at key nodes in the site area to update the load status of each area and recommended routes in real time; Set up an intelligent navigation sign system to visually display the congestion status of each area through LED color changes; Add tour guides at the entrances of high-load areas for guidance;

[0140] (5.3) Incentive Mechanism Design: Provide incentive measures such as extended visiting time, expert lectures, and discounts on cultural and creative products for tourists who follow the diversion suggestions and go to low-load areas to improve the diversion execution rate;

[0141] (5.4) Emergency evacuation plan: When the load ratio of a certain area exceeds the emergency threshold (R > 1.1), the emergency evacuation plan is activated. Ticket sales at the entrance of this area are suspended, additional management staff are dispatched to guide on-site visitors to disperse, and emergency evacuation instructions are issued through the public address system.

[0142] The above steps deeply utilize individual characteristics such as interest preferences, expected visiting time, and mobility ability in the visitor registration information, combine with the current diversion needs, and apply the improved Dijkstra algorithm to generate 3 - 5 alternative visiting routes for each visitor, giving priority to recommending routes passing through low-load areas, thus realizing the organic combination of diversion and personalized services.

[0143] In terms of guiding means, a multi-channel method combining mobile terminal APP, electronic display screens, intelligent guiding sign systems, and manual guiding is adopted to form an all-round guiding network, enhancing the transmission effect of diversion instructions. This step also designs an incentive mechanism to encourage visitors to go to low-load areas through measures such as extending the visiting time, expert explanations, and discounts on cultural and creative products, improving the diversion execution rate. For extreme situations, the plan also formulates an emergency evacuation plan. When the area load ratio exceeds the emergency threshold (R > 1.1), a series of emergency measures such as suspending ticket sales, dispatching additional management staff, and broadcasting evacuation instructions will be taken. This not only realizes the precise execution of the diversion strategy but also improves the visitors' visiting experience, maximizing the satisfaction of visitors' personalized needs while ensuring the safety of the site.

[0144] The feedback and adjustment in step (6) specifically include:

[0145] (6.1) Collection of visitor behavior data: Through mobile APP location tracking, video surveillance analysis, and comparison of entrance and exit counts, collect the actual movement trajectories, stay time distributions, and area conversion behaviors of visitors; collect evaluation data on visitors' perception of congestion, guiding satisfaction, and overall experience through in-APP questionnaires and on-site electronic evaluators.

[0146] (6.2) Evaluation of diversion effect: Calculate the following evaluation indicators:

[0147] Diversion strategy execution rate:

[0148] Regional load balance degree: where σ is the standard deviation and μ is the average value;

[0149] Visitor satisfaction: where S i is the satisfaction score of the i-th visitor;

[0150] (6.3) Adjustment of bearing capacity model parameters: Based on the collected environmental monitoring data and site structure response data, apply multiple regression analysis to update the weight coefficients of each environmental stress factor, and adaptively adjust the parameters of the dynamic bearing capacity calculation model;

[0151] (6.4) Adjustment of optimized parameters for diversion strategies: According to the evaluation results, adjust the objective function weight, constraint condition threshold, and convergence parameters in the particle swarm optimization algorithm to improve the efficiency of strategy generation;

[0152] (6.5) Closed-loop optimization mechanism: Establish a data-driven adaptive learning mechanism, and through deep reinforcement learning methods, enable the system to continuously optimize the decision-making model based on historical diversion effects.

[0153] The above steps collect the actual movement trajectories and residence time distributions of tourists through various means such as location tracking of mobile APPs, video surveillance analysis, and comparison of entrance and exit counts, and collect evaluation data on tourists' satisfaction with guidance and overall experience through questionnaires within the APP and electronic evaluation devices at stations, constructing a comprehensive feedback data collection system.

