A tourism industry management planning method for climate health care

Abstract

This invention discloses a tourism industry management and planning method for climate-based health and wellness tourism, belonging to the field of tourism management technology. Specifically, it includes: collecting a set of climate data and a set of tourist health profiles for the target tourist area; calculating the daily climate comfort level within the planning period based on the climate data set; inputting the climate comfort level sequence and the tourist health profile set into a climate-based health and wellness matching model to generate a daily suitability score for each tourist health profile; planning a sequence of health and wellness activities and spatial movement paths for each tourist health profile based on the suitability score sequence; summarizing the planning data of all tourist health profiles to generate an overall tourist distribution prediction and infrastructure load forecast; adjusting the density of the health and wellness activity sequence and the guidance strategy for spatial movement paths based on the prediction results to form the final planning scheme. This invention provides a scientific and systematic planning and management method for the climate-based health and wellness tourism industry.

Description

Technical Field

[0001] This invention relates to the field of tourism management technology, and specifically to a tourism industry management and planning method for climate-based health and wellness. Background Technology

[0002] With socio-economic development and increased health awareness, climate-based wellness tourism, which integrates natural ecological environments with health-promoting functions, has gradually become an important component of the tourism industry. Climate-based wellness tourism, by utilizing the specific climate conditions, natural environment, and ecological resources of a region to provide tourists with health-promoting experiences, has become a key direction for the transformation and upgrading of the tourism industry. Against this backdrop, how to scientifically and effectively manage and plan the tourism industry to achieve the organic integration of climate resources and wellness services has become a crucial issue for the industry's development.

[0003] Currently, in the field of tourism industry planning, some technical solutions have attempted to incorporate climate factors into their considerations. These existing technologies typically employ climate data analysis methods, collecting basic meteorological parameters such as temperature, humidity, and wind speed, and combining this with tourist flow statistics for assessing tourist comfort and predicting visitor volume. Some solutions have also established tourist behavior analysis models, inferring tourist preferences and activity patterns based on historical tourist data. These methods, to a certain extent, provide data support for tourism planning, forming relatively static tourism resource allocation schemes.

[0004] However, existing tourism management and planning methods typically remain at the macro-level assessment of overall regional climate comfort, failing to establish a precise match between individual tourists' health characteristics and specific climate parameters. In terms of planning models, most existing technologies employ static planning schemes based on historical data, lacking the ability to dynamically respond to real-time climate changes and sudden weather events. When faced with abrupt weather changes or significant fluctuations in climate comfort, existing static planning methods struggle to adjust and optimize wellness activities in a timely manner. Furthermore, due to the lack of differentiated consideration of individual tourists' health conditions and climate adaptability, existing methods often fail to provide truly personalized wellness experiences. Summary of the Invention

[0005] The purpose of this invention is to provide a tourism industry management and planning method for climate-based health and wellness, addressing the following technical problems:

[0006] Existing tourism management and planning methods typically remain at the macro-level assessment of overall regional climate comfort, failing to establish a precise matching relationship between the health characteristics of individual tourists and specific climate condition parameters; and they adopt static planning schemes based on historical data, lacking the ability to dynamically respond to real-time climate change and sudden weather events.

[0007] The objective of this invention can be achieved through the following technical solutions:

[0008] A tourism industry management and planning methodology for climate-based wellness includes the following steps:

[0009] S1. Collect climate data sets and tourist health profile sets for the target tourist area;

[0010] S2. Calculate the daily climate comfort level of the target tourist area within the planning period based on the climate data set;

[0011] S3. Input the climate comfort level sequence and the tourist health profile set into the climate health matching model to generate a daily suitability score for each tourist health profile within the planning period.

[0012] S4. Based on the suitability score sequence of each tourist's health profile, plan the sequence of health and wellness activities and spatial movement paths within the target tourism area for each tourist's health profile.

[0013] S5. Summarize the health and wellness activity sequences and spatial movement paths of all tourists’ health profiles to generate overall tourist distribution predictions and infrastructure load forecasts for the target tourist area within the planning period.

[0014] S6. Based on the overall tourist distribution forecast and infrastructure load expectation, adjust the layout density of health and wellness activity sequences and the guidance strategy for spatial movement paths to generate planning results.

[0015] As a further aspect of the present invention: in S1, the climate data set includes temperature, humidity, air pressure, air quality, sunshine duration, wind speed, and precipitation probability; the tourist health profile set includes basic physiological state data, environmental adaptability data, and climate tendency data, which are obtained based on tourist personal information and questionnaires.

[0016] As a further aspect of the present invention: the specific process for calculating the climate comfort level in S2 is as follows:

[0017] The climate datasets are normalized to ensure that the values ​​of each parameter are within the same dimension; weighting coefficients are then assigned to each parameter after normalization.

