A personalized climate tourism route recommendation method and system for health optimization

Abstract

The application belongs to the technical field of tourism route planning, and discloses a personalized climate tourism route recommendation method and system for health optimization, which comprises the following steps: collecting health adaptation data of a user, constructing a user immune adaptation ability model; obtaining climate characteristic data of a user's residence and each candidate tourism destination, and constructing a destination climate gradient relationship network; dynamically planning a gradual climate adaptation route according to the user immune adaptation ability model and the destination climate gradient relationship network; combining the gradual climate adaptation route with the user immune adaptation ability model to generate a stay duration configuration table; and performing health optimization on the gradual climate adaptation route and the stay duration configuration table according to predefined user travel constraints to form a gradual health tourism route. The application can maximize the health adaptation effect of the user under the premise of meeting the user's time constraints, and form a tourism route recommendation that takes into account the health benefits and the feasibility of the trip.

Description

Technical Field

[0001] This invention relates to the field of tourism route planning technology, and more specifically, to a method and system for recommending personalized climate tourism routes with health optimization as the goal. Background Technology

[0002] With the continuous enhancement of national health awareness and the rapid development of the health and wellness tourism market, more and more tourists tend to choose destinations with specific climatic therapeutic value for health and wellness vacations. As an important environmental factor affecting human health, changes in climate conditions such as temperature, humidity, air pressure, and sunlight can significantly impact tourists' respiratory, cardiovascular, and immune systems. Currently, tourism recommendation systems mainly plan routes based on users' interests, spending power, and destination popularity. Some systems have begun to introduce climate comfort indicators to recommend suitable tourist destinations and travel times for users. However, existing technologies still have considerable room for improvement in deeply integrating climate factors with users' health conditions, and a truly personalized climate tourism recommendation system optimized for health has not yet been formed.

[0003] Existing climate tourism recommendation technologies have the following shortcomings: First, they ignore the significant differences in immune adaptation capabilities among individual tourists. Different users have varying tolerance levels and adaptation rates to climate changes, making it difficult for uniform recommendation standards to meet personalized health needs. Second, existing technologies typically adopt a "point-to-point" direct route planning model, failing to fully consider the gradual adaptation needs of users transitioning from their place of residence to the climate of their target health and wellness destination. Sudden exposure to significantly different climate environments may trigger immune stress responses, leading to travel discomfort or even health risks. Third, they lack a systematic analysis of the climate gradient relationships between multiple destinations, making it impossible to scientifically plan climate transition paths and intermediate stops, thus hindering a smooth transition in the climate adaptation process. Fourth, they fail to accurately match and optimize individual users' immune adaptation rates with the duration of stay at each destination, potentially resulting in insufficient climate adaptation due to insufficient stays or wasted time and money due to excessive stays.

[0004] In view of this, the present invention proposes a personalized climate tourism route recommendation method and system for health optimization to solve the above problems. Summary of the Invention

[0005] To overcome the aforementioned deficiencies of the prior art and achieve the above objectives, the present invention provides the following technical solution:

[0006] A personalized climate tourism route recommendation method optimized for health includes:

[0007] Collect users' health adaptation data, analyze the immune adaptation curves and adaptation rate parameters of users to different climate and environmental changes based on the health adaptation data, and construct a user immune adaptation capacity model.

[0008] Acquire climate characteristic data of users' residences and candidate tourist destinations, dynamically analyze the multidimensional climate differences between users' residences and candidate tourist destinations, and among candidate tourist destinations, and construct a destination climate gradient relationship network.

[0009] Based on the user's immune adaptability model and the destination climate gradient relationship network, the target health and wellness destination and climate transition destination among the candidate tourist destinations are identified, and a gradual climate adaptation route from the user's residence to the target health and wellness destination is dynamically planned.

[0010] Based on the multidimensional climate difference between various climate transition destinations in the progressive climate adaptation route, and combined with the user's immune adaptation ability model, the shortest immune adaptation time and recommended stay time for users in each climate transition destination are calculated, and a stay time configuration table is generated.

[0011] Based on predefined user itinerary constraints, the progressive climate adaptation route and stay duration configuration table are optimized for health, and a progressive health and wellness tourism route is formed by combining them.

[0012] Furthermore, health adaptation data includes immune function indicators and health response records;

[0013] Methods for analyzing users' immune adaptation curves to different climatic and environmental changes include:

[0014] For each health response record, calculate the climate difference vector for the user under different climate differences; for each climate difference vector, calculate the corresponding comprehensive climate difference degree in turn; for each health response record, calculate the corresponding health response intensity in turn; pair the comprehensive climate difference degree and health response intensity of each health response record to form a climate difference-health response data pair; perform curve fitting on all climate difference-health response data pairs to obtain the user's immune adaptability curve.

[0015] Methods for analyzing users' adaptation rate parameters to different climate and environmental changes include:

[0016] All health response records are categorized to obtain the adaptation category for each health response record; for each health response record in each adaptation category, the basic adaptation rate for each climate dimension is calculated; based on the immune function index data, the user's immune regulation coefficient is calculated; the basic adaptation rate for each climate dimension is multiplied by the immune regulation coefficient to obtain the adaptation rate parameter for each climate dimension.

[0017] The method for constructing a user immune adaptability model is as follows: combine the immune adaptability curve with each adaptation rate parameter to construct the user immune adaptability model.

[0018] Furthermore, methods for dynamically analyzing multidimensional climate variability include:

[0019] The user's residence is aggregated with all candidate travel destinations to form a location set; each pair of different locations in the location set is paired to form multiple location pairs; for each location pair in the location pair set, the corresponding multidimensional climate difference is calculated based on the corresponding climate characteristic data; the multidimensional climate difference includes temperature difference, humidity difference, air pressure difference, elevation difference, ultraviolet radiation difference, and future climate difference.

[0020] Methods for constructing destination climate gradient relationship networks include:

[0021] The user's residence and all candidate tourist destinations are treated as nodes. An edge is established between the two nodes corresponding to each pair of locations. For each edge, the corresponding edge attributes are calculated in sequence. The edge attributes include multidimensional climate difference degree and climate gradient level. The climate feature data corresponding to the user's residence and all candidate tourist destinations are respectively used as the node attributes of the corresponding nodes. Based on all nodes, edges, edge attributes and node attributes, a destination climate gradient relationship network is constructed.

[0022] Furthermore, methods for identifying target wellness and health destinations include:

[0023] Obtain user data on health and wellness travel needs, filter out candidate travel destinations that match the health and wellness travel needs from all candidate travel destinations, and mark them as secondary screening destinations;

[0024] For each rescreened tourist destination, the corresponding health adaptation score and adaptation potential score are calculated sequentially based on the future climate difference between the destination and the user's place of residence and the adaptation rate parameter. Based on the preset adaptation weight, the health adaptation score and adaptation potential score of each rescreened tourist destination are weighted and summed to obtain the health and wellness adaptation score of each rescreened tourist destination.

[0025] The health and wellness suitability scores of all the re-screened tourist destinations were compared, and the candidate tourist destination with the highest health and wellness suitability score was selected as the target health and wellness destination.

[0026] Furthermore, methods for identifying climate transition destinations include:

[0027] Based on the user's immune adaptability model, calculate the user's single climate crossing threshold; obtain the future climate difference between the user's residence and the target health and wellness destination, and mark it as the direct climate difference; compare the direct climate difference with the single climate crossing threshold, and determine whether a climate transition destination needs to be set based on the comparison results.

[0028] If a climate transition destination needs to be set, obtain all the climate difference degrees between the user's residence and the target health and wellness destination, and combine them to obtain a climate difference vector; calculate the ideal climate gradient interval based on the direct climate difference degree and the single climate crossing threshold.

[0029] All candidate tourist destinations that are not the target health and wellness destinations are marked as candidate transitional destinations. All climate difference degrees between each candidate transitional destination and the user's residence are obtained and combined to form a climate offset vector. For each climate difference degree in the climate offset vector corresponding to each candidate transitional destination, it is determined whether two judgment conditions are met simultaneously, and the corresponding candidate transitional destination is retained or deleted based on the judgment result. For each climate difference degree in the climate offset vector corresponding to each candidate transitional destination, the corresponding gradient deviation component is calculated sequentially according to the ideal climate gradient interval. Based on the gradient deviation component, the gradient matching degree of each candidate transitional destination is calculated.

[0030] Based on the gradient matching degree, calculate the transition suitability score for each candidate transition destination; compare the transition suitability scores of all candidate transition destinations with the preset transition score thresholds, and select candidate transition destinations with transition suitability scores greater than the transition score thresholds as climate transition destinations.

[0031] Furthermore, methods for dynamically planning gradual climate adaptation pathways include:

[0032] The user's residence is used as the current starting point, and an empty sequence of climate transition destinations is created. If no climate transition destination exists, the progressive climate adaptation route is directly from the current starting point to the target health and wellness destination. If a climate transition destination exists, a route planning loop is defined.

