A method, system, device and medium for optimizing site selection of tourist attractions

Abstract

The present invention relates to the field of site selection optimization technology, and in particular to a site selection optimization method, system, device and medium for tourist attractions, including: obtaining candidate site selection information of rural tourist attractions, and using a geographic information system to perform spatial analysis on the candidate site selection information to obtain the geographical environment characteristics of the candidate points; constructing a Thiessen polygon optimization grid according to the geographical environment characteristics of the candidate points, and using a quadtree to divide the Thiessen polygon optimization grid to obtain site selection sub-areas; expressing the geographical environment characteristics of the candidate points in each site selection sub-area as a spatial entity to construct a graph structure; using a graph attention neural network algorithm to learn the graph structure to predict the optimal spatial coordinates of the site selection of the tourist attraction. The present invention realizes a method for optimizing the site selection of the tourist attraction by combining the characteristics of the quadtree and the graph structure, and can more accurately analyze the spatial connections such as cultural resources between the site selection of the tourist attraction, and provide more accurate and effective support for the planning and management of tourist attractions.

Description

Technical Field

[0001] The present invention relates to the technical field of site selection optimization, and in particular to a site selection optimization method, system, equipment and medium for tourist attractions. Background Art

[0002] With the rapid development of tourism, rural tourism is an important part of the tourism industry. The site selection and planning of rural tourist attractions have become a key link, which directly affects the efficiency and sustainability of rural tourism. However, the traditional site selection method of tourist attractions mainly relies on the experience and intuition of decision makers, lacks scientificity and objectivity, or only considers single factors such as local natural resources and cultural background, lacks comprehensive consideration and optimization of multiple factors, which leads to unreasonable planning of tourist attractions, affecting tourists' experience and sustainable development of the tourism industry. Therefore, it is urgent to develop a site selection optimization method for tourist attractions based on data analysis and geographic information system (GIS) to improve the accuracy and efficiency of site selection. Summary of the invention

[0003] The present invention provides a method, system, device and medium for optimizing the site selection of tourist attractions, and solves the technical problem that the traditional site selection method of tourist attractions mainly relies on the experience of decision makers or lacks comprehensive consideration and optimization of multiple factors.

[0004] In order to solve the above technical problems, the present invention provides a method, system, device and medium for optimizing the site selection of tourist attractions.

[0005] In a first aspect, the present invention provides a method for optimizing the site selection of a tourist attraction, the method comprising the following steps:

[0006] Acquire candidate site information of rural tourist attractions, and use a geographic information system to perform spatial analysis on the candidate site information to obtain geographic environmental characteristics of the candidate points; the candidate site geographical environmental characteristics include geographic spatial distribution characteristics and surrounding environmental characteristics of the candidate site, and the surrounding environmental characteristics include surrounding traffic information, natural resource characteristics, agricultural resource characteristics and regional cultural characteristics of the candidate site;

[0007] Constructing a Thiessen polygon optimization grid according to the geographic environment characteristics of the candidate points, and using a quadtree to divide each Thiessen polygon in the Thiessen polygon optimization grid to obtain a site selection sub-area;

[0008] Expressing the geographical environment characteristics of the candidate points of each of the site selection sub-regions as spatial entities and constructing a graph structure;

[0009] The graph structure is learned using a graph attention neural network algorithm to predict the optimal spatial coordinates of the scenic spot location.

[0010] In a further embodiment, the step of constructing a Thiessen polygon optimization grid according to the geographic environment characteristics of the candidate points includes:

[0011] Based on the geographic spatial distribution characteristics of the candidate site, construct a Thiessen polygon grid;

[0012] Using a machine learning algorithm to analyze the influence of the surrounding environment characteristics on the Thiessen polygon mesh, and obtain the surrounding environment influence;

[0013] The Thiessen polygon mesh is optimized according to the influence of the surrounding environment to obtain a Thiessen polygon optimized mesh.