[0018] Among them, the weighting coefficients of temperature and humidity are higher than those of air pressure and wind speed. The weighting coefficient of air quality is a variable value. When the air quality value is lower than the preset standard, its weighting coefficient is automatically increased. The weighted parameter values ​​are linearly superimposed to generate a comprehensive index. The comprehensive index is compared with multiple preset threshold intervals. Based on the comparison results, the comprehensive index is mapped to discrete climate comfort levels. The climate comfort level includes multiple progressively increasing suitability levels.

[0019] As a further aspect of the present invention: the specific process of generating the suitability score in step S3 is as follows:

[0020] Environmental adaptability data and climate tendency data for each tourist health profile are extracted from the tourist health profile set. The environmental adaptability data includes a description of tolerance to adverse climate conditions; the climate tendency data includes preferences for specific climate conditions.

[0021] The environmental adaptability data is matched with the climate comfort level sequence. The matching process involves finding dates in the climate comfort level sequence that conflict with the environmental adaptability data and lowering the suitability score on those conflicting dates. Climate trend data is then matched with the climate comfort level sequence to find dates in the climate comfort level sequence that match the climate trend data and raise the suitability score on those matching dates. For dates where the environmental adaptability data and climate trend data conflict, the matching result of the environmental adaptability data is prioritized. Finally, a suitability score sequence corresponding to the planning period dates is generated.

[0022] As a further aspect of the present invention: the specific process of planning the sequence of health and wellness activities and the spatial movement path in S4 is as follows:

[0023] Construct a spatiotemporal graph network for the target tourism area. The spatiotemporal graph network includes a set of nodes and a set of edges. Nodes represent health and wellness activity locations and accommodation locations, and edges represent the connection relationships between locations.

[0024] Climate comfort level sequence data is injected into the spatiotemporal graph network to form a network structure with time-series climate weights. Based on the suitability score sequence, dynamic path planning is performed on the spatiotemporal graph network to initialize a candidate path set for each tourist health profile. The candidate path set contains permutations and combinations of visiting different health and wellness activity locations on different dates.

[0025] The cumulative climate exposure of each path in the candidate path set is calculated. The cumulative climate exposure is the weighted sum of the climate comfort level of each node and the edge climate comfort level of the path. The candidate path set is filtered based on the cumulative climate exposure, and the paths with the cumulative climate exposure within the preset range are retained. The filtered paths are matched with the environmental adaptability data of the tourist health profile to generate personalized health and wellness activity sequences and spatial movement paths.

[0026] As a further aspect of the present invention: the construction process of the spatiotemporal graph network is as follows:

[0027] Collect the geographic coordinates of health and wellness activity locations and accommodation locations in the target tourism area to form a node set. Establish the connection relationship between nodes based on geographic information system data to form an edge set. Assign a time dimension attribute to each node, which includes the climate comfort level of the node on different dates. Assign a time dimension attribute to each edge, which includes the climate comfort level of the edge on different dates.

[0028] The climate comfort level of an edge is calculated by connecting the climate comfort levels of nodes at both ends with the physical characteristics of the edge. Based on the temporal attributes of nodes and edges, environmental attribute data is introduced, including vegetation coverage, water proximity, topographic relief, and building density. The environmental attribute data is coupled with the climate comfort level through multiple factors to generate a comprehensive climate weight for nodes and edges. Based on the set of nodes, the set of edges, and the corresponding comprehensive climate weight, a spatiotemporal graph network is constructed.

[0029] As a further aspect of the present invention: the specific process of generating the overall tourist distribution prediction and infrastructure load expectation in S5 is as follows:

[0030] Construct a multi-level spatiotemporal distribution network for the target tourist area. The multi-level spatiotemporal distribution network includes the scenic spot level, transportation hub level, and service facility level. Map the health and wellness activity sequence and spatial movement path of each tourist's health profile to the multi-level spatiotemporal distribution network to form the initial distribution state.

[0031] Dynamic propagation simulation of tourist flow is performed based on a multi-level spatiotemporal distribution network. The dynamic propagation simulation process includes calculating tourist gathering intensity at the scenic spot level, tourist transfer intensity at the transportation hub level, and tourist usage intensity at the service facility level. A tourist flow correlation model between levels is established, which represents the probability of tourist transfer between different levels. Through multiple rounds of iterative calculation, the tourist distribution status of each time segment within the planning period is obtained. Based on the tourist distribution status and combined with the capacity data of infrastructure at each level, the infrastructure load forecast is generated.

[0032] As a further aspect of the present invention: the process of generating the infrastructure load expectation is as follows:

[0033] For each node in the multi-level spatiotemporal distribution network, historical load data of the node is extracted. The historical load data contains infrastructure usage records at different time periods. Combined with the tourist distribution status, the real-time load rate of the node is calculated, and the load propagation relationship between nodes is established. The load propagation relationship is determined by the tourist flow path.

[0034] A load balancing calculation model is constructed, and the fluctuation cycle and trend of load rate in the time dimension and the load correlation strength between adjacent nodes in the spatial dimension are analyzed. The time dimension analysis results and the spatial dimension analysis results are integrated to generate a load balancing evaluation value for each node. Based on the load balancing evaluation value, nodes with abnormal load status are identified and an infrastructure load expectation report is generated.

