GIS-based culture and tourism spatio-temporal feature fusion system

Abstract

The invention belongs to the field of tourism data processing, and provides a GIS-based culture and tourism spatio-temporal feature fusion system, which comprises a data acquisition module used for acquiring culture and tourism spatio-temporal data; the data fusion module is used for establishing semantic association between the cultural tourism data based on the knowledge graph; the GIS topological structure construction module is used for constructing a topological graph of the culture and tourism data and constructing a topological relation between the culture and tourism data based on the similarity of the topological graph and the semantic association relation; the culture and tourism time-space feature fusion module is used for constructing a culture and tourism fusion map; matching the tourist trajectory data with the cultural tourism resources; determining an influence range of the cultural activity; the prediction module is used for predicting a tourist diffusion thermodynamic diagram of a preset destination in a preset time; and the visual display module is used for displaying the cultural tourism fusion map and dynamically displaying the tourist diffusion thermodynamic diagram on the cultural tourism fusion map.

Description

Technical Field

[0001] The present invention belongs to the field of tourism data processing, and in particular relates to a GIS-based culture and tourism spatiotemporal feature fusion system. Background Art

[0002] With the rapid development of information technology, geographic information systems (GIS), and artificial intelligence (AI), the cultural and tourism industries are gradually transforming towards digitalization and intelligentization. In recent years, various cultural and tourism big data have been gradually accumulated, including visitor behavior data, cultural resource information, and scenic spot operation data. However, cultural and tourism data often comes from a wide range of sources and in varying formats. This data suffers from heterogeneity, inconsistent spatiotemporal scales, and unclear semantic associations, hindering the deep integration and intelligent application of cultural and tourism resources. Therefore, leveraging advanced GIS technologies, AI algorithms, and big data processing methods to enhance the analytical capabilities of cultural and tourism data and achieve efficient data integration, visitor behavior prediction, and intelligent visualization has become a key research direction in the intelligent management of cultural and tourism.

[0003] Currently, GIS applications in tourism management are relatively mature, such as 3D visualization of scenic spots, route navigation, and visitor flow analysis. However, traditional GIS systems primarily rely on static data and lack the ability to deeply analyze and dynamically predict visitor behavior. Furthermore, cultural resource data often exhibits unstructured characteristics, such as text descriptions, historical background, and information on cultural activities, making it difficult to directly match them with the spatial data of tourist attractions. This results in a lack of correlation between cultural and tourism resources, hindering the in-depth development of cultural tourism integration.

[0004] On the other hand, tourist behavior analysis and prediction have become crucial components of smart tourism management. Traditional methods rely on statistical analysis of tourist trajectory data, but lack comprehensive consideration of multidimensional factors such as cultural resources, scenic environment, and social activities, resulting in low prediction accuracy. Furthermore, cultural activities (such as festivals, exhibitions, and intangible cultural heritage experiences) have a significant impact on tourist flow patterns, but existing research has limited analysis of the impact of cultural activities, making it difficult to provide scenic area managers with accurate passenger flow forecasting and control solutions. Summary of the Invention

[0005] In order to solve the problems in the prior art, the present invention provides a GIS-based culture and tourism spatiotemporal feature fusion system, which includes the following modules:

[0006] The data acquisition module is used to obtain cultural and tourism spatiotemporal data, and store and process them in the spatial geographic information format;

[0007] The data fusion module is used to project data from different sources into the same geographic coordinate system based on the spatial alignment method of coordinate matching; align data of different time granularities using the time window matching method; and establish semantic associations between cultural tourism data based on the knowledge graph;

[0008] A GIS topology structure construction module is used to construct a topological map of cultural and tourism data, and to construct the topological relationship between cultural and tourism data based on the similarity of the topological map and the semantic association relationship, including the adjacency, connectivity, inclusion and nearest neighbor relationships between cultural resources, tourist attractions, tourist trajectories and road networks;

[0009] A cultural and tourism spatiotemporal feature fusion module is used to identify the spatial correlation between cultural resources and tourist attractions based on the adjacency relationship and construct a cultural tourism fusion map; match tourist trajectory data with cultural tourism resources based on the connectivity relationship; and determine the impact range of cultural activities based on the inclusion relationship and nearest neighbor relationship;

[0010] A prediction module is used to predict the tourist diffusion heat map of a preset destination and a preset time based on the matching data of tourist trajectory data, cultural tourism resources, and the influence range of cultural activities;

[0011] The visualization display module is used to display the cultural tourism integration map and dynamically display the tourist diffusion heat map on the cultural tourism integration map.

[0012] Furthermore, the cultural and tourism spatiotemporal data include: cultural resource data, tourist attraction data, and tourist trajectory data.

[0013] Furthermore, the data fusion module includes:

[0014] The spatial alignment unit uses a coordinate matching method to standardize the projection of cultural and tourism data from different sources so that they are in a unified geographic coordinate system;

[0015] The time alignment unit uses a time window matching method to align data of different time granularities to ensure that cultural and tourism data are analyzed within the same time period;

[0016] The semantic association construction unit establishes semantic associations between cultural resources, tourist attractions, and tourist behaviors based on the knowledge graph to explore hidden cultural tourism relationships.

[0017] Furthermore, the GIS topology structure building module includes:

[0018] A topological map generation unit is used to construct a topological map of cultural and tourism data to represent the structured relationships between cultural resources, tourist attractions, tourist trajectories, and road network spatial elements;

[0019] a topological similarity calculation unit, configured to analyze the correlation between cultural and tourism data based on the structural similarity of the topological graph;

[0020] A topological semantic association construction unit is used to establish a topological relationship between cultural resources, tourist attractions, tourist trajectories, and road networks based on the topological map and the semantic association relationship.

[0021] Furthermore, the topology map generating unit includes:

[0022] The spatial element extraction subunit is used to extract cultural resources, tourist attractions, tourist trajectories, and road network spatial elements from the GIS database and convert the spatial elements into node information in the topological map;

[0023] A relationship edge construction subunit is used to construct edge information of a topological graph according to the spatial relationship and semantic relevance between the spatial elements, so as to establish a topological connection between the spatial elements;

[0024] The topology structure storage subunit is used to store the constructed topology graph using a graph database or a spatial database to support subsequent topology analysis and query.

[0025] Furthermore, the topology similarity calculation unit includes:

[0026] Topological feature extraction subunit, used to extract topological features of cultural and tourism data;

[0027] The graph matching calculation subunit is used to calculate the topological similarity between different cultural resources, tourist attractions, and tourist behaviors using a graph similarity algorithm, and to build relationships between cultural and tourism data based on the similarity.

[0028] Furthermore, the topological semantic association construction unit includes:

[0029] The adjacency relationship construction subunit is used to calculate the spatial adjacency between cultural resources and tourist attractions;

[0030] Connectivity construction subunit, used to calculate the accessibility between cultural resources, tourist attractions, tourist trajectories, and road networks;

[0031] The inclusion relationship construction sub-unit is used to calculate the spatial inclusion relationship of cultural resources, tourist attractions, and tourist trajectories;

[0032] The nearest neighbor relationship construction subunit is used to calculate the relationship between the tourist's current location and the nearest cultural tourism resources.

