Method, apparatus, and electronic device for storing and sharing mapping data based on a cloud platform

Abstract

The present invention provides a method, apparatus, and electronic device for storing and sharing mapping data based on a cloud platform. The method includes: constructing a cloud storage architecture; performing format conversion and standardization processing on heterogeneous mapping data stored in the cloud storage architecture based on a pre-established mapping data format standard and metadata specification to obtain standard mapping data; performing reconstruction processing on the standard mapping data to determine the classification type corresponding to the standard mapping data; establishing a data directory for the standard mapping data based on the classification type corresponding to the standard mapping data; constructing a multi-dimensional spatial index for the standard mapping data; and setting a service interface layer on the cloud storage architecture, where the service interface layer is used to provide a unified data access interface to query the standard mapping data through the multi-dimensional spatial index or the data directory. By adopting the above technical solution, a unified mapping data storage and sharing platform can be provided to achieve standardized storage, efficient management, and convenient sharing of mapping data.

Description

Technical Field

[0001] Embodiments of the present invention relate to the technical field of surveying and mapping data management, and in particular, to a method, device, and electronic device for storing and sharing surveying and mapping data based on a cloud platform. Background Art

[0002] At present, surveying and mapping geographic information has become an important resource in the national economy and is widely used in multiple fields.

[0003] With the increase in surveying and mapping geographic information, the following problems exist in practical applications: First, due to the diverse ways of obtaining geospatial data and the different software platforms for collecting and managing geographic information data, the data standards and data formats of geographic information are diverse; Second, in practical applications, it is necessary to utilize geographic information from different sources and types, resulting in a large amount of data conversion work and low data utilization rate; Third, the traditional surveying and mapping data management method lacks a unified data storage standard, making data sharing difficult and causing duplicate collection and duplicate construction.

[0004] Therefore, how to provide a technical solution to provide a unified surveying and mapping data storage and sharing platform to achieve standardized storage, efficient management, and convenient sharing of massive heterogeneous surveying and mapping data has become an urgent technical problem to be solved. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a method, device, and electronic device for storing and sharing surveying and mapping data based on a cloud platform, which can provide a unified surveying and mapping data storage and sharing platform to achieve standardized storage, efficient management, and convenient sharing of massive heterogeneous surveying and mapping data.

[0006] Embodiments of the present invention provide a method for storing and sharing surveying and mapping data based on a cloud platform, including: constructing a cloud storage architecture; performing format conversion and standardization processing on heterogeneous surveying and mapping data stored in the cloud storage architecture based on a pre-established surveying and mapping data format standard and metadata specification to obtain standard surveying and mapping data; performing reconstruction processing on the standard surveying and mapping data to determine the classification type corresponding to the standard surveying and mapping data; establishing a data directory for the standard surveying and mapping data based on the classification type corresponding to the standard surveying and mapping data; constructing a multi-dimensional space index for the standard surveying and mapping data; and setting a service interface layer on the cloud storage architecture, where the service interface layer is used to provide a unified data access interface to query the standard surveying and mapping data through the multi-dimensional space index or the data directory.

[0007] Optionally, the constructing of the cloud storage architecture includes:

[0008] Adopting the Hadoop distributed file system as the underlying storage architecture to achieve distributed storage of surveying and mapping data;

[0009] Build a distributed database cluster to support the storage and management of structured and unstructured surveying and mapping data.

[0010] Optionally, the reconstruction process for the standard surveying and mapping data to determine the classification type corresponding to the standard surveying and mapping data includes:

[0011] According to the super-resolution reconstruction framework based on the diffusion model and efficient bilinear attention fusion, enhance the image containing the standard surveying and mapping data to generate a high-resolution image, including: adding Gaussian noise to the image with a resolution lower than the preset resolution, and through a multi-step iterative reverse diffusion process, gradually restore and enhance the image details to generate multiple high-resolution images;

[0012] Based on the bilinear attention mechanism, establish the feature maps corresponding to each high-resolution image, and determine the bilinear similarity matrix between the feature maps by capturing the similarity between the feature maps at different scales and different types of features;

[0013] According to the feature maps, determine the terrain complexity of the local area corresponding to the feature maps, and based on the terrain complexity, adjust the parameters of the diffusion model and the attention weights to obtain the reconstruction result of the high-resolution image;

[0014] Use a multi-scale feature pyramid to determine the feature representations at different scales of the reconstruction result of the high-resolution image, and use the bilinear similarity matrix and bilinear attention mechanism between the feature maps for fusion operations to determine the classification type of the standard surveying and mapping data.

