Traffic and tourism fusion layout method, system and equipment based on multi-source spatial data and medium

Abstract

The invention relates to a traffic and tourism fusion layout method, system and device based on multi-source spatial data and a medium. The method comprises the following steps: acquiring multi-source spatial data, and preprocessing the multi-source spatial data to obtain preprocessed data; based on the pre-processed data, carrying out traffic travel suitability, travel traffic volume and scenic area connection intensity analysis to obtain a traffic travel suitability cost range, a travel traffic volume grid and a scenic area connection intensity matrix; combining the traffic tourism suitability cost surface with scenic spot data in the tourism resource data, and carrying out minimum cost path analysis to obtain a suitability corridor; superposing the tourism traffic grid and the suitable corridor to obtain a key lifting road section; superposing the scenic area connection strength matrix and the suitability corridor to obtain a branch road section needing to be supplemented; and in combination with matched service facilities, integrating the suitability galleries, the key lifting road sections and the branch road sections needing to be supplemented to obtain a traffic and tourism fusion layout scheme. By adopting the method, the scientificity and the landing performance of the layout can be improved.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of traffic and tourism integration, and particularly relates to a traffic and tourism integration layout method, system, device and medium based on multi-source spatial data. BACKGROUND

[0002] With the continuous progress of the technology in the field of traffic and tourism integration development, traffic and tourism integration layout planning has become a key technology for promoting the coordinated development of regional tourism economy and traffic network. In this field, traditional layout methods mostly rely on single type data, such as planning based only on traffic network density or tourism resource distribution.

[0003] In traditional technology, the matching of traffic lines and tourism resources is analyzed by manual investigation or single data model, and then a traffic and tourism integration layout scheme is determined. For example, a tourist highway is planned only according to the location of a scenic spot, or a tourist special line is laid out only considering traffic flow.

[0004] However, the current traditional method has many problems: on the one hand, the data source is single, and multi-source spatial data such as basic geography, traffic, tourism resources, and tourist behavior are not fully integrated, resulting in a lack of consideration of key factors such as road landscape quality, actual travel preferences of tourists, and correlation strength between scenic spots, so that the accessibility of the planned traffic and tourism lines is out of touch with the experience of tourists, such as some lines can connect scenic spots but have poor landscape quality, reducing the willingness of tourists to travel; on the other hand, there is a lack of systematic quantitative analysis means for multi-source data, making it difficult to achieve accurate matching of traffic and tourism resources, and the layout scheme is highly subjective and lacks scientificity, which cannot meet the needs of high-quality integration of traffic and tourism for scientific layout, and restricts the maximization of the benefits of traffic and tourism integration. SUMMARY

[0005] Therefore, it is necessary to provide a traffic and tourism integration layout method, system, device and medium based on multi-source spatial data which can be scientific and practical.

[0006] In a first aspect, the application provides a traffic and tourism integration layout method based on multi-source spatial data, comprising:

[0007] Obtaining multi-source spatial data and preprocessing the multi-source spatial data to obtain preprocessed data; the multi-source spatial data includes basic geographic data, traffic data, tourism resource data and tourist behavior data;

[0008] Based on preprocessed data, we conducted analyses of transportation-tourism suitability, tourism traffic volume, and scenic area connectivity strength, resulting in a transportation-tourism suitability cost surface, a tourism traffic volume grid, and a scenic area connectivity strength matrix. The transportation-tourism suitability cost surface characterizes the suitability of regional transportation and tourism resources; the tourism traffic volume grid characterizes the spatial distribution of tourist traffic flow; and the scenic area connectivity strength matrix characterizes the degree of correlation between tourist visits to different scenic areas.

[0009] By combining the cost surface of transportation and tourism suitability with scenic area data in tourism resource data, a minimum cost path analysis is conducted to obtain suitability corridors; suitability corridors are used to characterize routes where transportation and tourism resources are well matched.

[0010] By overlaying the tourism traffic volume grid with the suitability corridor, key improvement sections are obtained; key improvement sections are used to characterize sections with high tourist traffic and high traffic-tourism suitability that need optimization.

[0011] By overlaying the scenic area connectivity strength matrix with the suitability corridor, the branch road segments that need to be supplemented are obtained. The branch road segments that need to be supplemented are used to characterize the new road segments that need to be added when the inter-scenic area has a high degree of connectivity but insufficient traffic coverage.

[0012] By integrating supporting service facilities, suitable corridors, key improvement sections, and supplementary branch lines, a transportation and tourism integration layout plan is obtained.

[0013] In one embodiment, multi-source spatial data is acquired and preprocessed to obtain preprocessed data, including:

[0014] Acquire multi-source spatial data; basic geographic data includes elevation data, land use type data, and normalized difference vegetation index data; transportation data is used to characterize the regional road network and transportation hub distribution; tourism resource data includes the spatial location and grade information of scenic spots; tourist behavior data includes self-driving travel trajectory data and online travelogue text data;

[0015] The basic geographic data is processed to standardize the coordinate system, resulting in standard geographic data;

[0016] Perform topology checks and repairs on traffic data to obtain topology-optimized traffic data;

[0017] Spatial location correction is performed on tourism resource data to obtain tourism resource data with accurate location;

[0018] Spatiotemporal cleaning of tourist behavior data is performed to obtain effective tourist behavior data;

[0019] Spatial registration is performed on standard geographic data, topology-optimized traffic data, location-accurate tourism resource data, and effective tourist behavior data to obtain preprocessed data.

[0020] In one embodiment, based on preprocessed data, analyses of transportation-tourism suitability, tourism traffic volume, and scenic area connectivity strength are performed to obtain a transportation-tourism suitability cost surface, a tourism traffic volume grid, and a scenic area connectivity strength matrix, including:

[0021] Based on standard geographic data and location-accurate tourism resource data, a transportation and tourism suitability index is calculated to obtain a transportation and tourism suitability cost surface.

[0022] Based on topology-optimized traffic data and effective tourist behavior data, tourist traffic volume is calculated to obtain a tourist traffic volume raster.

[0023] Based on accurate location-based tourism resource data and effective tourist behavior data, the connection strength between scenic spots is calculated to obtain a scenic spot connection strength matrix.

[0024] In one embodiment, based on standard geographic data and location-accurate tourism resource data, a transportation-tourism suitability index is calculated to obtain a transportation-tourism suitability cost surface, including:

[0025] Topographic and surface analysis is performed on standard geographic data to obtain road zone visibility quality; road zone visibility quality includes road visibility range, water visibility, vegetation coverage, landscape type quality, and landscape diversity index.

[0026] By assigning resource level values ​​to accurately located tourism resource data, the value of cultural and tourism resources can be obtained.

[0027] Accessibility analysis is performed on topology-optimized traffic data to obtain traffic resource accessibility factors;

[0028] Using the following formula, the road-view quality, cultural and tourism resource value, and transportation resource accessibility factors are weighted and superimposed to calculate the transportation-tourism suitability index, thus obtaining the transportation-tourism suitability cost surface:

[0029]

[0030] in, For grid The transportation and tourism suitability index For grid The quality of the road field of view, For grid The value of cultural and tourism resources For grid Accessibility factors of transportation resources The weighting coefficients for the quality of the road field of view. This is a weighting coefficient for the value of cultural and tourism resources. This represents the weighting coefficient of the accessibility factor for transportation resources.

[0031] In one embodiment, based on topology-optimized traffic data and effective tourist behavior data, tourist traffic volume is calculated to obtain a tourist traffic volume grid, including:

[0032] Trajectory points are extracted from valid tourist behavior data to obtain a set of tourist trajectory points;

[0033] The following formula is used to perform kernel density estimation on the tourist trajectory point set to obtain a preliminary traffic volume raster:

[0034]

[0035] in, For position The kernel density value at that location, For the number of tourist trajectory points, For bandwidth, For kernel function, For the first The location of each tourist's trajectory point;

[0036] The initial traffic volume grid is normalized to obtain the tourism traffic volume grid.

[0037] In one embodiment, based on location-accurate tourism resource data and effective tourist behavior data, the connection strength between scenic spots is calculated to obtain a scenic spot connection strength matrix, including:

[0038] Based on self-driving tour trajectory data with accurate location tourism resource data and effective tourist behavior data, scenic spot visit sequences are extracted, trajectory co-occurrence frequency is calculated, and scenic spot trajectory association matrix is ​​obtained.

[0039] Based on the accurate location-based tourism resource data and the effective tourist behavior data, online travelogue text data is used for word segmentation and scenic area entity recognition. The co-occurrence frequency of scenic areas is calculated using the following formula to obtain the scenic area text association matrix:

[0040]

[0041] in, For the scenic area With the scenic area The text association value, The total number of valid online travelogue texts. As the first indicator variable, it is used to characterize the current situation when the first... The travelogue includes scenic spots When it is 1, The second indicator variable is used to characterize the situation when the first... The travelogue includes scenic spots The time is 1;

[0042] The following formula is used to weight and fuse the scenic area trajectory association matrix and the scenic area text association matrix to obtain the comprehensive scenic area association matrix:

[0043]

[0044] in, For the scenic area With the scenic area The overall correlation value, For the scenic area With the scenic area trajectory association value, For the scenic area With the scenic area The text association value, These are the weighting coefficients;

[0045] The comprehensive correlation matrix of scenic spots is normalized to obtain the correlation strength matrix of scenic spots.

[0046] In one embodiment, the transportation and tourism suitability cost surface and scenic area data from tourism resource data are combined to perform minimum cost path analysis, resulting in suitability corridors, including:

[0047] The transportation and tourism suitability cost surface is used as the cost resistance surface, and the scenic spot location points in the scenic spot data are used as the source points for cost path analysis.