[0033] Furthermore, the culture and tourism spatiotemporal feature fusion module includes:

[0034] The cultural tourism fusion map generation module is used to construct a cultural tourism fusion map on the GIS platform based on the adjacency relationship between cultural resources and scenic spots, and visually display the spatial correlation of cultural resources to tourist attractions;

[0035] A cultural tourism trajectory matching module matches tourist trajectory data with cultural tourism resources based on the connectivity relationship to identify tourist flow patterns in cultural scenic spots and analyze the impact of cultural resources on tourist behavior;

[0036] The cultural activity influence range determination unit analyzes the influence range of the cultural activity on the surrounding scenic spots based on the inclusion relationship and the nearest neighbor relationship, and determines the influence radius of the cultural activity.

[0037] Furthermore, the prediction module includes:

[0038] Tourist trajectory data analysis unit, used to extract and analyze tourist historical trajectory data;

[0039] Trajectory data preprocessing module, used to denoise, standardize and repair tourist trajectory breakpoints;

[0040] Trajectory pattern recognition module, used to extract tourist behavior patterns based on historical tourist trajectory data and identify the movement patterns of different types of tourists;

[0041] The cultural tourism resource matching unit is used to analyze the spatial matching relationship between tourist trajectory data and cultural tourism resources, identify the degree of tourists' interest in different cultural resources, and optimize tourist diffusion prediction based on the matching data;

[0042] The cultural activities impact range analysis unit is used to calculate the tourist attraction of cultural activities based on historical data and predict the future tourist diffusion range of cultural activities;

[0043] The tourist diffusion heat map generating unit generates a visual tourist diffusion heat map based on the tourist trajectory data, cultural tourism resource matching data and the influence range of cultural activities.

[0044] Furthermore, the visual display module includes:

[0045] The map data loading module is used to load multi-source data on cultural resources, tourist attractions, and tourist trajectories, and perform spatial rendering to support the visual display of cultural and tourism integrated maps;

[0046] The cultural resources and tourist attractions association rendering module is used to generate spatial association visualization effects based on the adjacency and connectivity relationships between cultural resources and tourist attractions;

[0047] The heat map generation module is used to calculate the tourist density distribution based on tourist trajectory data, cultural tourism resource matching data, and the impact range of cultural activities, and generate a heat map to visualize tourist flow trends;

[0048] The dynamic time series heat map module is used to generate dynamic heat maps based on tourist data in different time periods to show the temporal and spatial changing trends of tourist flows.

[0049] This invention provides a GIS-based system for integrating cultural and tourism spatiotemporal features. It addresses existing issues such as heterogeneous cultural and tourism data, inconsistent spatial alignment, inconsistent temporal scales, and ambiguous semantic associations, enabling deep integration, intelligent analysis, and dynamic display of cultural and tourism data. Compared to existing technologies, this invention offers the following advantages:

[0050] Through methods such as knowledge graph construction, semantic matching, and intelligent association calculation, the system deeply explores the implicit relationships between cultural resources, tourist attractions, and tourist behavior, establishing a highly correlated cultural tourism data network. Using spatial feature extraction, relationship edge construction, and topological structure storage, a topological network of cultural and tourism data is constructed, enabling spatial analysis and route optimization of cultural resources, scenic spots, and tourist behavior within a GIS environment. Using methods such as trajectory pattern recognition, tourist interest matching, and cultural event impact prediction, the system intelligently analyzes tourists' travel preferences, route choices, and cultural points of interest, improving the accuracy of tourist behavior prediction. Combining tourist trajectory data, cultural event information, and scenic area carrying capacity data, the system generates tourist diffusion heat maps and predicts future tourist flow trends, providing real-time warnings and optimization solutions for scenic area management. Using various GIS visualization methods, such as cultural tourism fusion maps, tourist diffusion heat maps, and interactive analysis controls, the system intuitively displays cultural and tourism data, supporting real-time interactive querying and dynamic adjustments.

[0051] The system can be widely used in many fields such as smart scenic spot management, cultural heritage protection, urban cultural tourism planning, personalized recommendations for tourists, etc. It supports the expansion of multiple data types and has good applicability and scalability.

[0052] This invention leverages GIS technology, machine learning, knowledge graphs, spatial analysis, and other methods to achieve standardized integration, intelligent analysis, precise prediction, and visual display of cultural and tourism data, significantly enhancing the intelligent level of cultural tourism management. This system not only optimizes the visitor experience and improves scenic area management efficiency, but also promotes the deep integration of culture and tourism, providing technical support for cultural communication, smart tourism, and precision marketing, with significant application value and promotional significance. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 It is a system structure diagram of the present invention;

[0055] Figure 2 It is a specific implementation of the system of the present invention. DETAILED DESCRIPTION

[0056] Below, the invention is preferably described with reference to the accompanying drawings and specific embodiments.

[0057] This embodiment solves the above problem through the following steps:

[0058] In one embodiment, reference Figure 1 The present invention provides a GIS-based culture and tourism spatiotemporal feature fusion system, which aims to integrate multi-source heterogeneous data such as cultural resources, tourist attractions, tourist trajectories, and transportation networks, and utilizes the spatial analysis capabilities, topological structure construction methods, and deep learning technologies of GIS to comprehensively analyze the spatial correlation, spatiotemporal evolution patterns, and tourist behavior characteristics of culture and tourism. It also uses visualization methods to display the geographical distribution, tourist flow trends, and intelligent recommended routes of cultural and tourism integration, so as to improve the efficiency of the coordinated utilization of cultural and tourism resources and provide accurate data support and intelligent decision-making capabilities for smart tourism and cultural heritage protection.

[0059] Specifically, the system includes the following modules:

[0060] The data acquisition module is used to obtain cultural and tourism spatiotemporal data and store and process them in the spatial geographic information format.

[0061] Specifically, the data acquisition module includes:

[0062] The cultural resource data acquisition unit is used to collect information related to cultural resources. The cultural resources include but are not limited to material cultural heritage, intangible cultural heritage, historical buildings, museums, cultural scenic spots, folk villages, cultural festivals, etc. The cultural resource data includes the geographical coordinates, classification information, historical background, operating status, opening hours, tourist visit records and tourist evaluation data of the cultural resources.

[0063] The tourist attraction data acquisition unit is used to collect spatial information of tourist attractions. The tourist attractions include but are not limited to 4A-level and above tourist attractions, historical and cultural blocks, natural scenic areas, theme parks, etc. The tourist attraction data includes the geographical boundaries of the scenic area, the distribution of tourist facilities, tourist flow statistics, the carrying capacity of the scenic area, the management information of the scenic area, the activity schedule of the scenic area, etc.

[0064] The tourist trajectory data acquisition unit is used to collect the tourist's movement trajectory data. The tourist trajectory data is obtained based on a variety of positioning technologies, including but not limited to GPS positioning data, WiFi probe data, mobile communication base station data, RFID sensing data, etc. The tourist trajectory data includes the tourist's time and space coordinates, movement speed, stay time, tour path and behavioral preference information.

