Destination global tourism big data management platform based on data processing

Abstract

The invention belongs to the technical field of smart tourism, and discloses a destination global tourism big data management platform based on data processing, and the platform comprises a sensing qualified point gathering module which collects global tourism data, constructs a geographic grid point network, sets a spatial grid point reconstruction rule, and carries out the automatic refining or merging of grid points; a track triggering mechanism is introduced, and when it is detected that the behavior frequency in the preset target area reaches a preset behavior frequency threshold value, fine-grained modeling is started to generate a geographic sensing structure; the behavior deconstruction coding module is used for analyzing continuous behaviors of tourists in a geographical perception structure and constructing a multi-dimensional situation coding vector; reconstructing a complete behavior chain of the tourist through a behavior jigsaw type deconstruction method and an implicit behavior compensation method; and a solid support is provided for deep analysis and intelligent service of global tourism data.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent tourism, and more specifically, to a big data management platform for the whole-region tourism of a destination based on data processing. Background Art

[0002] A patent with the publication number CN119690943A discloses a data processing platform based on big data. The platform includes a service end and a processing end. The processing end includes a collection module, a storage module, a quality inspection module, a processing module, a scheduling module, and a visualization module. The storage module is used to store both the structured data and the unstructured data in a preset database. The quality inspection module is used to obtain the stored data in the preset database for quality inspection to determine the inspection situation. The processing module is used to determine whether data conversion processing needs to be performed on the stored data according to the inspection situation. The scheduling module is used to schedule the stored data or the target data according to a preset time to generate a batch running task. The visualization module is used to perform visualization processing on the completed target batch running task according to the batch running situation to generate a target data table, achieving the effects of reducing costs, simplifying processes, and meeting the data volume processing requirements of different needs.

[0003] The existing big data management platforms for the whole-region tourism of a destination mainly have the following problems: In the prior art, a fixed geometric boundary or management area is usually used as the coverage area for geographical grid division, without fully utilizing the geographical distribution information of the whole-region tourism data itself, which may lead to the omission of some data or the inclusion of irrelevant areas, reducing the effectiveness of the grid network. In the prior art, the side length of the basic grid points is usually fixed and cannot be adjusted according to the data density of different regions. As a result, if the side length is too small, the number of initial grid points is too large, increasing the computational complexity; if the side length is too large, the fine differences within the lost area are affected, affecting the accuracy of subsequent analysis. In the prior art, the refinement or merging of grid points is usually based on static conditions, lacking a mechanism for dynamic determination according to real-time data characteristics, resulting in the grid network being unable to efficiently adapt to data changes in different time and space ranges.

[0004] Currently, the resource exchange between tourists and merchants usually adopts a method based on fixed weights or linear integral accumulation, without fully considering the differences in the immersive value scores of tourists, resulting in a lack of significant distinction between high-value tourists and low-value tourists, which is likely to cause fairness disputes. At the same time, the resource request processing mechanism in traditional platforms fails to effectively combine tourist activity levels and preferences, easily resulting in the phenomenon that a single highly active tourist occupies a large amount of resources, reducing the satisfaction of other tourists. In addition, the simple first-come-first-served or polling strategy is often adopted during the resource request process, without introducing flow control and dynamic current limiting measures, easily causing system congestion or resource allocation imbalance.

[0005] In view of this, the present invention proposes a destination global tourism big data management platform based on data processing to solve the above problems. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art and to achieve the above-mentioned purpose, the present invention provides the following technical solution: a destination global tourism big data management platform based on data processing, comprising: The perception aggregation grid module collects global tourism data and constructs a geographic grid network, sets spatial grid reconstruction rules, and automatically refines or merges grids; introduces a trajectory trigger mechanism, and enables fine-grained modeling to generate a geographic perception structure when it detects that the cumulative behavior frequency in the preset target area reaches the preset cumulative behavior frequency threshold; The behavior deconstruction coding module analyzes the continuous behavior of tourists in the geographical perception structure and constructs a multi-dimensional situation coding vector; through the behavior puzzle deconstruction method and implicit behavior compensation method, the complete behavior chain of tourists is reconstructed; The immersion value quantification module calculates the immersion value score of tourists based on the multi-dimensional situational coding vector and the complete behavior chain. It uses the resonance path matrix generation mechanism to compare the resonance similarity of different tourists on the complete activity path, generate the resonance path matrix between tourists, and establish a tourist behavior evolution map. The guidance recommendation feedback module generates personalized tour guidance paths for tourists based on their immersion value scores and the evolution map of their behavior. It adopts a reverse resonance recommendation strategy to push the most similar but unvisited geographical grid points to tourists based on their immersion value scores. The platform response management module links merchant resources around the geographical grid with the highest resonance similarity; introduces the resonance group package linkage mechanism to drive the release of merchant resources in the preset destination and form a resource sharing network; The points redemption reward module maps tourists' immersion value points into consumable points, supporting redemption between tourists and merchants. It adopts weighted fair queuing and leaky bucket flow limiting mechanisms to allocate merchant resources, dynamically balancing tourist satisfaction and resource utilization.

[0007] Preferably, the method for automatically refining or merging grid points comprises: Collect global tourism data, which includes tourist behavior data, environmental facilities data, merchant service data, spatial geographic data, and management policy data; clean the global tourism data through sliding window outlier detection technology, and perform standard deviation normalization to obtain normalized global tourism data; For the geographic coordinate points in the normalized global tourism data, the convex hull algorithm is used to extract the minimum convex boundary of all geographic coordinate points, and the required coverage area for constructing the geographic grid network is determined based on the minimum convex boundary; the required coverage area is divided according to the preset basic grid side length , perform preliminary spatial grid division; use the adaptive quadtree division method to generate an initial geographical grid network, for any point within the required coverage area , through the mapping function, realize the encoding mapping from geographical coordinate points to geographical grid points; Introduce a dynamic adjustment strategy based on spatial density, dynamically adjust the basic grid side length, and calculate any point within the required coverage area point density , according to the point density , adjust the basic grid side length through the grid side length adjustment function; By encoding all geographical coordinate points in the global tourism data, classify them into the corresponding geographical grid points; set the spatial grid reconstruction rule. For any grid point in the geographical grid network, within the preset time window, if there is a time period that meets the refinement trigger condition function, trigger the automatic refinement of the grid point; For any grid point in the geographical grid network, if there is an adjacent grid point, the adjacent grid point belongs to the adjacent grid point set of the current arbitrary grid point, and the cumulative behavior frequency within the adjacent grid point is less than the cumulative behavior frequency within the grid point, then trigger the automatic merging of the grid point.

[0008] Preferably, the generation method of the geographical perception structure includes: Introduce a trajectory trigger mechanism, collect and count trajectory points of tourist behavior data included in the global tourism data, and calculate the cumulative behavior frequency of trajectory points within the preset target area within the preset time period through a sliding time window; Judge whether the cumulative behavior frequency reaches the preset cumulative behavior frequency threshold. If it reaches, trigger fine-grained modeling; adjust the spatial division granularity according to the distribution density of trajectory points in the target area, including reducing the basic grid side length and deepening the quadtree division depth, to generate a geographical grid network with finer granularity; Remap and encode all trajectory points within the preset target area, and classify the trajectory points into the corresponding newly generated fine-grained grid points; based on the remapped trajectory points and their corresponding fine-grained grid points, generate a geographical perception structure including grid point encoding, spatial position information, cumulative behavior frequency of trajectory points within the time period, and trajectory point density information.