[0033] The route planning loop is as follows: From all climate transition destinations, select those whose future climate difference from the current starting point is less than or equal to the single climate crossing threshold and which are not yet included in the climate transition destination sequence as reachable transition destinations, and combine them to form the current reachable candidate set; if the current reachable candidate set is not empty, for each reachable transition destination in the current reachable candidate set, obtain the corresponding forward climate difference and backward climate difference, and calculate the corresponding forward safety and backward proximity; based on the forward safety, backward proximity, and transition suitability scores, calculate the recursive optimization score for each reachable transition destination; select the reachable transition destination with the highest recursive optimization score as the preferred transition destination, add the preferred transition destination to the end of the climate transition destination sequence, and update the current starting point as the preferred transition destination;

[0034] Repeat the route planning loop until the backward climate difference of the preferred transition destination is less than or equal to the single climate crossing threshold, then stop the route planning loop; generate a progressive climate adaptation route based on the user's residence, the sequence of climate transition destinations and the target health and wellness destination.

[0035] Furthermore, methods for calculating the shortest immune adaptation time for climate transition destinations include:

[0036] Based on the progressive climate adaptation route, each pair of adjacent locations is sequentially obtained and marked as a road segment node pair; where each road segment node pair includes a predecessor node and a successor node; the longest adaptation time of each road segment node pair is calculated and marked as the basic adaptation time;

[0037] Multi-dimensional interaction effects are introduced, and the interaction effects of multi-dimensional climate change are analyzed for each road segment node pair in turn. The multi-dimensional interaction correction coefficients of each road segment node pair are calculated. Cumulative adaptation effects are introduced, and the cumulative adaptation correction coefficients of each road segment node pair are calculated.

[0038] For each road segment node pair, the corresponding comprehensive adaptation time is calculated based on the basic adaptation time, multi-dimensional interaction correction coefficient, and cumulative adaptation correction coefficient. For each road segment node pair, the corresponding comprehensive adaptation time is used as the shortest immune adaptation time for the climate transition destination corresponding to the subsequent node.

[0039] Furthermore, methods for health-optimizing the configuration table of progressive climate adaptation routes and length of stay include:

[0040] Obtain user travel constraints, including expected departure date, expected arrival date, maximum travel duration, and time flexibility coefficient; sum the recommended stay durations for all climate transition destinations in the progressive climate adaptation route to obtain the total transition stay duration; obtain the geographical distances of each road segment node pair, and calculate the travel time for each road segment node pair based on the geographical distances of each road segment node pair and the preset average daily travel distance; calculate the initial travel duration based on the travel time of all road segment node pairs and the total transition stay duration.

[0041] Calculate the expected travel duration based on the expected arrival and departure dates; compare the expected travel duration with the maximum travel duration, and select the smaller value as the available travel duration; then compare the initial travel duration with the available travel duration; if the initial travel duration is less than or equal to the available travel duration, use the recommended stay duration for each climate transition destination as the corresponding optimized stay duration; if the initial travel duration is longer than the available travel duration, calculate the overtime based on the initial travel duration and the available travel duration, and determine the health optimization adjustment strategy based on the overtime duration and the time flexibility coefficient; the health optimization adjustment strategy includes a stay duration compression strategy and a route node simplification strategy.

[0042] Furthermore, if the timeout duration is less than or equal to the preset mild timeout threshold, a stay duration compression strategy is adopted for health optimization: the stay duration compression ratio is calculated based on the timeout duration, the total transition stay duration, and the time elasticity coefficient; the compressed stay duration for each climate transition destination is calculated based on the recommended stay duration and the stay duration compression ratio, and compared with the corresponding minimum immune adaptation duration; if the compressed stay duration is greater than or equal to the minimum immune adaptation duration, the compressed stay duration is used as the optimized stay duration for the corresponding climate transition destination; if the compressed stay duration is less than the minimum immune adaptation duration, the minimum immune adaptation duration is used as the optimized stay duration for the corresponding climate transition destination; the optimized stay durations for each climate transition destination in the progressive climate adaptation route are summarized to construct a health-optimized stay duration configuration table;

[0043] If the timeout duration exceeds the mild timeout threshold, a route node simplification strategy is adopted for health optimization: For each climate transition destination in the progressive climate adaptation route, the corresponding adaptation necessity and transition importance are calculated sequentially; the adaptation necessity and transition importance are weighted and summed based on preset importance weights to obtain the node importance score for each climate transition destination; a node simplification judgment process is defined and repeated until the simplified travel time corresponding to the progressive climate adaptation route is less than or equal to the available travel time, or all climate transition destinations in the node importance sequence have been judged; if the simplified travel time corresponding to the progressive climate adaptation route is still greater than the available travel time, the stay duration compression strategy is continued to be used for health optimization of the progressive climate adaptation route.

[0044] A personalized climate tourism route recommendation system for health optimization, implementing the aforementioned personalized climate tourism route recommendation method for health optimization, includes:

[0045] The immune adaptation module is used to collect users' health adaptation data, analyze the immune adaptation ability curves and adaptation rate parameters of users to different climate and environmental changes based on the health adaptation data, and construct a user's immune adaptation ability model.

[0046] The climate analysis module is used to acquire climate characteristic data of the user's residence and each candidate tourist destination, dynamically analyze the multidimensional climate differences between the user's residence and each candidate tourist destination, and among each candidate tourist destination, and construct a destination climate gradient relationship network.

[0047] The route planning module is used to determine the target health and wellness destination and the climate transition destination among the candidate tourist destinations based on the user's immune adaptability model and the destination climate gradient relationship network, and dynamically plan a gradual climate adaptation route from the user's residence to the target health and wellness destination.

[0048] The duration assessment module is used to calculate the minimum immune adaptation duration and recommended stay duration for users in each climate transition destination based on the multidimensional climate difference between each climate transition destination in the progressive climate adaptation route and combined with the user immune adaptation capability model, and generate a stay duration configuration table.

[0049] The health optimization module is used to optimize the configuration table of progressive climate adaptation routes and stay durations based on predefined user itinerary constraints, and to form progressive health and wellness tourism routes by combining them.

[0050] The technical effects and advantages of the personalized climate tourism route recommendation method and system for health optimization proposed in this invention are as follows:

[0051] By collecting users' health checkup data, physiological monitoring data, and historical travel health response records, a nonlinear regression algorithm is used to fit the immune adaptation curve of each user. Adaptation rate parameters across five climate dimensions (temperature, humidity, air pressure, altitude, and ultraviolet radiation) are calculated, enabling precise quantitative modeling of differences in immune adaptation among users. This effectively overcomes the shortcomings of existing technologies that use uniform recommendation standards and ignore individual differences. A destination climate gradient relationship network is constructed to systematically analyze the multidimensional climate differences and gradient levels between users' residences and candidate tourist destinations, as well as among candidate tourist destinations, providing data support for the scientific planning of climate transition paths. By calculating the user's single climate crossing threshold, candidate transition destinations located within the climate transition zone are selected. A progressive recursive algorithm is used to dynamically plan a gradual climate adaptation route from the user's residence to the target health and wellness destination, effectively avoiding sudden exposure to climate changes. The study addresses the immune stress and health risks caused by significantly different environments, aiming to achieve a smooth transition in the climate adaptation process. It introduces multi-dimensional interaction and cumulative adaptation effects, comprehensively considering the superimposed or offsetting effects of simultaneous changes in multiple climate dimensions, as well as the enhanced adaptability of users' immune systems as they gradually activate during continuous climate transitions. This allows for precise calculation of the minimum immune adaptation time and recommended stay duration for users at each climate transition destination, achieving accurate matching and optimization between individual user adaptation rates and destination stay durations. This avoids insufficient adaptation due to insufficient stay time or wasted time and economic costs due to excessive stay time. Furthermore, it employs stay duration compression and route node simplification strategies to optimize the gradual climate adaptation route and stay duration configuration table, maximizing user health adaptation effects while meeting time constraints. Ultimately, this results in a recommended gradual health and wellness tourism route that balances health benefits and itinerary feasibility. Attached Figure Description

[0052] Figure 1 This is a flowchart of a personalized climate tourism route recommendation method for health optimization according to Embodiment 1 of the present invention;

[0053] Figure 2 This is a schematic diagram of a personalized climate tourism route recommendation system for health optimization according to Embodiment 2 of the present invention. Detailed Implementation

[0054] 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.

[0055] Example 1

[0056] Please see Figure 1 As shown in this embodiment, a personalized climate travel route recommendation method for health optimization includes:

[0057] Collect users' health adaptation data, analyze the immune adaptation curves and adaptation rate parameters of users to different climate and environmental changes based on the health adaptation data, and construct a user immune adaptation capacity model.

[0058] Health adaptation data includes immune function indicator data and health response records. Immune function indicator data includes health checkup data and physiological monitoring data. Each health response record includes travel health response data, historical travel information, and historical climate and environmental data. Health adaptation data is obtained through user-authorized access to a personal health data management platform. This platform is a comprehensive health information aggregation platform that integrates data from medical institutions, smart wearable devices, user-reported data, and geographic environmental data, including but not limited to the National Health and Medical Big Data Platform, hospital electronic medical record systems, and third-party health management applications.