[0154] Regarding the diversion effect, this step also designs a special evaluation index system, including three dimensions: the execution rate of the diversion strategy, the regional load balance degree, and tourist satisfaction, realizing the quantitative evaluation of the diversion effect. Based on the collected environmental monitoring data and site structure response data, the solution dynamically updates the weight coefficients of environmental stress factors by applying multiple regression analysis, improving the adaptability of the bearing capacity calculation model. At the same time, according to the evaluation results, adjust the parameter settings in the particle swarm optimization algorithm, including the objective function weight, constraint condition threshold, and convergence parameters, to optimize the generation efficiency of the diversion strategy.

[0155] The data collection module specifically includes:

[0156] (1) Tourist flow collection unit: A multi-level perception network composed of entrance gate counters, distributed infrared sensors, depth cameras, and Wi-Fi probes to achieve tourist number statistics, density analysis, and movement trajectory tracking; among them, the camera uses edge computing technology and integrates artificial intelligence algorithms to only output statistical data instead of raw images to protect tourists' privacy;

[0157] (2) Environmental status collection unit: An environmental monitoring network composed of wireless temperature and humidity sensors, PM2.5 sensors, CO2 concentration sensors, and VOC sensors, using low-power wide-area network (LPWAN) technology to achieve data transmission, and the battery can supply power for continuous operation for more than 6 months;

[0158] (3) Structural health monitoring unit: A structural health monitoring network consisting of micro displacement sensors, vibration sensors, inclination sensors, and stress and strain sensors. It collects weak signals through a high-precision data collector and has a displacement detection accuracy of 0.01 mm and a vibration frequency response range of 0.1 Hz-100 Hz.

[0159] (4) Data preprocessing unit: The edge computing gateway is used to perform noise reduction, outlier detection and preliminary fusion processing on the collected raw data, reducing the amount of data transmission and improving the system response speed.

[0160] The system also includes an abnormal warning and emergency processing module, which specifically includes the following mechanisms:

[0161] Multi-level warning mechanism: Establish three levels of warning, including attention, warning and emergency, corresponding to different load ratio thresholds and environmental abnormal conditions;

[0162] Warning level warning: Single area load ratio R i >0.85 and lasts for more than 15 minutes;

[0163] Warning level warning: Single area load ratio R i >0.95 or R for 30 consecutive minutes i >>0.9;

[0164] Emergency warning: Multiple adjacent areas are simultaneously R i >0.9 or single region R i >1.1;

[0165] (3) Graded response measures: Attention-level alerts only notify management personnel to strengthen monitoring; Warning-level alerts initiate active diversion mechanisms, adjust ticket sales strategies, and strengthen on-site guidance; Emergency-level alerts immediately suspend entrances to relevant areas, initiate emergency evacuation plans, and convene emergency response teams to handle on-site situations;

[0166] (4) Abnormal event recording and analysis: Record the triggering conditions, response measures and processing effects of all warning events, analyze the patterns of abnormal events through data mining, optimize the warning thresholds and response strategies, and improve the system's ability to respond to emergencies.

[0167] The above description is only an implementation method of the present application, and does not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly used in other related technical fields, are also included in the patent protection scope of the present application.

Claims

1. A tourist diversion system for heritage protection areas based on dynamic bearing capacity, characterized by: It includes a data acquisition module, a bearing capacity calculation module, a diversion strategy optimization module, a visitor guidance module, and a feedback adjustment module; The data acquisition module is used to collect real-time data on visitor flow, temperature and humidity, air quality, and the health status of the site structure, and transmit the collected data to the bearing capacity calculation module; The bearing capacity calculation module receives the data transmitted by the data acquisition module, and calculates the dynamic bearing capacity of the site area based on the data, wherein the temperature data collected by the data acquisition module corresponds to the temperature pressure factor, the humidity data corresponds to the humidity pressure factor, the air quality data corresponds to the air quality pressure factor, the structural health status data corresponds to the structural health status pressure factor, and the tourist flow data corresponds to the tourist density pressure factor, and the calculation formula is as follows: Among them, C t is the current carrying capacity, C s is the theoretical maximum bearing capacity, P i is the i-th environmental pressure factor, a i is its weight coefficient, which is determined through historical data analysis and expert evaluation; The diversion strategy optimization module is connected to the bearing capacity calculation module, receives the dynamic bearing capacity calculation result, optimizes the visitor diversion strategy using the particle swarm optimization algorithm, and generates a diversion strategy; The visitor guidance module is connected to the diversion strategy optimization module, receives visitor guidance instructions according to the optimized diversion strategy, and guides visitors to tour along the optimized route through an electronic map navigation or intelligent guidance sign; The feedback adjustment module is connected to the visitor guidance module, collects real-time visitor behavior data and environmental change conditions, and transmits the feedback data to the diversion strategy optimization module for dynamically adjusting the diversion strategy.