[0035] As a further aspect of the present invention: the specific process of adjusting the arrangement density of the health and wellness activity sequence and the guidance strategy for spatial movement paths in step S6 is as follows:

[0036] Based on the locations of high-load and low-load areas in the load forecast report, the number of health and wellness activities in high-load areas on the corresponding dates is reduced, and the reduced activities are redistributed to low-load areas. Based on the redistributed distribution of health and wellness activity locations, spatial movement paths are updated, path connections are modified, and alternative paths to low-load areas are generated. Simultaneously, the operating routes and schedules of public transportation are adjusted to match the new spatial movement paths. The adjusted health and wellness activity sequences, updated spatial movement paths, and public transportation adjustment schemes are combined to form the planning results.

[0037] The beneficial effects of this invention are:

[0038] This invention establishes a climate comfort level assessment system by collecting individualized tourist health profiles and multidimensional climate data, and constructs a dynamic path planning method based on spatiotemporal graph networks, achieving personalized and precise management of climate-based health tourism. By fine-grained matching of tourist health characteristics with climate conditions, it generates personalized suitability scores and health activity sequences, effectively solving the problem of insufficient individualized consideration in existing technologies. By establishing a load balancing optimization mechanism, it adjusts the density of health activities and spatial movement paths in real time, overcoming the shortcomings of static planning in responding to dynamic climate changes. The microclimate scoring system is used to accurately classify and allocate health activity locations, improving the efficiency of climate resource utilization. Through the collaborative analysis of tourist distribution prediction and infrastructure load forecasting, it achieves rational allocation of tourism resources, avoiding the problem of excessive load in local areas. The entire solution, through the combination of multi-source data fusion, dynamic path planning, and load balancing adjustment technologies, forms a complete technical closed loop from individual to overall, from static to dynamic, significantly improving the scientific rigor and practicality of climate-based health tourism planning. Attached Figure Description

[0039] The invention will now be further described with reference to the accompanying drawings.

[0040] Figure 1 This is a flowchart illustrating the present invention. Detailed Implementation

[0041] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0042] Please see Figure 1 As shown, this invention is a tourism industry management and planning method for climate-based health and wellness, comprising the following steps:

[0043] S1. Collect climate data sets and tourist health profile sets for the target tourist area;

[0044] S2. Calculate the daily climate comfort level of the target tourist area within the planning period based on the climate data set;

[0045] S3. Input the climate comfort level sequence and the tourist health profile set into the climate health matching model to generate a daily suitability score for each tourist health profile within the planning period.

[0046] S4. Based on the suitability score sequence of each tourist's health profile, plan the sequence of health and wellness activities and spatial movement paths within the target tourism area for each tourist's health profile.

[0047] S5. Summarize the health and wellness activity sequences and spatial movement paths of all tourists’ health profiles to generate overall tourist distribution predictions and infrastructure load forecasts for the target tourist area within the planning period.

[0048] S6. Based on the overall tourist distribution forecast and infrastructure load expectation, adjust the layout density of health and wellness activity sequences and the guidance strategy for spatial movement paths to generate planning results.

[0049] In step S1 of this invention, core climate parameters such as temperature, humidity, air pressure, air quality, sunshine duration, wind speed, and precipitation probability are acquired in real time. During the data acquisition process, the system performs format verification on the data, removes outliers (such as temperature values ​​exceeding the physically reasonable range), and archives the data according to timestamps (accurate to the minute), forming a structured climate data set. The set is stored in a time-series database, supporting fast queries by time range and parameter type. Simultaneously, data quality tags are established to indicate the acquisition accuracy and update frequency of each parameter.

[0050] The construction of tourist health profiles requires the simultaneous processing of tourist personal information and questionnaire data. The system obtains personal information (such as age, gender, and underlying medical history) through the tourist registration interface. Sensitive information (such as ID numbers) is encrypted using data anonymization techniques, retaining only the key dimensions needed for profile analysis. Simultaneously, the system pushes structured questionnaires to tourist terminals. These questionnaires include questions related to environmental adaptability (such as tolerance to high and low temperatures) and climate preference (such as preference for humid or dry climates). After submission, the system performs semantic parsing on the questionnaire answers, converting qualitative descriptions (such as "intolerant to high temperatures") into quantifiable labels. This, combined with personal information, forms a tourist health profile set containing basic physiological data, environmental adaptability data, and climate preference data. Each profile is associated with a unique tourist identifier to ensure accurate matching with subsequent suitability scores.

[0051] In S2 of this invention, the specific process for calculating the climate comfort level is as follows:

[0052] First, the parameters of the climate dataset are normalized. The system uses a min-max normalization algorithm to map the original parameter values ​​to a unified dimensional range of 0-1 based on the historical extreme values ​​of each parameter (e.g., historical highest and lowest temperatures, historical maximum and minimum humidity values), eliminating calculation biases caused by unit differences (e.g., temperature in °C, humidity in % and wind speed in m / s). The normalized data is then temporarily stored in a computational cache, awaiting weight allocation.

