Dynamic tourism recommendation data analysis method and system

Abstract

The invention relates to the technical field of data processing, in particular to a dynamic tourism recommendation data analysis method and system, and the method comprises the following steps: based on tourist mobile terminal and scenic spot monitoring terminal data, combing tourist dynamic tracks, structured node arrival and departure moments and spatial distribution, and analyzing traffic pressure and resource limitation conditions; and adjusting a node sequence and a connection arrangement, screening travel conflicts and resource aggregation, and outputting a time-sharing recommendation path group. According to the method, tourist journeys and scenic spot multi-source states are dynamically collected and processed in a structured mode in the whole process, node arrival and departure information in a time sequence and scenic spot space capacity are mapped and fused, and dynamic retrieval of node resource pressure and traffic accessibility is achieved; space limited nodes and path sequence adjustment are efficiently completed according to real-time changing resources and travel elastic intervals, time-sharing path output generates a diversified access sequence for resource distribution and passenger flow trend, and the problems of conflicts and resource imbalance caused by a single static rule are avoided.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a dynamic tourism recommendation data analysis method and system. Background Technology

[0002] Data processing involves the collection, storage, organization, analysis, and utilization of various types of data. This technological field is widely used in multiple application scenarios such as internet services, artificial intelligence, intelligent recommendation systems, and information retrieval and management. Traditional dynamic tourism recommendation data analysis methods refer to techniques that collect and preliminarily analyze relevant data based on dynamic factors such as user location, behavioral habits, and travel history, and then use rule-based matching to make recommendations. This typically involves constructing user interest models or attraction preference models by setting static recommendation rules, keyword association, or user rating ranking, and then making recommendations based on the user's current location and time information, combined with pre-set travel routes and attraction information in an existing database.

[0003] Traditional dynamic tourism recommendations only involve user information collection and rule matching, lacking continuous linkage between the dynamic nature of the itinerary and changes in the spatiotemporal status of scenic spots. The recommendations are based on static model outputs and cannot dynamically identify actual conflicts between nodes within the route caused by traffic delays, adjustments to the opening of scenic spots, or changes in resource occupation. The connection between the arrival and departure times of nodes is not dynamically verified, which can easily lead to a disconnect between the itinerary suggestions and the actual scenario, resulting in problems such as tourist gatherings, node congestion, and unexecutable routes. It lacks the data processing and recommendation capabilities based on spatiotemporal evolution. Summary of the Invention

[0004] To address the technical problems existing in the prior art, embodiments of the present invention provide a dynamic tourism recommendation data analysis method and system. The technical solution is as follows: On the one hand, a dynamic tourism recommendation data analysis method is provided, including the following steps: S1: Based on the tourist's mobile terminal, analyze the reported departure time and current location, combine the opening hours and reception capacity of the scenic area monitoring terminal, determine the matching between the tourist's itinerary and the scenic area's opening, sort out the arrival and departure times of nodes, and obtain the tourist's time-series trajectory set; S2: Based on the tourist time-series trajectory set, retrieve the departure time of each node, analyze the distribution of tourists in the scenic area during the same period, compare the traffic process between nodes, and according to the path order, structure the spatial distribution of nodes and the interval between tourists to obtain dynamic resource distribution data. S3: Based on the dynamic distribution data of the resources, analyze the traffic pressure and dwell restrictions during the movement period between nodes, screen flexible sections, carry out spatial and traffic allocation, identify doubly restricted areas, and obtain spatially restricted node groups; S4: Based on the spatially constrained node group, adjust the nodes in the behavior sequence to the departure time, analyze the connection between the preceding and following nodes, compare the resource pressure of non-conflict sections, and reorder the access order according to the spatial and traffic conditions to obtain the optimized node time sequence chain. S5: Based on the node optimization time sequence chain, screen the traffic intervals of departure and arrival at each node, analyze the spatial distribution and reception capacity of each time period, determine the itinerary conflict and resource aggregation, sort out the node access and stay arrangements, and obtain the time-sharing recommended route group.

[0005] On the other hand, the tourist time-series trajectory set includes departure reference time, node arrival timetable, and node departure timetable; the resource dynamic distribution data includes node passenger flow occupancy status, node park entry capacity status, and node dwell capacity status; the space-constrained node group includes congested entry nodes, congested departure nodes, and nodes with limited dwell time; the node optimized time-series chain includes a node access order table, a node arrival / departure arrangement table, and an adjacent node connection timetable; and the time-sharing recommended path group includes time-sharing access path information, time-sharing node dwell information, and time-sharing path switching information.

[0006] On the other hand, the steps for obtaining the tourist time-series trajectory set are as follows: S101: Based on the tourist's mobile terminal, analyze the reported departure time and current location parameters, determine the consistency of the device identification number, combine the continuous positioning data sequence, and sort all positioning coordinates by equal time interval extraction method, and arrange them in the order of extraction time to obtain the time series positioning group. S102: Based on the time series positioning group, compare the spatial position of each end coordinate point with the node set by the scenic area monitoring terminal, synchronize the matching node number, retrieve the opening time period and reception capacity status of each node, identify the overlap between the end time of the trajectory segment and the opening time period of the node, determine the reception status of the node, and obtain the node access permission set. S103: Based on the node access permission set, sort the segment numbers that meet the entry conditions, analyze the start and end times of the corresponding trajectory segments, pair the end and start times of adjacent segments in the sorting sequence, and obtain the tourist time-series trajectory set.

[0007] On the other hand, the specific steps for obtaining the dynamic distribution data of the resources are as follows: S201: Based on the tourist time-series trajectory set, analyze the arrival and departure times of each node, determine the continuity of the start and end times of each visiting node in the path, filter the dwell period and movement interval between adjacent nodes in the path, optimize the data order according to the time sequence relationship in the path, and obtain the time-series connection sequence. S202: Based on the time sequence, compare the tourist location data recorded by the scenic area monitoring terminal in the same time period, determine the distribution density of tourists within the node space, filter the node numbers with dense tourists, and label the nodes and their corresponding time period density status to the original node data to obtain a spatial clustering label set. S203: Based on the spatial clustered annotation set, analyze the arrival and departure times of adjacent nodes, calculate the spatial distance and movement interval of node geographic coordinates, determine the spatial distribution and visitor interval characteristics between nodes, and organize all node and visitor information in a structured manner to obtain dynamic resource distribution data.

[0008] On the other hand, the specific steps for obtaining the spatially confined node group are as follows: S301: Based on the dynamic distribution data of the resources, analyze the traffic congestion and stay restriction status during the movement period between access nodes, determine the passenger flow occupancy status and stay carrying capacity status of adjacent nodes, compare the passenger flow distribution and stay pressure changes within the movement section, identify the node sections where passage is obstructed and stay is restricted, and obtain restricted section identification data. S302: Based on the restricted segment identification data, filter the flexible segments with adjustment windows, analyze the adjustability characteristics of the corresponding time period of the flexible segments, compare the overlap between the flexible segments and the restricted segments in the time sequence, determine the substitution space of the flexible segments for the restricted segments, set the flexible segments with substitution as switching relationships, and obtain the flexible switching mapping group. S303: Based on the aforementioned flexible switching mapping group, combined with tourist movement trajectory data and scenic area node resource distribution trends, analyze the conflict status between nodes within a time period, determine the passenger flow aggregation status and traffic conditions of conflicting nodes, compare the overlap range of resource-restricted and traffic-restricted nodes, and obtain the spatially restricted node group.