[0014] In a further embodiment, the step of dividing each Thiessen polygon in the Thiessen polygon optimization grid using a quadtree to obtain a site selection sub-region comprises:

[0015] The root node of the Thiessen polygon optimized grid is used as the root node of the quadtree, and the Thiessen polygon area of ​​each root node is divided into four quadrants to form four corresponding quadrant sub-areas, each quadrant sub-area corresponds to a child node;

[0016] Repeat the above steps to recursively divide each of the child nodes into four quadrants until the divided quadrant sub-regions meet the restriction conditions, stop the recursive division, form the final quadtree, and extract all the divided quadrant sub-regions from the final quadtree as the site selection sub-regions.

[0017] In a further embodiment, the step of expressing the geographical environment characteristics of the candidate points of each of the site selection sub-regions as spatial entities and constructing a graph structure comprises:

[0018] Taking each of the site selection sub-regions as a graph node in a graph structure, and constructing edges of the graph structure using a graph theory algorithm according to the relationship between each of the site selection sub-regions;

[0019] The constructed graph nodes and edges are added to the graph structure, and the attribute characteristics of each graph node and edge are defined according to the geographic environment characteristics of the candidate points of each of the site selection sub-areas, so as to associate the spatial entity with the geographic environment characteristics of the candidate points to form a graph structure.

[0020] In a further embodiment, the graph attention neural network algorithm includes a multi-layer graph convolution module, an attention mechanism module, a random pooling layer and an output layer based on Bayesian inference connected in sequence.

[0021] In a further embodiment, the step of using a graph attention neural network algorithm to learn the graph structure and predict the spatial coordinates of the optimal scenic spot location includes:

[0022] Encode the attribute features of the graph nodes in the graph structure to obtain the node feature vector;

[0023] The graph attention neural network algorithm is used to perform convolution and aggregation processing on the node feature vectors to obtain the node location spatial coordinate prediction results and the corresponding uncertainty measurement;

[0024] The optimal scenic spot site selection spatial coordinates are obtained according to the node site selection spatial coordinate prediction results and the uncertainty measurement.

[0025] In a further embodiment, the step of obtaining the optimal scenic spot site selection spatial coordinates according to the node site selection spatial coordinate prediction results and the uncertainty measure comprises:

[0026] Calculate the differences between all the node site selection spatial coordinate prediction results according to the uncertainty metric to obtain the site selection prediction difference;

[0027] According to the site selection prediction difference and the difference threshold, selecting excellent site selection spatial coordinates from all the node site selection spatial coordinate prediction results;

[0028] The weighted average of the excellent site selection spatial coordinates is calculated to obtain the optimal scenic spot site selection spatial coordinates.

[0029] In a second aspect, the present invention provides a site selection optimization system for tourist attractions, the system comprising:

[0030] The data acquisition module 101 is used to acquire candidate site information of rural tourist attractions, and perform spatial analysis on the candidate site information using a geographic information system to obtain geographic environmental characteristics of the candidate points; the geographic environmental characteristics of the candidate points include geographic spatial distribution characteristics and surrounding environmental characteristics of the candidate sites, and the surrounding environmental characteristics include surrounding traffic information, natural resource characteristics, agricultural resource characteristics and regional cultural characteristics of the candidate sites;

[0031] The regional optimization module 102 is used to construct a Thiessen polygon optimization grid according to the geographic environment characteristics of the candidate points, and divide each Thiessen polygon in the Thiessen polygon optimization grid by using a quadtree to obtain a site selection sub-region;

[0032] A graph structure building module 103 is used to express the geographical environment characteristics of the candidate points of each of the site selection sub-regions as spatial entities to build a graph structure;

[0033] The site selection prediction and optimization module 104 is used to use the graph attention neural network algorithm to learn the graph structure and predict the optimal scenic spot site selection spatial coordinates.

[0034] In a third aspect, the present invention further provides a computer device, comprising a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory so that the computer device performs the steps of implementing the above method.

[0035] In a fourth aspect, the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the steps of the above method when executed by a processor.