[0065] The traffic network data acquisition unit is used to collect traffic network information within the tourist area. The traffic network data includes but is not limited to highway data, pedestrian path data, subway line data, bus line data, taxi routes, shared transportation networks, parking lot distribution and road traffic status information.

[0066] The environmental data acquisition unit is used to collect data on environmental factors that affect cultural and tourism activities. The environmental data includes but is not limited to real-time meteorological data (temperature, precipitation, wind speed), air quality data, hydrological condition data, noise pollution data, etc.

[0067] The social media data acquisition unit is used to collect tourists' interactive data on social media platforms. The social media data includes but is not limited to tourists' check-in records, comment feedback, photo sharing, text evaluation, number of likes, number of reposts and hot topic trend data on social platforms.

[0068] The data storage and format conversion unit is used to store and standardize the collected data. The data storage and format conversion unit pre-processes the data based on the spatial geographic information format and stores the data in the GIS database. The storage methods include vector format storage, raster format storage and time series data storage to ensure that the collected cultural and tourism spatiotemporal data are compatible with the GIS system and support subsequent spatial analysis, topological relationship construction and visualization display.

[0069] The data fusion module is used to project data from different sources into the same geographic coordinate system based on the spatial alignment method of coordinate matching; align data of different time granularities using the time window matching method; and establish semantic associations between cultural tourism data based on the knowledge graph.

[0070] Specifically, the data fusion module includes:

[0071] A spatial alignment unit is used to perform standardized projection on cultural and tourism data from different sources based on a spatial alignment method of coordinate matching, so that the data can be integrated in the same geographic coordinate system. The spatial alignment unit specifically includes:

[0072] The coordinate conversion subunit is used to convert geographic coordinates between data in different formats. It supports conversions to commonly used geographic coordinate systems worldwide, including but not limited to WGS-84, GCJ-02, BD-09, EPSG:4326, and EPSG:3857. Coordinate conversion algorithms are used to convert cultural and tourism data from different sources into standardized geographic coordinate systems, such as converting BD-09 coordinates to WGS-84 coordinates, to ensure that data from different systems are not misaligned when visualized on the GIS platform. Coordinate projection transformation methods, such as Mercator or Gauss-Krüger projections, are used to support interchange between different map projection systems.

[0073] For example, in a cultural tourism project in Aba Prefecture, Sichuan Province, some visitor trajectory data is based on GCJ-02 coordinates, while remote sensing imagery data uses WGS-84 coordinates. The system uses a coordinate conversion subunit to convert all data to the EPSG:4326 coordinate system, ensuring accurate data matching on the GIS platform and improving the accuracy of spatial data fusion.

[0074] The precision correction subunit is used to correct spatial precision deviations in data from different sources. It uses high-precision geographic reference data (such as remote sensing imagery and precise mapping data) for offset correction to improve data fusion accuracy. It uses a benchmark alignment method to select high-precision geographic reference points for data offset correction, such as using geographic landmarks (such as subway stations and iconic buildings) for positioning comparison. Bilinear interpolation or nearest neighbor interpolation is used to spatially correct low-precision data to improve data alignment accuracy.

[0075] For example, when constructing a cultural resource map of the Zoige Grassland, the drone imagery data deviated by 5-10 meters from the scenic area boundaries in the GIS database. The precision correction subunit used remote sensing image correction methods to reduce the data alignment error to within 1 meter, thus ensuring the accuracy of the scenic area map.

[0076] The spatial projection subunit is used to perform spatial projection transformation on cultural and tourism data from different sources to ensure that the data can be uniformly visualized and analyzed on the GIS platform.

[0077] Equal-area projection or orthogonal projection is used to ensure that the area and direction of data such as cultural scenic area boundaries and tourist trajectories on the map are consistent; a multi-scale projection method is adopted, with Mercator projection used for large-scale maps and Gauss-Krüger projection used for local scenic areas to improve the accuracy of data visualization; further, combined with three-dimensional projection technology (such as TIN terrain modeling), the three-dimensional landscape data of cultural resources (such as scenic area stereo models) are projected and transformed to support GIS three-dimensional visualization.

[0078] For example, in the Huanglong Scenic Area's GIS system, different map layers use different projections. The system converts all data to EPSG:3857 using the spatial projection subunit, ensuring the correct alignment of scenic area topography, visitor movement patterns, and cultural landmarks for GIS visualization.

[0079] The time alignment unit is used to align data of different time granularities using a time window matching method to ensure the consistency of cultural and tourism data in the time dimension. The time alignment unit specifically includes:

[0080] The time window matching subunit is used to set a fixed time window and align cultural resource data, tourist attraction data, and tourist trajectory data collected at different times to ensure that the data is analyzed within the same time period. By setting a fixed time window (such as hourly or daily), data from different data sources are divided into time zones, so that cultural activities, tourist flow, environmental data, etc. are aligned on the same time axis. Sliding window matching is used to align data with different time granularities, such as matching and analyzing minute-level tourist trajectory data with hourly-level meteorological data. Event-based time windows are used to align sudden cultural events (such as festivals) to analyze the impact of cultural activities on tourist flow.

[0081] For example, in the visitor analysis of Jiuzhaigou Scenic Area, cultural festival data is updated daily, while visitor GPS trajectory data is recorded at the second level. The time window matching subunit aggregates GPS trajectory data at hourly granularity to match it with daily cultural event data, thereby analyzing the impact of cultural activities on visitor flow.

[0082] The time interpolation subunit is used to interpolate the timestamps between different data sources to fill in the missing time data and improve the continuity of the time series data. The time interpolation subunit supports interpolation methods such as linear interpolation, sliding average, and spline interpolation.

[0083] Linear interpolation is used to fill missing timestamp data to improve the integrity of time series data; spline interpolation is used to smooth tourist behavior data to fix data breakpoint problems; further, combined with the ARIMA time series model, data points in missing periods are predicted to improve data continuity.

[0084] The time scale conversion subunit is used to scale data of different granularities so that high-frequency sampling data (such as tourist GPS trajectories) and low-frequency data (such as cultural activity schedules) can be matched on the same time basis. The time scale conversion subunit supports multiple time scale conversions such as days, hours, and minutes.

[0085] The semantic association building unit is used to establish semantic associations between cultural tourism data based on the knowledge graph to explore the potential relationships between cultural resources, tourist attractions, and tourist behaviors. The semantic association building unit specifically includes:

[0086] The knowledge graph construction sub-unit is used to establish a knowledge graph model in the field of cultural tourism. The knowledge graph includes cultural resource nodes, tourist attraction nodes, tourist behavior nodes, environmental factor nodes and their associated edges.

[0087] Entity extraction technology is used to extract core entities from cultural and tourism databases, including cultural resources (such as museums, intangible cultural heritage projects), tourist attractions (such as 5A-level scenic spots, historical ancient cities), tourist behaviors (such as check-ins, comments, tour trajectories), environmental factors (such as weather, traffic conditions), etc., and construct entity nodes; relationship extraction methods are used to establish relationship edges between nodes based on the geographical location, historical background, related activities and other information of cultural resources, such as "Forbidden City-Historical Culture-Ming and Qing Dynasties" or "Dujiangyan-Tourist Attractions-Water Conservancy Projects"; RDF (Resource Description Framework) or Neo4j graph database is used to store knowledge graphs to support efficient query and calculation.