[0009] Preferably, the construction method of the multi-dimensional context encoding vector includes: Sort the trajectory points in the tourist behavior data of tourists in the global tourism data in chronological order, extract the timestamp, spatial position information, grid point encoding corresponding to the trajectory point, and behavior category of each trajectory point to form a continuous trajectory behavior sequence; For each trajectory behavior sequence, analyze its crossing path, time period, staying duration, moving speed, and direction change in the geographical perception structure, and statistically analyze the behavior pattern characteristics within each time period; extract multi-dimensional trajectory characteristics according to the spatial dimension, time dimension, behavior dimension, social dimension, and semantic dimension; adopt feature splicing and hash coding processing to combine the extracted multi-dimensional trajectory characteristics to generate a multi-dimensional context coding vector.

[0010] Preferably, the method for reconstructing the complete behavior chain of the tourist includes: Divide the sequence of multi-dimensional context coding vectors of the tourist obtained by parsing according to the chronological order and spatial adjacency relationship, and segment it into n behavior sub-fragments. The behavior sub-fragments reflect the local behavior characteristics of the tourist within a limited time period and spatial range, and are called behavior puzzles; For the incomplete behavior sub-fragments caused by data loss, sensing blind spots, or anomaly detection reasons, adopt an implicit behavior compensation method. Based on the tourist behavior data and environmental facility data, use a machine learning model to infer the missing behavior sub-fragments and their time series and spatial positions; Splice the behavior sub-fragments and the behavior sub-fragments obtained through implicit behavior compensation based on the chronological order and spatial adjacency relationship, and combine with the multi-dimensional trajectory characteristics corresponding to the multi-dimensional context coding vector to construct the complete behavior chain of the tourist.

[0011] Preferably, the method for establishing the tourist behavior evolution map includes: According to the multi-dimensional context coding vector and the complete behavior chain obtained by parsing the tourist in the geographical grid network, adopt a weighted vector aggregation technique to calculate the immersion value score of the tourist. The immersion value score of the tourist comprehensively reflects the behavior activity, behavior type, staying duration, and emotional participation degree of the tourist in the time and space dimensions; Combine the behavior category weight and the cumulative behavior frequency statistics, comprehensively calculate the behavior value, collect the tourist comment feedback data, introduce a sentiment analysis model to score the sentiment of the tourist comment feedback data, and generate the immersion value score of the tourist; Construct a resonance path matrix, adopt the dynamic time warping algorithm to match the multi-dimensional context coding vector sequences of different tourists, and calculate the path similarity; perform time alignment on the tourist behavior data, and calculate the Euclidean distance between the multi-dimensional feature vectors corresponding to the multi-dimensional context coding vector as the local distance; construct a complete activity path based on the local distance, and output the resonance similarity score of the tourist on the complete activity path; Construct a tourist behavior evolution map according to the constructed resonance path matrix. The tourist behavior evolution map is a weighted directed graph. Each node of the tourist behavior evolution map represents each tourist, and the edge represents the behavior relationship connection between two tourists; the weight of the edge represents the resonance similarity score of the tourist on the complete activity path.

[0012] Preferably, the method for generating the personalized tour guiding path includes: Using the tourist behavior evolution graph represented by a weighted directed graph, analyze the behavior similarity between any preset target tourist and other tourists in the tourist behavior evolution graph, identify the neighboring tourist group with the most similar behavior patterns, and infer the tour routes that the target tourist may be interested in based on the historical behavior evolution paths of this neighboring tourist group; Combining the environmental facility data and tourist behavior data, use the A* algorithm to obtain the optimal tour path that meets the tourist interest preferences and path coherence, which is defined as the personalized tour guiding path; feedback the generated personalized tour guiding path to the tourist mobile terminal in the form of multi-dimensional context encoding to provide real-time navigation and behavior suggestions.

[0013] Preferably, the method for pushing the geographical grid points with the highest similarity but not visited includes: Screen out the neighboring tourist groups whose resonance similarity scores on the complete activity path are greater than the preset resonance similarity score threshold of tourists on the complete activity path; according to the complete behavior chain of the preset target tourist, mark the geographical grid points that have been visited by it, and combine the complete behavior chains of the neighboring tourist groups to identify the geographical grid points that the target tourist has not visited but the neighboring tourists have visited as recommended candidate grid points; Introduce the immersion value score of the target tourist as a weight factor, and through the weighted vector aggregation method, comprehensively evaluate the resonance similarity score of the tourist on the complete activity path and the immersion value score of the tourist to form a recommended priority ranking model. For all recommended candidate grid points, preferentially recommend the geographical grid points with the highest interest matching degree and the highest immersion value score with the preset target tourist; Design a dynamic recommendation mechanism, dynamically generate a list of recommended geographical grid points according to the changes in tourist behavior data and the immersion value score of tourists, and use the push notification technology to send the latest recommendation results to the tourist mobile terminal in real time to assist tourists in making personalized tour plans.

[0014] Preferably, the method for forming the resource sharing network includes: Determine the core resonance node for the geographical grid point area with the highest resonance similarity score of tourists on the complete activity path; based on the spatial database technology, perform spatial mapping between this core resonance node and the merchant resources within the preset destination to establish the corresponding relationship between the geographical location and the merchant resources; Through the event-driven architecture, combine the LSTM time series prediction model to monitor the activation status of the resonance group package in real time, automatically push resource scheduling instructions to relevant merchants, and use the microservice architecture for elastic expansion; after receiving the instructions, the merchant-side resource management system completes inventory adjustment, personnel scheduling, and service preparation to achieve dynamic resource response; A resource sharing network covering preset target geographical grid points and merchants in the surrounding area is constructed using a graph database. Nodes in the resource sharing network represent merchant resources, and edges represent resource sharing cooperation relationships. The big data processing platform is used to collect tourist consumption data, merchant service feedback data, and user evaluation data in real time. The BERT sentiment classifier is used to evaluate service quality, and the resonance group package design and resource scheduling strategy are continuously optimized through multi-dimensional data fusion and causal inference methods.

[0015] Preferably, the method for dynamically balancing tourist satisfaction and resource utilization rate includes: The tourist immersion value score is mapped to consumable points through a non-linear weighted mapping function, and the non-linear weighted mapping function is defined as ; where is the consumable points of tourist ; is the immersion value score of tourist ; is the adjustment factor for controlling the overall amplification or reduction of consumable points; is the adjustment factor for controlling the shape of the consumable points mapping curve; is the base number of consumable points to ensure that all tourists have a minimum value of consumable points; The consumable points of tourist are stored in the points redemption reward module, and the balance of the tourist's consumable points is updated. When a tourist initiates a request to exchange for merchant resources, the platform adopts a weighted fair queuing mechanism, sorts the tourists in descending order according to their consumable points, processes the tourist requests in the descending order of consumable points, and allocates available merchant resources. The platform calculates the resource share that each tourist can obtain based on the current total amount of merchant resources and consumable points. A leaky bucket flow control mechanism is introduced to control the resource request traffic, and the control parameters of the resource request traffic are set, including the leaky bucket capacity and the request outflow rate, to ensure that the tourist request rate is less than the request outflow rate and the number of requests in the leaky bucket does not exceed the leaky bucket capacity, thereby dynamically balancing tourist satisfaction and resource utilization rate.