[0036] The present invention provides a method, system, device and medium for optimizing the site selection of tourist attractions. The method uses a geographic information system to perform spatial analysis on candidate site selection information to obtain the geographic environment characteristics of the candidate points; constructs a Thiessen polygon optimization grid according to the geographic environment characteristics of the candidate points, and uses a quadtree to divide each Thiessen polygon in the Thiessen polygon optimization grid to obtain a site selection sub-area; expresses the geographic environment characteristics of the candidate points in each site selection sub-area as a spatial entity to construct a graph structure; uses a graph attention neural network algorithm to learn the graph structure to predict the optimal site selection spatial coordinates. Compared with the prior art, the method optimizes the Thiessen polygon grid in combination with surrounding traffic information, cultural information and other data to express richer geographic spatial information, and uses the Thiessen polygon optimization grid and quadtree division to form a graph structure containing information such as cultural background, which can realize the refined processing and efficient query of geographic spatial data and surrounding environmental characteristics, and can more accurately analyze the spatial distribution and association of cultural resources and other cultural resources between the site selection of tourist attractions, and provide more accurate and effective support for the planning and management of tourist attractions. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 It is a schematic flow chart of a method for optimizing the site selection of tourist attractions provided by an embodiment of the present invention;

[0038] Figure 2 is a schematic diagram of a site selection optimization system for tourist attractions provided by an embodiment of the present invention;

[0039] Figure 3 It is a structural diagram of a computer device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The following specifically illustrates the implementation mode of the present invention in conjunction with the accompanying drawings. The embodiments are provided for illustrative purposes only and cannot be understood as limiting the present invention. The accompanying drawings are provided for reference and illustration only and do not constitute a limitation on the scope of patent protection of the present invention, because many changes can be made to the present invention without departing from the spirit and scope of the present invention.

[0041] refer to Figure 1 , the embodiment of the present invention provides a method for optimizing the site selection of tourist attractions, such as Figure 1 As shown, the method comprises the following steps:

[0042] S1. Obtain candidate site information for rural tourist attractions, and use a geographic information system to perform spatial analysis on the candidate site information to obtain geographic environmental characteristics of the candidate points; the geographic environmental characteristics of the candidate points include the geographic spatial distribution characteristics and surrounding environmental characteristics of the candidate sites, and the surrounding environmental characteristics include the surrounding traffic information, natural resource characteristics, agricultural resource characteristics and regional cultural characteristics of the candidate sites.

[0043] Since rural tourist attractions usually rely on local natural resources, such as mountains, rivers, fields, animals and plants, and compared with urban tourist attractions, rural tourist attractions usually contain rich cultural heritage and local characteristics, which can transform cultural resources into tourist attractions. At the same time, the agricultural characteristics, traffic conditions, accessibility of tourists and distance from surrounding cities in rural areas are all factors that need to be fully considered in the construction of rural tourist attractions. Therefore, in order to achieve comprehensive and reasonable planning of rural tourist attractions, the site selection of rural tourist attractions needs to comprehensively consider various factors such as local geographical location, natural resources, cultural background, market demand, tourist experience, environmental protection and social benefits. Factors are used to determine the optimal site selection plan. This embodiment collects candidate site information such as geographic information, transportation information, natural resources, agricultural resources, market information and cultural information of rural tourist attractions, and uses a geographic information system (GIS) to perform spatial analysis on the collected data to obtain the spatial distribution characteristics and surrounding environmental characteristics of the candidate sites. It should be noted that in order to ensure the accuracy of the data, this embodiment can clean, organize and standardize the collected data before using the geographic information system to perform spatial analysis on the collected data. These processes include removing duplicate and erroneous data, unifying data formats and standards, and processing missing values.

[0044] S2. Construct a Thiessen polygon optimization grid according to the geographic environment characteristics of the candidate points, and use a quadtree to divide each Thiessen polygon in the Thiessen polygon optimization grid to obtain a site selection sub-area.

[0045] In this embodiment, the step of constructing a Thiessen polygon optimization grid according to the geographic environment characteristics of the candidate points includes:

[0046] Based on the geographic spatial distribution characteristics of the candidate site, construct a Thiessen polygon grid;

[0047] Using a machine learning algorithm to analyze the influence of the surrounding environment characteristics on the Thiessen polygon mesh, and obtain the surrounding environment influence;

[0048] The Thiessen polygon mesh is optimized according to the influence of the surrounding environment to obtain a Thiessen polygon optimized mesh.