[0088] For example, the knowledge graph construction subunit connects the "Wuhou Temple" node to the "Zhuge Liang" node and further links it to the "Three Kingdoms Culture" topic. When the "Three Kingdoms Culture" topic is mentioned, relevant attractions such as the Wuhou Temple and Jinli Ancient Street are automatically linked.

[0089] The semantic matching subunit is used to perform semantic matching on cultural tourism text data based on natural language processing technology to identify the correlation between cultural resources. The semantic matching subunit adopts semantic analysis methods such as word vector model, TF-IDF method, BERT pre-training model, etc.

[0090] The TF-IDF (Term Frequency-Inverse Document Frequency) method is used to analyze the text descriptions of cultural resources, calculate their importance in the cultural and tourism dataset, and match them accordingly. For example, "Du Fu Thatched Cottage" and "Du Fu's Poetry" have a high degree of similarity in text descriptions; the Word2Vec word vector model is used to convert cultural and tourism text data into vector representations, and calculate the cosine similarity of different cultural resources. For example, the "Great Wall" and "Terracotta Warriors" have a high similarity in the historical and cultural dimensions; the BERT pre-training model is used to perform semantic matching on comments on cultural attractions, tourist feedback, and cultural resource introductions, and automatically extract deep semantic associations between cultural resources, such as the connection between "Qingcheng Mountain" and "Taoist culture."

[0091] For example, the BERT model can automatically retrieve relevant cultural resources such as "Big Wild Goose Pagoda" and "Famen Temple" for the search for "Tang Dynasty historical sites". Even if the words "Tang Dynasty historical sites" are not explicitly mentioned in the introduction of these attractions, semantic matching can still be performed.

[0092] The intelligent association calculation subunit is used to calculate the semantic correlation between different cultural tourism data. The intelligent association calculation subunit adopts methods such as graph neural network, random walk, path search algorithm, etc. to explore the complex relationship between cultural resources and tourism behavior.

[0093] Graph neural networks are used to embed knowledge graphs for learning, and deep relationships between cultural resources are automatically identified. For example, the "Wuhou Temple in Chengdu" and the "Baidi City in Chongqing" are both in the Three Kingdoms culture-related graph and can be identified as similar tourist destinations. A random walk algorithm is used to simulate the potential paths of tourists in the knowledge graph to explore their potential points of interest. For example, if a tourist is interested in the "Dunhuang Mogao Grottoes", he or she may also be interested in the "Yungang Grottoes". The system can generate a travel recommendation list based on this. A path search algorithm (such as the Dijkstra algorithm and A* search) is used to calculate the optimal associated path for tourists in the cultural tourism data graph and automatically recommend the most relevant cultural tourism resources. For example, the system can calculate the cultural and historical associated route from the "Forbidden City in Beijing" to the "Old Summer Palace" based on the shortest path, and provide relevant explanations to tourists.

[0094] Through the above structure, the data fusion module can achieve unified fusion of multi-source cultural and tourism data at the spatial, temporal and semantic levels, and improve the accuracy and intelligence level of cultural tourism spatiotemporal feature analysis.

[0095] The GIS topology structure construction module is used to construct a topological map of cultural and tourism data, and to construct the topological relationship between cultural and tourism data based on the similarity of the topological map and the semantic association relationship, including the adjacency, connectivity, inclusion and nearest neighbor relationships between cultural resources, tourist attractions, tourist trajectories and road networks.

[0096] Specifically, the GIS topology structure building module includes:

[0097] A topology map generation unit is used to construct a topology map of cultural and tourism data to represent the structured relationship between spatial elements such as cultural resources, tourist attractions, tourist trajectories, and road networks. The topology map generation unit specifically includes:

[0098] The spatial element extraction subunit is used to extract spatial elements such as cultural resources, tourist attractions, tourist trajectories, road networks, etc. from the GIS database, and convert the spatial elements into node information in the topological map.

[0099] According to the requirements of topological graph modeling, cultural resources, scenic spots, road networks, and tourist trajectories are converted into nodes in the topological graph respectively, where:

[0100] Cultural resource nodes are represented by POI point data, recording information such as name, category, and geographic coordinates.

[0101] Tourist attraction nodes are represented by polygons, and their center points are extracted as nodes, with additional attributes such as the area of ​​the scenic area and the tourist carrying capacity.

[0102] Road network nodes are represented by polyline endpoints. Intersections and key locations are extracted as nodes, and attributes such as road type and traffic conditions are stored.

[0103] Tourist trajectory nodes,based on the tourists’ historical trajectory data, perform DBSCAN clustering on the,stay points, identify high-frequency stay areas, and store them as nodes in the,topology structure.

[0104] The relationship edge construction subunit is used to construct the edge information of the topological graph according to the spatial relationship and semantic relevance between the spatial elements, so as to establish the topological connection between the spatial elements.

[0105] Specifically, connectivity edges are established between spatial elements such as cultural resources, tourist attractions, tourist trajectories, and road networks.

[0106] GIS network analysis is used to calculate the shortest path between scenic spots and cultural resources, and establish connecting edges; the accessibility of the road topology map is calculated. If two scenic spots or cultural resources are reachable on the road network, a connecting edge is established and the path length is stored.

[0107] Extract historical tourist trajectory data and analyze the movement paths of tourists between different scenic spots or cultural resources; calculate the migration probability of tourists from one cultural resource to another. If it exceeds a threshold (such as 60%), establish a connected relationship edge and assign a weight to the edge.

[0108] Identify the connection paths between subway stations, bus stops and scenic spots. If a scenic spot can be directly connected to another scenic spot by public transportation, establish a connection edge and store the transportation mode information.

[0109] The topology structure storage subunit is used to store the constructed topology graph using a graph database or a spatial database to support subsequent topology analysis and query.

[0110] A topological similarity calculation unit is used to analyze the correlation between cultural and tourism data based on the structural similarity of the topological graph, and the topological similarity calculation unit specifically includes:

[0111] The topological feature extraction subunit is used to extract the topological features of cultural and tourism data, including network topological features such as degree centrality, betweenness centrality, and clustering coefficient.

[0112] The topological feature extraction subunit includes:

[0113] The degree centrality calculation module calculates the degree centrality of cultural resources, tourist attractions, and visitor trajectories in the topological structure to measure the degree of direct connectivity between nodes in the network. It counts the number of directly connected nodes for a cultural resource or scenic spot, calculating its influence in the topological network. A normalization formula is used to standardize degree centrality to facilitate comparison between different types of data.

[0114] For example, if a cultural relic is directly connected to multiple popular scenic spots, the degree centrality of the relic is relatively high, indicating that it plays an important hub role in the cultural tourism network.

[0115] The betweenness centrality calculation module is used to calculate the betweenness centrality of cultural resources, tourist attractions and tourist trajectories in the cultural tourism network to measure the intermediary role of nodes in the tourist flow path; the shortest path calculation method is used to count the number of times a node appears on the shortest path between other nodes; the BFS (breadth-first search) or Dijkstra shortest path algorithm is used to calculate the optimal tourist flow path between cultural resources and determine the betweenness centrality based on this.