[0048] Based on the cost resistance surface and the source point, the minimum cumulative cost to the nearest scenic spot for each grid is calculated using the cost distance tool, thus obtaining the grid with the minimum cumulative cost;

[0049] Based on the minimum cumulative cost grid, the minimum cost path from each grid to the nearest source point is identified, resulting in the global minimum cost path network.

[0050] Density analysis is performed on the minimum cost path network across the entire region to identify the core corridors where paths converge and to obtain suitable corridors.

[0051] Secondly, this application also provides a transportation and tourism integrated layout system based on multi-source spatial data, including:

[0052] The data acquisition and preprocessing module is used to acquire multi-source spatial data and preprocess the multi-source spatial data to obtain preprocessed data; the multi-source spatial data includes basic geographic data, transportation data, tourism resource data and tourist behavior data;

[0053] The data analysis module is used to perform analysis on transportation-tourism suitability, tourism traffic volume, and scenic area connectivity based on preprocessed data, resulting in a transportation-tourism suitability cost surface, a tourism traffic volume grid, and a scenic area connectivity matrix. The transportation-tourism suitability cost surface is used to characterize the suitability of regional transportation and tourism resources; the tourism traffic volume grid is used to characterize the spatial distribution of tourist traffic flow; and the scenic area connectivity matrix is ​​used to characterize the degree of correlation between tourist visits to different scenic areas.

[0054] The corridor analysis module combines the transportation-tourism suitability cost surface with scenic area data from tourism resource data to conduct minimum cost path analysis and obtain suitability corridors. Suitability corridors are used to characterize routes where transportation and tourism resources are well matched.

[0055] The optimized road segment demand analysis module is used to overlay tourism traffic volume grids with suitability corridors to identify key road segments for improvement. Key road segments for improvement are used to characterize road segments with high tourist traffic and high traffic-tourism suitability that need optimization.

[0056] A new road segment demand analysis module is added to overlay the scenic area connectivity strength matrix with the suitability corridor to obtain the branch road segments that need to be supplemented. The branch road segments that need to be supplemented are used to characterize the new road segments that have high inter-scenic area connectivity but insufficient traffic coverage.

[0057] The transportation integration layout module is used to combine suitable corridors, key improvement sections, and supplementary branch line sections with supporting service facilities to obtain a transportation and tourism integration layout plan.

[0058] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect.

[0059] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the method described in the first aspect.

[0060] The aforementioned transportation and tourism integration layout method, system, equipment, and media based on multi-source spatial data ensure data reliability through multi-source data preprocessing, generate suitable corridors, key improvement sections, and supplementary branch lines through multi-dimensional analysis, and then integrate and plan supporting service facilities to form a layout scheme. This achieves precise matching of transportation and tourism resources, fully meets the actual travel needs of tourists and the characteristics of scenic spots, and improves the scientific and rational nature of the layout. At the same time, the entire process is logically closed-loop, and the data and results of each link are closely connected without redundant steps. It can provide a clear and implementable basis for transportation and tourism integration projects and strongly support the high-quality development of transportation and tourism integration. Attached Figure Description

[0061] To more clearly illustrate the technical solutions in the embodiments or related technologies of this application, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0062] Figure 1 This is a flowchart illustrating a transportation and tourism integration layout method based on multi-source spatial data in one embodiment.

[0063] Figure 2 This is a schematic diagram of a transportation and tourism integration layout system based on multi-source spatial data in one embodiment.

[0064] Figure 3 This is a schematic diagram of a computer device in one embodiment. Detailed Implementation

[0065] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0066] In one embodiment, such as Figure 1 As shown, a method for integrating transportation and tourism layout based on multi-source spatial data is provided. This embodiment illustrates the application of this method to a spatial layout terminal (hereinafter referred to as the terminal). It can be understood that this method can also be applied to a server, and can also be applied to a system including both a terminal and a server, and implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0067] A method for integrating transportation and tourism layout based on multi-source spatial data includes:

[0068] S1: Acquire multi-source spatial data and preprocess the multi-source spatial data to obtain preprocessed data.

[0069] The multi-source spatial data encompasses basic geographic data, transportation data, tourism resource data, and tourist behavior data, forming the core foundation for subsequent integrated transportation and tourism layout analysis. For example, the spatial layout terminal acquires basic geographic data through professional geographic data platforms such as the Earth System Science Data Sharing Service System to ensure the data possesses the resolution and accuracy required for spatial analysis. The terminal obtains transportation data from annual statistical reports released by local transportation authorities or from transportation data management platforms, covering the topological relationships of roads of different levels and basic information on transportation hubs. Tourism resource data (including the spatial location and level information of scenic spots) is obtained from official databases of cultural and tourism authorities or publicly available tourism resource survey results, ensuring the authority of scenic spot location coordinates and level classifications. Self-driving travel trajectory data within tourist behavior data is obtained from outdoor travel platforms with user trajectory recording functions (such as Liangbulu) through data cooperation or compliant data acquisition channels, including the spatiotemporal route information of tourists' self-driving journeys. The terminal obtains online travelogue text data from mainstream tourism platforms (such as Ctrip) within the scope permitted by platform rules using compliant web data collection tools (such as WebScraper), covering content such as tourist itineraries and scenic spot evaluations.

[0070] Among them, basic geographic data is used to reflect the natural geographic characteristics of the study area, and to characterize the regional topography, vegetation, and landscape types; transportation data is used to reflect the distribution and service capacity of the regional transportation network, that is, to characterize the distribution of the regional road network and transportation hubs; tourism resource data is used to clarify the distribution and value level of tourism resources in the region; and tourist behavior data is used to capture tourists' actual travel and sightseeing preferences, and also to characterize tourists' driving trajectories and scenic spot visit sequences. After acquiring the data, the spatial layout terminal will perform preprocessing according to the characteristics of different types of data, including format conversion to unify data storage standards, outlier removal to eliminate invalid data interference, and coordinate calibration to ensure spatial location consistency, etc., to finally obtain preprocessed data with unified format, valid data, and consistent spatial reference.

[0071] S2, based on preprocessed data, conducts analyses of transportation-tourism suitability, tourism traffic volume, and scenic area connectivity strength, respectively, to obtain the transportation-tourism suitability cost surface, tourism traffic volume grid, and scenic area connectivity strength matrix.

[0072] The system comprises three core analyses: a transportation-tourism suitability cost surface, a tourism traffic volume grid, and a scenic area connectivity strength matrix. The cost surface represents the suitability of regional transportation with tourism resources; the tourism traffic volume grid represents the spatial distribution of tourist traffic flow; and the connectivity strength matrix represents the degree of correlation between tourist visits to different scenic areas. Specifically, the spatial layout terminal conducts three core analyses based on preprocessed data. In the transportation-tourism suitability analysis, the system combines the natural geographical features of standard geographic data with the scenic area distribution from accurately located tourism resource data to quantitatively assess the matching degree between transportation and tourism resources within the region, forming a cost surface representing suitability. In the tourism traffic volume analysis, the system calculates tourist traffic flow in different areas based on the road network structure of topology-optimized transportation data and tourist trajectories from effective tourist behavior data, generating a grid reflecting traffic flow distribution. In the scenic area connectivity strength analysis, the system analyzes the degree of correlation between scenic areas based on scenic area information from accurately located tourism resource data and visit records from effective tourist behavior data, constructing a matrix reflecting the strength of correlation. Through these three analyses, the transportation-tourism suitability cost surface, the tourism traffic volume grid, and the scenic area connectivity strength matrix are obtained.

[0073] S3 combines the cost surface of transportation and tourism suitability with scenic area data in tourism resource data to conduct minimum cost path analysis and obtain suitability corridors.

[0074] For example, the spatial layout terminal first clarifies the roles of two types of core input data: the transportation-tourism suitability cost surface is stored in grid form, and the cost value of each grid cell quantifies the suitability of transportation and tourism resources in that area. The lower the cost value, the higher the compatibility of transportation accessibility, landscape quality, and tourism resource distribution, which can serve as a basis for obstacle planning; the scenic area data in the tourism resource data provides precise spatial location and level information of the scenic area. As the core destination of tourism transportation, the scenic area is the key source point (i.e., the starting point or end point of the path) for path planning. Subsequently, the spatial layout terminal uses an analysis logic that combines cost distance and path backtracking to conduct minimum cost path analysis: first, taking the location of the scenic area as the source point, based on the transportation-tourism suitability cost surface, the minimum cumulative cost from each grid cell in the entire area to the nearest source point (i.e., the sum of the cost values ​​of the grid cells passed through) is calculated; then, through the cost backtracking algorithm, the path is backtracked from each grid cell in the direction of cost reduction to the source point, forming a dispersed minimum cost path; finally, these paths are fused and density analyzed to extract the core routes with path convergence and low cost values, which are the suitability corridors, used to reflect the preferred routes that meet the requirements of transportation and tourism resource matching.

[0075] By calculating the transportation-tourism suitability index through multi-dimensional cost analysis, this approach breaks away from the limitations of traditional layout methods that rely on single-indicator evaluations. The minimum cost analysis first quantifies three core cost factors: road-area visibility quality, cultural and tourism resource value, and transportation resource accessibility. Then, a weighted summation formula is used to systematically integrate these factors to form a transportation-tourism suitability cost surface, enabling a scientific quantitative assessment of the matching degree between transportation and tourism resources. The cost analysis process considers not only the experiential value of natural landscapes but also the attractiveness of tourism resources and the convenience of transportation. This allows subsequent minimum cost path analysis to accurately select optimal routes with low resistance and high adaptability, ensuring that the generated suitability corridors not only meet transportation needs but also fully connect with high-quality tourism resources, thereby enhancing the scientific and rational nature of the integrated transportation-tourism layout.

[0076] S4 combines tourist traffic volume grids with suitability corridors to identify key sections for improvement.