[0049] Thiessen polygons are a data structure for expressing geographic spatial distribution. This embodiment constructs a Thiessen polygon grid through the geographic spatial distribution characteristics of the candidate site selection, so as to express the spatial distribution of geographic information through the Thiessen polygon grid, and then comprehensively considers and analyzes the influence of surrounding traffic information, natural resource characteristics, agricultural resource characteristics, regional cultural characteristics and other data of the candidate site selection on the Thiessen polygon grid, and optimizes the Thiessen polygon grid. It should be noted that since the surrounding traffic information, natural resource characteristics, agricultural resource characteristics, regional cultural characteristics and other data of the candidate site selection affect the Thiessen polygon grid in a linear and / or nonlinear relationship, this embodiment uses a machine learning algorithm to optimize the surrounding traffic information of the Thiessen polygon grid. , natural resource characteristics, agricultural resource characteristics, regional cultural characteristics and other surrounding environmental characteristics are analyzed to evaluate the impact of these data on the attractiveness of the scenic spot, obtain the influence of the surrounding environment, and analyze and adjust the Thiessen polygon grid according to the influence of the surrounding environment. For example, the size of the Thiessen polygon grid can be adjusted according to the traffic flow, and the density or distribution range of the Thiessen polygon grid in the geographic space can be adjusted according to the cultural distribution or market distribution, so that the final Thiessen polygon optimized grid can better reflect the actual situation and meet the needs. In this embodiment, when using a machine learning algorithm to analyze the impact of the Thiessen polygon grid, the machine learning algorithm includes but is not limited to a multi-layer perceptron MLP or a convolutional neural network CNN.

[0050] In order to more accurately analyze the spatial connections and features between the locations of scenic spots, this embodiment uses a quadtree to divide each Thiessen polygon in the Thiessen polygon optimization grid, so that the Thiessen polygon optimization grid is recursively divided into smaller sub-areas through quadtree partitioning, and these sub-areas are added to the graph structure as nodes to achieve more sophisticated spatial analysis and query operations, which can more accurately express the location and distribution of scenic spots, thereby searching for target scenic spot locations or areas more quickly and improving search efficiency. In this embodiment, the step of using a quadtree to divide each Thiessen polygon in the Thiessen polygon optimization grid to obtain a location sub-area includes:

[0051] The root node of the Thiessen polygon optimized grid is used as the root node of the quadtree, and the Thiessen polygon area of ​​each root node is divided into four quadrants to form four corresponding quadrant sub-areas, each quadrant sub-area corresponds to a child node, wherein, in order to avoid excessive differences, when dividing by the quadtree, the divided quadrant sub-areas need to be distributed as evenly as possible;

[0052] Repeat the above steps to recursively divide each of the child nodes into four quadrants until the divided quadrant sub-areas meet the preset restriction conditions, stop the recursive division, form a final quadtree, and extract all the divided quadrant sub-areas from the final quadtree as the site selection sub-areas. In this embodiment, the preset restriction conditions can be set as the divided quadrant sub-areas reaching a preset area threshold.

[0053] S3. Express the geographical environment characteristics of the candidate points of each of the site selection sub-areas as spatial entities and construct a graph structure.

[0054] In this embodiment, the step of expressing the geographical environment features of the candidate points of each of the site selection sub-regions as spatial entities and constructing a graph structure includes:

[0055] Taking each of the site selection sub-regions as a graph node in a graph structure, and constructing edges of the graph structure using a graph theory algorithm according to the relationship between each of the site selection sub-regions;

[0056] The constructed graph nodes and edges are added to the graph structure, and the attribute characteristics of each graph node and edge are defined according to the geographic environment characteristics of the candidate points of each of the site selection sub-areas, so as to associate the spatial entity with the geographic environment characteristics of the candidate points to form a graph structure.