[0009] On the other hand, the specific steps for obtaining the node optimized time-series chain are as follows: S401: Based on the spatially constrained node group, analyze the arrival and departure times of each node in the behavior sequence, determine the constrained time period of the node in the path time sequence, compare the original arrival and departure times of the node with the connection logic of adjacent nodes, identify the node time combination that needs to be adjusted, and obtain the time sequence adjustment factor set. S402: Based on the time-series adjustment factor set, determine the connection status between the preceding and following nodes, compare the traffic and passage parameters corresponding to the arrival and departure intervals of adjacent nodes, filter the node segments with connection time intervals less than a preset safety threshold, adjust the node order and association status of the segments, aggregate and rearrange the data, and obtain the connection conflict mapping information. S403: Based on the connection conflict mapping information, compare it with the resource pressure of the non-conflict section recorded by the server, determine the passenger flow occupancy status and the remaining capacity for entry into the park of the non-conflict section node, reorganize the connection time information of adjacent nodes, and obtain the node optimized time sequence chain.

[0010] On the other hand, the specific steps for obtaining the time-sharing recommended path group are as follows: S501: Based on the node optimization time chain, screen the departure time of each access node and the arrival time of the next node, calculate the traffic interval between nodes, determine the impact of traffic interval on path continuity, identify node combinations that cause connection conflicts due to intervals less than a first preset threshold or greater than a second preset threshold, and obtain a traffic connection anomaly index. S502: Based on the traffic connection anomaly index, determine the spatial distribution and reception capacity of the node in the time period, compare the passenger flow occupancy status and spatial carrying capacity of each node, filter the node numbers with obvious resource aggregation risk, and integrate the spatial and time period characteristics of each node to obtain resource aggregation characteristic information. S503: Based on the resource aggregation feature information, analyze the continuity of node sorting and the accessibility of dwelling arrangements, adjust the node order and arrival and departure arrangements, optimize the spatial connection relationship of all nodes, and obtain time-sharing recommended path groups.

[0011] On the other hand, the scenic area monitoring terminal refers to the equipment installed in various areas, entrances and nodes of the scenic area to collect data on the scenic area's opening status, number of people in the park, visitor flow and resource carrying capacity in real time. The tourist itinerary refers to the time arrangement of tourists' departure, arrival, sightseeing, stay and departure at different stages of the tourism process.

[0012] On the other hand, the "openness of the scenic area" refers to the state of the scenic area or attraction being open to the public at a certain time, the "nodes" refer to the various tourist destinations in the tourist's itinerary, and the "traffic process" refers to the travel process experienced by the tourist from one visit node to the next.

[0013] On the other hand, a dynamic tourism recommendation data analysis system is provided, which is applied to dynamic tourism recommendation data analysis methods, including: The trip trajectory construction module is based on the tourist's mobile terminal. It analyzes the reported departure time and current location, combines the opening hours and reception capacity of the scenic area monitoring terminal, determines the matching between the tourist's trip and the scenic area's opening, sorts out the arrival and departure times of nodes, and obtains the tourist's time-series trajectory set. Based on the tourist time-series trajectory set, the resource distribution association module retrieves the time from each node to the departure time, analyzes the distribution of tourists in the scenic area during the same period, compares the traffic process between nodes, and structures the spatial distribution of nodes and tourist intervals according to the path order to obtain dynamic resource distribution data. Based on the dynamic distribution data of the resources, the restricted node allocation module analyzes the traffic pressure and dwell restrictions during the movement period between nodes, filters flexible sections, performs spatial and traffic allocation, identifies doubly restricted areas, and obtains spatially restricted node groups. The temporal chain reordering module, based on the spatially constrained node group, adjusts the nodes in the behavior sequence to the departure time, analyzes the connection between the preceding and following nodes, compares the resource pressure of non-conflict sections, and reorders the access order according to spatial and traffic conditions to obtain the optimized temporal chain of nodes. The time-sharing route generation module optimizes the time sequence chain based on the nodes, screens the traffic intervals of departure and arrival at each node, analyzes the spatial distribution and reception capacity of each time period, judges the itinerary conflicts and resource aggregation, sorts out the node access and stay arrangements, and obtains the time-sharing recommended route group.

[0014] The beneficial effects of the technical solutions provided in the embodiments of the present invention include at least the following: By dynamically collecting and structuring tourist itineraries and multi-source status of scenic spots throughout the entire process, the system maps and integrates the time-series node arrival and departure information with the spatial capacity of the scenic spot. This enables dynamic retrieval of node resource pressure and traffic accessibility. Adjustments to spatially limited nodes and path sequences are efficiently completed based on real-time changes in resource and itinerary flexibility. Time-segmented path output generates diverse access sequences based on resource distribution and passenger flow trends, forming dynamically adaptable recommended paths and avoiding conflicts and resource imbalances caused by single static rules. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart of the main steps of the present invention; Figure 2 This is a flowchart of steps S1 of the present invention; Figure 3 This is a flowchart of steps S2 of the present invention; Figure 4 This is a flowchart of steps S3 of the present invention; Figure 5 This is a flowchart of step S4 of the present invention; Figure 6 This is a flowchart of steps S5 of the present invention; Figure 7 This is a system block diagram of the present invention. Detailed Implementation

[0017] The technical solution of the present invention will now be described with reference to the accompanying drawings.

[0018] To make the technical problems, technical solutions and advantages of the present invention clearer, a detailed description will be given below in conjunction with the accompanying drawings and specific embodiments.

[0019] This invention provides a dynamic tourism recommendation data analysis method, such as... Figure 1 As shown, it includes the following steps: S1: Based on the tourist's mobile terminal, analyze the reported departure time and current location, verify the opening time and reception capacity of the scenic area monitoring terminal, determine the matching between the tourist's itinerary rhythm and stay time and the scenic area's opening status, and combine the tourist's arrival time and departure time at each node to sort out the dynamic trajectory of different time periods and obtain the tourist time sequence trajectory set. S2: Based on the tourist time-series trajectory set, retrieve the actual arrival and departure times of each access node, analyze the tourist distribution of the scenic area monitoring terminals within the same time period, compare the traffic movement process between nodes, and structurally associate the node spatial distribution and tourist interval data according to the actual path sequence to obtain dynamic resource distribution data. S3: Based on the dynamic distribution data of resources, analyze the traffic congestion and stay restriction status corresponding to the movement time between access nodes, screen flexible sections, combine tourist movement trajectory data and scenic spot node resource distribution trends, carry out spatial and traffic allocation for conflicts between nodes, identify areas with both resource and passage restrictions, and obtain spatially restricted node groups. S4: Based on the spatially constrained node group, adjust the arrival and departure times of the corresponding nodes in the behavior sequence, analyze the connection between the nodes before and after, compare the resource pressure of the non-conflict segment recorded by the server, and reorder the access order according to the node space and traffic status to obtain the optimized node time sequence chain. S5: Based on node optimization of time sequence chain, screen the traffic interval between the departure time of each access node and the arrival time of the next node, analyze the spatial distribution and reception capacity of each time period, determine whether there are travel conflicts and resource aggregation between nodes, sort out the access order and the status of the stops, and obtain time-sharing recommended path groups.