[0077] For example, the spatial layout terminal uses a grid and vector overlay algorithm to associate traffic volume information in the tourism traffic volume grid with suitability corridors (vector lines), determining the traffic volume values ​​corresponding to each segment of the suitability corridor. Based on a set traffic volume threshold (determined through tourism traffic demand analysis to distinguish between high and low traffic volume segments), the terminal filters out segments within the suitability corridor whose traffic volume values ​​exceed the threshold. These segments simultaneously possess the characteristics of high tourism suitability (belonging to suitability corridors) and high tourist flow (high traffic volume), facing greater traffic pressure in actual operation and requiring higher standards for service quality and road conditions; therefore, they need to be prioritized for improvement. The spatial layout terminal records the spatial location, length, and traffic volume values ​​of these segments through attribute extraction, providing a clear segment range for subsequent traffic facility optimization.

[0078] By using a scenic area connectivity strength matrix to identify areas requiring additional branch lines, the shortcomings of insufficient transportation coverage between high-demand scenic areas in traditional layouts are addressed. By analyzing visitor behavior data, including trajectories and travelogues, the degree of connection between scenic areas is quantified. This data is then overlaid with suitability corridors to accurately identify highly connected scenic area pairs not covered by existing corridors. Planning new branch lines for these pairs effectively strengthens transportation links between core scenic areas, fills gaps in the transportation network, and makes the overall layout more aligned with actual visitor preferences. The new road segments are not planned blindly but based on the interconnected needs of scenic areas, complementing suitability corridors to construct a comprehensive transportation network of core corridors plus supplementary branch lines. This further enhances the practicality and feasibility of the layout plan, facilitating deep synergy between the transportation network and tourism resources.

[0079] S5, by overlaying the scenic area connectivity strength matrix with the suitability corridor, yields the branch line segments that need to be supplemented.

[0080] For example, the spatial layout terminal conducts an overlay analysis of the scenic area connection strength matrix and suitability corridors through multi-dimensional innovative logic to generate branch line segments that need to be supplemented. First, the spatial layout terminal introduces a dynamic threshold calibration mechanism, rather than using a fixed threshold to select scenic area pairs with high connection strength: based on the density of scenic areas and the distribution characteristics of tourist flow in the study area, combined with the regional tourism integration development planning goals, such as the linkage of core scenic areas and the expansion of rural tourism routes, a differentiated threshold is determined through the analytic hierarchy process. For example, the threshold for core tourist areas is lower than that for remote scenic areas, ensuring that high-density areas accurately identify strongly associated niche scenic area pairs, and that key linkage needs are not overlooked in low-density areas. At the same time, the scenic area connection strength matrix is ​​secondarily weighted and corrected, incorporating factors such as scenic area level and tourist satisfaction ratings, so that the connection strength is more in line with the priority of actual tourism needs.

[0081] Secondly, in the coverage assessment stage, we move beyond the single logic of simply looking at the existence of routes and construct a three-dimensional assessment system encompassing existence, traffic efficiency, and service suitability. First, we analyze spatial distance to determine if suitable corridors exist between high-connectivity scenic areas. Then, we extract the accessibility factors of the corresponding transportation resources and tourism traffic volume data. If the corridor segment is of low grade, resulting in insufficient traffic efficiency, or if traffic volume is saturated (exceeding the segment's carrying capacity threshold), or if there is a lack of age-friendly or child-friendly supporting services, even if the route exists, it is still considered insufficient coverage. Finally, when planning supplementary branch lines, we employ a dual-objective path algorithm that optimizes cost and maximizes value. This not only avoids areas with complex terrain and scarce tourism resources but also simultaneously overlays road-domain visibility quality data and scattered cultural and tourism resource points, such as rural tourism spots and intangible cultural heritage experience points. This ensures that branch lines meet connectivity needs while connecting high-quality landscapes and niche cultural and tourism resources along the way, giving them their own integrated transportation and tourism value. Furthermore, we flexibly plan branch line types based on scenic area types and tourist travel patterns to achieve precise adaptation between transportation modes and scenario requirements. Among them, scenic area types include mountain scenic areas and cultural scenic areas; tourist travel modes include self-driving and public transportation; and flexible planning branch line types include self-driving highways, lightweight rail transit connecting lines, and low-altitude tourism route take-off and landing point connecting lines.

[0082] S6, combined with supporting service facilities, integrates suitable corridors, key improvement sections, and supplementary branch lines to obtain a transportation and tourism integration layout plan.

[0083] For example, the spatial layout terminal integrates the three types of routes, eliminating issues such as route overlap and node conflicts through topology checks to ensure the spatial rationality of the route network. Based on the functional positioning and demand characteristics of the routes, it plans supporting service facilities, such as service stations (for tourists to rest and replenish supplies) and viewing platforms (for viewing the surrounding landscape) along key improvement sections, parking lots and charging piles (to meet the needs of self-driving tourists) along supplementary branch lines, and transportation hubs (to facilitate tourists to change modes of transportation) at the intersection of suitable corridors and other routes. The terminal spatially associates the integrated route network with the locations of supporting service facilities to form a complete layout scheme that includes information such as route direction, location and function of service facilities, and route level, i.e., a transportation and tourism integration layout scheme. This scheme covers core tourism resources and meets the transportation and service needs of tourists, providing a specific spatial implementation basis for the integrated development of regional transportation and tourism.

[0084] The aforementioned transportation and tourism integration layout method based on multi-source spatial data ensures data reliability through multi-source data preprocessing. It then combines multi-dimensional analysis of transportation and tourism suitability, tourism traffic volume, and the intensity of connections with scenic spots to accurately identify suitable corridors, key improvement sections, and supplementary branch lines. Finally, it integrates these into a layout plan that ensures efficient matching of transportation and tourism resources while meeting the actual travel needs of tourists. Furthermore, supporting service facilities enhance the plan's feasibility, providing scientific and feasible spatial layout support for the high-quality development of regional transportation and tourism integration. This avoids problems such as poor route accessibility and disconnect from tourist needs found in traditional layouts.

[0085] In an optional embodiment, multi-source spatial data is acquired and preprocessed to obtain preprocessed data, including the following steps:

[0086] S11, acquire multi-source spatial data.

[0087] Specifically, the spatial layout terminal collects multi-source spatial data through multiple channels, with clearly defined data types and contents. Basic geographic data includes elevation data, land use type data, and normalized difference vegetation index (NDVI) data. Elevation data reflects the regional topographic relief characteristics; land use type data reflects different land use patterns within the region, such as forest land, cultivated land, and construction land; and NDVI data characterizes the degree of vegetation cover in the region. Transportation data revolves around the regional road network and transportation hubs, covering the road network's direction, grade, and connectivity, as well as the location and scale of transportation hubs, thus characterizing the distribution and service capacity of the regional transportation network. Tourism resource data includes the spatial location and grade information of scenic spots (e.g., A-5A classification, reflecting the resource value and reception capacity of scenic spots). Tourist behavior data includes self-driving travel trajectory data and online travelogue text data. Self-driving travel trajectory data records the spatiotemporal paths of tourists' self-driving trips, while online travelogue text data includes information such as tourist itineraries and attraction reviews. These data can be used to analyze tourist travel patterns and travel preferences.

[0088] S12 performs coordinate system standardization on the basic geographic data to obtain standard geographic data.

[0089] For example, the spatial layout terminal first determines a unified target coordinate system, and then uses a coordinate transformation algorithm to convert elevation data, land use type data, and normalized vegetation index data from different coordinate systems to the target coordinate system, eliminating spatial benchmark differences between different data, and finally obtaining standard geographic data with unified coordinates and accurate spatial location. Coordinate systems include the Beijing 54 coordinate system, the Xi'an 80 coordinate system, and the WGS84 coordinate system, etc., and coordinate transformation algorithms include the seven-parameter transformation method and the four-parameter transformation method, etc.

[0090] S13, perform topology checks and repairs on the traffic data to obtain topology-optimized traffic data.

[0091] For example, the spatial layout terminal uses a topology inspection tool to detect topology errors in traffic data, such as broken lines, redundant nodes, and overlapping lines. For detected errors, a topology repair algorithm is used, such as capturing and connecting nodes at broken line locations, deleting redundant nodes, and removing overlapping lines, to ensure the correct topological relationships in the road network data, resulting in topology-optimized traffic data with a complete topological structure and clear logical relationships. Broken lines refer to gaps between two road network lines that should be connected; redundant nodes refer to multiple duplicate nodes at the same location; and overlapping lines refer to the same road network being drawn repeatedly.

[0092] By performing topology optimization, traffic data is checked and repaired, effectively resolving common topology errors in traditional traffic network data, such as broken lines, redundant nodes, and overlapping lines. Topology optimization constructs a structurally complete and logically clear traffic data structure, ensuring the connectivity and consistency of the road network. This provides a precise and reliable spatial framework for subsequent core steps such as tourism traffic volume calculation and route planning. It avoids problems such as traffic volume statistical bias and broken route planning caused by road network data defects, making the analysis results based on the road network more consistent with the actual traffic network situation. This provides solid basic data support for the integrated layout of transportation and tourism, improving the accuracy and feasibility of the overall layout plan.

[0093] S14. Spatial location correction is performed on the tourism resource data to obtain tourism resource data with accurate location.

[0094] For example, the spatial layout terminal uses high-precision terrain, landmarks and other information in standard geographic data as a reference. Through a spatial matching algorithm, it compares the initial position of the scenic spot in the tourism resource data with the reference information and calculates the position deviation value. Based on the deviation value, the coordinates of the scenic spot are adjusted so that the spatial position of the scenic spot accurately corresponds to the actual geographic environment. Finally, accurate tourism resource data with accurate spatial position and consistent with the actual geographic scene is obtained.

[0095] S15, perform spatiotemporal cleaning on tourist behavior data to obtain valid tourist behavior data.