[0015] Optionally, the surveying and mapping data storage and sharing method satisfies one or more of the following:

[0016] Optimize and correct the classification results based on empirical rules;

[0017] Establish a data hierarchical access control mechanism, and according to the classification type, determine the access permission levels of each standard surveying and mapping data, and record the data access process in a log.

[0018] Optionally, establishing a data directory for the standard surveying and mapping data based on the classification type corresponding to the standard surveying and mapping data includes:

[0019] Based on the classification type, use efficient convolutional sparse coding with a local competition algorithm to construct the feature representation of the data directory, including: converting the surveying and mapping data into a high-dimensional feature space; through convolutional operations, extract the local feature patterns of the high-dimensional feature space as the feature representation of the data directory;

[0020] The segmented management of surveying and mapping data is achieved through a dual-decoder architecture, including: decoding the spatial attributes of the surveying and mapping data through the first decoder, and processing the temporal attributes of the surveying and mapping data through the second decoder;

[0021] Through an intelligent classification framework based on sparse coding, using a local competition algorithm, based on the spatial and temporal attributes of the surveying and mapping data, determine the hierarchical relationship between different features, and use the hierarchical relationship between different features to construct a hierarchical data directory structure.

[0022] Optionally, the construction of the multi-dimensional spatial index for the standard surveying and mapping data includes:

[0023] Divide the spatial objects corresponding to the standard surveying and mapping data according to the minimum bounding rectangle, and establish a hierarchical tree index structure;

[0024] Use a B+ tree index structure to establish a B+ tree index for the spatial objects corresponding to the standard surveying and mapping data;

[0025] Fuse the tree index structure and the B+ tree index to generate the multi-dimensional spatial index.

[0026] Optionally, the construction of the multi-dimensional spatial index for the standard surveying and mapping data includes:

[0027] Based on the cross-attention mechanism of the linear variability of the Kalman filter, model the dynamic features of the spatial objects corresponding to the standard surveying and mapping data, and determine the target areas of each standard surveying and mapping data;

[0028] Based on the node splitting and merging operations of the R tree index, identify the correlation between different spatial objects, and organize the storage spaces with a correlation greater than a set threshold in the same R tree node;

[0029] According to the distribution characteristics of the spatial objects on the R tree nodes, dynamically adjust the node capacity and splitting threshold of the B+ tree to generate a hybrid index structure;

[0030] Establish a mapping relationship between the hybrid index structure and the target areas of each standard surveying and mapping data as the multi-dimensional spatial index.

[0031] Optionally, the surveying and mapping data storage and sharing method satisfies one or more of the following:

[0032] Optimize the query process of the standard surveying and mapping data, including at least one of the following: adopt a consistent hashing algorithm to balance the load of different query requests, and dynamically adjust the service node load; based on the Redis cache mechanism, cache the hot data in the surveying and mapping data; configure parallel query processing, query plan optimization, and batch data query functions;

[0033] Visualize query results, including: providing display methods in the form of lists, map visualizations, and statistical charts, and supporting multi-condition combined filtering, sorting functions, and data export functions;

[0034] Establish a monitoring mechanism, including: real-time monitoring of storage capacity and access traffic metrics.

[0035] Correspondingly, the present invention also provides a cloud platform-based mapping data storage and sharing device, including:

[0036] A construction module for constructing a cloud storage architecture;

[0037] A data processing module for performing format conversion and standardization processing on heterogeneous mapping data stored in the cloud storage architecture based on a pre-established mapping data format standard and metadata specification to obtain standard mapping data;

[0038] A data management module for reconstructing the standard mapping data, determining the classification type corresponding to the standard mapping data, and establishing a data directory for the standard mapping data based on the classification type corresponding to the standard mapping data, and constructing a multi-dimensional space index for the standard mapping data;

[0039] An access module for querying the standard mapping data through a multi-dimensional space index or data directory by setting a service interface layer on the cloud storage architecture, where the service interface layer is used to provide a unified data access interface.