[0020] The visitor time-series trajectory set includes departure reference time, node arrival timetable, and node departure timetable. The dynamic resource distribution data includes node visitor occupancy status, node park entry capacity status, and node dwell capacity status. The space-constrained node group includes congested entry nodes, congested departure nodes, and nodes with limited dwell time. The node optimization time-series chain includes a node access sequence table, a node arrival / departure schedule table, and a timetable for connecting adjacent nodes. The time-sharing recommended path group includes time-sharing access path information, time-sharing node dwell information, and time-sharing path switching information.

[0021] In S1, "tourist mobile terminal" refers to the smart device used by tourists to operate mobile applications such as map software, tourism apps, and mini-programs, mainly smartphones and tablets. Tourists actively plan their itineraries, check in at their locations, and navigate using these devices. The relevant data is collected by the terminal and uploaded to the platform. "Scenic area monitoring terminal" refers to hardware devices installed in various areas, entrances, and nodes of the scenic area to collect real-time data on the scenic area's opening status, number of visitors, visitor flow, and resource carrying capacity. Examples include turnstiles, cameras, and visitor counters. "Tourist itinerary rhythm" refers to the time arrangement of tourists' departure, arrival, sightseeing, stay, and departure at different stages of the tour, specifically reflected in the speed of stay at different nodes and the order of routes. "Scenic area opening status" refers to the opening status of the scenic area or attraction at a certain time, including opening hours, maximum number of visitors allowed, and whether certain areas are open. "Each node" refers to the various sightseeing targets in the tourist's itinerary, which can be specific attractions, entrances, exits, service facilities, or other spatially identifiable targets. "Dynamic trajectory" refers to the spatiotemporal path record formed by tourists from departure to each node's stay and departure within a certain time period, providing a continuous description of the entire tourism process.

[0022] In S2, a visit node refers to each attraction or stop that a tourist plans to or actually visits during their trip, serving as the basic data unit for behavioral analysis. The transportation process refers to the travel process a tourist goes through from one visit node to the next, including walking, taking a vehicle, and transferring, which usually involves route planning and time calculation. The actual route sequence refers to the sequence of visit nodes arranged according to the tourist's actual or planned tour order, serving as the reference chain for subsequent time series calculations and recommendation optimization. The node spatial distribution refers to the number of tourists gathered at each visit node (attraction) and the space occupancy within the same time period, reflecting the resource distribution status. Tourist interval data refers to the spatial distance and temporal arrival and departure of different tourists and groups, reflecting the density and dynamic changes of tourist flow.

[0023] In S3, traffic congestion and restricted stay conditions refer to the slow movement or obstructed arrival caused by tourist concentration and limited roads or transportation tools within a certain time period or node, as well as the inability to stay normally within attractions due to high tourist density and resource scarcity; flexible segments refer to time intervals in recommended routes or tourist plans where arrival or departure times can be adjusted, allowing for appropriate advancement or postponement, providing allocation space for dynamic scheduling and resource balancing; tourist movement trajectory data refers to the continuous location and time information recorded and uploaded by tourists through mobile terminals during their visit, reflecting their actual travel routes and timing; scenic area node resource distribution trends refer to the changing patterns and trends of tourist gathering, resource consumption, and reception pressure at various nodes in the scenic area over time, serving as an important reference for adjusting recommended routes; spatial and traffic allocation refers to the optimized allocation of scenic area resources and tourist flow by adjusting tourist access order and arrival time in response to spatial density and traffic conditions; restricted areas refer to scenic areas where tourists have difficulty arriving, staying, or leaving smoothly due to limited resources, traffic congestion, or restrictions imposed by opening policies.

[0024] In S4, the behavioral sequence refers to the chronological data chain of a tourist's travel behavior from departure to each visiting node, stay, and departure, serving as a crucial basis for analyzing dynamic paths. "Previous and subsequent nodes" refers to two adjacent visiting nodes in a tourist's itinerary, with the previous node being the point just departed and the subsequent node being the point about to arrive. "Connectivity" refers to the connection time required for actual movement between two adjacent nodes, the path continuity, and the degree of matching with the arrival and departure arrangements of the next node. "Resource pressure in non-conflict sections" refers to the actual utilization load of scenic area resources in node sections without traffic or resource conflicts, providing a reference for node adjustments. "Visit order" refers to the order in which tourists arrive at nodes according to recommendations or plans, and is the core content of dynamic adjustments in tourism recommendation data analysis methods.

[0025] In S5, traffic interval refers to the time required for a tourist to move or wait from leaving one node to actually arriving at the next node; each time period refers to different time periods divided according to the order of time during the analysis process, with corresponding spatial, resource, and behavioral data within each time period; itinerary conflict refers to abnormal situations such as overlap, delays, and waiting caused by factors such as time arrangement, traffic restrictions, or saturation of scenic resources; resource aggregation refers to the phenomenon of increased spatial and service pressure caused by an excessive number of tourists and excessive resource occupation at the same time, node, or area.

[0026] like Figure 2 As shown, the specific steps for obtaining the tourist time-series trajectory set are as follows: S101: Based on the tourist's mobile terminal, analyze the reported departure time and current location parameters, determine the consistency of the device identification number, combine the continuous positioning data sequence, and sort all positioning coordinates by equal time interval extraction method, and arrange them in the order of extraction time to obtain the time series positioning group. The "Departure Time" field is extracted from the raw data. This field undergoes standard time format conversion, transforming text formats such as "9:15 AM," "1 PM," and "7 PM" into 24-hour format ("09:15:00," "13:00:00," and "19:00:00"), and uniformly formatted as (hour:minute:second) to avoid inconsistencies affecting subsequent comparisons. Next, the latitude and longitude data from the "Current Location" field is read, and data validity is verified, removing outliers. Values ​​with longitude greater than 180° or latitude greater than 90° are considered invalid and removed. Following this, the "Equipment Number" field undergoes a consistency check. The list of valid device numbers registered in the tourist identity management system is retrieved, and each uploaded data entry is verified against its corresponding device number. If a number is not found in the registered list, the data entry is considered unauthorized, marked as illegal data, and excluded from subsequent analysis. This completes the device numbering process. After filtering, the continuous location records corresponding to the current device are obtained and sorted in ascending order by the "upload time" field to form a continuous trajectory chain. A fixed sampling time interval is set on this trajectory chain, for example, sampling once every 60 seconds, that is, from the start time "09:00:00" to the end time "10:00:00", a total of 60 points need to be sampled. At each hourly sampling time, if there is no accurate location record, the point is supplemented by linear interpolation. For example, if data is known to exist at "09:05:00" and "09:06:00", but no record is known at "09:05:30", the average latitude and longitude of the two points is taken as the estimated result for that time. When the positioning interval in the trajectory chain exceeds 180 seconds or the missing rate exceeds 30%, the trajectory segment is marked as a low-quality segment and is not included in the subsequent sequence. All high-quality sampling points are arranged in chronological order to construct a structured time series positioning group, which serves as the basis for further node determination and path analysis.