[0016] Compared with the prior art, the present invention has the following beneficial effects: In the process of constructing the initial geographical grid network, the present invention introduces a dynamic adjustment mechanism based on the spatial distribution density of the global tourism data. By calculating the density level of data points in each region, the grid side length of the corresponding region is automatically adjusted. Thus, smaller grids are used in data-intensive regions to enhance the fineness, and larger grids are used in data-sparse regions to reduce the computational burden. It effectively overcomes the problems of low computational efficiency or loss of spatial information caused by the fixed grid size in the prior art, and significantly improves the adaptability and processing performance of the platform.

[0017] A grid reconstruction rule based on dynamic triggering of spatial data changes is proposed, covering two reconstruction strategies: refinement and merging. In terms of grid refinement, a refinement trigger judgment method that comprehensively considers the cumulative frequency and statistical variance of behavioral data is adopted, so that the spatial grid can be automatically refined in high-frequency areas according to dynamic factors such as actual passenger flow and activity density, thereby improving the accuracy of spatial resolution. In terms of grid merging, the cumulative amount of behavioral data of adjacent grids is compared, and low-activity adjacent grids are automatically merged to reduce unnecessary grid subdivision and computational burden. Compared with the single and static grid division method in the prior art, the adaptive dynamic reconstruction strategy of this scheme can respond to the changes of global tourism data in real time, significantly enhancing the real-time and flexibility of the platform. The adaptability, computational efficiency and spatial resolution accuracy of the spatial grid network are significantly improved, providing solid support for the in-depth analysis and intelligent services of global tourism data.

[0018] The immersion value points of tourists are mapped into consumable points through nonlinear weighted mapping function, and the overall magnification and reduction of points and the shape of curves are controlled by adjustment factors to effectively magnify the difference in points between high immersion value tourists and low immersion value tourists, ensuring the fairness and differentiation of points distribution; by setting the base number of points, it is ensured that all tourists get basic points, avoiding the fairness problem caused by zeroing of points. The weighted fair queuing mechanism is adopted to sort and process resource requests according to the consumable points of tourists, taking into account the activity and immersion experience of tourists, and realizing the rationality and fairness of resource request processing priority. The leaky bucket current limiting mechanism is introduced to ensure that the tourist request flow is controlled and does not exceed the system carrying capacity by setting the leaky bucket capacity and the request outflow rate, so as to achieve system load balancing and avoid response delay caused by resource overload. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 This is a schematic diagram of the structure of the destination global tourism big data management platform based on data processing of the present invention; Figure 2 A schematic diagram of a flow chart of a method for generating a geographic perception structure provided by the present invention; Figure 3 It is a flow chart of the destination global tourism big data management method based on data processing of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0021] Embodiment 1

[0022] See also Figure 1 and Figure 2 As shown, Embodiment 1 further illustrates the destination global tourism big data management platform based on data processing proposed by the present invention, including: With the continuous development of the concept of global tourism, the acquisition, processing and management of destination tourism data have become important means to improve the quality of tourism services and tourist experience. The existing destination global tourism big data management platform usually divides the geographic grid based on fixed geometric boundaries or administrative management areas to cover different tourism data areas. However, this division method does not fully utilize the geographical distribution characteristics of global tourism data itself, which may cause some data to be omitted or include irrelevant areas, thereby reducing the coverage effectiveness of the geographic grid network and the accuracy of data processing.

[0023] The side length settings used to construct basic grid points in the prior art are usually fixed and cannot be dynamically adjusted according to the density of tourism data in different regions. When the side length is too small, it will lead to too many initial grid points, increasing the complexity of subsequent data processing and calculation; when the side length is too large, it is easy to lose the fine-grained differences in tourism data in the region, affecting the accuracy and reliability of subsequent analysis results. In addition, the refinement or merging of grid points in the prior art usually only relies on static condition judgment, lacking a mechanism for dynamic adjustment and judgment based on real-time data characteristics, resulting in the grid network being unable to flexibly adapt to data changes in different time and space ranges, affecting the adaptability and efficiency of the system in dynamic tourism scenarios.

[0024] The existing resource exchange mechanism between tourists and merchants usually adopts fixed weights or simple linear integral accumulation methods, which fails to fully reflect the difference in immersion value generated by tourists during the travel process, resulting in a lack of significant distinction between high immersion value tourists and low immersion value tourists, which easily leads to fairness issues. The mechanism used to process tourist resource requests in traditional platforms often does not fully take into account the activity and interest preferences of tourists, which can easily cause some highly active tourists to occupy a large amount of resources for a long time, reducing the participation and satisfaction of other tourists. At the same time, the processing method of resource requests usually adopts a first-come, first-served or simple polling strategy, lacks effective flow control and dynamic flow limiting measures, and is very likely to cause system congestion, request delays, and imbalanced resource allocation, limiting the stability and response efficiency of the global tourism data platform under high load conditions.

[0025] In order to effectively solve the above problems, the present invention proposes a destination global tourism big data management platform based on data processing, including: The Perception Aggregation Grid Module collects global tourism data, constructs a geographical grid network, sets spatial grid reconstruction rules, and automatically refines or merges the grids. It introduces a trajectory trigger mechanism. When the cumulative behavior frequency within a preset target area reaches the preset cumulative behavior frequency threshold, it enables fine-grained modeling to generate a geographical perception structure. The Behavior Deconstruction and Encoding Module analyzes the continuous behaviors of tourists in the geographical perception structure and constructs a multi-dimensional context encoding vector. Through the behavior jigsaw deconstruction method and the implicit behavior compensation method, it reconstructs the complete behavior chain of tourists. The Immersion Value Quantification Module calculates the tourist immersion value score based on the multi-dimensional context encoding vector and the complete behavior chain. Using the resonance path matrix generation mechanism, it compares the resonance similarities of different tourists on the complete activity path, generates the resonance path matrix among tourists, and establishes a tourist behavior evolution map. The Guided Recommendation and Feedback Module generates a personalized tour guide path for tourists based on the tourist immersion value score and the tourist behavior evolution map. It adopts a reverse resonance recommendation strategy and pushes the geographical grid with the highest similarity but not visited to tourists in combination with the tourist immersion value score. The Platform Response Management Module links merchant resources around the geographical grid with the highest resonance similarity. It introduces a resonance group package linkage mechanism to drive the release of merchant resources within the preset destination and form a resource sharing network. The Integral Exchange and Reward Module maps the tourist immersion value score into consumable points to support the exchange behavior between tourists and merchants. It adopts a weighted fair queuing and leaky bucket flow control mechanism to allocate merchant resources and dynamically balance tourist satisfaction and resource utilization.