[0057] Specifically, this embodiment regards each site selection sub-region as a spatial entity, and regards the site selection sub-region as a graph node, and uses a graph theory algorithm to construct the edges of the graph structure according to the association relationship between spatial entities, and adds the graph nodes and edges to the graph structure. The attributes and relationships of the graph nodes and edges are defined according to information such as geographic spatial characteristics and cultural background. This embodiment combines the advantages of spatial division and graph structure, utilizes the division characteristics of the quadtree, refines and processes the Thiessen polygon optimization grid, and adds all quadrant sub-regions obtained from the division as graph nodes of the graph structure to the graph structure, wherein each graph node corresponds to a Thiessen polygon sub-region. This application simultaneously utilizes the spatial division and graph structure to maintain the spatial relationship between scenic spots, which is conducive to the graph theory algorithm to analyze the spatial connection and association characteristics between scenic spots more efficiently and accurately through reasoning, query and other operations, and to express the relationship between them in the graph structure to form the final graph structure, wherein the association characteristics include the association relationship of surrounding environment characteristics such as cultural background. At the same time, this embodiment can enhance scalability. If other feature data of the site selection of scenic spots needs to be added, it is only necessary to further divide the Thiessen polygon optimization grid using the quadtree and update the graph structure.

[0058] S4. Use the graph attention neural network algorithm to learn the graph structure and predict the optimal spatial coordinates of the scenic spot location.

[0059] In this embodiment, the graph attention neural network algorithm includes a multi-layer graph convolution module, an attention mechanism module, a random pooling layer, and an output layer based on Bayesian inference connected in sequence. The step of using the graph attention neural network algorithm to learn the graph structure and predict the spatial coordinates of the optimal scenic spot location includes:

[0060] Encode the attribute features of the graph nodes in the graph structure to obtain the node feature vector;

[0061] The graph attention neural network algorithm is used to perform convolution and aggregation processing on the node feature vectors to obtain the node location spatial coordinate prediction results and the corresponding uncertainty measurement;

[0062] The optimal scenic spot site selection spatial coordinates are obtained according to the node site selection spatial coordinate prediction results and the uncertainty measurement.

[0063] This embodiment uses a graph attention neural network algorithm to predict each graph node of the graph structure, and can extract and update node features to obtain the prediction result and corresponding uncertainty measurement of each graph node. The multi-layer graph convolution module includes several serially connected graph convolution layers. The graph nodes and edges of the graph structure are subjected to feature extraction through the multi-layer graph convolution module, and then these extracted features are concatenated to obtain the final high-level node feature representation. The attention mechanism module is used to learn the correlation between the node feature representations, and the contribution of the neighboring nodes to the node feature representation is calculated. At the same time, a random pooling layer is introduced. The random pooling operation is performed on the random nodes layer to retain the most important neighbor nodes and remove some noise nodes. The attention mechanism introduced in this embodiment can make the model pay more attention to the important features and node correlation related to the site selection of scenic spots. The model can learn the influence weights between different nodes and infer the importance of nodes based on these weights, so as to better evaluate the suitability of each location as a potential scenic spot. At the same time, random pooling can help reduce the interference of noise nodes and retain the most important neighbor nodes. In the application scenario of site selection of rural tourist attractions, random pooling can filter out some insignificant nodes when considering the characteristics of the surrounding environment, so that the model can focus more on the node information that is helpful for decision-making and improve the accuracy of site selection. In addition, in the application scenario of site selection of rural tourist attractions, combined with Bayesian inference, certain uncertainties can be taken into account, and confidence or probability distribution information on whether each site selection location is suitable as a scenic spot can be provided, so as to more accurately evaluate the risk and prediction results of site selection.

[0064] In this embodiment, the step of obtaining the optimal scenic spot site selection spatial coordinates according to the node site selection spatial coordinate prediction result and the uncertainty measure includes:

[0065] Calculate the differences between all the node site selection spatial coordinate prediction results according to the uncertainty metric to obtain the site selection prediction difference;

[0066] According to the site selection prediction difference and the difference threshold, selecting excellent site selection spatial coordinates from all the node site selection spatial coordinate prediction results;

[0067] The weighted average of the excellent site selection spatial coordinates is calculated to obtain the optimal scenic spot site selection spatial coordinates. In this embodiment, the weights in the weighted average algorithm are dynamically allocated according to the site selection prediction difference.