[0027] S102: Based on the time series positioning group, compare the spatial position of each end coordinate point with the node set by the scenic area monitoring terminal, synchronize the matching node number, retrieve the opening time period and reception capacity status of each node, identify the overlap between the end time of the trajectory segment and the opening time period of the node, determine the reception status of the node, and obtain the node access permission set. The time and latitude / longitude data of the endpoint location points are extracted point by point, and then spatially matched with the spatial location list of each node in the scenic area system. Each scenic area node records its center coordinates and recognition radius. For example, if the center coordinates of a node are longitude 114.306 and latitude 30.593, and the recognition radius is set to 30 meters, the straight-line distance between each endpoint coordinate point and the node center point is calculated. If the distance does not exceed 30 meters, the node is considered to have been matched. After matching, the open time period set for the node is extracted. For example, if the node is set to be open from 08:30 to 17:30, and the endpoint location time is 10:00, then it is determined that the time is within the open time period, and the node is further extracted. Current reception data includes maximum capacity and real-time number of visitors. For example, if the maximum capacity is 1000 people and the real-time number is 940 people, a 95% capacity utilization rate is set as the reception threshold according to the judgment rules. If the real-time number does not exceed 950 people, the node is judged to have reception capacity, and the matching record is added to the access permission set. If the real-time number reaches 980 people, accounting for 98%, the record is judged to be in an overloaded state and removed from the permission set. If the endpoint matches multiple nodes successfully, the node number corresponding to the shortest distance is selected as the unique matching result. All successfully matched node numbers, times, and device identifiers that are allowed to enter will be integrated to form the node access permission set.

[0028] S103: Based on the node access permission set, sort the segment numbers that meet the entry conditions, analyze the start and end times of the corresponding trajectory segments, pair the end and start times of adjacent segments in the sorted sequence, and obtain the tourist time-series trajectory set. All segments are sorted in ascending order of their start time. For example, if segment number 001 starts at 08:40 and segment number 002 starts at 09:10, then segment 001 will be sorted first. After sorting, the end and start times of each pair of adjacent segments in the sorted sequence are extracted, and a continuity check is performed. For example, if segment 001 ends at 09:00 and segment 002 starts at 09:10, then there is a 10-minute interval between them. This interval will be recorded as a free movement or waiting period when constructing the trajectory chain later. If the end time of the first segment in a pair of segments is 09:20 and the start time of the second segment is 09:10, then it is judged as a time conflict, and the conflicting segment is marked as an abnormal chain. If the duration of any segment is less than 2 minutes, or the distance between nodes is less than 100 meters but the time taken exceeds 15 minutes, then it is considered a "short distance high consumption period". Such segments will be treated as abnormal segments when optimizing the time sequence chain later. The status information such as the number, matching node, start and end time, and whether there is a conflict of each trajectory segment is integrated to form a complete time sequence trajectory set of the tourist.

[0029] like Figure 3 As shown, the specific steps for obtaining dynamic resource distribution data are as follows: S201: Based on the tourist time-series trajectory set, analyze the arrival and departure times of each node, determine the continuity of the start and end times of each visited node in the path, filter the dwell period and movement interval between adjacent nodes in the path, optimize the data order according to the time sequence relationship in the path, and obtain the time-series connection sequence. Extract the arrival and departure times of all visited nodes in each trajectory, and construct time pairs by node number. For example, if node A arrives at 09:10:00 and departs at 09:25:00, its dwell time is 15 minutes. After listing the time pairs of each node in the complete trajectory, perform time sorting and verification on the node order within the same trajectory to determine if the node times show a monotonically increasing trend. If the arrival time of node B is earlier than the departure time of the previous node A (e.g., node B arrives at 09:20:00 while A departs at 09:25:00), it is considered a logical conflict, recorded as a path discontinuity segment, and added to the abnormal segment identification record table. After completing the path time continuity judgment, continue to filter the dwell period and movement interval between adjacent nodes. The dwell period refers to the time interval between the arrival and departure times of each node. The difference between the arrival and departure times is calculated. For example, if node C arrives at 10:00:00 and departs at 10:30:00, the dwell time is 30 minutes. The movement interval is the time interval between the departure time of the previous node and the arrival time of the next node. For example, if node C departs at 10:30:00 and node D arrives at 10:45:00, the movement interval is 15 minutes. For all paths, a dwell time column and a movement interval column are constructed. A filtering standard is set. If the dwell time of a certain segment is less than 5 minutes or the movement interval is greater than 30 minutes, it is marked as an abnormal segment. The number and location of the abnormal segment are automatically recorded. Then, according to the time order of the nodes, the nodes and their associated time information in the entire trajectory are reordered to ensure the continuity and structural integrity of the timeline. The node time sequence information that does not contain abnormal segments and has a reasonable time order is sorted out to form a time sequence connection sequence.

[0030] S202: Based on the time-series connection sequence, compare the tourist location data recorded by the scenic area monitoring terminal in the same time period, determine the distribution density of tourists within the node space, filter the node numbers with dense tourists, and label the nodes and the density status of the corresponding time period to the original node data to obtain the spatial cluster label set. The system retrieves visitor location data recorded by the scenic area's monitoring terminals. First, it extracts all visitor location records within the same time period, based on the arrival and departure times of each node in the time sequence. The location data is then categorized and summarized according to the spatial node it belongs to. For example, if node E has 250 visitors between 10:00 and 10:30, and the defined identification radius for this node is 30 meters, then the visitor density within this range is calculated to be 250 people. This density is estimated by dividing the total number of visitors by the node's area. If the node's area is 1200 square meters, then the density for this time period is 0.21 people per square meter. A density distribution threshold range is set: 0 to 0.1 is sparse, 0.1 to 0.25 is medium, and more than 0.25 is dense. Based on this classification standard, the node density status is judged to be medium. If the number of people in node F in the same time period is 500 and the area is 1600 square meters, then the density is 0.31 people per square meter, which is judged to be dense. The corresponding node number, time period, density value and density status are written into the spatial clustering annotation set. The annotation data is written back to the original node record, so that each node time period has an additional density status field and classification result on the basis of the original record, forming a spatial clustering annotation set.