[0026] The method for automatically refining or merging the grids includes: Collect global tourism data, which includes tourist behavior data, environmental facility data, merchant service data, spatial geographical data, and management policy data. Clean the global tourism data through the sliding window outlier detection technique and perform standard deviation normalization to obtain the normalized global tourism data. Tourist behavior data includes the movement trajectories of tourists at the destination, scenic spot turnstile entry and exit records, mobile communication base station signaling data (location and stay time), and electronic ticket usage data. Environmental facility data includes traffic condition data, environmental monitoring data, and scenic spot facility status data. Traffic condition data includes public transportation operation data, road traffic flow data, parking lot data, and tourist transfer point data. Environmental monitoring data includes meteorological data, air quality data, water quality data, and noise monitoring data; scenic area facility status data includes tourist service facilities, scenic spot opening information, operation status of scenic spot equipment, and intelligent navigation facilities; merchant service data includes merchant business data and tourist consumption record data; spatial geographic data includes scenic area topography and landform data and road network data; management policy data includes tourism policy announcements and crowd control measure data; For the geographical coordinate points in the normalized all-for-one tourism data, use the convex hull algorithm to extract the minimum convex boundary of all geographical coordinate points, and determine the required coverage area for constructing the geographical grid network according to the minimum convex boundary; divide the required coverage area according to the preset basic grid side length , and perform preliminary spatial grid division; use the adaptive quadtree division method to generate the initial geographical grid network, and for any point within the required coverage area, implement the coding mapping from geographical coordinate points to geographical grids through a mapping function; the mapping function is ; where represents the mapping function of any point mapped to the corresponding geographical grid code; represents the grid code connection operation; However, the prior art does not consider the reasonable setting of the basic grid side length. An unreasonable setting of the basic grid side length may result in too many initial grid points (increasing the computational overhead) or too few (losing fine information). Introduce a dynamic adjustment strategy based on spatial density to dynamically adjust the basic grid side length, calculate the point density of any point within the required coverage area, ; where represents the total number of points within the radius around any point ; according to the point density , adjust the basic grid side length through the grid side length adjustment function; The grid side length adjustment function is: ; where represents the grid side length corresponding to any point after adjustment; represents the preset minimum allowable grid side length; represents the preset maximum allowable grid side length; represents the attenuation factor, which controls the influence degree of the point density on the grid side length adjustment. According to the expert experience method, ranges from 0 to 1; By encoding all the geographical coordinate points in the global tourism data and classifying them into corresponding geographical grid points; setting spatial grid reconstruction rules, for any grid point in the geographical grid network, if there is a time period that meets the refinement trigger condition function within a preset time window, the grid point will be automatically refined. The refinement trigger condition function is ; where represents the refinement trigger determination result for the th grid point in the geographical grid network ; represents the cumulative behavior frequency of grid point within the time period ; represents the preset maximum behavior frequency of the grid point; represents the statistical variance of the behavior frequency; represents the maximum behavior frequency factor, which is used to adjust the influence degree of the maximum behavior frequency on the trigger condition; represents the variance factor, which is used to adjust the influence degree of the variance term on the trigger condition; represents all the time periods within the time window; according to the expert experience method, and take values in the range of 0 to 1; represents the index of the grid point; For any grid point in the geographical grid network, if there is an adjacent grid point, the adjacent grid point belongs to the adjacent grid point set of the current arbitrary grid point, and the cumulative behavior frequency within the adjacent grid point is less than the cumulative behavior frequency within the grid point, then the grid point will be automatically merged.

[0027] For example, taking a coastal global tourism demonstration area (with a coverage area of about 1500 square kilometers) as an example, the area includes the main urban area, multiple key tourist attractions (such as ancient towns, coastal resorts, mountain parks), rural tourist spots and nature reserves. The annual number of tourists received in this area exceeds 30 million person-times, and the distribution and movement of tourists show obvious spatio-temporal dynamic characteristics.

[0028] In order to achieve precise dynamic management of the tourist flow, environmental pressure and service supply in this area, the tourism management platform accesses the following multi-source global tourism data: Visitor behavior data: including real-time positioning trajectories of about 500,000 mobile devices, consumption payment data, and scenic area visit records; environmental facility data: covering 300 public service facilities (including parking lots, toilets, and scenic area service stations), about 60 environmental monitoring points (air quality and noise monitoring); merchant service data: business status, service capabilities, and consumption volume data of about 3,500 tourism-related merchants; spatial geographic data: high-precision topographic maps, street maps, and road network information; management policy data: including time-limited flow control, temporary traffic control during holidays, and emergency evacuation plans, etc.

[0029] The convex hull algorithm is used to automatically extract the minimum boundary range (with an area of about 1,200 square kilometers) of the global tourism area. Based on the preset basic grid point side length (initially set to 300 meters), an adaptive quadtree partitioning method is used to construct an initial geographical grid point network. Further, the basic grid point side length is automatically adjusted based on the spatial density (the point density is about 50 - 4,000 points per square kilometer).

[0030] For example: In the ancient town scenic area (with an area of about 15 square kilometers), the point density in the high-density tourist gathering area reaches about 3,500 points per square kilometer, and the platform automatically reduces the grid point side length to 50 meters to achieve fine monitoring of tourist flow and service status.

[0031] In the nature reserve (with an area of about 200 square kilometers), the point density is only about 100 points per square kilometer, and the platform dynamically expands the grid point side length to 500 meters to reduce the platform's computational overhead while maintaining the necessary monitoring accuracy; In actual operation, when holidays (such as the "National Day Golden Week") arrive, the platform monitors that the cumulative behavior frequency of some grid points in the core area of the ancient town scenic area exceeds 15,000 times within a 30-minute window, and the variance of the behavior frequency is relatively high. It automatically triggers grid refinement to generate sub-grid points with a smaller granularity (such as 25 meters) to facilitate targeted guidance of tourist flow and adjustment of temporary service measures (such as adding temporary channels and opening emergency parking points, etc.).

[0032] At the same time, in the nature reserve and some unpopular scenic areas, the platform finds that the cumulative behavior frequencies of multiple adjacent grid points are lower than those of adjacent grid points during the same time period (such as the cumulative behavior frequency is only 30% of the main grid point). The platform automatically triggers merging, and after merging, the grid point side length expands to 700 meters, reducing the platform's burden and avoiding the occupation of processing resources by invalid data.

[0033] Through the method of the present invention, the platform realizes real-time perception, dynamic response, and spatial management optimization of tourist flow, providing a solution with wide coverage, adjustable granularity, timely response, and high computational efficiency for the management side, especially suitable for the global tourism management scenario with a wide coverage area and complex tourist distribution.