[0096] For example, the spatial layout terminal performs spatiotemporal cleaning on tourist behavior data. During the collection process, tourist behavior data may contain invalid data, such as abnormal points in driving trajectory data and meaningless content in online travelogue text data. For driving travel trajectory data, the spatial layout terminal filters based on spatiotemporal logic, removing trajectory points outside the study area, trajectory points with abnormal instantaneous speeds, and trajectory segments with disordered time sequences. For online travelogue text data, a text filtering algorithm removes content without actual itinerary information, such as purely emotional expressions and advertisements, retaining valid text containing scenic spot visit records and the chronological order of the itinerary. Through this dual spatiotemporal cleaning, invalid interference data is removed, resulting in valid tourist behavior data that truly reflects tourists' travel and sightseeing behaviors.

[0097] S16 involves spatially registering standard geographic data, topology-optimized traffic data, location-accurate tourism resource data, and effective tourist behavior data to obtain preprocessed data.

[0098] For example, the spatial layout terminal performs spatial registration on standard geographic data, topology-optimized traffic data, location-accurate tourism resource data, and effective tourist behavior data. Although the four types of data have been processed separately, slight differences in spatial reference may exist, requiring registration to achieve precise spatial alignment. The spatial layout terminal selects multiple highly stable landmarks within the study area as registration control points, obtaining the coordinates of the control points for each of the four types of data. It calculates the coordinate deviations of the control points between different data sets and uses spatial transformation algorithms to fine-tune the data, ensuring that the four types of data are accurately superimposed under the same spatial reference. This ensures that the spatial positions of each type of data match without misalignment, ultimately integrating them into preprocessed data with a unified spatial reference and consistent data consistency. Stable landmarks include mountain peaks, river confluences, and large transportation hubs, while spatial transformation algorithms can include affine transformations and projection transformations.

[0099] In an optional embodiment, based on preprocessed data, analysis is performed on transportation-tourism suitability, tourism traffic volume, and scenic area connectivity strength to obtain a transportation-tourism suitability cost surface, a tourism traffic volume grid, and a scenic area connectivity strength matrix, including the following steps:

[0100] S21. Based on standard geographic data and location-accurate tourism resource data, calculate the transportation and tourism suitability index to obtain the transportation and tourism suitability cost surface.

[0101] For example, the spatial layout terminal uses standard geographic data and location-accurate tourism resource data as inputs to calculate the transportation-tourism suitability index and generate a cost surface. Standard geographic data provides natural geographic information such as topography, vegetation, and landscape of the study area, while location-accurate tourism resource data provides the location and grade information of scenic spots. Combining the two allows for a comprehensive assessment of the matching potential between transportation and tourism resources within the region. The spatial layout terminal first extracts road-area visibility quality from the standard geographic data and cultural and tourism resource value from the location-accurate tourism resource data. Then, combining factors related to transportation accessibility, it constructs a transportation-tourism suitability index calculation model, quantifying the suitability degree of different areas. The suitability index is presented in raster form; a lower index indicates a higher degree of matching between transportation and tourism resources in the area, forming a transportation-tourism suitability cost surface for subsequent path analysis. Road-area visibility quality includes road visibility range, water visibility, vegetation coverage, landscape type quality, and landscape diversity index.

[0102] S22. Based on topology-optimized traffic data and effective tourist behavior data, calculate tourist traffic volume to obtain a tourist traffic volume raster.

[0103] For example, the spatial layout terminal first matches the self-driving trajectories in the effective tourist behavior data with the road network in the topology-optimized traffic data to determine the driving segments of each trajectory on the road network; it counts the number of trajectories passing through each road segment per unit time, and calculates the tourist traffic volume in different road network areas by combining parameters such as road segment length and number of lanes; it then divides and assigns values ​​to the traffic volume data in grid units to form a tourist traffic volume grid that can intuitively reflect the spatial distribution of tourist traffic flow.

[0104] S23. Based on accurate location-based tourism resource data and effective tourist behavior data, calculate the connection strength between scenic spots to obtain the scenic spot connection strength matrix.

[0105] For example, the spatial layout terminal first extracts the tourist visit sequence of tourists from effective tourist behavior data, such as scenic spot A, scenic spot B and scenic spot C, and counts the common visit frequency of different scenic spot combinations (such as A and B, B and C); the frequency is weighted and corrected by factors such as scenic spot level and tourist evaluation to obtain the connection strength value between scenic spots; a matrix is ​​constructed with scenic spots as rows and columns, and the connection strength value is filled into the corresponding matrix elements to form a scenic spot connection strength matrix that can quantify the degree of closeness of the connection between scenic spots.

[0106] In an optional embodiment, based on standard geographic data and location-accurate tourism resource data, a transportation tourism suitability index is calculated to obtain a transportation tourism suitability cost surface, including the following steps:

[0107] S31 performs terrain and surface analysis on standard geographic data to obtain the road zone visibility quality.

[0108] The roadside visibility quality includes road visibility range, water visibility, vegetation coverage, landscape type quality, and landscape diversity index. For example, the spatial layout terminal first extracts elevation data from standard geographic data. Using a visibility analysis algorithm, it simulates the visible range of observation points along the road and calculates the proportion of water bodies within the visible range to obtain water visibility. Based on normalized vegetation index data, it quantifies the vegetation coverage around the road using a vegetation coverage calculation model to obtain vegetation coverage. Combining land use type data, it classifies the landscape aesthetics of different land use types (such as forest land, water areas, and cultivated land) to obtain landscape type quality. Using landscape ecology analysis methods, it calculates the richness and evenness of landscape types in the area surrounding the road to obtain the landscape diversity index. Through the analysis of these four dimensions, a comprehensive assessment of the roadside visibility quality, reflecting the roadside landscape experience, is formed.

[0109] S32 assigns resource level values ​​to accurately located tourism resource data to obtain the value of cultural and tourism resources.

[0110] For example, the spatial layout terminal formulates a value assignment rule based on the scenic spot level. Generally, the higher the level, the higher the value (e.g., 5A scenic spots are assigned the highest value, and 1A scenic spots are assigned the lowest value). The value assignment rule needs to be adjusted in combination with the regional tourism development positioning, the actual reception capacity of the scenic spot, and the scarcity of resources. According to the rule, each scenic spot in the accurately located tourism resource data is assigned a corresponding value value. If there are multiple scenic spots in the same area, it is also necessary to calculate the average or sum of the values ​​of the scenic spots in the area to form a cultural and tourism resource value that can quantitatively reflect the value level of regional tourism resources.

[0111] S33. Accessibility analysis is performed on topology-optimized traffic data to obtain traffic resource accessibility factors.

[0112] For example, the spatial layout terminal constructs a traffic accessibility analysis model based on the road network structure of traffic data optimized by topology. The model considers factors such as the road network level (e.g., the difference in traffic efficiency between expressways, national roads, and county roads), road network density, and distance to transportation hubs (e.g., airports and railway stations). The traffic accessibility analysis model calculates the shortest travel time and shortest travel distance from each grid cell in the study area to the nearest scenic spot or transportation hub. The calculation results are standardized and transformed into quantitative indicators with values ​​within a specific range, which are the traffic resource accessibility factors that can reflect the degree of traffic convenience.

[0113] S34. Using the following formula, the road-view quality, cultural and tourism resource value, and transportation resource accessibility factors are weighted and superimposed to calculate the transportation-tourism suitability index, thus obtaining the transportation-tourism suitability cost surface:

[0114]

[0115] in, For grid The transportation and tourism suitability index For grid The quality of the road field of view, For grid The value of cultural and tourism resources For grid Accessibility factors of transportation resources The weighting coefficients for the quality of the road field of view. This is a weighting coefficient for the value of cultural and tourism resources. This represents the weighting coefficient of the accessibility factor for transportation resources.

[0116] Specifically, the spatial layout terminal uses a specified formula to weight and superimpose factors such as roadside visibility quality, cultural and tourism resource value, and transportation resource accessibility to calculate the transportation-tourism suitability index and generate a cost surface. In the formula for the aforementioned transportation-tourism suitability index, Representative grid The transport and tourism suitability index is used to quantify the grid. The suitability of the matching between transportation and tourism resources within the region; For grid The quality of the roadside visibility reflects the level of landscape experience in the grid area; For grid The cultural and tourism resources value reflects the tourism appeal of this grid area; For grid The accessibility factor of transportation resources characterizes the degree of transportation convenience of the grid area; , , These are weighting coefficients for factors such as roadside visibility quality, cultural and tourism resource value, and transportation accessibility. These weighting coefficients are set based on the core needs of regional transportation and tourism development (such as emphasizing landscape experience or convenient transportation) and must meet certain requirements. The spatial layout terminal substitutes each grid cell into the formula for calculation. ,Will A raster layer is constructed using cost values ​​to form a transportation and tourism suitability cost surface, in which... The smaller the value, the higher the suitability for transportation and tourism in that grid area.

[0117] In an optional embodiment, based on topology-optimized traffic data and effective tourist behavior data, tourist traffic volume is calculated to obtain a tourist traffic volume grid, including the following steps:

[0118] S41, extract trajectory points from valid tourist behavior data to obtain a set of tourist trajectory points.

[0119] For example, the spatial layout terminal uses a trajectory data parsing algorithm to separate self-driving tour trajectory data from valid tourist behavior data. According to the time sequence, it extracts information such as location coordinates (latitude and longitude) and recording time from each trajectory. The extracted location coordinates are organized according to the trajectory and time sequence to form a tourist trajectory point set containing multiple tourist self-driving trajectories, each trajectory consisting of multiple ordered location points. This point set completely records the spatiotemporal path of the tourist's self-driving trip.

[0120] S42, using the following formula, kernel density estimation is performed on the tourist trajectory point set to obtain a preliminary traffic volume raster:

[0121]

[0122] in, For position The kernel density value at that location, For the number of tourist trajectory points, For bandwidth, For kernel function, For the first The location of each tourist's trajectory point.