[0031] S203: Based on the spatial clustered annotation set, analyze the arrival and departure times of adjacent nodes, calculate the spatial distance and movement interval of node geographic coordinates, determine the spatial distribution and tourist interval characteristics between nodes, and organize all node and tourist information in a structured manner to obtain dynamic resource distribution data; By comparing the arrival and departure times of adjacent nodes one by one, for example, node G arrives at 11:00 and departs at 11:20, while node H arrives at 11:35 and departs at 11:50, the movement interval between adjacent nodes is 15 minutes. The center coordinates of the nodes are extracted; for example, node G's coordinates are 114.310, 30.591, and node H's coordinates are 114.318, 30.589. The calculated spatial distance is 803 meters. Combining this with the movement time interval, the average speed of the tourists in this segment is calculated to be approximately 63 meters per minute. An interval feature judgment is then performed on this segment. If the distance is greater than 800 meters and the movement time is less than 12 minutes, then the segment is considered... For high-speed segments, if the distance is less than 200 meters but the time taken exceeds 20 minutes, it is considered a stationary segment. This judgment operation is repeated for each pair of nodes to generate records of the spatial interval and movement behavior characteristics of tourists in each segment. The tourist interval characteristics are further extracted, and the minimum interval distance of tourists within a node is defined as high-density gathering behavior if it is less than 2 meters, normal if it is 2 to 4 meters, and sparse distribution if it is more than 4 meters. The distribution status is obtained by combining the real-time tourist distribution images recorded by the monitoring terminal. Then, all node numbers, time periods, spatial distances, movement intervals, and tourist interval status are packaged and organized into structured dynamic resource distribution data, which is used as input for the next step of traffic allocation and route adjustment calculation.

[0032] like Figure 4 As shown, the specific steps for obtaining a spatially constrained node group are as follows: S301: Based on dynamic resource distribution data, analyze the traffic congestion and stay restriction status during the movement period between access nodes, determine the passenger flow occupancy status and stay capacity status of adjacent nodes, compare the passenger flow distribution and stay pressure changes within the movement segment, identify the node segments with obstructed passage and restricted stay, and obtain restricted segment identification data. Extract the node numbers, arrival times, departure times, and corresponding passenger flow occupancy and dwell capacity values ​​of adjacent access nodes in each trajectory. To determine traffic congestion, calculate the movement segment between the two nodes. From the start time to the end time of each movement segment, extract the total number of tourists on the segment and compare it with the maximum capacity of that segment. Set the traffic congestion judgment threshold as a capacity rate exceeding 85%. For example, if the maximum capacity of a segment is 200 people and the current number of people is 190, the current capacity rate is 95%, exceeding the 85% threshold. Record this segment as a traffic congestion segment. The criterion for limiting dwell time is the current number of dwellers at a node divided by the node's maximum capacity. The system compares the data, and if the percentage is higher than 90%, it is considered to be in a restricted stay state. For example, if node K has a maximum capacity of 500 people and the current number of people is 470, the percentage is 94%, then the stay state of this node is restricted. The system extracts all path segments between adjacent nodes and maps the passage status of each segment to the stay status. For continuous paths in the same mobile segment, if there is both traffic congestion and a restricted stay state at any node, then the segment is determined to be in a comprehensive restricted state. The path segment number, time period, start and end node information, and restriction type are marked as "traffic obstruction" or "stay restricted". The judgment result is recorded in the restricted segment identification data table and used as the input source for subsequent elastic scheduling calculations.

[0033] S302: Based on the restricted section identification data, filter the flexible sections with adjustment windows, analyze the adjustability characteristics of the corresponding time period of the flexible sections, compare the overlap between the flexible sections and the restricted sections in the time sequence, determine the substitution space of the flexible sections for the restricted sections, set the flexible sections with substitution as switching relationships, and obtain the flexible switching mapping group. Extract the start and end times and node numbers of all restricted segments. Traverse the remaining segments in the path that are not marked as restricted, and filter out segments with time fluctuations in the current tourist's movement trajectory as flexible segments. The elasticity criterion is that the node stay time exceeds 20 minutes and there are no conflicts between the preceding and following segments. For example, if a tourist stays at node L for 35 minutes, and the movement intervals before and after the node are both greater than 10 minutes, then this node segment is considered to have elasticity. Record the segment number and the adjustable time window. After extracting the movable time period corresponding to the flexible segment, compare it one by one with the restricted segments. The time periods are overlapped. If the start time of the adjustment space of the flexible segment is earlier than the start time of the restricted segment and the end time is later than the end time of the restricted segment, then the flexible segment is considered to be usable to replace the restricted segment. For example, if the time of the flexible segment is 10:00 to 10:45 and the time of the restricted segment is 10:15 to 10:35, the overlap length is 20 minutes, which is greater than the minimum replacement threshold of 10 minutes, and the replacement condition is met, a mapping relationship is established between the flexible segment number and the corresponding replaceable restricted segment number. This mapping relationship is recorded in the form of "restricted segment number - flexible segment number" key-value pairs and organized into a flexible switching mapping group.