[0040] The present invention also provides an electronic device, including: a processor and a memory, where the memory stores one or more computer-executable instructions, and the processor calls the one or more computer-executable instructions to execute the steps of the method for storing and sharing mapping data as described in any of the foregoing embodiments.

[0041] Compared with the prior art, the technical solutions of the embodiments of the present invention have the following advantages:

[0042] In the method for storing and sharing surveying and mapping data based on a cloud platform provided by an embodiment of the present invention, first, by constructing a cloud storage architecture, distributed storage of surveying and mapping data is achieved, enabling faster query operations to be performed. Next, through format conversion and standardization processing of heterogeneous surveying and mapping data, unification of the format of standard surveying and mapping data is achieved. Secondly, through reconstruction processing of the standard surveying and mapping data, the classification type of the standard surveying and mapping data is determined, reducing the difficulty of establishing a data directory. Finally, through multi-dimensional spatial indexing of the standard surveying and mapping data and setting up a service interface layer, real-time sharing of surveying and mapping data is achieved. That is, a unified platform for storing and sharing surveying and mapping data is provided to achieve standardized storage, efficient management, and convenient sharing of massive heterogeneous surveying and mapping data. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 is a flowchart of a method for storing and sharing surveying and mapping data based on a cloud platform in an embodiment of the present invention;

[0044] Figure 2 is a flowchart of a method for determining the classification type of standard surveying and mapping data in an embodiment of the present invention;

[0045] Figure 3 is a flowchart of a method for constructing a data directory in an embodiment of the present invention;

[0046] Figure 4 is a flowchart of a method for constructing a multi-dimensional spatial index in an embodiment of the present invention;

[0047] Figure 5 is a schematic structural diagram of a device for storing and sharing surveying and mapping data based on a cloud platform in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0048] As described in the background art, with the increase in surveying and mapping geographic information, there are various problems in practical applications, which seriously restrict the application of surveying and mapping geographic information.

[0049] To solve the above technical problems, an embodiment of the present invention provides a method for storing and sharing surveying and mapping data based on a cloud platform, including: constructing a cloud storage architecture; based on a pre-established surveying and mapping data format standard and metadata specification, performing format conversion and standardization processing on heterogeneous surveying and mapping data stored in the cloud storage architecture to obtain standard surveying and mapping data; performing reconstruction processing on the standard surveying and mapping data to determine the classification type corresponding to the standard surveying and mapping data; establishing a data directory for the standard surveying and mapping data based on the classification type corresponding to the standard surveying and mapping data; constructing a multi-dimensional spatial index for the standard surveying and mapping data; and setting up a service interface layer on the cloud storage architecture, where the service interface layer is used to provide a unified data access interface to query the standard surveying and mapping data through the multi-dimensional spatial index or the data directory.

[0050] By adopting the above method, first, through constructing a cloud storage architecture, the distributed storage of surveying and mapping data is realized, enabling faster execution of query operations; then, through format conversion and standardization processing of heterogeneous surveying and mapping data, the unification of the format of standard surveying and mapping data is achieved; secondly, through reconstruction processing of the standard surveying and mapping data, the classification types of the standard surveying and mapping data are determined, reducing the difficulty of establishing data directories; finally, through multi-dimensional spatial indexing and setting a service interface layer for the standard surveying and mapping data, the real-time sharing of surveying and mapping data is realized. That is, a unified storage and sharing platform for surveying and mapping data is provided to achieve the standardized storage, efficient management, and convenient sharing of massive heterogeneous surveying and mapping data.

[0051] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be illustrated by examples in conjunction with the accompanying drawings.

[0052] Refer to Figure 1 the flowchart of a method for storing and sharing surveying and mapping data based on a cloud platform in an embodiment of the present invention as shown in Figure 1 shown, the following steps can be executed:

[0053] A. Construct a cloud storage architecture.

[0054] Specifically, the cloud storage architecture provides a centralized platform that can realize the storage and management of a large amount of surveying and mapping data, so that users can conveniently upload, download, and manage surveying and mapping data without considering the complexity of the underlying hardware.

[0055] Moreover, the cloud storage architecture provides a data redundancy and backup mechanism to ensure the security of surveying and mapping data in case of hardware failures or other disasters.

[0056] In addition, the cloud storage architecture also supports the sharing and collaboration of surveying and mapping data. Users can easily share files and data with team members or external partners, improving work efficiency and the timeliness of data sharing.