[0116] For example, if a cultural museum is located between multiple tourist attractions and a large number of tourists stay or pass through it, its betweenness centrality is high, indicating that the node has a greater influence on the tourists' mobility patterns.

[0117] The clustering coefficient calculation module is used to calculate the local aggregation degree of cultural resources, tourist attractions and tourist behavior in the topological network to analyze the closeness between cultural tourism elements; calculate the ratio of the actual number of connecting edges in the subgraph formed by a cultural scenic spot and its adjacent nodes to the theoretical maximum possible number of edges; use the local clustering coefficient calculation method to analyze the degree of a certain scenic spot's agglomeration in the tourism network to determine its role in the tourist behavior pattern.

[0118] For example, if a cultural theme park is adjacent to multiple folk experience sites and catering centers, and tourists frequently move within the area, its clustering coefficient is high, indicating that a stable cultural tourism cluster has been formed in the area.

[0119] The graph matching calculation subunit is used to calculate the topological similarity between different cultural resources, tourist attractions, and tourist behaviors using graph similarity algorithms (such as graph edit distance, subgraph isomorphism matching, and deep learning graph embedding methods), and to build associations between cultural and tourism data based on the similarity.

[0120] The graph matching calculation subunit includes:

[0121] The graph edit distance calculation module is used to calculate the topological similarity between cultural resources and tourist attractions based on the graph edit distance to identify cultural tourism areas with similar network structures; calculate the minimum number of editing operations between two cultural resource subgraphs, including node addition, node deletion, edge weight adjustment and other operations; and use a dynamic programming algorithm to optimize the graph edit distance calculation to improve computational efficiency.

[0122] For example, if a historical and cultural block is similar to another in topological structure, that is, their cultural resource layout, tourist flow patterns, and scenic area facilities are similar, then their graph editing distance is small and they can be identified as similar cultural tourism destinations.

[0123] The subgraph isomorphism matching module is used to identify the structural consistency between cultural resources, tourist attractions and tourist behavior using the subgraph isomorphism matching method to discover similar cultural tourism patterns; the VF2 algorithm or Ullmann algorithm is used for subgraph matching to determine whether two cultural resource networks are structurally identical or similar; and subgraphs similar to known high-traffic scenic spots are searched in the cultural tourism topology map to identify potential popular tourist areas.

[0124] For example, if the tourist trajectory pattern of an ethnic customs park is highly consistent with that of a historical ancient town, it can be inferred that the cultural tourism attractions and tourist behavior patterns of the two are similar, and tourism management optimization or joint promotion can be carried out.

[0125] The deep learning graph embedding calculation module is used to use deep learning methods to perform embedding calculations on cultural and tourism topological graphs to quantify the similarities between different cultural resources, tourist attractions and tourist behaviors; deep learning models such as GraphSAGE and GCN (graph convolutional network) can be used to map high-dimensional topological data such as cultural resources, scenic spots, and tourist behaviors into low-dimensional vector space for similarity calculation; the training model recognizes patterns in cultural tourism networks, such as tourist flow trends and cultural scenic spot similarities, and generates a topological similarity matrix.

[0126] For example, by training the GCN model, the system can discover that the cultural center of a city is similar to the museum community of another city in topological structure, and then recommend optimizing the spatial layout of urban tourism resources.

[0127] A topological semantic association construction unit is used to establish a topological relationship between cultural resources, tourist attractions, tourist trajectories, and road networks based on the topological map and the semantic association relationship. The topological semantic association construction unit specifically includes:

[0128] The adjacency relationship construction subunit is used to calculate the spatial adjacency between cultural resources and tourist attractions. The adjacency relationship construction method includes: an adjacency judgment method based on spatial distance, setting a threshold, calculating the Euclidean distance or Manhattan distance between cultural resources and tourist attractions, and establishing an adjacency relationship if it is less than the threshold; an adjacency judgment method based on spatial buffer, generating a buffer zone of a certain range around the cultural resources, judging whether there are tourist attractions falling within the buffer zone, and if so, judging that the two are in an adjacency relationship.

[0129] The connectivity relationship construction subunit is used to calculate the accessibility between cultural resources, tourist attractions, tourist trajectories, and road networks. The connectivity relationship construction method includes: an accessibility calculation method based on GIS network analysis, calculating the shortest path between different cultural resources and tourist attractions, and judging whether there is a path connection; a dynamic connectivity calculation method based on tourist trajectories, analyzing the historical trajectory data of tourists from one cultural resource to another scenic spot. If the tourist trajectory shows continuous flow, a connectivity relationship is established.

[0130] The inclusion relationship construction sub-unit is used to calculate the spatial inclusion relationship of cultural resources, tourist attractions, and tourist trajectories. The method for constructing the inclusion relationship includes: an inclusion analysis method based on a point-surface relationship to determine whether a cultural resource point falls within the boundary of a certain scenic spot. If so, an inclusion relationship is established; a spatial attribution analysis method based on trajectory clustering to perform cluster analysis on tourist trajectory data to determine whether the activity range of tourists in a cultural attraction falls within the coverage range of a certain tourist attraction. If so, an inclusion relationship is established.

[0131] The nearest neighbor relationship construction sub-unit is used to calculate the relationship between the tourist's current location and the nearest cultural tourism resources. The nearest neighbor relationship construction method includes: a nearest neighbor search method based on spatial index, which adopts spatial index structures such as R-Tree and QuadTree to quickly retrieve the cultural resources or tourist attractions closest to the tourist's current location; a nearest neighbor recommendation method based on tourist behavior preferences, which combines the tourist's historical visit records and preference analysis to calculate the nearest cultural tourism spots that the tourist may be interested in.

[0132] Through the above structure, the GIS topology structure construction module can effectively establish the topological relationship between cultural resources, tourist attractions, tourist trajectories, and road networks, and provide basic support for spatial analysis, path optimization, and intelligent recommendation of cultural tourism data.

[0133] The culture and tourism spatiotemporal feature fusion module is used to identify the spatial correlation between cultural resources and tourist attractions based on the adjacency relationship and construct a cultural tourism fusion map; match tourist trajectory data with cultural tourism resources based on the connectivity relationship; and determine the influence range of cultural activities based on the inclusion relationship and nearest neighbor relationship.

[0134] Specifically, the culture and tourism spatiotemporal feature fusion module includes:

[0135] The cultural tourism integration map generation module is used to construct a cultural tourism integration map on the GIS platform based on the adjacency relationship between cultural resources and scenic spots, and visualize the spatial correlation of cultural resources to tourist attractions; using spatial visualization methods, overlay cultural resource points and tourist attraction surface data on the GIS map, and intuitively present the spatial interaction pattern between the two in the form of color, heat map, etc.; calculate the cultural attraction index of different cultural resources to surrounding scenic spots, and mark them in a hierarchical manner on the map to identify core cultural tourism integration areas; combine scenic spot tourist flow data to analyze the impact of cultural resources on tourist behavior, and display the scope of cultural attraction on the map.