[0053] Weighting coefficients are assigned to each normalized parameter according to preset rules. The weighting is based on the degree of climate's impact on human comfort, with temperature and humidity being the core influencing factors and having higher weighting coefficients than air pressure and wind speed. Sunshine duration and precipitation probability are assigned basic weights according to their usual influence levels. For air quality parameters, a built-in threshold monitoring mechanism is implemented. When air quality values ​​(such as PM2.5 concentration) fall below preset standards, an automatic weight adjustment logic is triggered, increasing the weighting coefficients of air quality parameters to highlight the negative impact of polluted weather on comfort. All weighting coefficients sum to 1 to ensure the rationality of the weighted calculation.

[0054] After weighting, the weighted parameter values ​​are linearly superimposed to generate a comprehensive index for a single time point. Then, a threshold comparison module is invoked to match the comprehensive index with multiple preset threshold intervals. These threshold intervals are divided into multiple discrete levels based on suitability (e.g., extremely unsuitable, unsuitable, moderately suitable, very suitable), with each interval corresponding to a fixed index range. Based on the interval the comprehensive index falls into, it is automatically mapped to the corresponding climate comfort level and arranged chronologically to form a climate comfort level sequence. This sequence includes the comfort level results for each day within the planning period.

[0055] In S3 of this invention, the specific process of generating a suitability score is as follows:

[0056] Environmental adaptability data and climate preference data of target tourists are extracted from the tourist health profile set. By associating tourist identifiers with corresponding profiles, tolerance descriptions (such as "high temperature tolerance threshold of 30℃" and "low temperature tolerance threshold of 5℃") are extracted from the environmental adaptability data and converted into numerical tolerance ranges. At the same time, preference preferences (such as "preferred temperature 18-25℃ and humidity 50%-60%)" are extracted from the climate preference data and converted into corresponding climate parameter preference ranges. Both types of data serve as the core basis for matching calculations.

[0057] The system matches environmental adaptability data with a climate comfort level sequence on a date-by-date basis. For each date's climate comfort level, if the corresponding climate parameter (e.g., the temperature range corresponding to a high-temperature level) exceeds the tourist's tolerance range (e.g., the tourist's high-temperature tolerance threshold of 30℃), it is determined to be a conflict date, and a reduction is applied based on the initial suitability score for that date; if the corresponding climate parameter is within the tolerance range, the initial score is maintained. Subsequently, the system matches climate tendency data with the level sequence again. If the date's climate parameter matches the tourist's preference range (e.g., a cool climate preference corresponds to a cool and suitable level), it is determined to be a consistent date, and the system applies an improvement based on the current score.

[0058] If conflicting results exist between environmental adaptability data and climate tendency data for the same date (e.g., tourists prefer high temperatures but have low heat tolerance thresholds, yet a certain date is rated as suitable for high temperatures), a priority determination logic is activated, prioritizing the matching results of the environmental adaptability data to ensure that the score primarily considers the tourists' physiological tolerance limits. After all dates are matched, the score is quantified into a value from 0 to 100 (higher values ​​indicate higher suitability). A suitability score sequence is generated by sorting the dates according to the planning period. Each date in the sequence corresponds to a unique suitability score and is associated with tourist identifiers and matching criteria, supporting subsequent traceability.

[0059] In S4 of this invention, the specific process of planning the sequence of health and wellness activities and spatial movement paths is as follows:

[0060] The construction of the spatiotemporal map network begins with the collection of geographic coordinate data. By connecting to the geographic information system (GIS) database of the target tourist area, the precise geographic coordinates (latitude and longitude) of health and wellness activity locations (such as health trails, hot spring areas, and forest therapy sites) and accommodation locations (such as homestays and health and wellness hotels) are extracted. At the same time, basic attribute information of each location (such as location type, capacity, and opening hours) is collected. After associating the coordinates with the attribute information, a structured set of nodes is formed, and each node is assigned a unique identifier to ensure traceability for subsequent indexing.

[0061] Based on the node set, the connection relationships between nodes are established through GIS spatial topology analysis technology, forming an edge set. The criteria for determining the connection relationship include the spatial distance between two points (such as whether they are within walking distance), actual transportation accessibility (such as whether there is a road or trail connection), and transportation mode suitability (such as whether it supports self-driving or sightseeing vehicles). Each edge records the starting node identifier, ending node identifier, and basic physical characteristics (such as path length, road surface type, and occlusion status).

[0062] Each node is assigned a time-dimensional attribute. By interfaceing with the climate comfort level sequence generated by S2, the daily climate comfort level within the planning period is associated with the node, forming the node's time-dimensional attribute for different dates. The attribute value directly maps to the corresponding date's comfort level (e.g., suitable, fair). For the edge's time-dimensional attribute, it is calculated by combining the climate comfort levels of the two endpoints and the edge's physical characteristics: if the edge's path length is long or there is shading (e.g., a tree-lined path), the average comfort level of the two endpoints is referenced, combined with the influence coefficient of physical characteristics (e.g., shading can reduce the impact of high temperatures), to generate the edge's climate comfort level for different dates, thus completing the assignment of the time-dimensional attribute.