[0059] Specifically, health checkup data includes, but is not limited to, white blood cell count, absolute lymphocyte count, and immunoglobulin G concentration; among them, white blood cell count reflects the user's overall immune defense capacity, absolute lymphocyte count reflects the user's specific immune capacity, and immunoglobulin G concentration reflects the user's humoral immune function level.

[0060] The physiological monitoring data is the heart rate variability index, which is used to reflect the user's autonomic nervous system regulation ability;

[0061] Travel health response data includes, but is not limited to, symptom type, symptom onset time, symptom duration, symptom severity, and recovery completion time. Symptom types include, for example, respiratory symptoms (coughing, nasal congestion, sore throat, etc. due to climate change), digestive symptoms (diarrhea, bloating, loss of appetite, etc. due to changes in environment), skin allergy symptoms (rashes, itching, dryness, etc. due to environmental changes), and sleep disturbance symptoms (difficulty falling asleep, early awakening, decreased sleep quality, etc. due to jet lag or environmental changes). Symptom onset time refers to the time when symptoms appear during the trip; symptom duration refers to the time from the appearance of a single symptom to its disappearance; symptom severity includes three levels: mild, moderate, and severe; and recovery completion time refers to the time when all symptoms disappear and the user's health status returns to normal.

[0062] Historical travel information includes, but is not limited to, departure point, destination point, departure date, and return date; among which, the departure point and destination point are used to determine the range of climate changes involved in the trip; the departure date and return date are used to determine the time span and seasonal characteristics of the trip;

[0063] Historical climate and environmental data include, but are not limited to, the daily average temperature, daily average relative humidity, daily average air pressure, altitude, and ultraviolet index values ​​for each departure and destination point in the historical travel basic information. Among them, the daily average temperature value is used to reflect the temperature environment characteristics; the daily average relative humidity value is used to reflect the humidity environment characteristics; the daily average air pressure value and altitude value are used to reflect the air pressure environment characteristics; and the ultraviolet index value is used to reflect the light environment characteristics.

[0064] Methods for analyzing users' immune adaptation curves to different climatic and environmental changes include:

[0065] For each health response record, a climate difference vector is calculated for the user under different climatic conditions. Specifically, for each health response record, the differences in temperature, humidity, air pressure, altitude, and UV radiation between the departure point and the destination point are calculated. These differences are then aggregated to construct a climate difference vector for each health response record. Specifically, the temperature difference is equal to the daily average temperature of the destination point minus the daily average temperature of the departure point; the humidity difference is equal to the daily average relative humidity of the destination point minus the daily average relative humidity of the departure point; the air pressure difference is equal to the daily average air pressure of the destination point minus the daily average air pressure of the departure point; the altitude difference is equal to the altitude of the destination point minus the altitude of the departure point; and the UV radiation difference is equal to the UV index of the destination point minus the UV index of the departure point.

[0066] For each climate difference vector, the corresponding comprehensive climate difference degree is calculated sequentially. Specifically, temperature difference, humidity difference, air pressure difference, altitude difference, and ultraviolet radiation difference are collectively referred to as climate difference values. The absolute values ​​of the climate difference values ​​in each climate difference vector are taken and normalized, and corresponding climate weights are assigned to different climate difference values. Based on the climate weights, the normalized climate difference values ​​in the same climate difference vector are weighted and summed to obtain the comprehensive climate difference degree corresponding to each climate difference vector. The comprehensive climate difference degree is used to reflect the overall degree of difference in climate environment between two locations.

[0067] For each health response record, the corresponding health response intensity is calculated sequentially. Different numerical labels are assigned to different symptom severity levels and marked as severity labels. For example, mild symptoms are labeled with a severity label of 1, moderate symptoms with a severity label of 2, and severe symptoms with a severity label of 3. The severity label is obtained based on the symptom severity in each health response record. The severity label and symptom duration in each health response record are normalized, and different response weights are assigned to the severity label and symptom duration. Based on the response weights, the normalized severity label and symptom duration corresponding to the same symptom in the same health response record are weighted and summed to obtain the symptom response intensity of a single symptom in each health response record. The mean of all symptom response intensities corresponding to the same health response record is calculated to obtain the health response intensity of each health response record. The health response intensity is used to reflect the degree of health impairment of users under climate change conditions.

[0068] The comprehensive climate difference degree of each health response record is paired with the health response intensity to form a climate difference-health response data pair. A nonlinear regression algorithm is used to fit curves to all climate difference-health response data pairs to obtain the user's immune adaptability curve. The immune adaptability curve uses the comprehensive climate difference degree as the independent variable and the health response intensity as the dependent variable to describe the user's expected health response level under different climate difference conditions.

[0069] It should be noted that the climate weights and response weights are all preset by those skilled in the art based on the actual situation; the nonlinear regression algorithm is a well-known technology in the field, and the specific process will not be described in detail here.

[0070] Methods for analyzing users' adaptation rate parameters to different climate and environmental changes include:

[0071] All health response records are categorized to obtain the adaptation category for each record. Specifically, the absolute values ​​of each climate difference value for each health response record are taken to obtain the absolute difference value. For each health response record, the largest absolute difference value among all corresponding absolute difference values ​​is obtained and marked as the maximum difference value. The maximum difference value of each health response record is compared with a preset dominant threshold. Health response records with a maximum difference value greater than the dominant threshold are assigned to the corresponding adaptation category, while those with a maximum difference value less than or equal to the dominant threshold are deleted. The adaptation categories include temperature adaptation category (maximum difference value is temperature difference value), humidity adaptation category (maximum difference value is humidity difference value), air pressure adaptation category (maximum difference value is air pressure difference value), altitude adaptation category (maximum difference value is altitude difference value), and ultraviolet radiation adaptation category (maximum difference value is ultraviolet radiation difference value). It should be noted that the dominant threshold is preset by those skilled in the art based on actual conditions.

[0072] For each health response record in each adaptation category, the baseline adaptation rate for the corresponding climate dimension is calculated. Specifically, the symptom onset times in the same health response record are compared, and the earliest symptom onset time is taken as the initial symptom time. The difference between the recovery completion time and the initial symptom time is calculated to obtain the adaptation completion time. The ratio between the maximum difference value and the adaptation completion time in each health response record is calculated to obtain the adaptation rate value for each health response record. The mean of the adaptation rate values ​​of all health response records in the same adaptation category is calculated to obtain the baseline adaptation rate for the corresponding climate dimension of each adaptation category. Among them, the climate dimension corresponding to the temperature adaptation category is the temperature dimension, the climate dimension corresponding to the humidity adaptation category is the humidity dimension, the climate dimension corresponding to the air pressure adaptation category is the air pressure dimension, the climate dimension corresponding to the altitude adaptation category is the altitude dimension, and the climate dimension corresponding to the ultraviolet adaptation category is the ultraviolet radiation dimension.

[0073] Based on immune function index data, the user's immune regulation coefficient is calculated. Specifically, the white blood cell count, absolute lymphocyte count, and immunoglobulin G concentration are normalized and corresponding immune weights are assigned. The normalized white blood cell count, absolute lymphocyte count, and immunoglobulin G concentration are then weighted and summed based on these immune weights to obtain a baseline immune score. The heart rate variability index is normalized to obtain a regulatory capacity score. Corresponding coefficient weights are assigned to both the baseline immune score and the regulatory capacity score, and the two scores are then weighted and summed based on these coefficient weights to obtain the immune regulation coefficient. The immune regulation coefficient reflects the user's immune system's ability to regulate environmental changes. It should be noted that all immune weights and coefficient weights are pre-set by those skilled in the art based on actual conditions.

[0074] The basic adaptation rate for each climate dimension is multiplied by the immune regulation coefficient to obtain the adaptation rate parameters for each climate dimension. These parameters include temperature adaptation rate, humidity adaptation rate, air pressure adaptation rate, altitude adaptation rate, and ultraviolet (UV) adaptation rate. Temperature adaptation rate reflects how quickly a user adapts to temperature changes; humidity adaptation rate reflects how quickly a user adapts to humidity changes; air pressure adaptation rate reflects how quickly a user adapts to air pressure changes; altitude adaptation rate reflects how quickly a user adapts to altitude changes; and UV adaptation rate reflects how quickly a user adapts to UV changes.

[0075] The method for constructing a user immune adaptability model is as follows: combine the immune adaptability curve with each adaptation rate parameter to construct the user immune adaptability model.

[0076] Acquire climate characteristic data of user residence and each candidate tourist destination, dynamically analyze the multidimensional climate differences between user residence and each candidate tourist destination, and among each candidate tourist destination, and construct a destination climate gradient relationship network.