[0034] S303: Based on the elastic switching mapping group, combined with tourist movement trajectory data and scenic area node resource distribution trends, analyze the conflict status between nodes within a time period, determine the passenger flow gathering status and passage conditions of conflict nodes, compare the overlap range of resource-constrained and passage-constrained nodes, and obtain the spatially constrained node group. The formula used to determine the passenger flow concentration and traffic conditions at conflict nodes is: ; Calculate the conflict clustering intensity value, compare the overlap range of resource-constrained and access-constrained nodes, and obtain the spatially constrained node group, where, Representative access node To node The intensity of conflict aggregation during the corresponding movement period Representative node To node The total number of tourists during the corresponding travel period, as calculated from monitoring data. Representative node To node The duration of the corresponding movement period, Represents the nodes already recorded by the server. To node The historical average tourist flow rate during the corresponding time period; the conflict aggregation intensity value refers to the value of tourists moving from nodes. To the node The absolute difference between the current actual tourist flow intensity and the historical average tourist flow rate during the travel period; this value is used to quantify the deviation between the real-time tourist gathering or dispersal situation at a specific node and the previous normal traffic level; the larger the value, the more significant the tourist flow at that node has gathered or become abnormal in the current period, and the more likely traffic conflicts or resource bottlenecks will occur; the smaller the value, the more similar the current tourist flow at that node is to the historical traffic status, and the lower the risk of conflict. First, extract the data from the actual tourist trajectory from the visiting node. Move to node The path segment is identified, and its start and end times within the current time window are marked to obtain the corresponding movement period. Then, by using the scenic area's gate statistics system and mobile terminal trajectory data, the number of all tourists passing through this route segment within that time period is counted to form the original value of the number of tourists. Simultaneously, historical traffic flow rate data for this path within the same time period over the past 5 days was retrieved from the server, and the raw value of historical traffic intensity was calculated using the arithmetic mean. To ensure that data with different dimensions can be computed under a unified dimension, the above three parameters are subjected to min-max normalization, where normalization is performed using the formula... Assuming the number of tourists ranges within the observable interval, The range of movement time is Seconds, historical traffic intensity range is If the number of people per second is 1, then for a node pair from A to B, the observed data is: The normalization results are as follows: Substitute into the formula Then, node pair C to D is selected for comparison, with the original monitoring value being... The normalization result is Substituting into the formula, we get: The determination interval is set as follows: like This indicates that the tourist's current travel status is only slightly different from the historical travel pattern, and is in a conflict-free state; if If the tourist flow deviation is moderate, it indicates a mild conflict situation; if This indicates that the current tourist traffic density is significantly abnormal, belonging to a state of severe conflict. For node pair A to B, the calculation is... ,satisfy It falls into the severe conflict zone; for node pair C to D, the calculation is as follows: Similarly satisfied This also falls into the severe conflict zone. The results indicate that the visitor traffic intensity on the A to B and C to D routes during the current time period is significantly higher than historical norms, resulting in significant clustered conflicts. Therefore, these routes are marked as restricted access routes. Subsequently, the normalized value of the remaining resource availability at the route's endpoint is used for further assessment. If this value is less than the set resource restriction threshold of 0.25, such as the remaining resource availability at node D... If a path segment with restricted access overlaps with a resource-restricted node, it is considered a spatially restricted node and participates in the construction of a spatially restricted node group. For example... Figure 5 As shown, the specific steps for obtaining the node optimization time-series chain are as follows: S401: Based on spatially constrained node groups, analyze the arrival and departure times of each node in the behavioral sequence, determine the constrained time periods of the node in the path time sequence, compare the original arrival and departure times of the node with the connection logic of adjacent nodes, identify the node time combinations that need to be adjusted, and obtain the time sequence adjustment factor set. The original behavior sequence data of each node is extracted sequentially, including the arrival and departure times of each node in the original path. This time period is then correlated with the corresponding restricted status of the node. The judgment rule is: if the time interval of a node under resource-restricted or access-restricted status overlaps with the original arrival or departure time, then the node's time is considered a restricted period. For example, if node A's resource-restricted period is from 10:15 to 10:45, while the tourist's original planned arrival time is 10:20 and departure time is 10:35, then there is a complete overlap, confirming that this node is a node whose time needs adjustment. Further, the node's preceding and following node numbers and their respective arrival and departure times are extracted, and it is determined whether the time logic satisfies "the departure time of the preceding node ≤ the arrival time of the current node" and "when...". "Previous node departure time ≤ subsequent node arrival time" means that if the current node arrives earlier than the previous node departs (e.g., the previous node departs at 10:25 while the current node arrives at 10:20), it is a time conflict, and the conflict type is recorded as "previous node compression conflict". If the current node departs at 10:50 while the subsequent node arrives at 10:45, it is recorded as "subsequent node squeezing conflict". All node numbers with such time logic contradictions are combined with their original planned arrival and departure times to form time adjustment combinations. Each combination is marked with a conflict type and recorded as a time period to be adjusted. The node number, original time point, conflict logic, and conflict time period are extracted from the time adjustment combinations and structured into a time sequence adjustment factor set for subsequent connection structure repair. S402: Based on the time sequence adjustment factor set, the connection status between the node and the preceding and following nodes is judged. The traffic and passage parameters corresponding to the arrival and departure intervals of adjacent nodes are compared. Node segments with insufficient connection are filtered out, and the node order and association status of the segments are adjusted. The data is aggregated and rearranged to obtain connection conflict mapping information. Iterate through the preceding and following node numbers in the behavior sequence one by one, and extract the connection information between the two nodes, including the departure time of the preceding node, the arrival time of the current node, the departure time of the current node, and the arrival time of the following node. Calculate the interval between the preceding and following time pairs in each segment. If the interval of any segment is less than 5 minutes, it is considered an insufficiently connected segment. For example, if the departure time of the preceding node is 10:25 and the arrival time of the current node is 10:27, the interval is 2 minutes. Less than 5 minutes is considered a tightly connected segment. Combined with traffic parameters, extract the estimated walking or traffic time required for this segment. For example, if the estimated walking time from node B to C is 6 minutes, then 2 minutes is much less than 6 minutes, constituting an unreachable logic and marked as insufficiently connected. Continue to extract information for each insufficiently connected segment. The corresponding behavior sequence number and node number are combined, and their temporal arrangement is checked. If a certain sequence adjustment can avoid the above conflict, the current segment and its adjacent segments are adjusted and the behavior chain is regenerated. For example, the original sequence BCD is adjusted to BDC and the time logic is rechecked. If the interval between adjacent segments after adjustment is greater than the set minimum requirement of 5 minutes and the travel time meets the minimum movement requirement, the adjusted sequence relationship is recorded, a node sequence rearrangement pair is constructed, the sequence adjustment record is compared with the original sequence to mark the change position, a connection change field is generated, and all nodes in the adjusted segment are re-aggregated into a behavior sequence data. The node status, time connection, change flags, etc. before and after adjustment are organized into structured connection conflict mapping information. S403: Based on the connection conflict mapping information, the resource pressure of the non-conflict segment recorded by the server is compared, the passenger flow occupancy status and park entry reserve status of the nodes in the non-conflict segment are determined, the connection time information of adjacent nodes is reorganized, and the node optimized time sequence chain is obtained. Extract the original path numbers and node order corresponding to each conflict segment. Retrieve the non-conflict path segment dataset recorded on the server. Compare the resource status of non-conflict segments within the same time period and near node range. Extract the real-time passenger flow and maximum capacity for each node in the non-conflict segment. Calculate the current occupancy rate and determine if the rescheduling conditions are met. The scheduling criteria are set as follows: occupancy rate not exceeding 85% and remaining capacity greater than 50 people. If node E has a maximum capacity of 1000 people and the current number of people is 800, then the occupancy rate is 80%, and the remaining capacity is 200 people, meeting the scheduling conditions. Therefore, this node can be used as a replacement node. Path optimization involves extracting time periods and conflict segments, reorganizing the connection times, resetting the arrival time to the start time of the earliest available time period, and calculating a reasonable departure time. For example, if a non-conflicting node's entry time is from 10:50 to 11:20, then node E is set to arrive at 10:50 and leave at 11:10 and inserted into the original path. The arrival and departure times of path nodes are rearranged, and the adjusted order, time segments, and connection status information are recorded. A node access chain arranged chronologically is generated, where each node includes arrival time, departure time, and the time interval between it and the preceding and following nodes. A structured node optimization time sequence chain is output. Figure 6 As shown, the specific steps for obtaining the time-sharing recommended path group are as follows: S501: Based on node optimization of time sequence chain, screen the departure time of each access node and the arrival time of the next node, calculate the traffic interval between nodes, determine the impact of traffic interval on path continuity, identify node combinations that cause connection conflicts due to excessively short or long intervals, and obtain a traffic connection anomaly index. The process extracts the departure time of the current node and the arrival time of the next node for each node, defining the time difference between these two times as the traffic interval. Traffic interval calculation requires subtraction in minutes. For example, if the departure time of node A is 10:15 and the arrival time of node B is 10:30, the interval is 15 minutes. This interval is compared with the standard travel time for this route. If the route is a pedestrian section, the set travel benchmark is 1.5 minutes per 100 meters. If the distance between two nodes is 600 meters, the minimum travel time is 9 minutes. Comparing the actual interval of 15 minutes with the benchmark travel time of 9 minutes determines that the travel time for this section is sufficient. If the interval is only 5 minutes, which is lower than the baseline of 9 minutes, it constitutes a conflict of the "too short interval" type. If the interval exceeds 30 minutes and the travel distance is less than 500 meters, it is considered a conflict of the "too long interval" type. For example, if the path segment is only 350 meters long and the standard travel time is about 5 minutes, but the interval is 40 minutes, it is judged as a resource utilization gap. This type of node combination is marked as a redundant stagnation segment. All node pairs marked as "too short" or "too long" and their time, space and path segment information are included in the anomaly list. A unique index number is generated for each anomaly combination. The number, node name, interval value, segment distance, expected travel time and judgment result are uniformly recorded to form a traffic connection anomaly index. S502: Based on the traffic connection anomaly index, the spatial distribution and reception capacity of the node in the time period are judged. The passenger flow occupancy status and spatial carrying capacity of each node are compared. The node numbers with obvious resource aggregation risks are screened. The spatial and time period characteristics of each node are integrated to obtain resource aggregation characteristic information. The spatial location and visitor data records of each node within the corresponding time period are extracted. For the current node, the number of visitors in the park and the maximum capacity of the node are extracted from the monitoring terminal records. The current resource pressure status is determined by calculating the occupancy rate. For example, if the current number of visitors at node C is 720 and the maximum capacity is 800, the occupancy rate is 90%, which is within the resource shortage range. The resource pressure range is divided into: low load (less than 60%), medium load (60% to 85%), and high load (above 85%). Node C is classified as high load. Further analysis is conducted to determine whether the spatial area where the node is located is a hotspot area, and the spatial range corresponding to the node is extracted. The status information of other nodes within 100 meters is collected. If at least two nodes in the surrounding area belong to the high-load range, the area is marked as a resource agglomeration area. The node number, time period, occupancy rate, spatial location and surrounding resource status are merged into a resource feature record. For each node that has both traffic abnormalities and high resource load, cross-marking is performed. Node numbers that have both spatial carrying capacity pressure and traffic connection abnormalities are selected and marked as resource agglomeration risk nodes. Their spatial coordinates, time period, passenger flow density and reception capacity are encapsulated to form a resource agglomeration feature information record group.