[0063] Further environmental attribute data for the target area is collected, including vegetation cover (e.g., forest coverage) and water proximity (e.g., distance to lakes) obtained through remote sensing image analysis, topographic relief (e.g., slope range) extracted from GIS topographic data, and building density (e.g., floor area ratio of surrounding buildings) obtained from regional planning data. These environmental attribute data are quantified into values ​​between 0 and 1 (e.g., higher vegetation cover results in a quantified value closer to 1). Then, a multi-factor coupling model is used to fuse these values ​​with the climate comfort levels of corresponding nodes and edges. For example, nodes with high vegetation cover will have their comprehensive climate weight appropriately increased based on their original comfort level, while edges with high building density will have their weights adjusted based on ventilation conditions. After fusion, comprehensive climate weights for nodes and edges are generated. Finally, the node set, edge set, and corresponding comprehensive climate weights are integrated to construct a spatiotemporal graph network with spatiotemporal attributes. The network data is stored in a graph database to support efficient path retrieval and calculation.

[0064] The construction process of the spatiotemporal graph network is as follows:

[0065] The climate comfort level sequence data generated by S2 is injected into the constructed spatiotemporal graph network. By associating nodes and edges with time dimension attributes, the network acquires time-series climate weight characteristics—that is, the same node or edge corresponds to different comprehensive climate weights on different dates. The network structure changes dynamically with the time dimension, providing data support for subsequent dynamic path planning.

[0066] Based on the suitability score sequence of the tourist health profile generated by S3, a dynamic path planning algorithm is invoked to initialize a candidate path set for each tourist health profile. The initialization process needs to combine the date sequence within the planning period (e.g., 5 days) to generate permutations and combinations of visiting different health and wellness activity locations on different dates: for example, Day 1 from the accommodation to the forest therapy point, Day 2 to the hot spring area. At the same time, it is necessary to meet the accessibility between locations (based on the connection relationship of edge sets) and the basic needs of tourists (e.g., the daily activity time does not exceed the preset limit). The candidate path set needs to cover multiple combination possibilities to ensure the space for subsequent screening.

[0067] The cumulative climate exposure is calculated for each path in the candidate path set. The calculation logic is based on the nodes and edges contained in the path: the comprehensive climate weight (corresponding to the visit date) of each node in the path and the comprehensive climate weight (corresponding to the travel date) of each edge are multiplied by a preset weight coefficient (e.g., a higher node weight coefficient for a longer stay time and a lower edge weight coefficient for a shorter travel time). All weighted values ​​are then linearly superimposed to obtain the cumulative climate exposure of the path, thus quantifying the overall climate suitability of the path.

[0068] Based on the cumulative climate exposure, the candidate route set is filtered according to a preset range (e.g., cumulative exposure is in the range of [60, 80], the specific range is set based on regional climate characteristics), eliminating routes with excessively high cumulative exposure (poor climate suitability) or excessively low cumulative exposure (potentially indicating monotonous activities). After filtering, the remaining routes are matched with the environmental adaptability data of the tourist health profile: for example, if tourists have low tolerance for humid environments, routes with a low proportion of humid climate nodes are prioritized; if tourists have low tolerance for long-distance walking, routes with a high proportion of long-distance walking paths are eliminated. Finally, the optimal route is determined based on the matching results. At the same time, combined with the opening hours and activity duration requirements of each location, personalized health and wellness activity sequences sorted by date are generated (e.g., Day 19:00-11:00 forest therapy, 15:00-16:00 hot spring relaxation) and corresponding spatial movement routes (e.g., accommodation point → forest therapy point: via XX trail, 30-minute walk).

[0069] In S5 of this invention, the specific process of generating the overall tourist distribution prediction and infrastructure load forecast is as follows:

[0070] Overall tourist distribution prediction begins with the construction of a multi-level spatiotemporal distribution network. For the target tourist area, a multi-level network structure is constructed based on functional dimensions, including scenic spot, transportation hub, and service facility levels: Scenic spot level nodes include all health and wellness activity locations (such as forest therapy areas and hot spring attractions), collecting attributes such as geographic coordinates, maximum capacity, and opening hours; Transportation hub level nodes cover walking trail hubs, sightseeing bus stops, parking lots, etc., recording the node's transfer capacity, number of connected scenic spots / facilities, and mode of transportation; Service facility level nodes include restaurants, medical stations, public restrooms, and shopping areas, labeling the node's service capacity (such as number of seats, patient capacity), service radius, and operating hours. Each level of node is assigned a unique identifier, and connections between levels are established through spatial relationships (such as binding a scenic spot node with adjacent transportation hub nodes and service facility nodes), forming a complete multi-level spatiotemporal distribution network.