[0057] It should be noted that the surveying and mapping data in this solution can refer to image data, digital data, and other types of data. This solution does not limit the type of surveying and mapping data, as long as the surveying and mapping data can reflect geographical information.

[0058] In this embodiment, the steps of constructing the cloud storage architecture include:

[0059] Adopt the Hadoop distributed file system as the underlying storage architecture to realize the distributed storage of surveying and mapping data; construct a distributed database cluster to support the storage and management of structured and unstructured surveying and mapping data.

[0060] In some embodiments, HDFS allows surveying and mapping data to be scattered and stored on multiple nodes, forming a distributed file system, enabling the surveying and mapping data to be scattered and stored in multiple geographical locations to improve availability and fault tolerance.

[0061] A distributed database cluster is a database architecture that stores data on multiple nodes, aiming to improve data availability, scalability, and fault tolerance. Compared with traditional single-database systems, distributed database clusters can handle larger-scale data and higher concurrent requests, and are suitable for modern big data and high-concurrency application scenarios.

[0062] In some embodiments, the distributed database cluster may include one or more of Apache Cassandra (i.e., a highly scalable and highly available NoSQL database), MongoDB (i.e., a document-oriented NoSQL database), Google Spanner (i.e., a distributed relational database), and Amazon DynamoDB.

[0063] In some embodiments, a data redundancy backup mechanism can also be designed to ensure data security.

[0064] In short, adopting the above examples makes the cloud storage architecture have powerful data storage, data sharing, and data security performance, and provides flexibility, security, and scalability for data storage.

[0065] B. Based on a pre-established surveying and mapping data format standard and metadata specification, perform format conversion and standardization processing on the heterogeneous surveying and mapping data stored in the cloud storage architecture to obtain standard surveying and mapping data.

[0066] Specifically, for a large amount of surveying and mapping data obtained, the formats and / or data specifications between individual surveying and mapping data are not completely consistent. Even for the same surveying and mapping data, when using different surveying and mapping devices, their corresponding formats are not the same, so preprocessing is required.

[0067] More specifically, the surveying and mapping data format standard and metadata specification define the format requirements that the surveying and mapping data should meet. In this way, when storing the surveying and mapping data in the cloud storage architecture, format detection operations, conversion, and formatting processing can be performed to make all the surveying and mapping data have the same data format.

[0068] In this way, the unified format makes the storage, retrieval, and management of data simpler and more efficient.

[0069] In some embodiments, interpolation processing can also be performed to ensure data integrity and accuracy.

[0070] C. Reconstruct the standard surveying and mapping data to determine the classification type corresponding to the standard surveying and mapping data.

[0071] Specifically, for different standard surveying and mapping data, they may represent the geomorphic features of the same area, or multiple standard surveying and mapping data can be used to represent the same geomorphic feature, and thus the classification type corresponding to the standard surveying can be determined.

[0072] This classification of standard surveying and mapping data according to specific criteria (such as type, source, and use) realizes the clustering of standard surveying and mapping data. Thus, when performing indexing operations, a class of data can be obtained, enabling users to more intuitively understand the content and structure of the data and thus utilize the data more effectively.

[0073] As a specific embodiment, in the classification management of surveying and mapping data, first, perform basic classification according to data types, including vector data (elements such as points, lines, and surfaces), raster data (remote sensing images, DEMs, etc.), 3D model data, and attribute data.

[0074] Secondly, according to the application level of the surveying and mapping data, divide the surveying and mapping data into different levels such as basic geographic information data, thematic geographic information data, and metadata.

[0075] Thirdly, establish a data hierarchical access control mechanism. By setting the data access permission level, implement role-based access control and record the data access process in a log to ensure the security and traceability of data access.

[0076] In this embodiment, a bidirectional channel attention super-resolution network can be used to determine the classification type corresponding to the standard surveying and mapping data.

[0077] More specifically, refer to Figure 2 the flowchart of a method for determining the classification type of standard surveying and mapping data in an embodiment of the present invention as shown in Figure 2 shown, and the following steps can be executed:

[0078] C1. According to the super-resolution reconstruction framework based on the diffusion model and efficient bilinear attention fusion, enhance the image containing the standard surveying and mapping data to generate a high-resolution image.