[0077] Methods for obtaining climate characteristic data of user residence and candidate tourist destinations include:

[0078] By calling the meteorological data service interface, meteorological observation data of the user's residence and candidate tourist destinations within a preset query period are obtained. The user's residence refers to the geographical area where the user currently resides, and candidate tourist destinations refer to geographical areas that conform to the national tourism resource classification standards and relevant regulations for health and wellness tourism. The meteorological data service interface includes, but is not limited to, the National Meteorological Data Network open interface, the National Meteorological Science Data Center interface, and third-party meteorological data platform interfaces. The preset query period is pre-set by those skilled in the art based on actual conditions. The meteorological observation data includes, but is not limited to, daily average temperature, daily average relative humidity, daily average air pressure, and ultraviolet index.

[0079] Obtain the altitude values ​​of the user's residence and each candidate tourist destination, and mark them as surface elevation values; calculate the climate characteristic data of the user's residence and each candidate tourist destination based on meteorological observation data, and add the surface elevation values ​​of the user's residence and each candidate tourist destination to the corresponding climate characteristic data; among which, the climate characteristic data includes average temperature value, average humidity value, average air pressure value, surface elevation value and average ultraviolet index value.

[0080] Specifically, the average temperature value is calculated by averaging all daily average temperature values ​​within the preset query period; the average humidity value is calculated by averaging all daily average relative humidity values ​​within the preset query period; the average air pressure value is calculated by averaging all daily average air pressure values ​​within the preset query period; and the average ultraviolet index value is calculated by averaging all ultraviolet index values ​​within the preset query period.

[0081] Methods for dynamically analyzing multidimensional climate variability include:

[0082] The user's residence is aggregated with all candidate travel destinations to form a location set; each pair of different locations in the location set is paired to form multiple location pairs; for each location pair in the location pair set, the corresponding multidimensional climate difference is calculated based on the corresponding climate characteristic data; the multidimensional climate difference includes temperature difference, humidity difference, air pressure difference, elevation difference, ultraviolet radiation difference, and future climate difference.

[0083] Specifically, the method involves obtaining the average temperature values ​​of the two locations in the location pair and calculating the difference between them to obtain the temperature difference; obtaining the average humidity values ​​of the two locations in the location pair and calculating the difference between them to obtain the humidity difference; obtaining the average air pressure values ​​of the two locations in the location pair and calculating the difference between them to obtain the air pressure difference; obtaining the surface elevation values ​​of the two locations in the location pair and calculating the difference between them to obtain the elevation difference; and obtaining the average ultraviolet index values ​​of the two locations in the location pair and calculating the average ultraviolet index of the two locations. The difference between ultraviolet index values ​​is used to obtain the ultraviolet radiation difference. Temperature difference, humidity difference, air pressure difference, elevation difference, and ultraviolet radiation difference are collectively referred to as climate difference. The absolute values ​​of temperature difference, humidity difference, air pressure difference, elevation difference, and ultraviolet radiation difference are taken separately, normalized, and then weighted and summed based on climate weights to obtain the future climate difference. It should be noted that if there is a location in the location pairing that is the user's residence, then in the process of calculating the climate difference, the climate characteristic data of the user's residence is used as the benchmark value. The corresponding climate difference is obtained by calculating the difference between the meteorological characteristic data of other locations and the benchmark value.

[0084] Methods for constructing destination climate gradient relationship networks include:

[0085] Using the user's residence and all candidate tourist destinations as nodes, edges are established between the two nodes corresponding to each pair of locations. For each edge, the corresponding edge attributes are calculated sequentially. Specifically, the future climate difference between the two nodes corresponding to each edge is obtained. Each future climate difference is compared with a preset gradient level threshold set to determine the climate gradient level of each future climate difference. The gradient level threshold set includes multiple gradient level intervals, each of which corresponds to a climate gradient level. The climate gradient level is used to reflect the degree of climate difference between two locations. It should be noted that the gradient level threshold set is preset by those skilled in the art based on actual conditions. The multidimensional climate difference between the locations corresponding to each edge and the climate gradient level are combined to obtain the edge attributes of each edge. The climate feature data corresponding to the user's residence and all candidate tourist destinations are used as the node attributes of the corresponding nodes. Based on all nodes, edges, edge attributes, and node attributes, a destination climate gradient relationship network is constructed.

[0086] Based on the user's immune adaptability model and the destination climate gradient relationship network, the target health and wellness destination and climate transition destination are identified among the candidate tourist destinations, and a gradual climate adaptation route from the user's residence to the target health and wellness destination is dynamically planned.

[0087] Methods for identifying target wellness and health destinations include:

[0088] We obtain users' health and wellness travel needs data through travel demand information forms filled out and uploaded by users themselves. This data includes, but is not limited to, desired health and wellness travel types and desired climate characteristics. Desired health and wellness travel types include forest health and wellness (i.e., health and wellness activities that achieve relaxation and health promotion through the absorption of negative oxygen ions and forest bathing in a forest environment), seaside health and wellness (i.e., health and wellness activities that utilize marine climate, seawater bathing, and beach walks to nourish the user's mind and body), and plateau health and wellness (i.e., health and wellness activities that utilize the unique low-oxygen environment and climate conditions of plateau regions to exercise physical functions and regulate cardiopulmonary function). Desired climate characteristics include warm and dry, warm and humid, cool and dry, and cool and humid.

[0089] From all candidate tourist destinations, those that meet the health and wellness travel needs data are selected and marked as secondary screening destinations. Specifically, the health and wellness type and climate characteristics of each candidate tourist destination are obtained from a pre-constructed destination attribute set. The destination attribute set includes the health and wellness type and climate characteristics of each candidate tourist destination, which are pre-constructed by those skilled in the art based on the actual situation of each candidate tourist destination. From all candidate tourist destinations, those with the same health and wellness type as the desired health and wellness type are selected and marked as initial screening destinations. From all initial screening destinations, those with the same climate characteristics as the desired climate characteristics are selected and marked as secondary screening destinations.

[0090] For each rescreened tourist destination, a corresponding health and wellness adaptation score is calculated. Specifically, the future climate difference between the user's residence and the rescreened tourist destination is obtained from the destination climate gradient relationship network. The future climate difference is substituted into the immune adaptation curve in the user's immune adaptability model to obtain the health response intensity, which is marked as the predicted response intensity. The difference between the predicted response intensity and the predicted response intensity is calculated to obtain the health adaptation score. The absolute value of each climate difference corresponding to the rescreened tourist destination is taken to obtain the absolute difference. The ratio between each absolute difference and the adaptation rate parameter of the corresponding climate dimension in the user's immune adaptability model is calculated to obtain the climate adaptation time for each climate dimension. Among them, temperature difference corresponds to temperature adaptation rate, humidity difference corresponds to humidity adaptation rate, air pressure difference corresponds to air pressure adaptation rate, elevation difference corresponds to altitude adaptation rate, and ultraviolet difference corresponds to ultraviolet adaptation rate. From the climate adaptation time of each climate dimension, the climate adaptation time with the largest value is selected as the longest adaptation time. The longest adaptation time is normalized, and the difference between the predicted and normalized longest adaptation time is calculated to obtain the adaptation potential score.

[0091] Corresponding adaptation weights are set for the health adaptation score and the adaptation potential score, and the health adaptation score and the adaptation potential score are weighted and summed based on the adaptation weights to obtain the health and wellness adaptation score; the health and wellness adaptation score is used to comprehensively reflect the degree of health adaptation of users to the rescreened tourist destination; it should be noted that each adaptation weight is preset by those skilled in the art according to the actual situation.

[0092] The health and wellness suitability scores of all the re-screened tourist destinations were compared, and the candidate tourist destination with the highest health and wellness suitability score was selected as the target health and wellness destination.

[0093] Methods for identifying climate transition destinations include:

[0094] Based on the user's immune adaptability model, a single climate crossing threshold is calculated. Specifically, based on the immune adaptability curve in the user's immune adaptability model, the comprehensive climate difference corresponding to when the health response intensity reaches a preset acceptable response threshold is obtained, and this is used as the single climate crossing threshold. The acceptable response threshold is preset by those skilled in the art according to actual circumstances. For example, the acceptable response threshold is set to... This indicates that the intensity of the health reaction does not exceed Users can adapt normally during this time; the single climate crossing threshold is used to represent the maximum value of the overall climate difference that a user can accept during a single location change;

[0095] The future climate difference between the user's residence and the target health and wellness destination is obtained from the destination climate gradient relationship network and marked as the direct climate difference. The direct climate difference is compared with the single climate crossing threshold. If the direct climate difference is less than or equal to the single climate crossing threshold, it is determined that the user can go directly to the target health and wellness destination without setting a climate transition destination. If the direct climate difference is greater than the single climate crossing threshold, it is determined that the user needs to go through a climate transition destination for gradual adaptation, and the climate gradient screening algorithm is used to determine the climate transition destination.

[0096] Specifically, from the destination climate gradient relationship network, all climate difference degrees between the user's residence and the target health and wellness destination are obtained and combined to obtain a climate difference vector; the ratio of the direct climate difference degree to the single climate crossing threshold is calculated, and the calculation result is rounded up to obtain the minimum number of transitions; whereby the minimum number of transitions is used to represent the minimum number of location changes required for the user to reach the target health and wellness destination from their residence.