[0136] For example, the system created a cultural tourism integration map for the Zoige Grassland on a GIS map. Visitor flow data indicated that the Tibetan Cultural Village had a high appeal for the scenic area. The GIS map showed that the cultural village's appeal extended as far as the main entrance to the Zoige Scenic Area.

[0137] The cultural tourism trajectory matching module matches the tourist trajectory data with cultural tourism resources based on the connectivity relationship to identify the flow patterns of tourists in cultural scenic spots and analyze the impact of cultural resources on tourist behavior.

[0138] Cluster analysis of GPS trajectory data is used to perform DBSCAN clustering on tourist stop points, extract the main stop areas, and match them with corresponding cultural resources or scenic spots; the movement paths of tourists between different cultural resources are calculated, and the shortest path analysis or trajectory pattern matching algorithm is used to identify tourists' preferences for visiting cultural attractions; the trajectory flow network model is used to analyze the flow trends of tourists between cultural attractions and identify high-frequency tourist flow paths.

[0139] Calculate the frequency of tourists' visits to cultural resources and evaluate the attractiveness of different cultural resources; count the time tourists spend around cultural resources, and if it exceeds a set threshold (such as 30 minutes), it is determined that the tourists have visited the cultural resources; use social media check-in data to analyze the frequency of tourists' check-ins at cultural resources and calculate the popularity of cultural resources; combine tourist trajectory data to analyze the subsequent flow paths of tourists after visiting a cultural resource and evaluate the impact of cultural resources on tourist routes.

[0140] For example, through analyzing visitor trajectory data, the system discovered that most tourists departing from Jiuzhaigou Scenic Area head to Huanglong Scenic Area, where a Tibetan and Qiang Cultural Experience Center is located along the way. Visitors' GPS trajectories indicate that the center is a frequently visited destination. Therefore, the system can identify the center's connectivity with Jiuzhaigou and Huanglong, enabling optimized cultural recommendations.

[0141] The cultural activity influence range determination unit analyzes the influence range of the cultural activity on the surrounding scenic spots based on the inclusion relationship and the nearest neighbor relationship, and determines the influence radius of the cultural activity.

[0142] Point-surface relationship analysis is used to determine whether cultural activities occur within a certain tourist attraction. If the boundary of the cultural activity is completely surrounded by the scenic area, it is determined that the cultural activity mainly affects the scenic area. The area where tourists stay during the cultural activity is calculated to analyze whether they are mainly concentrated within a specific scenic area. If the tourist density increases significantly, it indicates that the cultural activity has a strong impact on the scenic area.

[0143] For example, during the horse racing event held on the Zoige Grassland, GPS data from visitors showed a 50% increase in visitor numbers compared to normal days, with significantly longer stays. Therefore, the impact of this cultural event can be identified as being within the main Zoige Grassland area, allowing for future optimization of transportation and activities.

[0144] The K-Nearest Neighbor algorithm is used to calculate the nearest neighbor distance between cultural activities and surrounding scenic spots, and to analyze the probability of cultural activities affecting surrounding scenic spots. Spatial interpolation methods (such as Kriging interpolation) are used to predict the actual impact range of cultural activities based on the tourist density distribution during cultural activities, and to generate a heat map of the impact of cultural activities. Combined with historical cultural activity data, the impact of different types of cultural activities on tourist flow patterns is analyzed, and the potential attraction of future cultural activities to surrounding scenic spots is predicted.

[0145] For example, analysis of the Tibetan Music Festival held in Jiuzhaigou showed a 40% increase in visitor numbers and a 30% increase in hotel occupancy within a 5-kilometer radius. Using the KNN algorithm, the impact of this cultural event can be extended to the Huanglong Scenic Area, enabling the design of integrated tourism routes in the future.

[0146] Through the above structure, the cultural and tourism spatiotemporal feature fusion module can effectively identify the spatial relationship between cultural resources and tourist attractions, match tourist trajectory data with cultural tourism resources, and calculate the impact range of cultural activities, thereby improving the intelligent management capabilities of cultural tourism resources and providing data support for scenic area optimization and tourist guidance.

[0147] The prediction module is used to predict the tourist diffusion heat map at a preset destination and preset time based on the matching data of tourist trajectory data, cultural tourism resources and the influence range of cultural activities.

[0148] Specifically, the prediction module includes:

[0149] A tourist trajectory data analysis unit is used to extract and analyze tourist historical trajectory data to identify tourist flow patterns and provide a data basis for tourist diffusion prediction. The tourist trajectory data analysis unit includes:

[0150] The trajectory data preprocessing module is used to denoise, standardize and repair trajectory breakpoints of tourist trajectory data to ensure the accuracy and completeness of the trajectory data.

[0151] Kalman filtering or particle filtering algorithms can be used to smooth GPS trajectory data to eliminate GPS positioning errors; trajectory interpolation methods (such as linear interpolation and spline interpolation) can be used to fill in missing trajectory points to repair trajectory breakpoints caused by signal loss or equipment failure; coordinate conversion algorithms (such as WGS-84, GCJ-02, and BD-09 coordinate system conversions) can be used to ensure that the trajectory data matches the coordinates of the GIS map system.

[0152] For example, in the Jiuzhaigou scenic area, GPS signals are weak in certain canyon areas, resulting in interrupted trajectories. Using the Kalman filter algorithm, the system smooths trajectories and completes the possible paths of tourists, making the trajectory data more accurately reflect their actual movement.

[0153] The trajectory pattern recognition module is used to extract tourist behavior patterns based on tourist historical trajectory data and identify the movement patterns of different types of tourists to optimize the tourist diffusion prediction model.

[0154] The DBSCAN (density clustering) algorithm is used to identify tourists' high-frequency stopover points (such as scenic area entrances, tourist service centers, and cultural activity venues); HMM (hidden Markov model) or LSTM (long short-term memory network) is used to analyze tourists' historical trajectories and predict their possible next movement locations; and the K-Means clustering algorithm is used to classify tourists, such as "in-depth cultural experience tourists", "short-term sightseeing tourists", "random roaming tourists", etc., to optimize the personalized prediction model.

[0155] For example, in the Ruoergai Grassland in Aba Prefecture, Sichuan, tourists typically enter the scenic area early in the morning, explore along specific routes during the day, and return to the main urban area in the evening. Using the LSTM prediction model, the system can predict tourist flow directions at different time periods in advance, thereby optimizing scenic area management.

[0156] The cultural tourism resource matching unit analyzes the spatial matching relationship between tourist trajectory data and cultural tourism resources, identifies tourists' interest in different cultural resources, and optimizes tourist diffusion prediction based on this matching data. Specifically, it counts the length of time tourists spend around a cultural resource. If the stay exceeds a set threshold (e.g., 30 minutes), the tourist is deemed to have visited the cultural resource. The TF-IDF model is used to analyze tourists' attention to different cultural resources on social media and calculate the cultural resource's tourism attraction index. The PageRank algorithm is used to calculate the influence of cultural resources across the entire tourism network and assign weights to the prediction model.