[0071] The health and wellness activity sequence and spatial movement path corresponding to each tourist's health profile are mapped to a multi-level spatiotemporal distribution network according to the time dimension. For example, if a tourist goes to attraction A from 19:00 to 11:00 on Day 1, transfers at transportation hub B from 11:00 to 11:30, and dines at restaurant C from 11:30 to 12:30, then within the corresponding time segment, the tourist's identifier is associated with the nodes of attraction A, transportation hub B, and service facility C, respectively. After all tourists are mapped, the initial distribution state of the network is formed, and each node is marked with the initial number of tourists in the corresponding time segment.

[0072] Dynamic propagation simulation of tourist flow is performed based on the initial distribution state. At the scenic spot level, the tourist gathering intensity per unit time is calculated by combining the planned stay time of tourists at each scenic spot and the opening hours of the scenic spot. That is, the ratio of the actual number of tourists at the scenic spot node to the maximum capacity within a certain time segment. The higher the ratio, the greater the gathering intensity. At the transportation hub level, the tourist transfer intensity of the hub node per unit time is statistically analyzed based on tourist transfer plans (e.g., from scenic spot A to scenic spot D, it is necessary to pass through hub B) and the departure frequency / carrying capacity of transportation modes, reflecting the real-time transfer pressure of the hub. At the service facility level, the tourist usage intensity of the facility node per unit time is calculated based on the service needs of tourists (e.g., dining, medical consultation) and the service efficiency of the facility (e.g., average service duration), quantifying the real-time service pressure of the facility.

[0073] A tourist flow correlation model is established to characterize the tourist transfer probability between different levels: By analyzing historical tourist behavior data (such as the percentage of tourists who chose to go to transportation hub B after leaving attraction A in the same period in the past, and the percentage of tourists who went to service facility C from transportation hub B), combined with the current tourist route planning, a transfer probability matrix between nodes at different levels is determined (such as the transfer probability from attraction to transportation hub, and the transfer probability from transportation hub to service facility). Based on this model, multiple rounds of iterative calculations are performed: Starting from the initial distribution state, simulations are performed step by step according to time segments within the planning period (such as each segment being 30 minutes). In each iteration, the number of tourists at each level node is updated according to the transfer probability, and finally, the tourist distribution state of each node in the entire region within each time segment is obtained, forming a time-series tourist distribution prediction result.

[0074] The process of generating the expected infrastructure load is as follows:

[0075] The infrastructure load forecast is generated on a node-by-node basis in a multi-level spatiotemporal distribution network. First, historical load data for each node is extracted: by connecting to the historical operation logs of the regional tourism management system, infrastructure usage records (such as the number of visitors entering scenic spots, the occupancy rate of restaurant seats, and the number of visits to medical stations) are obtained for each node during different time periods (such as the same quarter last year) in the past. These records are then organized into a structured historical load dataset by time segment, and the corresponding climate conditions and holiday factors (such as higher load on weekends than on weekdays) are labeled to provide a reference benchmark for subsequent calculations.

[0076] Based on real-time visitor distribution, the real-time load rate of each node is calculated: using the node's infrastructure capacity data (such as the maximum capacity of attractions and the maximum number of seats in restaurants) as a benchmark, the number of visitors in the current time segment is divided by the capacity data to obtain the real-time load rate. The closer the load rate is to 1, the closer the facility is to saturation. Simultaneously, load propagation relationships between nodes are established: based on visitor flow paths (such as a fixed flow route from attraction E to service facility F), the associated nodes for load propagation are determined. If an increase in the number of visitors to attraction E leads to an increase in its load rate, the number of visitors flowing to service facility F may subsequently increase, further pushing up F's load rate. These relationships are quantified and stored through path association.

[0077] A load balancing calculation model is constructed to analyze the load status from both temporal and spatial dimensions: In the temporal dimension, the time series of historical load data and current predicted load data are extracted to identify the fluctuation cycle of the load rate (e.g., the peak load period for tourist attractions is from 10:00 to 12:00 every day) and the trend of change (e.g., the load rate continues to rise during holidays), and the load fluctuation amplitude of different time segments is quantified; In the spatial dimension, the load correlation strength between adjacent nodes (e.g., two public restrooms in the same area) is calculated, and the spatial load dependency is determined by analyzing the degree of synchronous change of the load rate of adjacent nodes in historical data (e.g., whether the load of restroom B is also high when the load of restroom A is high).

[0078] The analysis results from both temporal and spatial dimensions are integrated. For example, if a service facility node experiences peak load fluctuations temporally and has a high load correlation with adjacent nodes spatially, its load balance assessment value will decrease. Threshold ranges are defined based on the load balance assessment value (e.g., 0.8-1.0 indicates balanced load, 0.5-0.8 indicates basic balance, and below 0.5 indicates abnormal load). Nodes with abnormal load conditions are identified (e.g., attractions with a load rate consistently exceeding 0.9, and service facilities with a load balance value below 0.5). Finally, the load rate, fluctuation trends, and abnormal states of each node are integrated to generate an infrastructure load forecast report. This report includes a list of high-load nodes for each time segment within the planning period, load peak predictions, and optimization suggestions for abnormal nodes (e.g., adding temporary service personnel, adjusting opening hours).