[0097] Divide each climate difference degree in the climate difference vector by the minimum number of transitions to obtain the ideal climate gradient interval; the ideal climate gradient interval includes the ideal temperature interval, ideal humidity interval, ideal air pressure interval, ideal elevation interval, and ideal ultraviolet interval.

[0098] All candidate tourist destinations that are not the target health and wellness destinations are marked as candidate transitional destinations. All climate difference degrees between each candidate transitional destination and the user's residence are obtained and combined to form a climate offset vector. For each climate difference degree in the climate offset vector corresponding to each candidate transitional destination, it is determined whether two judgment conditions are simultaneously met. If all climate difference degrees in the climate offset vector simultaneously meet both judgment conditions, the corresponding candidate transitional destination is determined to be within the climate transition zone of the user's residence and is retained. If there are climate difference degrees in the climate offset vector that do not simultaneously meet both judgment conditions, the corresponding candidate transitional destination is determined to be outside the climate transition zone of the user's residence and is deleted. Specifically, the judgment conditions are: whether the climate difference degree in the climate offset vector is in the same direction as the corresponding climate difference degree in the climate difference vector (i.e., whether they are both positive or both negative), and whether the absolute value of the climate difference degree in the climate offset vector is less than the absolute value of the corresponding climate difference degree in the climate difference vector.

[0099] For each climate difference degree in the climate offset vector corresponding to each candidate transition destination, the absolute value of the difference between the value and an integer multiple of the corresponding interval in the ideal climate gradient interval is calculated sequentially. The smallest absolute value is then selected as the gradient bias component corresponding to each climate difference degree. The specific range of the integer multiples is as follows: , To minimize the number of transitions, all gradient deviation components corresponding to the same candidate transition destination are normalized and then averaged to obtain the gradient deviation value for each candidate transition destination. The difference between the gradient deviation value and each gradient deviation value is calculated to obtain the gradient matching degree for each candidate transition destination. The gradient matching degree reflects the closeness of the candidate transition destination to the ideal climate gradient. For example, the climate difference degree is the temperature difference degree, and the temperature difference degree in the climate offset vector is... The temperature difference in the climate difference vector is The minimum number of transitions is 4, and the ideal temperature interval corresponding to the temperature difference is... Therefore, the range of values ​​for integer multiples is... The integer multiples of the ideal temperature interval are as follows: , , The absolute values ​​of the differences are as follows: , , Therefore, the smallest absolute value is That is, the gradient deviation component of the temperature difference is ;

[0100] The gradient matching degree of each candidate transition destination is normalized to obtain a transition suitability score for each candidate transition destination. The transition suitability score reflects the suitability of the candidate transition destination as a climate transition destination; the higher the value, the more suitable the corresponding candidate transition destination is as a climate transition destination. The transition suitability scores of all candidate transition destinations are compared with preset transition score thresholds. If the transition suitability score is greater than the transition score threshold, the corresponding candidate transition destination is selected as a climate transition destination. If the transition suitability score is less than or equal to the transition score threshold, the corresponding candidate transition destination is not selected as a climate transition destination. It should be noted that the transition score thresholds are preset by those skilled in the art based on actual conditions.

[0101] The methods for dynamic programming of gradual climate adaptation pathways include:

[0102] The user's place of residence is used as the current starting point, and an empty climate transition destination sequence is created. If no climate transition destination exists, the progressive climate adaptation route is directly from the current starting point to the target health and wellness destination. If a climate transition destination exists, multiple climate transition destinations are selected from all climate transition destinations and added to the climate transition destination sequence in sequence.

[0103] Specifically, the route planning loop process is defined as follows: from all climate transition destinations, select climate transition destinations whose future climate difference with the current starting point is less than or equal to the single climate crossing threshold and which have not been added to the climate transition destination sequence, and mark them as reachable transition destinations; combine all reachable transition destinations to form the current reachable candidate set.

[0104] If the current reachable candidate set is empty, it is determined that it is impossible to continue from the current starting point, and a prompt message is sent to the user, suggesting that the user adjust the target health and wellness destination or lower the acceptable response threshold.

[0105] If the current reachable candidate set is not empty, then for each reachable transitional destination in the current reachable candidate set, the corresponding recursive optimization score is calculated sequentially. The calculation process of the recursive optimization score is as follows: from the destination climate gradient relationship network, obtain the future climate difference between the reachable transitional destination and the current starting point, and mark it as the forward climate difference; from the destination climate gradient relationship network, obtain the future climate difference between the reachable transitional destination and the target health and wellness destination, and mark it as the backward climate difference; after normalizing the forward climate difference, calculate the difference between 1 and the normalized forward climate difference to obtain the forward safety; after normalizing the backward climate difference, calculate the difference between 1 and the normalized backward climate difference to obtain the backward proximity.

[0106] Forward safety, backward proximity, and transition suitability scores are assigned corresponding recursive weights. Based on these recursive weights, the forward safety, backward proximity, and transition suitability scores for the reachable transition destination are weighted and summed to obtain the recursive optimal score. Forward safety reflects the health and safety level from the current starting point to the corresponding reachable transition destination, while backward proximity reflects the climatic proximity between the corresponding reachable transition destination and the target health and wellness destination. It should be noted that each recursive weight is preset by those skilled in the art based on actual conditions.

[0107] Select the reachable transition destination with the highest recursive score from the current reachable candidate set and mark it as the preferred transition destination; add the preferred transition destination to the end of the climate transition destination sequence and update the current starting point as the preferred transition destination.

[0108] Repeat the route planning loop until the backward climate difference of the preferred transition destination is less than or equal to the single climate crossing threshold, then stop the route planning loop; generate a progressive climate adaptation route based on the user's residence, the sequence of climate transition destinations and the target health and wellness destination.

[0109] The gradual climate adaptation route is stored in the form of an ordered sequence of nodes, including the route start point, route points along the way, and route end point. The route start point is the user's residence, the route points along the way are the various climate transition destinations in the climate transition destination sequence, and the route end point is the target health and wellness destination.

[0110] Based on the multidimensional climate differences between various climate transition destinations in the progressive climate adaptation route, and combined with the user's immune adaptation capability model, the minimum immune adaptation time and recommended stay time for users in each climate transition destination are calculated, and a stay time configuration table is generated.

[0111] Methods for calculating the shortest immune adaptation time for climate transition destinations include:

[0112] Based on the progressive climate adaptation route, each pair of adjacent locations is sequentially acquired and marked as a road segment node pair. Each road segment node pair includes a preceding node and a succeeding node. The preceding node is the location at the beginning of the progressive climate adaptation route, and the succeeding node is the location at the end of the progressive climate adaptation route. The longest adaptation time for each road segment node pair is calculated and marked as the basic adaptation time. The basic adaptation time is used to reflect the initial estimated time required for the user to complete climate adaptation in the climate dimension with the slowest adaptation speed, to ensure that the user completes basic adaptation in all climate dimensions.

[0113] This paper introduces multi-dimensional interaction effects and analyzes the interaction effects of multi-dimensional climate change on each road segment node pair in turn, calculating the multi-dimensional interaction correction coefficient for each road segment node pair. The multi-dimensional interaction effect refers to the superposition or offsetting effect on user health adaptation when multiple climate dimensions change simultaneously. The superposition effect means that the changes in multiple climate dimensions have a unidirectional impact on user health, leading to increased adaptation difficulty; the offsetting effect means that the changes in multiple climate dimensions have a negative impact on user health, leading to reduced adaptation difficulty.

[0114] Specifically, a climate dimension interaction matrix is ​​constructed to store the interaction relationships between various climate dimensions. This matrix is ​​pre-set by those skilled in the art based on climate medicine-related research. The climate dimension interaction matrix is ​​a symmetric matrix, and each element in the matrix represents the interaction coefficient between two climate dimensions. An interaction coefficient greater than zero indicates a superposition effect between the two climate dimensions, an interaction coefficient less than zero indicates a cancellation effect between the two climate dimensions, and an interaction coefficient equal to zero indicates no interaction effect between the two climate dimensions. For example, the interaction coefficient between the temperature dimension and the humidity dimension is positive, indicating that when both temperature and humidity increase, a superposition of discomfort will occur.

[0115] For each road segment node pair, the multidimensional climate difference degree between the preceding and succeeding nodes is obtained from the destination climate gradient relationship network and marked as the road segment climate difference degree. The direction of change of each climate difference degree in the road segment climate difference degree corresponding to each road segment node pair is determined sequentially. If the climate difference degree is greater than zero, the corresponding direction of change is positive; if the climate difference degree is less than zero, the corresponding direction of change is negative; if the climate difference degree is equal to zero, the corresponding direction of change is unchanged. For every two different climate difference degrees in the road segment climate difference degree, the consistency of direction is determined sequentially. If the directions of change of two climate difference degrees are both positive or both negative, they are determined to be in the same direction; if the directions of change of two climate difference degrees are one positive and one negative, they are determined to be negative; if one of the two climate difference degrees has no change, they are determined to be without interaction.