[0123] Specifically, the spatial layout terminal uses a kernel density estimation formula to analyze the tourist trajectory point set and obtain a preliminary traffic volume grid. Kernel density estimation is a non-parametric statistical method used to estimate the distribution density of spatial point data. It can transform discrete tourist trajectory points into a continuous density surface, reflecting the spatial distribution of traffic volume. In the above formula for calculating the kernel density value, Representative position The kernel density value at a given location is positively correlated with the density of tourist trajectory points at that location and can indirectly represent the traffic volume. The number of tourist trajectory points, i.e., the total number of trajectory points participating in the density calculation; The bandwidth is used to control the influence range of the kernel function. The larger the bandwidth, the smoother the density surface; the smaller the bandwidth, the better the density surface reflects the density of local points. The bandwidth needs to be adjusted according to the range of the study area and the distribution density of trajectory points. The kernel function, typically a Gaussian kernel function, is used to calculate the position. With the trajectory points The closer the distance between them, the greater the weight. For the first The location coordinates of each tourist trajectory point. The spatial layout terminal divides the study area into grid cells, and the center position of each grid cell is... Substitute into the formula to calculate ,Will The initial traffic volume values ​​are used as the initial values ​​for the grid cells to form a preliminary traffic volume grid.

[0124] S43, normalize the initial traffic volume grid to obtain the tourist traffic volume grid.

[0125] For example, the spatial layout terminal first calculates the maximum and minimum kernel density values ​​of all grid cells in the preliminary traffic volume grid; then, using a linear normalization algorithm, it maps the kernel density value of each grid cell to a specified interval such as [0,1] or [1,10]. The calculation formula is as follows: ,in The normalized traffic volume value. This is the original kernel density value. This represents the minimum nuclear density. M represents the maximum kernel density, and N represents the upper and lower limits of the target interval. Through normalization, the traffic volume data has a unified dimension and value range, forming a tourism traffic volume raster that facilitates subsequent analysis.

[0126] In an optional embodiment, based on location-accurate tourism resource data and effective tourist behavior data, the connection strength between scenic spots is calculated to obtain a scenic spot connection strength matrix, including the following steps:

[0127] S51. Based on accurate location-based tourism resource data and effective tourist behavior data, self-driving tourism trajectory data is used to extract scenic spot visit sequences, calculate trajectory co-occurrence frequencies, and obtain a scenic spot trajectory association matrix.

[0128] For example, the spatial layout terminal uses self-driving travel trajectory data from accurate location tourism resource data and effective tourist behavior data as a basis to extract scenic spot visit sequences and calculate trajectory co-occurrence frequencies to construct a scenic spot trajectory association matrix. First, the spatial layout terminal spatially matches the self-driving travel trajectory data with the scenic spot locations in the accurate location tourism resource data to determine the scenic spots passed through by each trajectory and arranges them in chronological order to form a scenic spot visit sequence, such as scenic spot 1 → scenic spot 1 → scenic spot 3. Then, it counts the number of consecutive occurrences of different scenic spot combinations (such as scenic spot 1 and scenic spot 2, scenic spot 2 and scenic spot 3) in all visit sequences, and this number is the trajectory co-occurrence frequency between scenic spots. Finally, the terminal constructs a matrix with scenic spots as rows and columns, and fills the trajectory co-occurrence frequency of each pair of scenic spots into the corresponding matrix elements to form a scenic spot trajectory association matrix that reflects the degree of scenic spot association based on self-driving trajectories.

[0129] S52. Based on accurate location-based tourism resource data and effective tourist behavior data, online travelogue text data is segmented and scenic area entity recognition is performed. The co-occurrence frequency of scenic areas is calculated using the following formula to obtain the scenic area text association matrix:

[0130]

[0131] in, For the scenic area With the scenic area The text association value, The total number of valid online travelogue texts. As the first indicator variable, it is used to characterize the current situation when the first... The travelogue includes scenic spots When it is 1, The second indicator variable is used to characterize the situation when the first... The travelogue includes scenic spots The time is 1.

[0132] In the above formula, For the scenic area With the scenic area The text association value is the total number of times both appear together in the online travelogue text data; The total number of valid online travelogue texts represents the size of the trajectory sample used in the calculation. As the first indicator variable, it is used to characterize the current situation when the first... The travelogue includes scenic spots The value is 1 if there is no such value, and 0 if there is none. The second indicator variable is used to characterize the situation when the first... The travelogue includes scenic spots The value is 1 if there is no value, and 0 if there is none. This is achieved by considering all... Each valid online travelogue text is checked to determine whether it simultaneously includes information about scenic spots. and scenic area and will meet the conditions and Accumulate the cases where all are 1, and the final result is... Able to quantify scenic spots With the scenic area The degree of correlation in online travelogue text data provides key data support for subsequent analysis of the connection strength between scenic spots.

[0133] For example, the spatial layout terminal uses online travelogue text data from accurately located tourism resource data and effective tourist behavior data as a basis to perform word segmentation and scenic spot entity recognition. Using the aforementioned formula, it calculates the co-occurrence frequency of scenic spots and constructs a scenic spot text association matrix. Specifically, first, the spatial layout terminal uses a Chinese word segmentation algorithm to segment the online travelogue text data, breaking down continuous text into independent words or phrases. The terminal constructs a scenic spot entity dictionary based on the scenic spot names in the accurately located tourism resource data and uses an entity recognition algorithm to extract the scenic spot names from the word segmentation results, determining the scenic spots mentioned in each travelogue. Next, it counts the number of times different scenic spot combinations appear simultaneously in all travelogues; this number is the text co-occurrence frequency between scenic spots. A higher frequency indicates a greater probability that tourists mention two scenic spots simultaneously in their travelogues. Finally, it constructs a matrix with scenic spots as rows and columns, filling the corresponding matrix elements with the text co-occurrence frequency of each pair of scenic spots, forming a scenic spot text association matrix that reflects the degree of scenic spot association based on the travelogue text. The Chinese word segmentation algorithm can be the Jieba word segmentation algorithm, and the entity recognition algorithm can be rule-based entity recognition or machine learning-based entity recognition.

[0134] S53. Using the following formula, the scenic area trajectory association matrix and the scenic area text association matrix are weighted and fused to obtain the comprehensive scenic area association matrix:

[0135]

[0136] in, For the scenic area With the scenic area The overall correlation value, For the scenic area With the scenic area trajectory association value, For the scenic area With the scenic area The text association value, These are the weighting coefficients.

[0137] Specifically, the spatial layout terminal uses a specified formula to weightedly fuse the scenic area trajectory association matrix and the scenic area text association matrix to obtain a comprehensive scenic area association matrix. In the formula, Representative scenic area With the scenic area The comprehensive correlation value reflects the degree of correlation between scenic spots under the two types of data. The higher the value, the stronger the correlation. For the scenic area With the scenic area The trajectory correlation value is taken from the corresponding element in the scenic area trajectory correlation matrix, reflecting the actual travel correlation of self-driving tourists; For the scenic area With the scenic area The text association value is taken from the corresponding element in the scenic area text association matrix, reflecting the scenic area association in tourists' subjective descriptions; This is a weighting coefficient, with a value range of [0,1], used to balance the influence of trajectory association values ​​and text association values. Determined through the analytic hierarchy process (AHP) or expert scoring, if more emphasis is placed on actual travel behavior... If the value is close to 1, and more emphasis is placed on tourists' subjective preferences, The value is close to 0. The spatial layout terminal pairs each scenic area in the matrix. and Substitute into the formula to calculate This forms a comprehensive relational matrix for the scenic area.

[0138] S54. Normalize the comprehensive correlation matrix of the scenic area to obtain the connection strength matrix of the scenic area.

[0139] For example, the spatial layout terminal performs normalization processing on the scenic area comprehensive association matrix, because the scenic area comprehensive association matrix contains... The range of values ​​may vary significantly due to factors such as the number of scenic spots and the scale of data, making it inconvenient for subsequent overlay analysis with suitability corridors. Therefore, normalization is necessary to unify the dimensions. The spatial layout terminal first calculates the maximum value of all elements in the comprehensive correlation matrix of scenic spots. and minimum value A linear normalization algorithm is used to calculate the comprehensive correlation value of each element. Mapping to the [0,1] interval, the calculation formula is as follows: (in (This represents the normalized connection strength value); for the diagonal elements in the matrix (the connections within the same scenic area), set to 0 (because there is no need to analyze the connections between scenic areas themselves). Normalization ensures that the scenic area connection data has a uniform value range, forming a scenic area connection strength matrix that can be directly used for subsequent overlay analysis.

[0140] In an optional embodiment, the transportation tourism suitability cost surface and scenic area data from tourism resource data are combined to perform minimum cost path analysis to obtain suitability corridors, including the following steps:

[0141] S61 uses the transportation and tourism suitability cost surface as the cost resistance surface and the scenic area location points in the scenic area data as the source points for cost path analysis.

[0142] For example, the spatial layout terminal defines the transportation-tourism suitability cost surface as the cost resistance surface, and selects scenic spot location points from the scenic spot data as the source points for cost path analysis. In the transportation-tourism suitability cost surface, the cost value of each grid cell represents the level of transportation-tourism suitability in that area. The lower the cost value, the higher the suitability and the smaller the resistance to transportation, which conforms to the core principle that higher selection preference corresponds to lower cost. Therefore, it can be directly used as the cost resistance surface for path analysis. The scenic spot location points in the scenic spot data are the core destinations of tourism transportation. Tourists' trips usually start or end at scenic spots. Using these location points as source points ensures that the subsequently calculated paths revolve around scenic spots, which meets the need for tourism transportation routes to connect core tourism resources. The spatial layout terminal clarifies the spatial correspondence between the cost resistance surface and the source points through spatial data association operations.