[0079] In S6 of this invention, the specific process of adjusting the arrangement density of the health and wellness activity sequence and the guidance strategy for spatial movement paths is as follows:

[0080] First, extract the location and time-series information of high-load areas from the report (e.g., a scenic spot is high-load from 10:00 to 12:00 on Day 2), and the location and capacity redundancy data of low-load areas (e.g., a health and wellness trail has a load rate below a preset threshold during the same period). For high-load areas, combine the visitor distribution status of the corresponding date, and reduce the number of health and wellness activities according to the extent of the load rate exceeding the threshold—the higher the load rate, the greater the reduction percentage, while ensuring that the retained activities meet the core needs of the visitor's health profile (e.g., prioritize medical health and wellness activities).

[0081] Reduced wellness activities will be redistributed to low-load areas. The redistribution process should be based on the infrastructure capacity threshold of low-load areas (such as the maximum number of people that a trail can carry and the service capacity of facilities) to avoid creating new overload. At the same time, the climate comfort level of the area should be taken into account (if the comfort level of the low-load area is "suitable" on the day, it will be given priority) to ensure that the activity experience matches the expectations of tourists.

[0082] Based on the redistributed distribution of health and wellness activity locations, the spatial movement paths are updated: nodes pointing to high-load areas in the original path are deleted, activity nodes in low-load areas are added, and path connection relationships are modified. If there is no direct passage between the new node and the accommodation location, temporary connections are supplemented through the edge set of the multi-level spatiotemporal distribution network (such as adding temporary sightseeing bus routes) to generate alternative paths to low-load areas. At the same time, the spatial accessibility (such as whether the walking time is within a reasonable range) and traffic adaptability (such as whether it matches the preferred mode of transportation of tourists) of the alternative paths are verified.

[0083] Simultaneously adjust the operation routes and schedules of public transportation: based on the travel demand of alternative routes, add or extend bus and sightseeing bus routes covering low-load areas, increase the frequency of services during peak activity periods (such as increasing departure frequency 1 hour before the start of the activity), reduce redundant services on routes in high-load areas, and ensure that the capacity of transportation vehicles matches the tourist flow of new routes.

[0084] Finally, the adjusted sequence of health and wellness activities (including dates, time periods, and activity locations), the updated spatial movement paths (including node connections, modes of transportation, and duration), and the public transportation adjustment plan (including routes and schedules) will be integrated and verified to ensure there are no load conflicts or path contradictions, thus forming a complete planning result.

[0085] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A tourism industry management and planning method for climate-based health and wellness, characterized in that, Includes the following steps: S1. Collect climate data sets and tourist health profile sets for the target tourist area; S2. Calculate the daily climate comfort level of the target tourist area within the planning period based on the climate data set; S3. Input the climate comfort level sequence and the tourist health profile set into the climate health matching model to generate a daily suitability score for each tourist health profile within the planning period. S4. Based on the suitability score sequence of each tourist's health profile, plan the sequence of health and wellness activities and spatial movement paths within the target tourism area for each tourist's health profile. S5. Summarize the health and wellness activity sequences and spatial movement paths of all tourists’ health profiles to generate overall tourist distribution predictions and infrastructure load forecasts for the target tourist area within the planning period. S6. Based on the overall tourist distribution forecast and infrastructure load expectation, adjust the arrangement density of health and wellness activity sequences and the guidance strategy for spatial movement paths to generate planning results; In S4, the specific process of planning the sequence of health and wellness activities and spatial movement paths is as follows: Construct a spatiotemporal graph network for the target tourism area. The spatiotemporal graph network includes a set of nodes and a set of edges. Nodes represent health and wellness activity locations and accommodation locations, and edges represent the connection relationships between locations. Climate comfort level sequence data is injected into the spatiotemporal graph network to form a network structure with time-series climate weights. Based on the suitability score sequence, dynamic path planning is performed on the spatiotemporal graph network to initialize a candidate path set for each tourist health profile. The candidate path set contains permutations and combinations of visiting different health and wellness activity locations on different dates. The cumulative climate exposure of each path in the candidate path set is calculated. The cumulative climate exposure is the weighted sum of the climate comfort level of each node and the edge climate comfort level of the path. The candidate path set is filtered according to the cumulative climate exposure, and the paths with the cumulative climate exposure within the preset range are retained. The filtered paths are matched with the environmental adaptability data of the tourist health profile to generate personalized health and wellness activity sequences and spatial movement paths. The construction process of the spatiotemporal graph network is as follows: Collect the geographic coordinates of health and wellness activity locations and accommodation locations in the target tourism area to form a node set. Establish the connection relationship between nodes based on geographic information system data to form an edge set. Assign a time dimension attribute to each node, which includes the climate comfort level of the node on different dates. Assign a time dimension attribute to each edge, which includes the climate comfort level of the edge on different dates. The climate comfort level of an edge is calculated by connecting the climate comfort levels of nodes at both ends with the physical characteristics of the edge. Based on the temporal attributes of nodes and edges, environmental attribute data is introduced, including vegetation coverage, water proximity, topographic relief, and building density. The environmental attribute data is coupled with the climate comfort level through multiple factors to generate a comprehensive climate weight for nodes and edges. Based on the set of nodes, the set of edges, and the corresponding comprehensive climate weight, a spatiotemporal graph network is constructed.