[0068] Specifically, in order to better understand the uncertainty characteristics of the model output and make more accurate and reliable site selection prediction decisions through these characteristics, this embodiment can use KL divergence or cross entropy to analyze the uncertainty metric, calculate the differences between all the node site selection spatial coordinate prediction results, and filter the prediction results according to the differences. This can more comprehensively consider the impact of different factors on the node site selection spatial coordinate prediction results, obtain more accurate site selection coordinates, and improve the accuracy of site selection prediction.

[0069] The embodiment of the present invention provides a method for optimizing the site selection of tourist attractions. The method uses a geographic information system to perform spatial analysis on candidate site selection information to obtain the geographic environment characteristics of the candidate points; constructs a Thiessen polygon optimization grid according to the geographic environment characteristics of the candidate points, and uses a quadtree to divide each Thiessen polygon in the Thiessen polygon optimization grid to obtain a site selection sub-area; expresses the geographic environment characteristics of the candidate points in each site selection sub-area as a spatial entity to construct a graph structure; uses a graph attention neural network algorithm to learn the graph structure to predict the optimal site selection spatial coordinates of the scenic spot. The site selection optimization method proposed in this embodiment can be used to more finely manage and plan the site selection of the scenic spot by dividing the Thiessen polygon optimization grid by a quadtree, and uses the Thiessen polygon optimization grid graph neural network algorithm and the machine learning algorithm to learn and simulate the spatial distribution and association of data such as cultural resources, so as to achieve a deeper query and analysis of the spatial information of the scenic spot, so that the model can better predict the optimal site selection spatial coordinates of the scenic spot, thereby improving the prediction accuracy.

[0070] It should be noted that the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0071] In one embodiment, Figure 2 As shown, an embodiment of the present invention provides a site selection optimization system for tourist attractions, the system comprising:

[0072] The data acquisition module 101 is used to acquire candidate site information of rural tourist attractions, and perform spatial analysis on the candidate site information using a geographic information system to obtain geographic environmental characteristics of the candidate points; the geographic environmental characteristics of the candidate points include geographic spatial distribution characteristics and surrounding environmental characteristics of the candidate sites, and the surrounding environmental characteristics include surrounding traffic information, natural resource characteristics, agricultural resource characteristics and regional cultural characteristics of the candidate sites;

[0073] The regional optimization module 102 is used to construct a Thiessen polygon optimization grid according to the geographic environment characteristics of the candidate points, and divide each Thiessen polygon in the Thiessen polygon optimization grid by using a quadtree to obtain a site selection sub-region;

[0074] A graph structure building module 103 is used to express the geographical environment characteristics of the candidate points of each of the site selection sub-regions as spatial entities to build a graph structure;

[0075] The site selection prediction and optimization module 104 is used to use the graph attention neural network algorithm to learn the graph structure and predict the optimal scenic spot site selection spatial coordinates.

[0076] For the specific definition of a site selection optimization system for tourist attractions, please refer to the above-mentioned definition of a site selection optimization method for tourist attractions, which will not be repeated here. Those of ordinary skill in the art will appreciate that the various modules and steps described in conjunction with the embodiments disclosed in this application can be implemented in hardware, software, or a combination of both. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0077] The embodiment of the present invention provides a site selection optimization system for tourist attractions. The system performs spatial analysis on candidate site selection information through a data acquisition module; constructs a Thiessen polygon optimization grid through a regional optimization module, and divides each Thiessen polygon in the Thiessen polygon optimization grid using a quadtree to obtain site selection sub-regions; and implements graph structure learning through a graph structure establishment module and a site selection prediction optimization module to predict the optimal site selection spatial coordinates of the tourist attraction. Compared with the prior art, the present embodiment can simultaneously utilize the advantages of machine learning algorithms, spatial division, and graph structures to more accurately analyze the spatial connections and features between scenic spots, realize refined processing and efficient query of candidate site selection information, thereby obtaining more accurate site selection optimization results for tourist attractions, and providing more accurate and effective data support for the planning and management of tourist attractions.