[0034] The following problems existing in the prior art are solved: In the prior art, a fixed geometric boundary or management area is usually used as the coverage area for geographical grid division, without fully utilizing the geographical distribution information of the global tourism data itself, which may lead to omission of some data or inclusion of irrelevant areas, reducing the effectiveness of the grid network. In the prior art, the side length of the basic grid points is usually fixed and cannot be adjusted according to the data density of different regions. As a result, if the side length is too small, the number of initial grid points is too large, increasing the computational complexity; if the side length is too large, the fine differences in the lost area are affected, affecting the accuracy of subsequent analysis. In the prior art, the refinement or merging of grid points is usually based on static conditions, lacking a mechanism for dynamic determination according to the characteristics of real-time data, resulting in the grid network being unable to efficiently adapt to data changes within different time and space ranges.

[0035] Advantages over the prior art: During the construction of the initial geographical grid network, a dynamic adjustment mechanism is introduced based on the spatial distribution density of the global tourism data. By calculating the density level of data points in each region, the grid side length of the corresponding region is automatically adjusted, so as to use smaller grids in data-intensive regions to enhance the fineness and larger grids in data-sparse regions to reduce the computational burden. It effectively overcomes the problems of low computational efficiency or loss of spatial information caused by fixed grid sizes in the prior art, and significantly improves the adaptability and processing performance of the platform.

[0036] A grid reconstruction rule triggered dynamically based on spatial data changes is proposed, covering two reconstruction strategies of refinement and merging. In terms of grid refinement, a refinement trigger determination method that comprehensively considers the cumulative frequency and statistical variance of behavior data is adopted, enabling the spatial grid to be automatically refined in high-frequency regions according to dynamic factors such as actual passenger flow and activity density, thereby improving the spatial analysis accuracy. In terms of grid merging, the cumulative amounts of behavior data of adjacent grid points are compared, and low-activity adjacent grid points are automatically merged to reduce unnecessary grid subdivision and computational burden. Compared with the single and static grid division method in the prior art, the adaptive dynamic reconstruction strategy of this solution can respond to the changes of the global tourism data in real time, significantly enhancing the real-time performance and flexibility of the platform. It significantly improves the adaptability, computational efficiency and spatial analysis accuracy of the spatial grid network, providing a solid support for the in-depth analysis and intelligent services of the global tourism data.

[0037] The method for generating the geographical perception structure includes: Introduce a trajectory trigger mechanism, collect and count trajectory points of the tourist behavior data included in the global tourism data, and calculate the cumulative behavior frequency of the trajectory points in the preset target area within the preset time period through a sliding time window; Judge whether the cumulative behavior frequency reaches the preset cumulative behavior frequency threshold. If it reaches, trigger fine-grained modeling; adjust the spatial division granularity according to the density of trajectory points in the target area, including reducing the side length of the basic grid point and deepening the quadtree division depth, so as to generate a finer-grained geographical grid network; Remap and encode all trajectory points in the preset target area, and classify the trajectory points into the newly generated fine-grained grid points; based on the remapped trajectory points and their corresponding fine-grained grid points, generate a geographical perception structure including grid point encoding, spatial position information, cumulative behavior frequency of trajectory points within a time period, and trajectory point density information.

[0038] The construction method of the multi-dimensional context encoding vector includes: Sort the trajectory points in the tourist behavior data in the global tourism data in chronological order, and extract the timestamp, spatial position information, grid point encoding corresponding to the trajectory point, and behavior category of each trajectory point to form a continuous trajectory behavior sequence; For each trajectory behavior sequence, analyze its crossing path, time period, stay duration, moving speed, and direction change in the geographical perception structure, and count the behavior pattern characteristics in each time period; extract multi-dimensional trajectory characteristics according to the spatial dimension (including geographical grid point encoding, jump sequence, relative position information), time dimension (including timestamp, time interval, stay / move duration), behavior dimension (including behavior category, frequency, intensity), social dimension, and semantic dimension; use feature splicing and hash encoding processing to combine the extracted multi-dimensional trajectory characteristics to generate a multi-dimensional context encoding vector.

[0039] The reconstruction method of the complete behavior chain of tourists includes: Divide the obtained multi-dimensional context encoding vector sequence of tourists according to the chronological order and spatial adjacency relationship, and split it into n behavior sub-fragments. The behavior sub-fragments reflect the local behavior characteristics of tourists within a limited time period and spatial range, and are called behavior puzzles; For the incomplete behavior sub-fragments caused by data loss, sensing blind spots, or anomaly detection, adopt an implicit behavior compensation method. Based on tourist behavior data and environmental facility data, use a machine learning model to infer the missing behavior sub-fragments and their time series and spatial positions; Stitch the behavior sub-fragments and the behavior sub-fragments obtained through implicit behavior compensation based on the chronological order and spatial adjacency relationship, and combine the multi-dimensional trajectory characteristics corresponding to the multi-dimensional context encoding vector to construct the complete behavior chain of tourists; the complete behavior chain includes the moving trajectory of tourists from entering the preset target area to leaving.

[0040] The establishment method of the tourist behavior evolution map includes: Based on the multi-dimensional context coding vectors and complete behavior chains parsed for tourists in the geographical grid network, the weighted vector aggregation technique is used to calculate the immersive value score of tourists. The immersive value score of this tourist comprehensively reflects the behavioral activity, behavior type, stay duration, and emotional engagement of tourists in the time and space dimensions; Combined with the behavior category weights and cumulative behavior frequency statistics, the behavior value is comprehensively calculated, and the tourist comment feedback data is collected. An emotion analysis model is introduced to score the emotions of the tourist comment feedback data, and the immersive value score of tourists is generated; Construct a resonance path matrix, use the dynamic time warping algorithm to match the multi-dimensional context coding vector sequences of different tourists, and calculate the path similarity; perform time alignment on the tourist behavior data, and calculate the Euclidean distance between the multi-dimensional feature vectors corresponding to the multi-dimensional context coding vectors as the local distance; construct a complete activity path based on the local distance, and output the resonance similarity score of tourists on the complete activity path; According to the constructed resonance path matrix, construct a tourist behavior evolution map. The tourist behavior evolution map is a weighted directed graph. Each node of the tourist behavior evolution map represents each tourist, and the edge represents the behavioral relationship connection between two tourists; the weight of the edge represents the resonance similarity score of tourists on the complete activity path.

[0041] The method for generating a personalized tour guidance path includes: Using the tourist behavior evolution map represented by a weighted directed graph, analyze the behavioral similarity between any preset target tourist and other tourists in the tourist behavior evolution map, identify the neighboring tourist group with the most similar behavior patterns, and infer the tour routes that the target tourist may be interested in based on the historical behavior evolution paths of this neighboring tourist group; Combined with the environmental facility data and tourist behavior data, use the A* algorithm to obtain the optimal tour path that meets the tourist interest preferences and path coherence, which is defined as the personalized tour guidance path; feedback the generated personalized tour guidance path to the tourist mobile terminal in the form of multi-dimensional context coding to provide real-time navigation and behavior suggestions.