[0157] For example, in the Huanglong Scenic Area, the average length of stay of tourists at different cultural sites varies significantly. By calculating visitor dwell time, the system discovered that a certain ancient temple is visited more frequently than other cultural resources. This weighting was then given higher priority in the prediction model, optimizing the accuracy of the visitor diffusion heat map.

[0158] The cultural activity impact analysis unit is used to calculate the tourist attraction of cultural activities based on historical data and predict the future tourist diffusion range of cultural activities. Specifically, time series analysis is used to calculate the impact trend of specific cultural activities on tourist flow; regression analysis models (such as random forest regression and XGBoost) are used to evaluate the incremental contribution of cultural activities to the number of tourists;

[0159] Combine external variables such as meteorological data, holiday factors, and traffic conditions to optimize the accuracy of tourist diffusion prediction.

[0160] For example, at Chengdu's Kuanzhai Alley, visitor numbers typically increase by over 30% during its annual major cultural festival. By analyzing data from the past five years using an ARIMA model, the system can predict visitor proliferation during future cultural festivals and optimize the scenic area's reception capacity.

[0161] Furthermore, we predict future visitor diffusion heatmaps for cultural events based on historical visitor flow patterns. Specifically, we use spatial interpolation methods (Kriging interpolation and inverse distance weighting (IDW)) to predict the impact of cultural events based on historical visitor flow data. We also use graph neural networks to learn the impact diffusion patterns of cultural events and predict future visitor flow trends. Finally, we use ABM to simulate visitor movement paths during cultural events and model visitor diffusion under different scenarios.

[0162] For example, during the Tibetan New Year celebrations in Jiuzhaigou, tourists typically move between multiple cultural attractions. Using Kriging interpolation, the system can predict visitor density at different time periods and generate a tourist diffusion heat map on a GIS map, helping management optimize crowd flow guidance plans.

[0163] The tourist diffusion heat map generation unit generates a visual tourist diffusion heat map based on the tourist trajectory data, cultural tourism resource matching data, and the impact range of cultural activities, and provides dynamic display capabilities. Specifically, it uses Gaussian kernel density estimation (KDE) to calculate the density distribution of tourists in different areas and generate heat maps. GIS time series animation is used to dynamically display the tourist diffusion process on the map, supporting interactive operations with a time slider. In combination with real-time data stream processing (such as Apache Kafka and Flink), it supports real-time updates of tourist diffusion prediction results.

[0164] For example, during the Qingming Festival in Dujiangyan, the system generated a tourist diffusion heat map on a GIS map based on a tourist trajectory prediction model. Scenic area managers could view tourist flow trends in real time and adjust management strategies, such as increasing security or optimizing traffic control.

[0165] A visualization display module is used to display the cultural tourism integration map and dynamically display the tourist diffusion heat map on the cultural tourism integration map.

[0166] The visual display module includes:

[0167] The map data loading module is used to load multi-source data such as cultural resources, tourist attractions, and tourist trajectories, and perform spatial rendering to support the visual display of cultural and tourism integrated maps.

[0168] Specifically, the GIS vector data loading method is adopted to load vector data such as cultural resources, scenic area boundaries, road networks, etc. from PostGIS, Shapefile, GeoJSON and other format files, and render them on the map; the raster image overlay technology is adopted to integrate digital elevation models (DEM), remote sensing images (DOM) and cultural tourism data to enhance the realism of the map; a multi-layer structure is adopted to render different data types (such as cultural resource points, scenic area boundaries, and tourist trajectories) into independent layers, and support dynamic control of layer visibility.

[0169] For example, when loading cultural tourism data for Aba Prefecture, Sichuan Province, onto a GIS platform, the boundaries of the Jiuzhaigou scenic area are rendered as polygons, the Tibetan Cultural Village is displayed as point features, and tourist trajectories are visualized as line segments. Users can choose to display or hide specific information using layer control switches.

[0170] The cultural resources and tourist attractions association rendering module is used to generate spatial association visualization effects based on the adjacency and connectivity relationships between cultural resources and tourist attractions, so as to intuitively display the characteristics of cultural tourism integration.

[0171] Specifically, the spatial adjacency visualization method is used to draw lines between cultural resource points and their associated scenic spots, and the line color and thickness are adjusted according to the adjacency strength; the network topology structure visualization is used to model the connectivity between cultural resources and tourist attractions, and the influence range of cultural resources is displayed with a force-directed layout; the cluster analysis visualization is used to classify similar cultural resources by color, and cultural resources of the same category are marked with different colors on the map to enhance contrast.

[0172] For example, on the GIS map, the Jiuzhaigou Scenic Area is connected to the surrounding Tibetan cultural experience points by a blue line, indicating that the two have a strong cultural connection, while the line connecting it to the Huanglong Scenic Area is lighter in color, indicating a weaker connection.

[0173] The heat map generation module is used to calculate the tourist density distribution based on tourist trajectory data, cultural tourism resource matching data and the influence range of cultural activities, and generate a heat map to visually display the tourist flow trend.

[0174] Specifically, the kernel density estimation method is used to calculate the density distribution of tourists in different areas, and a heat map is generated based on the calculation results; interpolation algorithms (such as inverse distance weighted IDW and Kriging) are used to predict the tourist flow in unsampled areas and fill the data blank areas in the heat map; the color gradient mapping method is used to color-code different density areas, such as red for tourist-dense areas and blue for tourist-sparse areas.

[0175] For example, on the GIS map of Jiuzhaigou Scenic Area, the Wuhua Lake and Nuorilang Waterfall areas where tourists most frequently gather are rendered as red high-density areas, while the more remote Zharu Temple area is rendered as blue low-density area, intuitively showing the distribution of tourist flow.

[0176] The dynamic time series heat map module is used to generate dynamic heat maps based on tourist data in different time periods to show the temporal and spatial changing trends of tourist flows.

[0177] Specifically, a time series animation rendering method is adopted to generate snapshots of tourist distribution in different time periods based on the timestamps of tourist flow data, and dynamically display tourist flows in the form of frame animations; a sliding window calculation method is adopted to aggregate and analyze tourist flow data of the past 24 hours or a week, and generate a tourist heat map that changes over time; a GIS interactive control is used to allow users to select a specific time period through a slider or timeline and view the tourist flow within that time period.

[0178] For example, on a GIS map, users can drag the time slider to view visitor traffic within Jiuzhaigou Scenic Area at different time periods. For example, at 9 a.m., the density of visitors to Wuhua Lake is high, while at 3 p.m., visitors are mainly concentrated at Nuorilang Waterfall, and the flow of visitors gradually decreases at night.

[0179] like Figure 2 As shown in the figure, based on the above system, 28 4A scenic spots and 3 5A scenic spots in Aba Tibetan and Qiang Autonomous Prefecture, Sichuan Province were taken as research objects. First, the spatiotemporal classification sample knowledge base of cultural and tourism integration was determined. Then, based on the sample knowledge base, a GIS system for the spatiotemporal integration of cultural and tourism was developed. The GIS of basic geographic information and the three-dimensional landscape model of scenic spots were used, and the POIs, scenic spot POIs, scenic spot road network structures, and tourist trajectory data of each scenic spot in the tourist destination were integrated. The spatiotemporal characteristics of cultural and tourism integration were extracted according to the needs of tourist types and the tourism space layout was visualized.