2. The tourism industry management and planning method for climate-based health and wellness as described in claim 1, characterized in that, In S1, the climate data set includes temperature, humidity, air pressure, air quality, sunshine duration, wind speed, and precipitation probability; the tourist health profile set includes basic physiological state data, environmental adaptability data, and climate tendency data, which are obtained based on tourist personal information and questionnaires.

3. The tourism industry management and planning method for climate-based health and wellness as described in claim 1, characterized in that, In S2, the specific process for calculating the climate comfort level is as follows: The climate datasets are normalized to ensure that the values ​​of each parameter are within the same dimension; weighting coefficients are then assigned to each parameter after normalization. Among them, the weighting coefficients of temperature and humidity are higher than those of air pressure and wind speed. The weighting coefficient of air quality is a variable value. When the air quality value is lower than the preset standard, its weighting coefficient is automatically increased. The weighted parameter values ​​are linearly superimposed to generate a comprehensive index. The comprehensive index is compared with multiple preset threshold intervals. Based on the comparison results, the comprehensive index is mapped to discrete climate comfort levels. The climate comfort level includes multiple progressively increasing suitability levels.

4. The tourism industry management and planning method for climate-based health and wellness as described in claim 1, characterized in that, In S3, the specific process of generating the suitability score is as follows: Environmental adaptability data and climate tendency data for each tourist health profile are extracted from the tourist health profile set. The environmental adaptability data includes a description of tolerance to adverse climate conditions; the climate tendency data includes preferences for specific climate conditions. The environmental adaptability data is matched with the climate comfort level sequence. The matching process involves finding dates in the climate comfort level sequence that conflict with the environmental adaptability data and lowering the suitability score on those conflicting dates. Climate trend data is then matched with the climate comfort level sequence to find dates in the climate comfort level sequence that match the climate trend data and raise the suitability score on those matching dates. For dates where the environmental adaptability data and climate trend data conflict, the matching result of the environmental adaptability data is prioritized. Finally, a suitability score sequence corresponding to the planning period dates is generated.

5. A tourism industry management and planning method for climate-based health and wellness according to claim 1, characterized in that, In step S5, the specific process for generating the overall tourist distribution prediction and infrastructure load forecast is as follows: Construct a multi-level spatiotemporal distribution network for the target tourist area. The multi-level spatiotemporal distribution network includes the scenic spot level, transportation hub level, and service facility level. Map the health and wellness activity sequence and spatial movement path of each tourist's health profile to the multi-level spatiotemporal distribution network to form the initial distribution state. Dynamic propagation simulation of tourist flow is performed based on a multi-level spatiotemporal distribution network. The dynamic propagation simulation process includes calculating tourist gathering intensity at the scenic spot level, tourist transfer intensity at the transportation hub level, and tourist usage intensity at the service facility level. A tourist flow correlation model between levels is established, which represents the probability of tourist transfer between different levels. Through multiple rounds of iterative calculation, the tourist distribution status of each time segment within the planning period is obtained. Based on the tourist distribution status and combined with the capacity data of infrastructure at each level, the infrastructure load forecast is generated.

6. A tourism industry management and planning method for climate-based health and wellness according to claim 5, characterized in that, The process of generating the expected infrastructure load is as follows: For each node in the multi-level spatiotemporal distribution network, historical load data of the node is extracted. The historical load data contains infrastructure usage records at different time periods. Combined with the tourist distribution status, the real-time load rate of the node is calculated, and the load propagation relationship between nodes is established. The load propagation relationship is determined by the tourist flow path. A load balancing calculation model is constructed, and the fluctuation cycle and trend of load rate in the time dimension and the load correlation strength between adjacent nodes in the spatial dimension are analyzed. The time dimension analysis results and the spatial dimension analysis results are integrated to generate a load balancing evaluation value for each node. Based on the load balancing evaluation value, nodes with abnormal load status are identified and an infrastructure load expectation report is generated.

7. A tourism industry management and planning method for climate-based health and wellness according to claim 6, characterized in that, In step S6, the specific process of adjusting the arrangement density of the health and wellness activity sequence and the guidance strategy for spatial movement paths is as follows: Based on the locations of high-load and low-load areas in the load forecast report, the number of health and wellness activities in high-load areas on the corresponding dates is reduced, and the reduced activities are redistributed to low-load areas. Based on the redistributed distribution of health and wellness activity locations, spatial movement paths are updated, path connections are modified, and alternative paths to low-load areas are generated. Simultaneously, the operating routes and schedules of public transportation are adjusted to match the new spatial movement paths. The adjusted health and wellness activity sequences, updated spatial movement paths, and public transportation adjustment schemes are combined to form the planning results.

Images