[0042] The method for pushing the geographical grid points with the highest similarity but not visited includes: Screen out the neighboring tourist groups whose resonance similarity scores on the complete activity path are greater than the preset resonance similarity score threshold of tourists on the complete activity path; according to the complete behavior chain of the preset target tourist, mark the geographical grid points that have been visited by it, and combined with the complete behavior chains of the neighboring tourist groups, identify the geographical grid points that have not been visited by the target tourist but have been visited by the neighboring tourists as the recommended candidate grid points; Introduce the immersion value score of the target tourists as a weight factor. Through the weighted vector aggregation method, comprehensively evaluate the resonance similarity score of tourists on the complete activity path and the immersion value score of tourists to form a recommended priority ranking model. For all recommended candidate grid points, preferentially recommend the geographical grid points with the highest matching degree with the preset target tourist interests and the highest immersion value score; Design a dynamic recommendation mechanism. According to the changes in tourist behavior data and the immersion value score of tourists, dynamically generate a list of recommended geographical grid points. Use push notification technology to send the latest recommendation results to the tourist mobile terminal in real time to assist tourists in making personalized tour plans.

[0043] The method for forming a resource sharing network includes: Determine the core resonance node for the geographical grid point area with the highest resonance similarity score of tourists on the complete activity path; based on spatial database technology, perform spatial mapping between this core resonance node and merchant resources within the preset destination to establish the corresponding relationship between geographical location and merchant resources; Through the event-driven architecture, combined with the LSTM time series prediction model, monitor the activation status of the resonance group package in real time, automatically push resource scheduling instructions to relevant merchants, and use the microservice architecture for elastic expansion; after receiving the instructions, the merchant-side resource management system completes inventory adjustment, personnel scheduling, and service preparation to achieve dynamic resource response; Use a graph database to construct a resource sharing network covering the preset target geographical grid points and surrounding area merchants. The nodes in the resource sharing network represent merchant resources, and the edges represent resource sharing cooperation relationships; use the big data processing platform to collect tourist consumption data, merchant service feedback data, and user evaluation data in real time; use the BERT sentiment classifier to evaluate service quality, and continuously optimize the resonance group package design and resource scheduling strategy through multi-dimensional data fusion and causal inference methods.

[0044] The method for dynamically balancing tourist satisfaction and resource utilization rate includes: Map the immersion value score of tourists to consumable points through a non-linear weighted mapping function, and define the non-linear weighted mapping function as ; where is the consumable points of tourist ; is the immersion value score of tourist ; is the adjustment factor for controlling the overall amplification or reduction of consumable points. According to the expert experience method, ranges from 0 to 1; is the adjustment factor for controlling the shape of the consumable points mapping curve, realizing an increasing or decreasing non-linear mapping to reflect a greater difference in points for tourists with high immersion value scores; The base of spendable points is to ensure that all tourists have a minimum spendable points value; The tourists Spendable points Stored in the points redemption reward module, and update the tourists' expendable points balance; when tourists initiate a request to redeem merchant resources, the platform adopts a weighted fair queuing mechanism to sort tourists in descending order according to their expendable points, and processes tourist requests in descending order of expendable points, and allocates available merchant resources; The platform calculates the resource share available to each tourist based on the current total merchant resources and consumable points; introduces a leaky bucket flow limiting mechanism to control resource request traffic, and sets control parameters for resource request traffic, including leaky bucket capacity and request outflow rate, to ensure that the tourist request rate is less than the request outflow rate and the number of requests in the leaky bucket does not exceed the leaky bucket capacity, thereby dynamically balancing tourist satisfaction and resource utilization.

[0045] The following technical problems existing in the prior art are solved: At present, the resource exchange between tourists and merchants usually adopts a method based on fixed weights or linear integral accumulation, which fails to fully consider the differences in tourists' immersion value scores, resulting in a lack of significant distinction between high-value tourists and low-value tourists, which is easy to cause fairness disputes; at the same time, the resource request processing mechanism in the traditional platform fails to effectively combine the activity and preferences of tourists, and it is easy for a single highly active tourist to monopolize a large amount of resources, reducing the satisfaction of other tourists; in addition, a simple first-come-first-served or polling strategy is often adopted in the resource request process, and flow control and dynamic flow limiting measures are not introduced, which is easy to cause system congestion or imbalance in resource allocation.

[0046] Compared with the prior art, the beneficial effects are as follows: the immersion value points of tourists are mapped into consumable points through a nonlinear weighted mapping function, and the overall magnification and reduction of the points and the shape of the curve are controlled by the adjustment factor, so as to effectively amplify the difference in points between tourists with high immersion value and tourists with low immersion value, and ensure the fairness and differentiation of points distribution; By setting the points base, all tourists are guaranteed to obtain basic points, thus avoiding the fairness problem caused by points returning to zero. A weighted fair queuing mechanism is adopted to sort and process resource requests according to the points that tourists can spend, taking into account the activity and immersive experience of tourists, and achieving the rationality and fairness of the priority of resource request processing. A leaky bucket current limiting mechanism is introduced. By setting the leaky bucket capacity and the request outflow rate, it is ensured that the tourist request flow is controlled and does not exceed the system carrying capacity, so as to achieve system load balancing and avoid response delays caused by resource overload.

[0047] The preset cumulative behavior frequency threshold is set by the staff. By collecting different cumulative behavior frequencies, the average value of multiple cumulative behavior frequencies is taken as the preset cumulative behavior frequency threshold. Similarly, the preset resonance similarity score threshold of tourists on the complete activity path is set.

[0048] In this embodiment, a dynamic adjustment mechanism is introduced based on the spatial distribution density of the global tourism data during the construction of the initial geographical grid network. By calculating the density level of data points in each region, the grid side length of the corresponding region is automatically adjusted, so that smaller grids are used in data-intensive regions to enhance the fineness, and larger grids are used in data-sparse regions to reduce the computational burden. It effectively overcomes the problems of low computational efficiency or spatial information loss caused by fixed grid sizes in the prior art, and significantly improves the adaptability and processing performance of the platform.

[0049] A grid reconstruction rule triggered dynamically based on spatial data changes is proposed, covering two reconstruction strategies: refinement and merging. In terms of grid refinement, a refinement trigger determination method that comprehensively considers the cumulative frequency and statistical variance of behavior data is adopted, enabling the spatial grid to be automatically refined in high-frequency regions according to dynamic factors such as actual passenger flow and activity density, thereby improving the spatial analysis accuracy. In terms of grid merging, the cumulative amounts of behavior data of adjacent grids are compared, and low-activity adjacent grids are automatically merged to reduce unnecessary grid subdivision and computational burden. Compared with the single and static grid division methods in the prior art, the adaptive dynamic reconstruction strategy of this solution can respond to the changes in global tourism data in real time, significantly enhancing the real-time performance and flexibility of the platform. It significantly improves the adaptability, computational efficiency, and spatial analysis accuracy of the spatial grid network, providing a solid support for the in-depth analysis and intelligent services of global tourism data.

[0050] The immersive value score of tourists is mapped to consumable points through a non-linear weighted mapping function, and a regulation factor is used to control the overall amplification and reduction of the points and the curve shape, effectively amplifying the difference in points between high-immersion-value tourists and low-immersion-value tourists to ensure the fairness and discrimination of point allocation; by setting a point base, it is ensured that all tourists obtain basic points, avoiding fairness issues caused by zero points. A weighted fair queuing mechanism is adopted to sort and process resource requests based on the consumable points of tourists, taking into account both tourist activity and immersive experience, and realizing the rationality and fairness of the priority of resource request processing. A leaky bucket flow limiting mechanism is introduced. By setting the leaky bucket capacity and request outflow rate, it is ensured that the tourist request flow is controlled and does not exceed the system's carrying capacity, realizing system load balancing and avoiding response delays caused by resource overload.