[0143] S62, based on the cost resistance surface and source point, calculates the minimum cumulative cost from each grid cell to the nearest scenic area using the cost distance tool, and obtains the minimum cumulative cost grid cell.

[0144] For example, the spatial layout terminal calculates the minimum cumulative cost from each grid cell to the nearest scenic spot based on the cost resistance surface and the source point, using a cost distance tool to generate a minimum cumulative cost grid. The core principle of the cost distance tool is to calculate the sum of the costs of all grid cells traversed from each grid cell to the nearest source point (scenic spot location point), i.e., the minimum cumulative cost. This cost value reflects the total resistance from the grid area to the nearest scenic spot; a lower value indicates a more convenient journey. During the calculation, the spatial layout terminal considers the movement costs between grid cells (such as the cost differences between adjacent grid cells) and uses an iterative algorithm to gradually traverse all grid cells, ensuring the accuracy of the minimum cumulative cost calculation for each grid cell. After calculation, the minimum cumulative cost value of each grid cell is used as an attribute value to construct a grid layer, forming the minimum cumulative cost grid. This grid provides the cost distance basis for subsequent identification of minimum cost paths.

[0145] S63, based on the minimum cumulative cost grid, identifies the minimum cost path from each grid to the nearest source point, and obtains the global minimum cost path network.

[0146] For example, the spatial layout terminal uses a minimum cumulative cost grid as a basis to identify the minimum cost path from each grid to the nearest source point, constructing a global minimum cost path network. The identification process employs a cost backtracking algorithm. This algorithm starts from each grid cell and, based on the cost value distribution of the minimum cumulative cost grid, backtracks gradually in the direction of decreasing cost value until it reaches the nearest source point (scenic spot location). The grid cells traversed during the backtracking process are connected to form the minimum cost path from that grid to the source point. The spatial layout terminal performs this backtracking operation on all non-source grid cells within the study area, obtaining a large number of dispersed minimum cost paths. The terminal then uses a path fusion algorithm to merge adjacent, overlapping, or consistent paths, eliminating path redundancy and forming a set of paths covering the entire area and connecting all scenic spots—the global minimum cost path network. The paths in this network satisfy both the minimum transportation cost and the consideration of landscape quality and tourism resource distribution, meeting the core requirements of tourism transportation routes.

[0147] S64 performs density analysis on the minimum cost path network across the entire region, identifies the core corridors where paths converge, and obtains suitable corridors.

[0148] For example, the spatial layout terminal performs density analysis on the minimum cost path network across the entire region to identify core corridors where paths converge, ultimately obtaining suitable corridors. The core of density analysis is to statistically analyze the length or number of minimum cost paths per unit area within the study region. Higher density indicates more convergent paths, higher priority of transportation routes, and greater suitability as core tourism transportation corridors. The spatial layout terminal performs sliding window analysis on the minimum cost path network across the entire region by setting reasonable analysis windows (such as circular or rectangular windows), calculating the path density value within each window. Then, the density values ​​are classified into levels using the natural breakpoint method, extracting the areas corresponding to the highest density levels; these areas are the core corridors where paths converge. Finally, the core corridors are smoothed to eliminate local broken lines or breaks, forming continuous and complete corridor lines, which are the suitable corridors that can preferentially connect areas with dense tourism resources and high transportation suitability.

[0149] The aforementioned transportation and tourism integration layout method based on multi-source spatial data integrates multiple types of multi-source spatial data and performs systematic preprocessing. It combines multi-dimensional analysis to generate suitable corridors, key improvement sections, and supplementary branch lines. Then, it integrates supporting service facilities to form a layout plan. This ensures that the layout fully considers traffic accessibility, landscape quality, and the matching degree of tourism resources, while accurately meeting the actual travel needs of tourists and the related needs of scenic spots. This improves the scientificity and rationality of the transportation and tourism integration layout, and provides a clear direction for subsequent optimization of transportation facilities and improvement of supporting services. It strongly supports the high-quality integrated development of transportation and tourism and has strong practical guiding value.

[0150] To further illustrate the solutions of this application's embodiments, a specific example is provided below. The spatial layout method for the integrated development of transportation and tourism includes the following steps:

[0151] The scenic area and road network data are sourced from the Ministry of Transport's 2024 statistical data; elevation data (DEM 30m), land use type data (LULC 30m), and normalized difference vegetation index (NDVI 10m) data are sourced from the data sharing service system. Travel trajectory data is from the Liangbulu website, obtaining 1189 GPS tracks from 2024 driving data; travelogue data is from Ctrip's 2024 travelogues, collecting 4628 entries totaling 7.1 million words using Web Scraper, with most travelogues covering rich travel experiences and detailed itinerary descriptions.

[0152] 1. Transportation and tourism suitability analysis based on geographic information data

[0153] This evaluation focuses on road-regional visibility quality, transportation resource conditions, and cultural and tourism resource conditions as its core modules. Based on the principle that higher preference corresponds to lower cost, a transportation-tourism suitability cost surface is constructed. The analysis of road selection preferences and suitable transportation-tourism corridors provides data support for the selection of tourism transportation routes.

[0154] (1) Road field of vision quality

[0155] Road visibility quality includes road visibility based on the road's visual range and landscape quality. Landscape quality is constructed from four indicator layers: water visibility, vegetation coverage, landscape type quality, and landscape diversity index. Related geospatial data analysis was conducted using the ArcGIS Pro platform.

[0156] The Geodesic Viewshed tool was used to analyze the line-of-sight range of the road area using DEM data and road network data. Road data included highways, national roads, provincial roads, county roads, and railways. Points were generated along the routes at 10km intervals and used as observation points for analysis.

[0157] The visibility of water bodies is reclassified and calculated by overlaying the line of sight with the water body.

[0158] Using LULC data and the Fragstats 4.2 spatial pattern analysis system, the Shannon diversity index was calculated by combining land use type data with the 1000m moving window method.

[0159] Based on land use type, landscape quality is classified according to factors such as scenic beauty and scarcity. NDVI is graded according to the Natural Breaks classification method.

[0160] Based on the Natural Breaks classification, the calculated results of each indicator are graded and assigned values ​​according to the grade scores. The sum of all indicators yields the overall landscape quality.

[0161] Based on the buffer range of each level of road, the road zone visibility quality cost is extracted. The lower the cost value, the higher the road zone visibility quality.

[0162] (2) Transportation resources

[0163] Transportation resource conditions include the service capacity of various types and levels of roads in tourism transportation options, as well as the service convenience of the proximity of relevant transportation hubs.

[0164] Based on research on provincial tourism transportation routes, routes with stronger preferences for cross-regional transportation modes have lower selection costs. Furthermore, considering the impact range of various road types and levels, buffer zones are established and cost values ​​are constructed.

[0165] Transportation hubs, including high-speed rail / train stations and airports, are mapped across the entire region using a 1km network of points. The distance from each point to the nearest transportation hub is calculated, and the overall transportation hub service convenience capability is analyzed. This is then categorized using Natural Breaks and assigned a graded value. Areas with higher levels of transportation hub resources are more likely to have their road sections selected first.

[0166] (3) Tourism resource conditions

[0167] Tourism resource conditions include the distribution density of A-5A level scenic spots. The denser the distribution of A-level scenic spots, the greater the potential for tourism transportation route selection, indicating a higher likelihood of route selection in that area. The kernel density of A-5A level scenic spots was calculated separately, classified using the Natural Breaks classification method, and assigned values ​​according to the scenic spot level.

[0168] The traffic tourism suitability cost surface is generated by combining modules such as road area visibility quality, traffic resource conditions, and cultural and tourism resource conditions.

[0169] Based on the buffer zones of roads at all levels, the total cost of the road network is extracted. The lower the cost value, the higher the road's suitability for tourism transportation. This cost assessment also considers the quality of scenic views, transportation resources, and cultural and tourism resources.

[0170] Using each A-level scenic area as the source point and the transportation-tourism suitability cost surface as the cost grid, the minimum cost path is analyzed using the CostConnectivity tool. The results simultaneously consider the shortest transportation route and the quality of roadside landscapes and tourism resources. Lower path costs indicate greater preference for this option. Paths that overlap with existing or planned transportation routes represent the best tourism transportation value for those routes. Locally deviated routes from transportation routes indicate that the direction of deviation represents better tourism and landscape resources, and should be the focus of future construction of transportation service stations, landscape nodes, and branch lines. Ultimately, a suitability corridor is constructed.

[0171] 2. Tourism traffic volume analysis based on tourist trajectory data

[0172] Tourists' subjective driving route selection can intuitively demonstrate the distribution of tourism traffic in local or cross-regional areas. GPS trajectory data for self-driving tourism can effectively illustrate tourists' subjective route selection. By using self-driving tourism GPS data, we can explore the spatial traffic distribution characteristics of tourist flow roads and assess the potential traffic volume distribution of road networks. Routes with high traffic volume are key areas for future traffic quality improvement, including road surface quality and service stations.

[0173] The travel trajectory data comes from the Liangbulu platform, which has a wider user base and more comprehensive trajectory data. It has been applied in tourism transportation research and has a certain degree of maturity and representativeness. Considering the impact of the COVID-19 pandemic on tourism behavior from 2020 to 2022 and the slow recovery of the tourism industry in 2023, this study selects self-driving travel trajectory data from 2024 to study tourist trajectory traffic.

[0174] A total of 1,189 GPS tracks were collected from driving data in 2024. These vector GPS tracks were converted to raster data in ArcGIS Pro, overlaid and merged for counting, and the resulting track traffic volumes were synthesized. Abnormal spatial locations and frequencies were removed, and the frequency paths were converted into lines to generate visitor track traffic frequencies.