[0116] If the determination of directional consistency indicates a change in the same direction, the absolute value of the corresponding interaction coefficient in the climate dimension interaction matrix is ​​taken as the effective interaction coefficient of the corresponding road segment node pair. If the determination of directional consistency indicates a change in opposite directions, the negative of the absolute value of the corresponding interaction coefficient in the climate dimension interaction matrix is ​​taken as the effective interaction coefficient of the corresponding road segment node pair. If the determination of directional consistency indicates no interaction, the effective interaction coefficient of the corresponding road segment node pair is zero. All effective interaction coefficients corresponding to the same road segment node pair are summed to obtain the total interaction effect of each road segment node pair. Each total interaction effect is normalized and then incremented by one to obtain the multi-dimensional interaction correction coefficient of each road segment node pair. The multi-dimensional interaction correction coefficient is used to correct the basic adaptation time to reflect the comprehensive impact of multi-dimensional climate change.

[0117] The cumulative adaptation effect is introduced, and the cumulative adaptation correction coefficient of each road segment node pair is calculated. The cumulative adaptation effect refers to the phenomenon that after users pass through multiple climate transition destinations in the progressive climate adaptation route, their immune system is gradually activated and their ability to adapt to subsequent climate change is gradually enhanced.

[0118] Specifically, based on the order of each road segment node pair in the progressive climate adaptation route, all road segment node pairs are sequentially assigned incremental road segment numbers; where the range of values ​​for the road segment numbers is... , The number of road segment node pairs is defined; a cumulative adaptive decay function is defined to describe the gradual increase in user adaptability as the road segment number increases; specifically, the cumulative adaptive decay function is an exponential decay form with the cumulative decay base as the base and the road segment number minus one as the exponent; wherein, the cumulative decay base is a value greater than zero and less than one, which is preset by those skilled in the art according to the actual situation; for example, the cumulative decay base is set to When the road segment number is 1, the cumulative adaptation correction coefficient is equal to 1, indicating that there is no cumulative adaptation effect in the first road segment; when the road segment number is 2, the cumulative adaptation correction coefficient is equal to... This indicates that the basic adaptation time for the second road segment can be shortened. .

[0119] For each road segment node pair, the corresponding comprehensive adaptation time is calculated based on the basic adaptation time, the multi-dimensional interaction correction coefficient, and the cumulative adaptation correction coefficient. Specifically, the basic adaptation time is multiplied sequentially by the multi-dimensional interaction correction coefficient and the cumulative adaptation correction coefficient to obtain the comprehensive adaptation time. For each road segment node pair, the corresponding comprehensive adaptation time is used as the minimum immune adaptation time for the climate transition destination corresponding to the subsequent node. The minimum immune adaptation time refers to the minimum stay time required for the user to complete basic climate adaptation at the climate transition destination, ensuring that the user's immune system has basically adapted to the current climate environment before moving to the next destination.

[0120] Methods for calculating the recommended length of stay in climate transition destinations include:

[0121] For each climate transition destination in the progressive climate adaptation route, the product of the corresponding shortest immune adaptation time and the preset health benefit gain coefficient is calculated sequentially to obtain the recommended stay time for each climate transition destination. The health benefit gain coefficient is a value greater than or equal to one and is preset by those skilled in the art based on actual conditions. The recommended stay time is used to reflect the suggested stay time for users to obtain better health recovery benefits in the climate transition destination, and the recommended stay time is given priority when time permits.

[0122] Methods for generating a stay duration configuration table include:

[0123] The minimum acclimatization time and recommended stay time for all climate transition destinations in the progressive climate adaptation route are summarized to generate a stay time configuration table; the stay time configuration table is used to support the subsequent health optimization module's optimization of travel time constraints and route adjustment.

[0124] Based on predefined user itinerary constraints, the progressive climate adaptation route and stay duration configuration table are optimized for health, and a progressive health and wellness tourism route is formed by combining them.

[0125] Methods for health optimization of the progressive climate adaptation route and stay duration configuration table include:

[0126] The user's travel needs information is obtained through a self-filled and uploaded travel needs information form. These constraints include, but are not limited to, expected departure date, expected arrival date, maximum travel duration, and time flexibility coefficient. The expected departure date is the date the user plans to depart from their place of residence; the expected arrival date is the date the user expects to arrive at the target wellness destination; the maximum travel duration is the longest acceptable travel time from departure to arrival at the target wellness destination; and the time flexibility coefficient indicates the user's flexibility in scheduling their travel time, ranging from zero to one. A higher time flexibility coefficient indicates a more flexible user's time requirements and a greater willingness to accept time adjustments; a lower time flexibility coefficient indicates a more stringent time requirements and a greater willingness to accept time adjustments.

[0127] Based on the stay duration configuration table, the recommended stay duration for all climate transition destinations in the progressive climate adaptation route is obtained; the recommended stay durations for all climate transition destinations are summed to obtain the total transition stay duration; the geographical distance of each road segment node pair is obtained, and the ratio between the geographical distance of each road segment node pair and the preset average daily travel distance is calculated to obtain the travel time for each road segment node pair; wherein, the geographical distance is calculated by calling the geographic information service interface based on the latitude and longitude coordinates of adjacent locations; the average daily travel distance is preset by those skilled in the art based on conventional travel methods; the travel time for all road segment node pairs is summed to obtain the total travel time; the sum of the total transition stay duration and the total travel time is calculated to obtain the initial travel time; wherein, the initial travel time is used to reflect the total time required for the user to complete the entire progressive climate adaptation route according to the recommended stay duration;

[0128] The expected travel time is calculated by calculating the difference between the expected arrival date and the expected departure date. This expected travel time is then compared to the maximum travel time, and the smaller of the two is selected as the available travel time. The initial travel time is then compared to the available travel time. If the initial travel time is less than or equal to the available travel time, the user's travel constraints are met, and no travel optimization is needed. The recommended stay duration for each climate transition destination is used as the corresponding optimized stay duration. If the initial travel time is longer than the available travel time, the user's travel constraints are not met, and the difference between the initial travel time and the available travel time is calculated to obtain the overtime. Based on the overtime and the time flexibility coefficient, a health optimization adjustment strategy is determined. This strategy includes a stay duration compression strategy and a route node simplification strategy.

[0129] If the timeout duration is less than or equal to the preset mild timeout threshold, a stay duration compression strategy is adopted for health optimization. Specifically, the ratio between the timeout duration and the total transition stay duration is calculated to obtain the basic compression ratio. The basic compression ratio is multiplied by the time elasticity coefficient and then incremented by one to obtain the stay duration compression ratio. For each climate transition destination in the progressive climate adaptation route, the ratio between the corresponding recommended stay duration and the stay duration compression ratio is calculated to obtain the compressed stay duration. The compressed stay duration is compared with the corresponding minimum immune adaptation duration. If the compressed stay duration is greater than or equal to the minimum immune adaptation duration, the compressed stay duration is used as the optimized stay duration for the corresponding climate transition destination. If the compressed stay duration is less than the minimum immune adaptation duration, the minimum immune adaptation duration is used as the optimized stay duration for the corresponding climate transition destination. The optimized stay durations for each climate transition destination in the progressive climate adaptation route are summarized to construct a health-optimized stay duration configuration table. It should be noted that the mild timeout threshold is preset by those skilled in the art based on actual conditions.

[0130] If the timeout duration exceeds the preset mild timeout threshold, a route node simplification strategy is adopted for health optimization. Specifically, for each climate transition destination in the progressive climate adaptation route, the corresponding adaptation necessity and transition importance are calculated sequentially. The adaptation necessity is calculated by normalizing the shortest immune adaptation time. The transition importance is calculated by obtaining the future climate difference between the climate transition destination and its predecessor nodes and its successor nodes from the destination climate gradient relationship network, and then... The preceding and subsequent climate differences are labeled as pre- and post-climate differences. The sum of the pre- and post-climate differences is calculated to obtain the transition span value. The transition span value is normalized to obtain the transition importance. Corresponding importance weights are set for adaptation necessity and transition importance, and a weighted sum is calculated based on the importance weights to obtain the node importance score for each climate transition destination. The node importance score is used to reflect the importance of the climate transition destination in the gradual climate adaptation route. Each importance weight is preset by those skilled in the art according to the actual situation.

[0131] The node simplification judgment process is defined as follows: All climate transition destinations are sorted in ascending order according to their corresponding node importance scores to obtain a node importance sequence; the climate transition destination with the lowest node importance score that has not been marked as a node to be simplified is selected from the node importance sequence and marked as a node to be simplified; the preceding and following nodes of the node to be simplified are obtained and marked as the preceding simplified node and the following simplified node, respectively; the future climate difference between the preceding and following simplified nodes is obtained from the destination climate gradient relationship network and marked as the cross-climate difference; the cross-climate difference is compared with the single climate cross threshold; if the cross-climate difference is less than or equal to the single climate cross threshold, the node to be simplified is removed from the progressive climate adaptation route, and the preceding and following simplified nodes are connected; if the cross-climate difference is greater than the single climate cross threshold, the corresponding node to be simplified is retained.