2. A method for diverting visitors in a site protection area based on dynamic bearing capacity, characterized in that: (1) Data acquisition: Real-time collect data on visitor flow, temperature and humidity, air quality, and the health status of the site structure in the site protection area, and define that the temperature data corresponds to the temperature pressure factor, the humidity data corresponds to the humidity pressure factor, the air quality data corresponds to the air quality pressure factor, the structural health status data corresponds to the structural health status pressure factor, and the visitor flow data corresponds to the visitor density pressure factor; (2) Dynamic calculation of carrying capacity: The current dynamic carrying capacity of the site area is calculated based on the collected data. The calculation is performed using the formula Among them, C t is the current carrying capacity, C s is the theoretical maximum bearing capacity, P i is the i-th environmental pressure factor, a i is its weight coefficient, which is determined through historical data analysis and expert evaluation; (3) Regional load assessment: According to the current visitor distribution and the dynamic bearing capacity calculated in step (2), calculate the load ratio R = N / C of each area of the site, where N is the number of visitors in the current area and C is the current dynamic bearing capacity of the area, and divide each area into a low-load area, a medium-load area, and a high-load area according to the load ratio. Among them, the low-load area (R ≤ 0.6) means free entry is allowed; the medium-load area (0.6 < R ≤ 0.9) means flow restriction and guidance; the high-load area (R > 0.9) means entry is prohibited and an alarm is triggered; (4) Diversion strategy optimization: Based on the distribution of the low-load area, medium-load area, and high-load area determined in step (3), use the particle swarm optimization algorithm to generate a diversion strategy. The strategy includes the number of visitors transferred from the high-load area to the low-load area, the transfer path, and the control of the visitor flow direction between areas. The optimization goal is to balance the load ratio of each area and ensure the visitor experience and site safety; (5) Visitor guidance execution: According to the diversion strategy optimized in step (4), push personalized tour route suggestions to visitors through an electronic tour map or an intelligent guidance sign system, and set prompt information at the entrance of the high-load area to guide visitors to flow to the low-load area; (6) Feedback and adjustment: Collect actual visitor tour behavior data and environmental change data, evaluate the diversion effect, and feedback the evaluation result to step (2) and step (4) to dynamically adjust the bearing capacity calculation parameters and the diversion strategy optimization weight to form a closed-loop optimization mechanism.

3. A method for diverting tourists to a heritage site protection area based on dynamic bearing capacity according to claim 2, characterized in that: The data acquisition in step (1) specifically includes: (1.1) Collection of tourist flow data: Deploy infrared counters, depth cameras, and Wi-Fi probe sensors at the entrances, exits, main tourist attractions, and key bifurcation paths in the heritage protection area to count the number of tourists in each area in real time and record the changes in crowd density. Among them, the infrared counter uses a two-way counting algorithm to accurately distinguish between incoming and outgoing tourists. The depth camera combines computer vision algorithms to generate a heat map of crowd density. The Wi-Fi probe estimates the number of people staying in the area by capturing the MAC addresses of mobile devices. (1.2) Collection of temperature and humidity data: Deploy wireless temperature and humidity sensor nodes at a density of 3 - 5 meters per point in different functional areas of the heritage site. The sampling frequency is once every 5 minutes. Record the temperature change range and humidity fluctuation value at each point in real time, and calculate the temperature and humidity anomaly index based on historical data for the same period. (1.3) Collection of air quality data: Deploy sensors for detecting PM2.5, PM10, CO2 concentration, and volatile organic compounds to monitor the changes in air quality caused by tourist activities. The sampling frequency is once every 10 minutes. (1.4) Collection of data on the structural health status of the heritage site: Install micro-displacement sensors, vibration sensors, and stress-strain sensors at the key load-bearing structures, historical building walls, and ground pavements of the heritage site. Continuously collect structural response data for 24 hours, and perform preliminary processing through edge computing devices to extract characteristic parameters of the structural health status.