[0078] Figure 3A computer device provided by an embodiment of the present invention includes a memory, a processor and a transceiver, which are connected via a bus; the memory is used to store a set of computer program instructions and data, and can transmit the stored data to the processor, and the processor can execute the program instructions stored in the memory to perform the steps of the above method.

[0079] The memory may include a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories; the processor may be a central processing unit, a microprocessor, an application-specific integrated circuit, a programmable logic device, or a combination thereof. By way of example but not limitation, the programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic, or any combination thereof.

[0080] Additionally, the memory may be a physically separate unit or may be integrated with the processor.

[0081] It can be understood by those skilled in the art that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have the same component arrangement.

[0082] In one embodiment, the present invention provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0083] The embodiments of the present invention provide a method, system, device and medium for optimizing the site selection of tourist attractions. The method for optimizing the site selection of tourist attractions utilizes the partitioning characteristics of quadtrees and the advantages of graph structures to deeply learn and simulate the spatial relationships and surrounding environmental characteristics of scenic spots, thereby achieving a deeper level of query and analysis of surrounding environmental characteristics such as scenic spot spatial information and cultural background, providing more basis and support for scenic spot planning, and promoting the sustainable development of scenic spots.

[0084] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., an SSD), etc.

[0085] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0086] The above-mentioned embodiments only express several preferred implementation modes of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in the technical field, several improvements and substitutions can be made without departing from the technical principles of the present invention, and these improvements and substitutions should also be regarded as the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be based on the protection scope of the claims.

Claims

1. A method for optimizing the site selection of tourist attractions, characterized in that: The following steps are involved: Acquire candidate site information of rural tourist attractions, and use a geographic information system to perform spatial analysis on the candidate site information to obtain geographic environmental characteristics of the candidate points; the candidate site geographical environmental characteristics include geographic spatial distribution characteristics and surrounding environmental characteristics of the candidate site, and the surrounding environmental characteristics include surrounding traffic information, natural resource characteristics, agricultural resource characteristics and regional cultural characteristics of the candidate site; Constructing a Thiessen polygon optimization grid according to the geographic environment characteristics of the candidate points, and using a quadtree to divide each Thiessen polygon in the Thiessen polygon optimization grid to obtain a site selection sub-area; Expressing the geographical environment characteristics of the candidate points of each of the site selection sub-regions as spatial entities and constructing a graph structure; Using a graph attention neural network algorithm to learn the graph structure, the optimal spatial coordinates of the scenic spot are predicted; The step of constructing a Thiessen polygon optimization grid according to the geographic environment characteristics of the candidate points includes: Based on the geographic spatial distribution characteristics of the candidate site, construct a Thiessen polygon grid; Using a machine learning algorithm to analyze the influence of the surrounding environment characteristics on the Thiessen polygon mesh, and obtain the surrounding environment influence; Optimizing the Thiessen polygon mesh according to the surrounding environment influence to obtain a Thiessen polygon optimized mesh; The step of using the graph attention neural network algorithm to learn the graph structure and predict the optimal scenic spot location spatial coordinates includes: Encode the attribute features of the graph nodes in the graph structure to obtain the node feature vector; The graph attention neural network algorithm is used to perform convolution and aggregation processing on the node feature vectors to obtain the node location spatial coordinate prediction results and the corresponding uncertainty measurement; Obtaining the optimal scenic spot site selection spatial coordinates according to the node site selection spatial coordinate prediction results and the uncertainty measurement; The step of obtaining the optimal scenic spot site selection spatial coordinates according to the node site selection spatial coordinate prediction result and the uncertainty measure comprises: Calculate the differences between all the node site selection spatial coordinate prediction results according to the uncertainty metric to obtain the site selection prediction difference; According to the site selection prediction difference and the difference threshold, selecting excellent site selection spatial coordinates from all the node site selection spatial coordinate prediction results; The weighted average of the excellent site selection spatial coordinates is calculated to obtain the optimal scenic spot site selection spatial coordinates.