[0035] S503: Based on resource aggregation feature information, analyze the continuity of node sorting and the accessibility of dwelling arrangements, adjust the node order and arrival and departure arrangements, optimize the spatial connection relationship of all nodes, and obtain time-sharing recommended path groups; The process extracts the access order, arrival time, and departure time of nodes. First, it checks the logical consistency of the order for each group of consecutive nodes, determining if the order satisfies geographical continuity. If nodes are geographically more than 1 kilometer apart but consecutive in the order, they are marked as geographically disordered combinations. Further, it cross-references the dwell time of each node with its resource aggregation status. If a node is marked as a high-density area but the scheduled dwell time still exceeds 20 minutes, it is determined to be an adjustable dwell point. This node can serve as an optimization entry point. The current order, node number, and adjustment flag are recorded. Adjustable points are then extracted and re-optimized. A new set of candidate sorting is generated. For example, the original sorting position of node E is adjusted from 3 to 5. At the same time, the connection with the time segments of the nodes before and after is judged. If the traffic interval under the new sorting is in the range of 8 to 25 minutes and the expected travel time of each segment is less than the interval time, then the sorting is feasible. All sorting adjustment schemes are traversed in turn, and the combination schemes that simultaneously meet the requirements of geographical order, controllable resource load, and reasonable traffic interval are screened out to form a node sequence list. Each node contains the optimized sorting number, arrival time, departure time, and spatial location code. All node records are aggregated into time-sharing recommended path groups according to the time sequence.

[0036] like Figure 7 As shown, a dynamic tourism recommendation data analysis system includes: The trip trajectory construction module is based on the tourist's mobile terminal. It analyzes the reported departure time and current location, combines the opening hours and reception capacity of the scenic area monitoring terminal, determines the matching between the tourist's trip and the scenic area's opening, sorts out the arrival and departure times of nodes, and obtains the tourist's time-series trajectory set. The resource distribution association module retrieves the time-series trajectory set of tourists from each node to the departure time, analyzes the distribution of tourists in the scenic area during the same period, compares the traffic process between nodes, and structures the spatial distribution of nodes and the interval between tourists according to the path order to obtain dynamic resource distribution data. Based on dynamic resource distribution data, the restricted node allocation module analyzes the traffic pressure and dwell restrictions during the movement period between nodes, filters flexible sections, performs spatial and traffic allocation, identifies doubly restricted areas, and obtains spatially restricted node groups. The temporal chain reordering module is based on spatially constrained node groups. It adjusts the nodes in the behavior sequence to the departure time, analyzes the connection between the preceding and following nodes, compares the resource pressure of non-conflict sections, and reorders the access order according to spatial and traffic conditions to obtain the optimized temporal chain of nodes. The time-sharing route generation module optimizes the time sequence chain based on nodes, screens the traffic intervals of departures and arrivals at each node, analyzes the spatial distribution and reception capacity of each time period, judges itinerary conflicts and resource aggregation, sorts out the node access and stay arrangements, and obtains time-sharing recommended route groups.

[0037] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the present invention should be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of protection of the described technical solutions.

Claims

1. A dynamic tourism recommendation data analysis method, characterized in that, The method includes: S1: Based on the tourist's mobile terminal, analyze the reported departure time and current location, combine the opening hours and reception capacity of the scenic area monitoring terminal, determine the matching between the tourist's itinerary and the scenic area's opening, sort out the arrival and departure times of nodes, and obtain the tourist's time-series trajectory set; S2: Based on the tourist time-series trajectory set, retrieve the departure time of each node, analyze the distribution of tourists in the scenic area during the same period, compare the traffic process between nodes, and according to the path order, structure the spatial distribution of nodes and the interval between tourists to obtain dynamic resource distribution data. S3: Based on the dynamic distribution data of the resources, analyze the traffic congestion and restricted stay during the movement period between nodes, select flexible sections, carry out spatial and traffic allocation, identify the doubly restricted areas, and obtain spatially restricted node groups; S4: Based on the spatially constrained node group, adjust the nodes in the behavior sequence to the departure time, analyze the connection between the preceding and following nodes, compare the resource pressure of non-conflict sections, and reorder the access order according to the spatial and traffic conditions to obtain the optimized node time sequence chain. S5: Based on the node optimization time sequence chain, screen the traffic intervals of departure and arrival at each node, analyze the spatial distribution and reception capacity of each time period, determine the itinerary conflict and resource aggregation, sort out the node access and stay arrangements, and obtain the time-sharing recommended route group.

2. The dynamic tourism recommendation data analysis method according to claim 1, characterized in that, The tourist time-series trajectory set includes departure reference time, node arrival timetable, and node departure timetable. The resource dynamic distribution data includes node passenger flow occupancy status, node park entry capacity status, and node dwell capacity status. The space-constrained node group includes congested entry nodes, congested departure nodes, and nodes with limited dwell time. The node optimization time-series chain includes a node access order table, a node arrival / departure arrangement table, and an adjacent node connection timetable. The time-sharing recommended path group includes time-sharing access path information, time-sharing node dwell information, and time-sharing path switching information.