[0132] Repeat the node simplification judgment process until the simplified travel time corresponding to the progressive climate adaptation route (i.e., the initial travel time corresponding to the simplified progressive climate adaptation route) is less than or equal to the available travel time, or all climate transition destinations in the node importance sequence have been judged; if the simplified travel time corresponding to the progressive climate adaptation route is still greater than the available travel time, then continue to use the stay time compression strategy for health optimization of the progressive climate adaptation route; if the stay time compression strategy still cannot meet the user's travel constraints, then issue a prompt message to the user, suggesting that the user extend the maximum travel time or adjust the target health and wellness destination.

[0133] By combining the health-optimized, gradual climate adaptation route with the health-optimized stay duration configuration table, a gradual health and wellness tourism route can be formed.

[0134] This embodiment collects users' health checkup data, physiological monitoring data, and historical travel health response records. It uses a nonlinear regression algorithm to fit the individual user's immune adaptation curve and calculates the user's adaptation rate parameters across five climate dimensions: temperature, humidity, air pressure, altitude, and ultraviolet radiation. This achieves precise quantitative modeling of differences in immune adaptation among different users, effectively overcoming the shortcomings of existing technologies that use uniform recommendation standards and ignore individual differences. By constructing a destination climate gradient relationship network, it systematically analyzes the multidimensional climate differences and climate gradient levels between the user's residence and each candidate tourist destination, as well as among the candidate tourist destinations, providing data support for the scientific planning of climate transition paths. By calculating the user's single climate crossing threshold, it filters candidate transition destinations located within the climate transition zone and uses a step-by-step recursive algorithm to dynamically plan a gradual climate adaptation route from the user's residence to the target health and wellness destination, effectively avoiding sudden exposure to extreme temperatures. The study addresses the immune stress and health risks caused by significant climate differences, aiming to achieve a smooth transition in the climate adaptation process. It introduces multi-dimensional interaction and cumulative adaptation effects, comprehensively considering the superimposed or offsetting effects of simultaneous changes in multiple climate dimensions, as well as the enhanced adaptability of users' immune systems as they gradually activate during continuous climate transitions. This allows for precise calculation of the minimum immune adaptation time and recommended stay duration for users at each climate transition destination, achieving accurate matching and optimization between individual user adaptation rates and destination stay durations. This avoids insufficient adaptation due to insufficient stay time or wasted time and economic costs due to excessive stay time. Furthermore, it employs stay duration compression and route node simplification strategies to optimize the gradual climate adaptation route and stay duration configuration table, maximizing user health adaptation effects while meeting time constraints. Ultimately, this results in a recommended gradual health and wellness tourism route that balances health benefits and itinerary feasibility.

[0135] Example 2

[0136] Please see Figure 2 As shown in the figure, the parts not described in detail in this embodiment are described in Embodiment 1. A personalized climate tourism route recommendation system for health optimization is provided, including an immune adaptation module, a climate analysis module, a route planning module, a duration assessment module, and a health optimization module; the modules are connected by wired and / or wireless means to realize data transmission between the modules.

[0137] The immune adaptation module is used to collect users' health adaptation data, analyze the immune adaptation ability curves and adaptation rate parameters of users to different climate and environmental changes based on the health adaptation data, and construct a user's immune adaptation ability model.

[0138] The climate analysis module is used to acquire climate characteristic data of the user's residence and each candidate tourist destination, dynamically analyze the multidimensional climate differences between the user's residence and each candidate tourist destination, and among each candidate tourist destination, and construct a destination climate gradient relationship network.

[0139] The route planning module is used to determine the target health and wellness destination and the climate transition destination among the candidate tourist destinations based on the user's immune adaptability model and the destination climate gradient relationship network, and dynamically plan a gradual climate adaptation route from the user's residence to the target health and wellness destination.

[0140] The duration assessment module is used to calculate the minimum immune adaptation duration and recommended stay duration for users in each climate transition destination based on the multidimensional climate difference between each climate transition destination in the progressive climate adaptation route and combined with the user immune adaptation capability model, and generate a stay duration configuration table.

[0141] The health optimization module is used to optimize the configuration table of progressive climate adaptation routes and stay durations based on predefined user itinerary constraints, and to form progressive health and wellness tourism routes by combining them.

[0142] Example 3

[0143] This application also provides an electronic device. The electronic device may include one or more processors and one or more memories. The memories store computer-readable code that, when executed by the one or more processors, can perform a personalized climate travel route recommendation method for health optimization as described above.

[0144] The method or system according to the embodiments of this application can also be implemented using the architecture of the electronic device shown in this application. The electronic device may include a bus, one or more CPUs, ROM, RAM, a communication port connected to a network, input / output, a hard disk, etc. The storage device in the electronic device, such as ROM or hard disk, may store a personalized climate travel route recommendation method for health optimization provided in this application. Furthermore, the electronic device may also include a user interface. Of course, the architecture shown in this application is merely exemplary; when implementing different devices, one or more components of the electronic device shown in this application may be omitted according to actual needs.

[0145] Example 4

[0146] One embodiment of this application discloses a computer-readable storage medium. The computer-readable storage medium stores computer-readable instructions. When executed by a processor, the computer-readable instructions can perform a personalized climate travel route recommendation method for health optimization according to an embodiment of this application, as described with reference to the above figures. The storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. Volatile memory may include, for example, random access memory (RAM) and cache memory. Non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc.

[0147] Furthermore, according to embodiments of this application, the processes described in the above-referenced flowcharts can be implemented as computer software programs. For example, this application provides a non-transitory machine-readable storage medium storing machine-readable instructions that can be executed by a processor to perform instructions corresponding to the method steps provided in this application, such as a personalized climate travel route recommendation method for health optimization. When this computer program is executed by a central processing unit (CPU), it performs the functions defined in the method of this application.

[0148] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0149] All formulas in this manual are dimensionless and calculated numerically. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0150] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. A personalized climate tourism route recommendation method for health optimization, characterized in that, include: Collect users' health adaptation data, analyze the immune adaptation curves and adaptation rate parameters of users to different climate and environmental changes based on the health adaptation data, and construct a user immune adaptation capacity model. Acquire climate characteristic data of user residence and each candidate tourist destination, dynamically analyze the multidimensional climate differences between user residence and each candidate tourist destination, and among each candidate tourist destination, and construct a destination climate gradient relationship network; among which, the multidimensional climate differences include temperature differences, humidity differences, air pressure differences, elevation differences, ultraviolet radiation differences, and future climate differences. Based on the user's immune adaptability model and the destination climate gradient relationship network, the target health and wellness destination and climate transition destination among the candidate tourist destinations are identified, and a gradual climate adaptation route from the user's residence to the target health and wellness destination is dynamically planned. The methods for dynamic programming of gradual climate adaptation pathways include: The user's residence is used as the current starting point, and an empty sequence of climate transition destinations is created. If no climate transition destination exists, the progressive climate adaptation route is directly from the current starting point to the target health and wellness destination. If a climate transition destination exists, a route planning loop is defined. The route planning loop is as follows: Based on the user's immune adaptability model, calculate the user's single climate crossing threshold; from all climate transition destinations, select those whose future climate difference from the current starting point is less than or equal to the single climate crossing threshold and which are not yet included in the climate transition destination sequence as reachable transition destinations, and combine them to form the current reachable candidate set; if the current reachable candidate set is not empty, for each reachable transition destination in the current reachable candidate set, sequentially obtain the corresponding forward climate difference and backward climate difference, and calculate the corresponding forward safety and backward proximity; calculate the transition suitability score for each reachable transition destination, and calculate the recursive optimal score for each reachable transition destination based on the forward safety, backward proximity, and transition suitability scores; select the reachable transition destination with the highest recursive optimal score as the preferred transition destination, add the preferred transition destination to the end of the climate transition destination sequence, and update the current starting point as the preferred transition destination. Repeat the route planning loop until the backward climate difference of the preferred transition destination is less than or equal to the single climate crossing threshold, then stop the route planning loop; generate a progressive climate adaptation route based on the user's residence, the sequence of climate transition destinations and the target health and wellness destination. Based on the multidimensional climate difference between various climate transition destinations in the progressive climate adaptation route, and combined with the user's immune adaptation ability model, the shortest immune adaptation time and recommended stay time for users in each climate transition destination are calculated, and a stay time configuration table is generated. Based on predefined user itinerary constraints, the progressive climate adaptation route and stay duration configuration table are optimized for health, and a progressive health and wellness tourism route is formed by combining them.