[0051] Embodiment 2

[0052] Please refer to Figure 3 As shown, for the parts not described in detail in this embodiment, refer to the description content of Embodiment 1. A destination global tourism big data management method based on data processing is provided, including: S1. Collect global tourism data and build a geographic grid network, set spatial grid reconstruction rules, and automatically refine or merge grids; introduce a trajectory trigger mechanism, and enable fine-grained modeling to generate a geographic perception structure when the cumulative behavior frequency in the preset target area reaches the preset cumulative behavior frequency threshold; S2. Analyze the continuous behaviors of tourists in the geographical perception structure and construct a multi-dimensional situational coding vector; reconstruct the complete behavior chain of tourists through the behavior puzzle deconstruction method and implicit behavior compensation method; S3. Based on the multi-dimensional situational coding vector and the complete behavior chain, the tourist immersion value score is calculated. The resonance path matrix generation mechanism is used to compare the resonance similarity of different tourists on the complete activity path, generate the resonance path matrix between tourists, and establish the tourist behavior evolution map; S4. Generate personalized tour guidance paths for tourists based on their immersion value scores and tourist behavior evolution maps; adopt a reverse resonance recommendation strategy to push the highest similarity but unvisited geographical grid points to tourists based on their immersion value scores; S5. The platform links merchant resources around the geographical grid points with the highest resonance similarity; introduces a resonance group package linkage mechanism to drive the release of merchant resources in the preset destination and form a resource sharing network; S6. Map the tourists’ immersion value points into consumable points to support the exchange between tourists and merchants; use weighted fair queuing and leaky bucket flow limiting mechanism to allocate merchant resources, and dynamically balance tourist satisfaction and resource utilization.

[0053] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters and thresholds in the formula are set by technicians in this field according to actual conditions.

[0054] The above is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments. All technical solutions under the concept of the present invention belong to the protection scope of the present invention. It should be pointed out that for ordinary technical users in this technical field, some improvements and modifications without departing from the principle of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A big data management platform for the whole destination of tourism based on data processing, characterized in that, include: The perception aggregation grid module collects global tourism data and constructs a geographic grid network, sets spatial grid reconstruction rules, and automatically refines or merges grids; introduces a trajectory trigger mechanism, and enables fine-grained modeling to generate a geographic perception structure when it detects that the cumulative behavior frequency in the preset target area reaches the preset cumulative behavior frequency threshold; The behavior deconstruction coding module analyzes the continuous behavior of tourists in the geographical perception structure and constructs a multi-dimensional situation coding vector; through the behavior puzzle deconstruction method and implicit behavior compensation method, the complete behavior chain of tourists is reconstructed; The immersion value quantification module calculates the immersion value score of tourists based on the multi-dimensional situational coding vector and the complete behavior chain. It uses the resonance path matrix generation mechanism to compare the resonance similarity of different tourists on the complete activity path, generate the resonance path matrix between tourists, and establish a tourist behavior evolution map. The guidance recommendation feedback module generates personalized tour guidance paths for tourists based on their immersion value scores and the evolution map of their behavior. It adopts a reverse resonance recommendation strategy to push the most similar but unvisited geographical grid points to tourists based on their immersion value scores. The platform response management module links merchant resources around the geographical grid with the highest resonance similarity; introduces the resonance group package linkage mechanism to drive the release of merchant resources in the preset destination and form a resource sharing network; The points redemption reward module maps tourists' immersion value points into consumable points, supporting redemption between tourists and merchants. It adopts weighted fair queuing and leaky bucket flow limiting mechanisms to allocate merchant resources, dynamically balancing tourist satisfaction and resource utilization.

2. The destination global tourism big data management platform based on data processing according to claim 1, wherein The method for automatically thinning or merging grid points comprises: Collect global tourism data, which includes tourist behavior data, environmental facilities data, merchant service data, spatial geographic data, and management policy data; clean the global tourism data through sliding window outlier detection technology, and perform standard deviation normalization to obtain normalized global tourism data; For the geographic coordinate points in the normalized all-for-one tourism data, use the convex hull algorithm to extract the minimum convex boundary of all geographic coordinate points, and determine the required coverage area for constructing the geographic grid network according to the minimum convex boundary; divide the required coverage area according to the preset basic grid side length , and perform preliminary spatial grid division; adopt the adaptive quadtree division method to generate the initial geographic grid network. For any point within the required coverage area, implement the encoding mapping from the geographic coordinate point to the geographic grid through the mapping function; Introduce a dynamic adjustment strategy based on spatial density to dynamically adjust the basic lattice side length, and calculate any point within the required coverage area point density , according to the point density , adjust the basic lattice side length through the lattice side length adjustment function; By encoding all geographic coordinate points in the global tourism data, they are classified into corresponding geographic grid points; setting spatial grid reconstruction rules, for any grid point in the geographic grid network, within the preset time window, if there is a time period that meets the refinement trigger condition function, the grid point is automatically refined; For any grid point in the geographic grid network, if there is an adjacent grid point, the adjacent grid point belongs to the adjacent grid point set of any current grid point, and the cumulative behavior frequency in the adjacent grid point is less than the cumulative behavior frequency in the grid point, then the automatic merging of the grid points is triggered.

3. The destination global tourism big data management platform based on data processing according to claim 2, characterized in that The method for generating the geographic perception structure comprises: Introduce a trajectory trigger mechanism to collect and count the trajectory points of tourist behavior data contained in the global tourism data, and calculate the cumulative behavior frequency of trajectory points in the preset target area within the preset time period through a sliding time window; Determine whether the cumulative behavior frequency reaches the preset cumulative behavior frequency threshold. If it reaches, trigger fine-grained modeling; adjust the spatial division granularity according to the density of trajectory points in the target area, including reducing the side length of the basic grid point and deepening the quadtree division depth, so as to generate a geographical grid network with finer granularity. Remap and encode all trajectory points in the preset target area, and classify the trajectory points into the newly generated fine-grained grid points; based on the remapped trajectory points and their corresponding fine-grained grid points, generate a geographical perception structure including grid point encoding, spatial position information, cumulative behavior frequency of trajectory points within a time period, and trajectory point density information.

4. The destination-wide tourism big data management platform based on data processing according to claim 3, characterized in that The construction method of the multi-dimensional context encoding vector includes: Sort the trajectory points in the tourist behavior data in the global tourism data in chronological order, and extract the timestamp, spatial position information, grid point encoding corresponding to the trajectory point, and behavior category of each trajectory point to form a continuous trajectory behavior sequence. For each trajectory behavior sequence, analyze its crossing path, time period, stay duration, moving speed, and direction change in the geographical perception structure, and statistically analyze the behavior pattern characteristics within each time period; extract multi-dimensional trajectory features according to the spatial dimension, time dimension, behavior dimension, social dimension, and semantic dimension; use feature splicing and hash encoding processing to combine the extracted multi-dimensional trajectory features to generate a multi-dimensional context encoding vector.