[0180] The prior art mentioned in the above background technology section and specific embodiments section of the present invention can be regarded as part of the present invention and used to understand the meaning of some technical features or parameters.

Claims

1. A GIS-based culture and tourism spatiotemporal feature fusion system, characterized by: The system comprises: The data acquisition module is used to obtain cultural and tourism spatiotemporal data, and store and process them in the spatial geographic information format; The data fusion module is used to project data from different sources into the same geographic coordinate system based on the spatial alignment method of coordinate matching; align data of different time granularities using the time window matching method; and establish semantic associations between cultural tourism data based on the knowledge graph; A GIS topology structure construction module is used to construct a topological map of cultural and tourism data, and to construct the topological relationship between cultural and tourism data based on the similarity of the topological map and the semantic association relationship, including the adjacency, connectivity, inclusion and nearest neighbor relationships between cultural resources, tourist attractions, tourist trajectories and road networks; A cultural and tourism spatiotemporal feature fusion module is used to identify the spatial correlation between cultural resources and tourist attractions based on the adjacency relationship and construct a cultural tourism fusion map; match tourist trajectory data with cultural tourism resources based on the connectivity relationship; and determine the impact range of cultural activities based on the inclusion relationship and nearest neighbor relationship; A prediction module is used to predict the tourist diffusion heat map of a preset destination and a preset time based on the matching data of tourist trajectory data, cultural tourism resources, and the influence range of cultural activities; The visualization display module is used to display the cultural tourism integration map and dynamically display the tourist diffusion heat map on the cultural tourism integration map.

2. The GIS-based culture and tourism spatiotemporal feature fusion system according to claim 1 is characterized in that: The cultural and tourism spatiotemporal data include: cultural resource data, tourist attraction data, and tourist trajectory data.

3. The GIS-based culture and tourism spatiotemporal feature fusion system according to claim 1 is characterized in that: The data fusion module includes: The spatial alignment unit uses a coordinate matching method to standardize the projection of cultural and tourism data from different sources so that they are in a unified geographic coordinate system; The time alignment unit uses a time window matching method to align data of different time granularities to ensure that cultural and tourism data are analyzed within the same time period; The semantic association construction unit establishes semantic associations between cultural resources, tourist attractions, and tourist behaviors based on the knowledge graph to explore hidden cultural tourism relationships.

4. The GIS-based culture and tourism spatiotemporal feature fusion system according to claim 1 is characterized in that: The GIS topology structure building module includes: A topological map generation unit is used to construct a topological map of cultural and tourism data to represent the structured relationships between cultural resources, tourist attractions, tourist trajectories, and road network spatial elements; a topological similarity calculation unit, configured to analyze the correlation between cultural and tourism data based on the structural similarity of the topological graph; A topological semantic association construction unit is used to establish a topological relationship between cultural resources, tourist attractions, tourist trajectories, and road networks based on the topological map and the semantic association relationship.

5. The GIS-based culture and tourism spatiotemporal feature fusion system according to claim 4 is characterized in that: The topology map generating unit includes: The spatial element extraction subunit is used to extract cultural resources, tourist attractions, tourist trajectories, and road network spatial elements from the GIS database and convert the spatial elements into node information in the topological map; A relationship edge construction subunit is used to construct edge information of a topological graph according to the spatial relationship and semantic relevance between the spatial elements, so as to establish a topological connection between the spatial elements; The topology structure storage subunit is used to store the constructed topology graph using a graph database or a spatial database to support subsequent topology analysis and query.

6. The GIS-based culture and tourism spatiotemporal feature fusion system according to claim 4 is characterized in that: The topology similarity calculation unit includes: Topological feature extraction subunit, used to extract topological features of cultural and tourism data; The graph matching calculation subunit is used to calculate the topological similarity between different cultural resources, tourist attractions, and tourist behaviors using a graph similarity algorithm, and to build relationships between cultural and tourism data based on the similarity.

7. The GIS-based culture and tourism spatiotemporal feature fusion system according to claim 4 is characterized in that: The topological semantic association construction unit includes: The adjacency relationship construction subunit is used to calculate the spatial adjacency between cultural resources and tourist attractions; Connectivity construction subunit, used to calculate the accessibility between cultural resources, tourist attractions, tourist trajectories, and road networks; The inclusion relationship construction sub-unit is used to calculate the spatial inclusion relationship of cultural resources, tourist attractions, and tourist trajectories; The nearest neighbor relationship construction subunit is used to calculate the relationship between the tourist's current location and the nearest cultural tourism resources.

8. The GIS-based culture and tourism spatiotemporal feature fusion system according to claim 1 is characterized in that: The culture and tourism spatiotemporal feature fusion module includes: The cultural tourism fusion map generation module is used to construct a cultural tourism fusion map on the GIS platform based on the adjacency relationship between cultural resources and scenic spots, and visually display the spatial correlation of cultural resources to tourist attractions; A cultural tourism trajectory matching module matches tourist trajectory data with cultural tourism resources based on the connectivity relationship to identify tourist flow patterns in cultural scenic spots and analyze the impact of cultural resources on tourist behavior; The cultural activity influence range determination unit analyzes the influence range of the cultural activity on the surrounding scenic spots based on the inclusion relationship and the nearest neighbor relationship, and determines the influence radius of the cultural activity.

9. The GIS-based culture and tourism spatiotemporal feature fusion system according to claim 1 is characterized in that: The prediction module includes: Tourist trajectory data analysis unit, used to extract and analyze tourist historical trajectory data; Trajectory data preprocessing module, used to denoise, standardize and repair tourist trajectory breakpoints; Trajectory pattern recognition module, used to extract tourist behavior patterns based on historical tourist trajectory data and identify the movement patterns of different types of tourists; The cultural tourism resource matching unit is used to analyze the spatial matching relationship between tourist trajectory data and cultural tourism resources, identify the degree of tourists' interest in different cultural resources, and optimize tourist diffusion prediction based on the matching data; The cultural activities impact range analysis unit is used to calculate the tourist attraction of cultural activities based on historical data and predict the future tourist diffusion range of cultural activities; The tourist diffusion heat map generating unit generates a visual tourist diffusion heat map based on the tourist trajectory data, cultural tourism resource matching data and the influence range of cultural activities.

10. The GIS-based culture and tourism spatiotemporal feature fusion system according to claim 1 is characterized in that: The visual display module includes: The map data loading module is used to load multi-source data on cultural resources, tourist attractions, and tourist trajectories, and perform spatial rendering to support the visual display of cultural and tourism integrated maps; The cultural resources and tourist attractions association rendering module is used to generate spatial association visualization effects based on the adjacency and connectivity relationships between cultural resources and tourist attractions; The heat map generation module is used to calculate the tourist density distribution based on tourist trajectory data, cultural tourism resource matching data, and the impact range of cultural activities, and generate a heat map to visualize tourist flow trends; The dynamic time series heat map module is used to generate dynamic heat maps based on tourist data in different time periods to show the temporal and spatial changing trends of tourist flows.

Images