3. The dynamic tourism recommendation data analysis method according to claim 1, characterized in that, The specific steps for obtaining the tourist time-series trajectory set are as follows: S101: Based on the tourist's mobile terminal, analyze the reported departure time and current location parameters, determine the consistency of the device identification number, combine the continuous positioning data sequence, and sort all positioning coordinates by equal time interval extraction method, and arrange them in the order of extraction time to obtain the time series positioning group. S102: Based on the time series positioning group, compare the spatial position of each end coordinate point with the node set by the scenic area monitoring terminal, synchronize the matching node number, retrieve the opening time period and reception capacity status of each node, identify the overlap between the end time of the trajectory segment and the opening time period of the node, determine the reception status of the node, and obtain the node access permission set. S103: Based on the node access permission set, sort the segment numbers that meet the entry conditions, analyze the start and end times of the corresponding trajectory segments, pair the end and start times of adjacent segments in the sorting sequence, and obtain the tourist time-series trajectory set.

4. The dynamic tourism recommendation data analysis method according to claim 1, characterized in that, The specific steps for obtaining the dynamic distribution data of the resources are as follows: S201: Based on the tourist time-series trajectory set, analyze the arrival and departure times of each node, determine the continuity of the start and end times of each visiting node in the path, filter the dwell period and movement interval between adjacent nodes in the path, optimize the data order according to the time sequence relationship in the path, and obtain the time-series connection sequence. S202: Based on the time sequence, compare the tourist location data recorded by the scenic area monitoring terminal in the same time period, determine the distribution density of tourists within the node space, filter the node numbers with dense tourists, and label the nodes and their corresponding time period density status to the original node data to obtain a spatial clustering label set. S203: Based on the spatial clustered annotation set, analyze the arrival and departure times of adjacent nodes, calculate the spatial distance and movement interval of node geographic coordinates, determine the spatial distribution and visitor interval characteristics between nodes, and organize all node and visitor information in a structured manner to obtain dynamic resource distribution data.

5. The dynamic tourism recommendation data analysis method according to claim 1, characterized in that, The specific steps for obtaining the spatially constrained node group are as follows: S301: Based on the dynamic distribution data of the resources, analyze the traffic congestion and stay restriction status during the movement period between access nodes, determine the passenger flow occupancy status and stay carrying capacity status of adjacent nodes, compare the passenger flow distribution and stay pressure changes within the movement section, identify the node sections where passage is obstructed and stay is restricted, and obtain restricted section identification data. S302: Based on the restricted segment identification data, filter the flexible segments with adjustment windows, analyze the adjustability characteristics of the corresponding time period of the flexible segments, compare the overlap between the flexible segments and the restricted segments in the time sequence, determine the substitution space of the flexible segments for the restricted segments, set the flexible segments with substitution as switching relationships, and obtain the flexible switching mapping group. S303: Based on the aforementioned flexible switching mapping group, combined with tourist movement trajectory data and scenic area node resource distribution trends, analyze the conflict status between nodes within a time period, determine the passenger flow aggregation status and traffic conditions of conflicting nodes, compare the overlap range of resource-restricted and traffic-restricted nodes, and obtain the spatially restricted node group.

6. The dynamic tourism recommendation data analysis method according to claim 1, characterized in that, The specific steps for obtaining the node optimized time-series chain are as follows: S401: Based on the spatially constrained node group, analyze the arrival and departure times of each node in the behavior sequence, determine the constrained time period of the node in the path time sequence, compare the original arrival and departure times of the node with the connection logic of adjacent nodes, identify the node time combination that needs to be adjusted, and obtain the time sequence adjustment factor set. S402: Based on the time-series adjustment factor set, determine the connection status between the preceding and following nodes, compare the traffic and passage parameters corresponding to the arrival and departure intervals of adjacent nodes, filter the node segments with connection time intervals less than a preset safety threshold, adjust the node order and association status of the segments, aggregate and rearrange the data, and obtain the connection conflict mapping information. S403: Based on the connection conflict mapping information, compare it with the resource pressure of the non-conflict section recorded by the server, determine the passenger flow occupancy status and the remaining capacity for entry into the park of the non-conflict section node, reorganize the connection time information of adjacent nodes, and obtain the node optimized time sequence chain.

7. The dynamic tourism recommendation data analysis method according to claim 1, characterized in that, The specific steps for obtaining the time-sharing recommended path group are as follows: S501: Based on the node optimization time chain, screen the departure time of each access node and the arrival time of the next node, calculate the traffic interval between nodes, determine the impact of traffic interval on path continuity, identify node combinations that cause connection conflicts due to intervals less than a first preset threshold or greater than a second preset threshold, and obtain a traffic connection anomaly index. S502: Based on the traffic connection anomaly index, determine the spatial distribution and reception capacity of the node in the time period, compare the passenger flow occupancy status and spatial carrying capacity of each node, filter the node numbers with obvious resource aggregation risk, and integrate the spatial and time period characteristics of each node to obtain resource aggregation characteristic information. S503: Based on the resource aggregation feature information, analyze the continuity of node sorting and the accessibility of dwelling arrangements, adjust the node order and arrival and departure arrangements, optimize the spatial connection relationship of all nodes, and obtain time-sharing recommended path groups.

8. The dynamic tourism recommendation data analysis method according to claim 1, characterized in that, The scenic area monitoring terminal refers to the equipment installed in various areas, entrances and nodes of the scenic area to collect data on the scenic area's opening status, number of people in the park, visitor flow and resource carrying capacity in real time. The tourist itinerary refers to the time arrangement of tourists' departure, arrival, sightseeing, stay and departure at different stages of the tourism process.

9. The dynamic tourism recommendation data analysis method according to claim 1, characterized in that, The term "scenic area opening" refers to the state of a scenic area or attraction being open to the public at a certain time. The term "each node" refers to each tourist destination in the tourist's itinerary. The term "traffic process" refers to the travel process experienced by a tourist as they move from one visit node to the next.

10. A dynamic tourism recommendation data analysis system, the system being used to implement the dynamic tourism recommendation data analysis method as described in any one of claims 1-9, characterized in that, The system includes: The trip trajectory construction module is based on the tourist's mobile terminal. It analyzes the reported departure time and current location, combines the opening hours and reception capacity of the scenic area monitoring terminal, determines the matching between the tourist's trip and the scenic area's opening, sorts out the arrival and departure times of nodes, and obtains the tourist's time-series trajectory set. Based on the tourist time-series trajectory set, the resource distribution association module retrieves the time from each node to the departure time, analyzes the distribution of tourists in the scenic area during the same period, compares the traffic process between nodes, and structures the spatial distribution of nodes and tourist intervals according to the path order to obtain dynamic resource distribution data. Based on the dynamic distribution data of the resources, the restricted node allocation module analyzes the traffic pressure and dwell restrictions during the movement period between nodes, filters flexible sections, performs spatial and traffic allocation, identifies doubly restricted areas, and obtains spatially restricted node groups. The temporal chain reordering module, based on the spatially constrained node group, adjusts the nodes in the behavior sequence to the departure time, analyzes the connection between the preceding and following nodes, compares the resource pressure of non-conflict sections, and reorders the access order according to spatial and traffic conditions to obtain the optimized temporal chain of nodes. The time-sharing route generation module optimizes the time sequence chain based on the nodes, screens the traffic intervals of departure and arrival at each node, analyzes the spatial distribution and reception capacity of each time period, judges the itinerary conflicts and resource aggregation, sorts out the node access and stay arrangements, and obtains the time-sharing recommended route group.

Images