[0175] 3. Analysis of the Connectivity Strength of Tourist Attractions Based on Online Travelogue Text Data

[0176] Scenic spots, as destinations, are a key element in tourism transportation research. Travelogues reflect tourists' preferences for visiting multiple scenic spots and their order of visits, revealing the relationships between them. Studying the strength of connections between scenic spots through travelogue data can provide a basis for transportation route selection. Scenic spots with higher connectivity require more consideration of transportation modes between destinations, including prioritizing improvements to public transportation (railways, flights) and road services.

[0177] This study focuses on 981 A-level scenic spots and collects travelogues uploaded by tourists to Ctrip in 2024. A total of 7.1 million words of travelogues, each mentioning at least two A-level scenic spots, were selected. Using an open-source large language model, the collected travelogues were processed into 4,628 valid tour routes with a defined order.

[0178] Using a map API platform, nodes (such as attractions and landmarks) in each tour route are converted into latitude and longitude coordinates and then geospatialized on the ArcGIS Pro platform.

[0179] To further optimize the geographic information of the tour route, a KD-tree algorithm is used to perform a nearest neighbor query on each node in the route to determine its nearest attraction, and then replace the original node coordinates with the attraction coordinates. To avoid interference from uncertainties such as cross-provincial coordinates on the tour route, a distance threshold is set: if the distance between a node and its nearest attraction exceeds 20 kilometers, the node coordinates are ignored.

[0180] For each tour route, when two nodes in the route are connected, the weight of the "edge" between the two nodes is incremented by one to quantify the degree of connection between the attractions.

[0181] Based on the suitability of transportation for tourism, the volume of tourism traffic, and the connectivity of tourist attractions, a schematic diagram of the tourism transportation structure is constructed, including a core tourism transportation hub relying on Chengdu; two ring-shaped tourism transportation regional connection rings connecting the transportation hub; two inter-provincial tourism transportation axes connecting the north and south; and nine tourism transportation and cultural corridors.

[0182] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0183] Based on the same inventive concept, this application also provides a transportation and tourism integration layout system based on multi-source spatial data for implementing the aforementioned transportation and tourism integration layout method based on multi-source spatial data. The solution provided by this system is similar to the implementation scheme described in the above method. Therefore, the specific limitations of one or more embodiments of the transportation and tourism integration layout system based on multi-source spatial data provided below can be found in the limitations of the transportation and tourism integration layout method based on multi-source spatial data described above, and will not be repeated here.

[0184] In one exemplary embodiment, such as Figure 2 As shown, a transportation and tourism integrated layout system 200 based on multi-source spatial data is provided, including:

[0185] The data acquisition and preprocessing module 201 is used to acquire multi-source spatial data and preprocess the multi-source spatial data to obtain preprocessed data; the multi-source spatial data includes basic geographic data, transportation data, tourism resource data and tourist behavior data;

[0186] The data analysis module 202 is used to perform analysis on transportation-tourism suitability, tourism traffic volume, and scenic area connectivity based on preprocessed data, respectively, to obtain a transportation-tourism suitability cost surface, a tourism traffic volume grid, and a scenic area connectivity matrix. The transportation-tourism suitability cost surface is used to characterize the suitability of regional transportation and tourism resources; the tourism traffic volume grid is used to characterize the spatial distribution of tourist traffic flow; and the scenic area connectivity matrix is ​​used to characterize the degree of correlation between tourist visits between scenic areas.

[0187] The corridor analysis module 203 is used to combine the transportation tourism suitability cost surface and the scenic area data in the tourism resource data to conduct minimum cost path analysis and obtain suitability corridors; the suitability corridor is used to characterize the routes that match the degree of matching between transportation and tourism resources;

[0188] The optimized road segment demand analysis module 204 is used to overlay the tourism traffic volume grid with the suitability corridor to obtain the key road segments for improvement; the key road segments for improvement are used to characterize road segments with high tourist flow and high traffic and tourism suitability that need to be optimized.

[0189] The new road segment demand analysis module 205 is used to overlay the scenic area connection strength matrix with the suitability corridor to obtain the branch road segments that need to be supplemented; the branch road segments that need to be supplemented are used to characterize the new road segments that have high inter-scenic area correlation but insufficient traffic coverage.

[0190] The Transportation Integration Layout Scheme Module 206 is used to integrate suitable corridors, key improvement sections, and supplementary branch line sections with supporting service facilities to obtain a transportation and tourism integration layout scheme.

[0191] Furthermore, the data acquisition and preprocessing module 201 is also used for:

[0192] Acquire multi-source spatial data; basic geographic data includes elevation data, land use type data, and normalized difference vegetation index data; transportation data is used to characterize the regional road network and transportation hub distribution; tourism resource data includes the spatial location and grade information of scenic spots; tourist behavior data includes self-driving travel trajectory data and online travelogue text data;

[0193] The basic geographic data is processed to standardize the coordinate system, resulting in standard geographic data;

[0194] Perform topology checks and repairs on traffic data to obtain topology-optimized traffic data;

[0195] Spatial location correction is performed on tourism resource data to obtain tourism resource data with accurate location;

[0196] Spatiotemporal cleaning of tourist behavior data is performed to obtain effective tourist behavior data;

[0197] Spatial registration is performed on standard geographic data, topology-optimized traffic data, location-accurate tourism resource data, and effective tourist behavior data to obtain preprocessed data.

[0198] Furthermore, the data analysis module 202 is also used for:

[0199] Based on standard geographic data and location-accurate tourism resource data, a transportation and tourism suitability index is calculated to obtain a transportation and tourism suitability cost surface.

[0200] Based on topology-optimized traffic data and effective tourist behavior data, tourist traffic volume is calculated to obtain a tourist traffic volume raster.

[0201] Based on accurate location-based tourism resource data and effective tourist behavior data, the connection strength between scenic spots is calculated to obtain a scenic spot connection strength matrix.

[0202] Furthermore, the data analysis module 202 is also used for:

[0203] Topographic and surface analysis is performed on standard geographic data to obtain road zone visibility quality; road zone visibility quality includes road visibility range, water visibility, vegetation coverage, landscape type quality, and landscape diversity index.

[0204] By assigning resource level values ​​to accurately located tourism resource data, the value of cultural and tourism resources can be obtained.

[0205] Accessibility analysis is performed on topology-optimized traffic data to obtain traffic resource accessibility factors;

[0206] Using the following formula, the road-view quality, cultural and tourism resource value, and transportation resource accessibility factors are weighted and superimposed to calculate the transportation-tourism suitability index, thus obtaining the transportation-tourism suitability cost surface:

[0207]

[0208] in, For grid The transportation and tourism suitability index For grid The quality of the road field of view, For grid The value of cultural and tourism resources For grid Accessibility factors of transportation resources The weighting coefficients for the quality of the road field of view. This is a weighting coefficient for the value of cultural and tourism resources. This represents the weighting coefficient of the accessibility factor for transportation resources.

[0209] Furthermore, the data analysis module 202 is also used for:

[0210] Trajectory points are extracted from valid tourist behavior data to obtain a set of tourist trajectory points;

[0211] The following formula is used to perform kernel density estimation on the tourist trajectory point set to obtain a preliminary traffic volume raster:

[0212]

[0213] in, For position The kernel density value at that location, For the number of tourist trajectory points, For bandwidth, For kernel function, For the first The location of each tourist's trajectory point;

[0214] The initial traffic volume grid is normalized to obtain the tourism traffic volume grid.

[0215] Furthermore, the data analysis module 202 is also used for:

[0216] Based on self-driving tour trajectory data with accurate location tourism resource data and effective tourist behavior data, scenic spot visit sequences are extracted, trajectory co-occurrence frequency is calculated, and scenic spot trajectory association matrix is ​​obtained.

[0217] Based on accurate location-based tourism resource data and effective tourist behavior data, we perform word segmentation and scenic spot entity recognition on online travelogue text data. The co-occurrence frequency of scenic spots is calculated using the following formula to obtain the scenic spot text association matrix:

[0218]

[0219] in, For the scenic area With the scenic area The text association value, The total number of valid online travelogue texts. As the first indicator variable, it is used to characterize the current situation when the first... The travelogue includes scenic spots When it is 1, The second indicator variable is used to characterize the situation when the first... The travelogue includes scenic spots The time is 1;

[0220] The following formula is used to weight and fuse the scenic area trajectory association matrix and the scenic area text association matrix to obtain the comprehensive scenic area association matrix:

[0221]

[0222] in, For the scenic area With the scenic area The overall correlation value, For the scenic area With the scenic area trajectory association value, For the scenic area With the scenic area The text association value, These are the weighting coefficients;

[0223] The comprehensive correlation matrix of scenic spots is normalized to obtain the correlation strength matrix of scenic spots.

[0224] Furthermore, the corridor analysis module 203 is also used for:

[0225] The transportation and tourism suitability cost surface is used as the cost resistance surface, and the scenic spot location points in the scenic spot data are used as the source points for cost path analysis.

[0226] Based on the cost resistance surface and the source point, the minimum cumulative cost to the nearest scenic spot for each grid is calculated using the cost distance tool, thus obtaining the grid with the minimum cumulative cost;

[0227] Based on the minimum cumulative cost grid, the minimum cost path from each grid to the nearest source point is identified, resulting in the global minimum cost path network.

[0228] Density analysis is performed on the minimum cost path network across the entire region to identify the core corridors where paths converge and to obtain suitable corridors.

[0229] In one embodiment, such as Figure 3 A computer device 300 is provided, comprising:

[0230] At least one processor 301, and at least one memory 302 communicatively connected to said processor 301; said memory stores application code executable by said processor, said application code being executed by said processor to enable said processor to perform the steps of the traffic and tourism fusion layout method based on multi-source spatial data as described above;

[0231] The computer device may also include: sensor 303;

[0232] The processor 301, memory 302, and sensor 303 can be connected via bus 304 or other means. The figure shows an example of connection via bus 304. Figure 3 The character is represented by a single thick line, but this does not mean that there is only one bus or a type of bus.