2. A method for optimizing the site selection of tourist attractions according to claim 1, characterized in that: The step of dividing each Thiessen polygon in the Thiessen polygon optimization grid by using a quadtree to obtain a site selection sub-region comprises: The root node of the Thiessen polygon optimized grid is used as the root node of the quadtree, and the Thiessen polygon area of ​​each root node is divided into four quadrants to form four corresponding quadrant sub-areas, each quadrant sub-area corresponds to a child node; Repeat the above steps to recursively divide each of the child nodes into four quadrants until the divided quadrant sub-areas meet the preset restriction conditions, stop the recursive division, form the final quadtree, and extract all the divided quadrant sub-areas from the final quadtree as the site selection sub-areas.

3. A method for optimizing the site selection of tourist attractions according to claim 1, characterized in that: The step of expressing the geographical environment characteristics of the candidate points of each of the site selection sub-areas as spatial entities and constructing a graph structure comprises: Taking each of the site selection sub-regions as a graph node in a graph structure, and constructing edges of the graph structure using a graph theory algorithm according to the relationship between each of the site selection sub-regions; The constructed graph nodes and edges are added to the graph structure, and the attribute characteristics of each graph node and edge are defined according to the geographic environment characteristics of the candidate points of each of the site selection sub-areas, so as to associate the spatial entity with the geographic environment characteristics of the candidate points to form a graph structure.

4. A method for optimizing the site selection of tourist attractions as claimed in claim 3, characterized in that: The graph attention neural network algorithm includes a multi-layer graph convolution module, an attention mechanism module, a random pooling layer and an output layer based on Bayesian inference that are connected in sequence.

5. A site selection optimization system for tourist attractions, characterized in that: The system comprises: A data acquisition module is used to acquire candidate site information of rural tourist attractions, and to perform spatial analysis on the candidate site information using a geographic information system to obtain geographic environmental characteristics of the candidate points; the geographic environmental characteristics of the candidate points include geographic spatial distribution characteristics and surrounding environmental characteristics of the candidate sites, and the surrounding environmental characteristics include surrounding traffic information, natural resource characteristics, agricultural resource characteristics, and regional cultural characteristics of the candidate sites; A regional optimization module is used to construct a Thiessen polygon optimization grid according to the geographical environment characteristics of the candidate points, and to divide each Thiessen polygon in the Thiessen polygon optimization grid using a quadtree to obtain a site selection sub-region; A graph structure building module is used to express the geographical environment characteristics of the candidate points of each of the site selection sub-areas as spatial entities to build a graph structure; A site selection prediction and optimization module is used to learn the graph structure using a graph attention neural network algorithm to predict the spatial coordinates of the optimal site selection of the scenic spot; The step of constructing a Thiessen polygon optimization grid according to the geographic environment characteristics of the candidate points specifically includes: Based on the geographic spatial distribution characteristics of the candidate site, construct a Thiessen polygon grid; Using a machine learning algorithm to analyze the influence of the surrounding environment characteristics on the Thiessen polygon mesh, and obtain the surrounding environment influence; Optimizing the Thiessen polygon mesh according to the surrounding environment influence to obtain a Thiessen polygon optimized mesh; The site selection prediction and optimization module is specifically used for: Encode the attribute features of the graph nodes in the graph structure to obtain the node feature vector; The graph attention neural network algorithm is used to perform convolution and aggregation processing on the node feature vectors to obtain the node location spatial coordinate prediction results and the corresponding uncertainty measurement; Obtaining the optimal scenic spot site selection spatial coordinates according to the node site selection spatial coordinate prediction results and the uncertainty measurement; The step of obtaining the optimal scenic spot location spatial coordinates according to the node location spatial coordinate prediction result and the uncertainty measure specifically includes: Calculate the differences between all the node site selection spatial coordinate prediction results according to the uncertainty metric to obtain the site selection prediction difference; According to the site selection prediction difference and the difference threshold, selecting excellent site selection spatial coordinates from all the node site selection spatial coordinate prediction results; The weighted average of the excellent site selection spatial coordinates is calculated to obtain the optimal scenic spot site selection spatial coordinates.

6. A computer device, characterized in that: The computer device comprises a processor and a memory, wherein the processor is connected to the memory, the memory is used to store a computer program, and the processor is used to execute the computer program stored in the memory, so that the computer device executes the method according to any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the method according to any one of claims 1 to 4 is implemented.

Images