2. The personalized climate tourism route recommendation method for health optimization according to claim 1, characterized in that, Health adaptation data includes immune function indicators and health response records; Methods for analyzing users' immune adaptation curves to different climatic and environmental changes include: For each health response record, calculate the climate difference vector for the user under different climate differences; for each climate difference vector, calculate the corresponding comprehensive climate difference degree in turn; for each health response record, calculate the corresponding health response intensity in turn; pair the comprehensive climate difference degree and health response intensity of each health response record to form a climate difference-health response data pair; perform curve fitting on all climate difference-health response data pairs to obtain the user's immune adaptability curve. Methods for analyzing users' adaptation rate parameters to different climate and environmental changes include: All health response records are categorized to obtain the adaptation category for each health response record; for each health response record in each adaptation category, the basic adaptation rate for each climate dimension is calculated; based on the immune function index data, the user's immune regulation coefficient is calculated; the basic adaptation rate for each climate dimension is multiplied by the immune regulation coefficient to obtain the adaptation rate parameter for each climate dimension. The method for constructing a user immune adaptability model is as follows: combine the immune adaptability curve with each adaptation rate parameter to construct the user immune adaptability model.

3. The personalized climate tourism route recommendation method for health optimization according to claim 2, characterized in that, Methods for dynamically analyzing multidimensional climate variability include: The user's residence is aggregated with all candidate tourist destinations to form a location set; each pair of different locations in the location set is paired to form multiple location pairs; for each location pair in the location pair set, the corresponding multidimensional climate difference is calculated based on the corresponding climate characteristic data. Methods for constructing destination climate gradient relationship networks include: The user's residence and all candidate tourist destinations are treated as nodes. An edge is established between the two nodes corresponding to each pair of locations. For each edge, the corresponding edge attributes are calculated in sequence. The edge attributes include multidimensional climate difference degree and climate gradient level. The climate feature data corresponding to the user's residence and all candidate tourist destinations are respectively used as the node attributes of the corresponding nodes. Based on all nodes, edges, edge attributes and node attributes, a destination climate gradient relationship network is constructed.

4. The personalized climate tourism route recommendation method for health optimization according to claim 3, characterized in that, Methods for identifying target wellness and health destinations include: Obtain user data on health and wellness travel needs, filter out candidate travel destinations that match the health and wellness travel needs from all candidate travel destinations, and mark them as secondary screening destinations; For each rescreened tourist destination, the corresponding health adaptation score and adaptation potential score are calculated sequentially based on the future climate difference between the destination and the user's place of residence and the adaptation rate parameter. Based on the preset adaptation weight, the health adaptation score and adaptation potential score of each rescreened tourist destination are weighted and summed to obtain the health and wellness adaptation score of each rescreened tourist destination. The health and wellness suitability scores of all the re-screened tourist destinations were compared, and the candidate tourist destination with the highest health and wellness suitability score was selected as the target health and wellness destination.

5. The personalized climate tourism route recommendation method for health optimization according to claim 4, characterized in that, Methods for identifying climate transition destinations include: Obtain the future climate difference between the user's residence and the target health and wellness destination, and mark it as the direct climate difference; compare the direct climate difference with the single climate crossing threshold, and determine whether a climate transition destination needs to be set based on the comparison results. If a climate transition destination needs to be set, obtain all the climate difference degrees between the user's residence and the target health and wellness destination, and combine them to obtain a climate difference vector; calculate the ideal climate gradient interval based on the direct climate difference degree and the single climate crossing threshold. All candidate tourist destinations that are not the target health and wellness destinations are marked as candidate transitional destinations. All climate difference degrees between each candidate transitional destination and the user's residence are obtained and combined to form a climate offset vector. For each climate difference degree in the climate offset vector corresponding to each candidate transitional destination, it is determined whether two judgment conditions are met simultaneously, and the corresponding candidate transitional destination is retained or deleted based on the judgment result. For each climate difference degree in the climate offset vector corresponding to each candidate transitional destination, the corresponding gradient deviation component is calculated sequentially according to the ideal climate gradient interval. Based on the gradient deviation component, the gradient matching degree of each candidate transitional destination is calculated. Based on the gradient matching degree, calculate the transition suitability score for each candidate transition destination; compare the transition suitability scores of all candidate transition destinations with the preset transition score thresholds, and select candidate transition destinations with transition suitability scores greater than the transition score thresholds as climate transition destinations.

6. The personalized climate tourism route recommendation method for health optimization according to claim 5, characterized in that, Methods for calculating the shortest immune adaptation time for climate transition destinations include: Based on the progressive climate adaptation route, each pair of adjacent locations is sequentially obtained and marked as a road segment node pair; where each road segment node pair includes a predecessor node and a successor node; the longest adaptation time of each road segment node pair is calculated and marked as the basic adaptation time; Multi-dimensional interaction effects are introduced, and the interaction effects of multi-dimensional climate change are analyzed for each road segment node pair in turn. The multi-dimensional interaction correction coefficients of each road segment node pair are calculated. Cumulative adaptation effects are introduced, and the cumulative adaptation correction coefficients of each road segment node pair are calculated. For each road segment node pair, the corresponding comprehensive adaptation time is calculated based on the basic adaptation time, multi-dimensional interaction correction coefficient, and cumulative adaptation correction coefficient. For each road segment node pair, the corresponding comprehensive adaptation time is used as the shortest immune adaptation time for the climate transition destination corresponding to the subsequent node.

7. The personalized climate tourism route recommendation method for health optimization according to claim 6, characterized in that, Methods for health optimization of the progressive climate adaptation route and stay duration configuration table include: Obtain user travel constraints, including expected departure date, expected arrival date, maximum travel duration, and time flexibility coefficient; sum the recommended stay durations for all climate transition destinations in the progressive climate adaptation route to obtain the total transition stay duration; obtain the geographical distances of each road segment node pair, and calculate the travel time for each road segment node pair based on the geographical distances of each road segment node pair and the preset average daily travel distance; calculate the initial travel duration based on the travel time of all road segment node pairs and the total transition stay duration. Calculate the expected travel duration based on the expected arrival and departure dates; compare the expected travel duration with the maximum travel duration, and select the smaller value as the available travel duration; then compare the initial travel duration with the available travel duration; if the initial travel duration is less than or equal to the available travel duration, use the recommended stay duration for each climate transition destination as the corresponding optimized stay duration; if the initial travel duration is longer than the available travel duration, calculate the overtime based on the initial travel duration and the available travel duration, and determine the health optimization adjustment strategy based on the overtime duration and the time flexibility coefficient; the health optimization adjustment strategy includes a stay duration compression strategy and a route node simplification strategy.

8. The personalized climate tourism route recommendation method for health optimization according to claim 7, characterized in that, If the timeout duration is less than or equal to the preset mild timeout threshold, a stay duration compression strategy is adopted for health optimization: The stay duration compression ratio is calculated based on the timeout duration, the total transition stay duration, and the time flexibility coefficient; the compressed stay duration for each climate transition destination is calculated based on the recommended stay duration and the stay duration compression ratio, and compared with the corresponding minimum immune adaptation duration; if the compressed stay duration is greater than or equal to the minimum immune adaptation duration, the compressed stay duration is used as the optimized stay duration for the corresponding climate transition destination; if the compressed stay duration is less than the minimum immune adaptation duration, the minimum immune adaptation duration is used as the optimized stay duration for the corresponding climate transition destination; the optimized stay durations for each climate transition destination in the progressive climate adaptation route are summarized to construct a health-optimized stay duration configuration table. If the timeout duration exceeds the mild timeout threshold, a route node simplification strategy is adopted for health optimization: for each climate transition destination in the progressive climate adaptation route, the corresponding adaptation necessity and transition importance are calculated sequentially; the adaptation necessity and transition importance are weighted and summed based on the preset importance weight to obtain the node importance score of each climate transition destination. Define a node simplification judgment process and repeat the process until the simplified travel time corresponding to the progressive climate adaptation route is less than or equal to the available travel time, or all climate transition destinations in the node importance sequence have been judged. If the simplified travel time corresponding to the progressive climate adaptation route is still greater than the available travel time, then the progressive climate adaptation route will continue to be optimized using a stay duration compression strategy.

9. A personalized climate tourism route recommendation system for health optimization, implementing the personalized climate tourism route recommendation method for health optimization as described in any one of claims 1-8, characterized in that, include: The immune adaptation module is used to collect users' health adaptation data, analyze the immune adaptation ability curves and adaptation rate parameters of users to different climate and environmental changes based on the health adaptation data, and construct a user's immune adaptation ability model. The climate analysis module is used to acquire climate characteristic data of the user's residence and each candidate tourist destination, dynamically analyze the multidimensional climate differences between the user's residence and each candidate tourist destination, and among each candidate tourist destination, and construct a destination climate gradient relationship network. The route planning module is used to determine the target health and wellness destination and the climate transition destination among the candidate tourist destinations based on the user's immune adaptability model and the destination climate gradient relationship network, and dynamically plan a gradual climate adaptation route from the user's residence to the target health and wellness destination. The duration assessment module is used to calculate the minimum immune adaptation duration and recommended stay duration for users in each climate transition destination based on the multidimensional climate difference between each climate transition destination in the progressive climate adaptation route and combined with the user immune adaptation capability model, and generate a stay duration configuration table. The health optimization module is used to optimize the configuration table of progressive climate adaptation routes and stay durations based on predefined user itinerary constraints, and to form progressive health and wellness tourism routes by combining them.

Images