[0233] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps in the above method embodiments.

[0234] For the device embodiments, since they basically correspond to the method embodiments, the relevant parts can be referred to in the description of the method embodiments. The device embodiments described above are merely illustrative. The components described as separate parts may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this disclosure according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0235] The above-described embodiments are merely illustrative of several implementation methods of the embodiments of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of the patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the embodiments of this application, and these modifications and improvements all fall within the protection scope of the embodiments of this application.

Claims

1. A method for integrating transportation and tourism layout based on multi-source spatial data, characterized in that, The method includes: Acquire multi-source spatial data and preprocess the multi-source spatial data to obtain preprocessed data; the multi-source spatial data includes basic geographic data, transportation data, tourism resource data, and tourist behavior data; Based on the preprocessed data, analysis of transportation-tourism suitability, tourism traffic volume, and scenic area connectivity strength is performed to obtain a transportation-tourism suitability cost surface, a tourism traffic volume grid, and a scenic area connectivity strength matrix. The transportation-tourism suitability cost surface is used to characterize the suitability of regional transportation and tourism resources; the tourism traffic volume grid is used to characterize the spatial distribution of tourist traffic flow; and the scenic area connectivity strength matrix is ​​used to characterize the degree of correlation between tourist visits to different scenic areas. By combining the transportation and tourism suitability cost surface with the scenic area data in the tourism resource data, a minimum cost path analysis is performed to obtain suitability corridors; the suitability corridors are used to characterize routes where the matching degree between transportation and tourism resources is satisfactory. The tourism traffic volume grid is overlaid with the suitability corridor to obtain the key improvement road sections; the key improvement road sections are used to characterize road sections with high tourist flow and high traffic tourism suitability that need to be optimized. The connection strength matrix of the scenic area is superimposed with the suitability corridor to obtain the branch road segments that need to be supplemented; the branch road segments that need to be supplemented are used to characterize the new road segments that need to be added when the inter-scenic area has a high degree of correlation but insufficient traffic coverage. By integrating the supporting service facilities, the suitable corridors, the key improvement sections, and the supplementary branch lines, a transportation and tourism integration layout plan is obtained.

2. The method according to claim 1, characterized in that, The process of acquiring multi-source spatial data and preprocessing the multi-source spatial data to obtain preprocessed data includes: Acquire multi-source spatial data; the basic geographic data includes elevation data, land use type data, and normalized difference vegetation index data; the transportation data is used to characterize the regional road network and transportation hub distribution; the tourism resource data includes the spatial location and grade information of scenic spots; the tourist behavior data includes self-driving travel trajectory data and online travelogue text data; The basic geographic data is subjected to coordinate system normalization processing to obtain standard geographic data; Perform topology checks and repairs on traffic data to obtain topology-optimized traffic data; Spatial location correction is performed on tourism resource data to obtain tourism resource data with accurate location; Spatiotemporal cleaning of tourist behavior data is performed to obtain effective tourist behavior data; Spatial registration is performed on the standard geographic data, the topology-optimized traffic data, the location-accurate tourism resource data, and the effective tourist behavior data to obtain preprocessed data.

3. The method according to claim 2, characterized in that, Based on the preprocessed data, the following analyses are performed: transportation-tourism suitability, tourism traffic volume, and scenic area connectivity strength, resulting in a transportation-tourism suitability cost surface, a tourism traffic volume grid, and a scenic area connectivity strength matrix: Based on the standard geographic data and the location-accurate tourism resource data, the transportation and tourism suitability index is calculated to obtain the transportation and tourism suitability cost surface. Based on the topology-optimized traffic data and the effective tourist behavior data, the tourist traffic volume is calculated to obtain a tourist traffic volume grid. Based on the accurate location tourism resource data and the effective tourist behavior data, the connection strength between scenic spots is calculated to obtain the scenic spot connection strength matrix.

4. The method according to claim 3, characterized in that, The calculation of the transportation and tourism suitability index based on the standard geographic data and the location-accurate tourism resource data, resulting in the transportation and tourism suitability cost surface, includes: The standard geographic data is subjected to topographic and surface analysis to obtain the road area visibility quality; the road area visibility quality includes road visibility range, water visibility, vegetation coverage, landscape type quality and landscape diversity index. The accurate location-based tourism resource data is assigned resource level values ​​to obtain the cultural and tourism resource value. Accessibility analysis is performed on the topology-optimized traffic data to obtain the traffic resource accessibility factor; The weighting coefficients of the road zone visibility quality, the cultural and tourism resource value, and the transportation resource accessibility factor were determined by combining expert consultation with the analytic hierarchy process. The following formula is used to calculate the transportation tourism suitability index by weighting and superimposing the road zone view quality, the cultural and tourism resource value, and the transportation resource accessibility factor, thus obtaining the transportation tourism suitability cost surface: in, For grid The transportation and tourism suitability index For grid Road field of view quality, For grid The value of cultural and tourism resources For grid Accessibility factors of transportation resources The weighting coefficients for the road domain view quality are as follows: This refers to the weighting coefficient for the value of the aforementioned cultural and tourism resources. is the weighting coefficient of the traffic resource accessibility factor.

5. The method according to claim 3, characterized in that, The process of calculating tourist traffic volume based on the topology-optimized traffic data and the effective tourist behavior data to obtain a tourist traffic volume grid includes: Trajectory points are extracted from the valid tourist behavior data to obtain a set of tourist trajectory points; The kernel density of the tourist trajectory point set is estimated using the following formula to obtain a preliminary traffic volume raster: in, For position The kernel density value at that location, For the number of tourist trajectory points, For bandwidth, For kernel function, For the first The location of each tourist's trajectory point; The initial traffic volume grid is normalized to obtain the tourism traffic volume grid.

6. The method according to claim 3, characterized in that, The process of calculating the connection strength between scenic spots based on the accurate location tourism resource data and the effective tourist behavior data, to obtain a scenic spot connection strength matrix, includes: Based on the accurate location tourism resource data and the effective tourist behavior data, the self-driving tourism trajectory data is used to extract scenic spot visit sequences, calculate trajectory co-occurrence frequency, and obtain the scenic spot trajectory association matrix. Based on the accurate location-based tourism resource data and the effective tourist behavior data, online travelogue text data is used for word segmentation and scenic area entity recognition. The co-occurrence frequency of scenic areas is calculated using the following formula to obtain the scenic area text association matrix: in, For the scenic area With the scenic area The text association value, The total number of valid online travelogue texts. As the first indicator variable, it is used to characterize the current situation when the first... The travelogue includes scenic spots When it is 1, The second indicator variable is used to characterize the situation when the first... The travelogue includes scenic spots The time is 1; The scenic area trajectory association matrix and the scenic area text association matrix are weighted and fused using the following formula to obtain the comprehensive scenic area association matrix: in, For the scenic area With the scenic area The overall correlation value, For the scenic area With the scenic area trajectory association value, For the scenic area With the scenic area The text association value, These are the weighting coefficients; The comprehensive correlation matrix of the scenic area is normalized to obtain the connection strength matrix of the scenic area.

7. The method according to claim 1, characterized in that, The step of combining the transportation and tourism suitability cost surface with the scenic area data in the tourism resource data to perform minimum cost path analysis and obtain suitability corridors includes: The transportation and tourism suitability cost surface is used as the cost resistance surface, and the scenic spot location points in the scenic spot data are used as the source points for cost path analysis. Based on the cost resistance surface and the source point, the minimum cumulative cost from each grid to the nearest scenic spot is calculated using the cost distance tool to obtain the minimum cumulative cost grid. Based on the minimum cumulative cost grid, the minimum cost path from each grid to the nearest source point is identified to obtain the global minimum cost path network; Density analysis is performed on the global minimum cost path network to identify the core corridors where paths converge, thus obtaining suitable corridors.

8. A transportation and tourism integrated layout system based on multi-source spatial data, characterized in that, The system includes: The data acquisition and preprocessing module is used to acquire multi-source spatial data and preprocess the multi-source spatial data to obtain preprocessed data; the multi-source spatial data includes basic geographic data, transportation data, tourism resource data, and tourist behavior data. The data analysis module is used to perform transportation-tourism suitability analysis, tourism traffic volume analysis, and scenic area connectivity analysis based on the preprocessed data, respectively, to obtain a transportation-tourism suitability cost surface, a tourism traffic volume grid, and a scenic area connectivity matrix. The transportation-tourism suitability cost surface is used to characterize the suitability of regional transportation and tourism resources; the tourism traffic volume grid is used to characterize the spatial distribution of tourist traffic flow; and the scenic area connectivity matrix is ​​used to characterize the degree of correlation between tourist visits to different scenic areas. The corridor analysis module is used to combine the transportation tourism suitability cost surface and the scenic area data in the tourism resource data to perform minimum cost path analysis and obtain suitability corridors; the suitability corridors are used to characterize routes where the matching degree between transportation and tourism resources is consistent. The optimized road segment demand analysis module is used to overlay the tourism traffic volume grid with the suitability corridor to obtain key improvement road segments; the key improvement road segments are used to characterize road segments with high tourist flow and high traffic tourism suitability that need to be optimized. A new road segment demand analysis module is added to overlay the scenic area connection strength matrix with the suitability corridor to obtain the branch road segments that need to be supplemented; the branch road segments that need to be supplemented are used to characterize the new road segments that have high inter-scenic area correlation but insufficient traffic coverage. The transportation integration layout module is used to combine the suitable corridors, the key improvement sections, and the supplementary branch line sections with supporting service facilities to obtain a transportation and tourism integration layout plan.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the method of any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images