5. The destination global tourism big data management platform based on data processing according to claim 4, characterized in that, The reconstruction method of the complete behavior chain of the tourist includes: Divide the sequence of multi-dimensional context encoding vectors of tourists obtained by analysis according to chronological order and spatial adjacency relationship, and split it into n behavior sub-fragments. The behavior sub-fragments reflect the local behavior characteristics of tourists within a limited time period and spatial range, and are called behavior puzzles. For the incomplete behavior sub-fragments caused by data loss, sensing blind spots, or anomaly detection reasons, adopt an implicit behavior compensation method, and based on tourist behavior data and environmental facility data, use a machine learning model to infer the missing behavior sub-fragments and their time series and spatial positions. Based on chronological order and spatial adjacency relationship, splice the behavior sub-fragments and the behavior sub-fragments obtained by implicit behavior compensation, and combine the multi-dimensional trajectory features corresponding to the multi-dimensional context encoding vector to construct the complete behavior chain of tourists.

6. The big data management platform for destination global tourism based on data processing according to claim 5, characterized in that, The establishment method of the tourist behavior evolution map includes: According to the multi-dimensional context encoding vector and the complete behavior chain obtained by analyzing tourists in the geographical grid network, use the weighted vector aggregation technology to calculate the immersion value score of tourists. The immersion value score of this tourist comprehensively reflects the behavior activity, behavior type, stay duration, and emotional participation of tourists in the time and space dimensions. Combined with the behavior category weight and cumulative behavior frequency statistics, comprehensively calculate the behavior value, and collect tourist comment feedback data. Introduce an emotion analysis model to score the emotions of the tourist comment feedback data, and generate the immersion value score of tourists. Construct a resonance path matrix, use the dynamic time warping algorithm to match the multi-dimensional context encoding vector sequences of different tourists, and calculate the path similarity; perform time alignment on the tourist behavior data, and calculate the Euclidean distance between the multi-dimensional feature vectors corresponding to the multi-dimensional context encoding vectors as the local distance; construct a complete activity path based on the local distance, and output the resonance similarity score of the tourist on the complete activity path. Construct a tourist behavior evolution graph according to the constructed resonance path matrix. The tourist behavior evolution graph is a weighted directed graph. Each node of the tourist behavior evolution graph represents each tourist, and the edge represents the behavioral relationship connection between two tourists; the weight of the edge represents the resonance similarity score of the tourist on the complete activity path.

7. The big data management platform for the whole destination tourism based on data processing according to claim 6, characterized in that The method for generating the personalized tour guide path includes: Use the tourist behavior evolution graph represented by the weighted directed graph to analyze the behavioral similarity between any preset target tourist and other tourists in the tourist behavior evolution graph, identify the neighboring tourist group with the most similar behavior patterns, and infer the tour routes that the target tourist may be interested in based on the historical behavior evolution paths of the neighboring tourist group. Combine the environmental facility data and the tourist behavior data, use the A* algorithm to obtain the optimal tour path that meets the tourist interest preferences and path coherence, and define it as the personalized tour guide path; feedback the generated personalized tour guide path to the tourist mobile terminal in the form of multi-dimensional context encoding to provide real-time navigation and behavior suggestions.

8. The destination global tourism big data management platform based on data processing according to claim 7, characterized in that The method for pushing the geographical grid points with the highest similarity but not visited includes: Screen out the neighboring tourist groups whose resonance similarity scores on the complete activity path are greater than the preset resonance similarity score threshold of tourists on the complete activity path; mark the geographical grid points that have been visited according to the complete behavior chain of the preset target tourist, and combine the complete behavior chains of the neighboring tourist groups to identify the geographical grid points that the target tourist has not visited but the neighboring tourists have visited as the recommended candidate grid points. Introduce the immersion value score of the target tourist as a weight factor, and through the weighted vector aggregation method, comprehensively evaluate the resonance similarity score of the tourist on the complete activity path and the immersion value score of the tourist to form a recommended priority ranking model. For all the recommended candidate grid points, give priority to recommending the geographical grid points with the highest interest matching degree and the highest immersion value score with the preset target tourist. Design a dynamic recommendation mechanism, dynamically generate a list of recommended geographical grid points according to the changes in tourist behavior data and the immersion value score of tourists, and use the push notification technology to send the latest recommendation results to the tourist mobile terminal in real time to assist tourists in personalized tour planning.

9. The destination global tourism big data management platform based on data processing according to claim 8, characterized in that, The method for forming the resource sharing network includes: Determine the core resonance node in the geographical grid point area with the highest resonance similarity score of tourists on the complete activity path; based on the spatial database technology, perform spatial mapping between the core resonance node and the merchant resources in the preset destination to establish the corresponding relationship between the geographical location and the merchant resources. Through an event-driven architecture, combined with an LSTM time series prediction model, the activation status of the resonance group package is monitored in real time, and resource scheduling instructions are automatically pushed to relevant merchants, and elastic expansion is carried out using a microservices architecture; after receiving the instructions, the merchant-side resource management system completes inventory adjustment, personnel scheduling, and service preparation to achieve dynamic resource response; A graph database is used to construct a resource sharing network covering preset target geographical grid points and surrounding area merchants. The nodes in the resource sharing network represent merchant resources, and the edges represent resource sharing cooperation relationships; a big data processing platform is used to collect tourist consumption data, merchant service feedback data, and user evaluation data in real time; a BERT sentiment classifier is used to evaluate service quality, and the resonance group package design and resource scheduling strategy are continuously optimized through multi-dimensional data fusion and causal inference methods.

10. The big data management platform for destination-wide tourism based on data processing according to claim 9, wherein, The method for dynamically balancing tourist satisfaction and resource utilization rate includes: The tourist immersion value score is mapped into consumable points through a non-linear weighted mapping function. The non-linear weighted mapping function is defined as ; where is the consumable points of the tourist ; is the immersion value score of the tourist ; is the adjustment factor for controlling the overall amplification or reduction of the consumable points is the adjustment factor for controlling the shape of the consumable points mapping curve is the base of the consumable points, ensuring that all tourists have a minimum value of consumable points Store the consumable points of tourists in the points redemption reward module and update the balance of the tourists' consumable points; when a tourist initiates a request to exchange for merchant resources, the platform adopts a weighted fair queuing mechanism to sort the tourists in descending order according to their consumable points, process the tourist requests in the descending order of consumable points, and allocate available merchant resources; ​ The platform calculates the resource share that each tourist can obtain based on the current total merchant resources and consumable points; a leaky bucket flow limiting mechanism is introduced to control the resource request traffic, and control parameters for the resource request traffic are set, including the leaky bucket capacity and the request outflow rate, to ensure that the tourist request rate is less than the request outflow rate, and the number of requests in the leaky bucket does not exceed the leaky bucket capacity, thereby dynamically balancing tourist satisfaction and resource utilization rate.

Images