4. The method for diverting tourists to a heritage site protection area based on dynamic bearing capacity according to claim 2, characterized in that: The dynamic calculation of bearing capacity in step (2) specifically includes: (2.1) Calculation of environmental pressure factors: Temperature pressure factor calculation formula: Where T is the current temperature, T opt is the most suitable temperature for sightseeing, T max is the maximum acceptable temperature; Temperature pressure factor calculation formula: Where H is the current humidity, H opt The most suitable humidity for sightseeing is H max is the maximum acceptable humidity deviation; Air quality pressure factor calculation formula: AQI is the air quality index. max is the maximum acceptable air quality index; Structural health status pressure factor calculation formula: Where S i is the structural stress or displacement value of the ith monitoring point, S i,max is the safety threshold for a period, and n is the total number of monitoring points; (2.2) Determination of weight coefficients: Determine the weight coefficients of each pressure factor through the analytic hierarchy process combined with the principal component analysis of historical monitoring data, and establish a season-time period adjustment matrix to dynamically adjust the weights in different seasons and time periods. (2.3) Dynamic bearing capacity calculation: by formula Calculate the current bearing capacity, where C0 is the theoretical maximum bearing capacity, w′ i is the adjusted weight coefficient, p i is the i-th environmental pressure factor; the discrete monitoring point data are spatially interpolated by cubic spline interpolation method to generate a thermal map of the carrying capacity distribution of the entire site area, which is updated every 15 minutes.

5. The method for diverting tourists in the heritage protection area based on dynamic bearing capacity according to claim 2, Features: The regional load assessment in step (3) specifically includes: (3.1) Division of heritage site areas: Based on the heritage protection level, historical value assessment, and tourist behavior patterns of the heritage site, divide the heritage protection area into three functional areas: core protection area, general display area, and edge service area, and further divide them into n management units. Each management unit is equipped with independent crowd monitoring devices. (3.2) Load ratio calculation: For each management unit i, calculate the current load ratio Where N i is the number of tourists in the current unit, C i is the current dynamic bearing capacity of the unit; (3.3) Load rating: According to the load ratio R value, combined with the results of the heritage vulnerability assessment, establish a multi-level load rating standard, specifically as follows: Core protection area: Low load area (R ≤ 0.5), medium load area (0.5 < R ≤ 0.8), high load area (R > 0.8); General display area: Low load area (R ≤ 0.6), medium load area (0.6 < R ≤ 0.9), high load area (R > 0.9); Edge service area: Low load area (R ≤ 0.7), medium load area (0.7 < R ≤ 0.95), high load area (R > 0.95); (3.4) Analysis of regional linkage relationships: Establish a graph of tourist flow relationships between adjacent management units, analyze the linkage effects of changes in the load status of each unit, and predict the changes in load distribution after tourist diversion.

6. The method for diverting tourists in the heritage protection area based on dynamic bearing capacity according to claim 2, Features: The diversion strategy optimization in step (4) specifically includes: (4.1) Problem modeling: The tourist diversion problem is modeled as a multi-objective optimization problem, and the objective function is defined as: Among them, R i is the load ratio of the ith region, R avg is the target average load ratio, T i is the average time tourists spend in each area, D i is the walking distance of tourists, E is the comprehensive tour experience score, and w1 to w4 are weight coefficients; (4.2) Particle swarm algorithm parameter settings: set the number of particles to 50, the maximum number of iterations to 200, the inertia weight w to decrease linearly from 0.9 to 0.4, the acceleration constant c1 = c2 = 2.0, and use the local optimal particle swarm algorithm with a V-type topology structure to improve the convergence speed; (4.3) Diversion strategy encoding: Each particle represents a possible diversion strategy, encoded as X = (p1, p2, ...., p n ,r1,r2,...,r m ), where P i represents the proportion of tourists transferred from the i-th high-load area to other areas, rj represents the recommendation weight of the j-th path; (4.4) Constraint setting: The load ratio of any area must not exceed the safety threshold of that area: The load ratio of the core cultural relics area shall not exceed 0.8: R i ≤0.8, core cultural heritage area; The one-way walking distance of tourists shall not exceed the preset maximum value: Path collection; The flow of tourists between areas must not exceed the channel capacity: (4.5) Strategy generation and verification: Generate the optimal diversion strategy through iterative optimization, including the number of tourists to be transferred from each high-load area, the number of tourists that can be received in each low-load area, the weight distribution of recommended routes, and the control of tourist flow between areas; use historical data to perform Monte Carlo simulation to verify the effectiveness of the strategy, ensuring that the load ratio of the high-load area can be reduced to a safe level in more than 90% of the scenarios.

7. The method for diverting tourists from heritage protection areas based on dynamic carrying capacity according to claim 2, Features: The tourist guidance execution in step (5) specifically includes: (5.1) Personalized route generation: Based on the interest preferences, expected tour time, mobility and other characteristics in the tourist registration information, combined with the current diversion strategy, the improved Dijkstra algorithm is used to generate 3-5 alternative tour routes for each tourist, with priority given to routes passing through low-load areas; (5.2) Multi-channel guidance implementation: push personalized guide maps and voice prompts through mobile terminal APP; install electronic display screens at key nodes in the site area to update the load status of each area and recommended routes in real time; set up an intelligent guide sign system to intuitively display the congestion status of each area through LED color changes; add tour guides at the entrance of high-load areas; (5.3) Incentive mechanism design: For tourists who follow the diversion recommendations and go to low-load areas, incentives such as extended visit time, expert explanations, and discounts on cultural and creative products are provided to improve the diversion implementation rate; (5.4) Emergency evacuation plan: When the load ratio of a certain area exceeds the emergency threshold (R>1.1), the emergency evacuation plan is activated, ticket sales at the entrance to the area are suspended, additional management personnel are dispatched to guide on-site tourists to disperse, and emergency evacuation instructions are issued through the broadcasting system.

8. The method for diverting tourists from heritage protection areas based on dynamic carrying capacity according to claim 2, Features: The feedback and adjustment in step (6) specifically include: (6.1) Tourist behavior data collection: Through mobile APP location tracking, video surveillance analysis and entrance and exit count comparison, the actual movement trajectory, stay time distribution and area transition behavior of tourists are collected; through the questionnaire in the APP and the electronic evaluator of the site, the evaluation data of tourists on congestion perception, guidance satisfaction and overall experience are collected; (6.2) Diversion effect evaluation: Calculate the following evaluation indicators: Diversion strategy execution rate: Regional load balance: Where σ is the standard deviation and μ is the mean Visitor satisfaction: Where S i Score the satisfaction of the i-th tourist; (6.3) Bearing capacity model parameter adjustment: Based on the collected environmental monitoring data and site structure response data, multivariate regression analysis is used to update the weight coefficients of various environmental pressure factors and adaptively adjust the dynamic bearing capacity calculation model parameters; (6.4) Diversion strategy optimization parameter adjustment: According to the evaluation results, adjust the objective function weight, constraint threshold and convergence parameters in the particle swarm algorithm to improve the efficiency of strategy generation; (6.5) Closed-loop optimization mechanism: Establish a data-driven adaptive learning mechanism, and through deep reinforcement learning methods, enable the system to continuously optimize the decision-making model based on historical diversion effects.

Images