[0079] Among them, the bidirectional channel attention network can enhance the recognition ability of image geomorphic features. This network adopts a bidirectional feature extraction channel, where the forward channel is responsible for capturing prominent surface features such as stone buds, stone forests, and karst caves, etc., large-scale structures, and the reverse channel focuses on extracting detailed features such as underground rivers and dissolution fissures. Through this bidirectional feature extraction mechanism, the system can comprehensively grasp the complex geographical features of karst landforms, laying a foundation for subsequent refined classification management.

[0080] In this embodiment, during the process of constructing an image containing standard surveying and mapping data by the diffusion model, a hierarchical noise prediction strategy is adopted to generate high-resolution geomorphic details by gradually denoising.

[0081] Specifically, Gaussian noise is added to an image with a resolution lower than a preset resolution, and through a multi-step iterative reverse diffusion process, the image details are gradually restored and enhanced to generate multiple high-resolution images.

[0082] In this process, by gradually restoring and enhancing the image details, the key features of the corresponding landform in the image can be obtained. For example, details such as the edge of a karst cave and the texture of a stalagmite are ensured to be accurately retained during the reconstruction process.

[0083] In this embodiment, the steps of the super-resolution reconstruction framework based on the diffusion model and efficient bilinear attention fusion may include:

[0084] Adopt a diffusion model (such as DDPM or DDIM) as the generation backbone, and utilize the gradually denoising ability of the diffusion model to generate high-quality details. Usually, the U-Net structure is used, which includes an encoder-decoder architecture and skip connections.

[0085] Among them, the parameters of the U-Net structure may include:

[0086] Input / output number of channels: For an RGB image, it is 3 channels. For the super-resolution task, the input may be 3 channels or the Y channel (YCbCr color space) of a low-resolution image.

[0087] Base number of channels: Usually 64 to 128 (for example, 64). As the network depth doubles, for example, the number of channels in each layer of the encoder is [64, 128, 256, 512].

[0088] Residual block structure: Each layer contains 2 to 4 residual blocks, and each residual block contains: 2 3×3 convolutions, with an efficient bilinear attention module embedded in the middle, and the skip connection uses a 1×1 convolution to adjust the number of channels.

[0089] Time step embedding: Encode the time step into a 128-dimensional vector through an MLP.

[0090] In some embodiments, an attention mechanism can also be adopted. For example, in each residual block of the U-Net, replace the traditional convolutional layer with an efficient bilinear attention module to enhance local feature interaction while capturing global dependencies; also, for example, add bilinear attention at the skip connection between the encoder and the decoder to dynamically fuse multi-scale features and improve the reconstruction effect of edges and textures; furthermore, for example, adjust the attention weights according to the noise levels at different diffusion time steps, focusing on the structure in the early stage and the details in the later stage.

[0091] Next, the computational complexity of the bilinear operation is reduced through low-rank decomposition or channel grouping. For example, using decomposed matrix multiplication to replace the fully connected interaction, a mechanism that combines spatial attention (locating important regions) and channel attention (emphasizing key feature channels) is implemented. Then, the outputs of both are fused through bilinear interpolation.

[0092] Among them, the efficient bilinear attention may include:

[0093] 1) Bilinear pooling design

[0094] Input feature map: Assume the input feature size is [B, C, H, W]

[0095] Bilinear interaction: Decomposition strategy: Decompose the bilinear matrix into two low-rank matrices. For example:

[0096] Q = WqX ∈ RC×r, K = WkX ∈ RC×rQ = WqX ∈ RC×r, K = WkX ∈ RC×r, where r is the rank (usually taken as C / 4 to C / 8), reducing the computational complexity.

[0097] Group Bilinear: Divide the channels into 4 to 8 groups, and calculate the bilinear interaction independently for each group, reducing the number of parameters

[0098] Output fusion: The bilinear output adjusts the channels through a 1×1 convolution and adds it to the original features.

[0099] 2) Spatial-channel collaborative attention

[0100] Spatial attention branch: Use dilated convolution (Dilation = 2) to expand the receptive field and generate a spatial weight map [B, 1, H, W].

[0101] Channel attention branch: Global average pooling + fully connected layer to generate channel weights [B, C, 1, 1].

[0102] Dynamic gating fusion mechanism.

[0103] In some embodiments, learnable gating weights can also be introduced to adaptively adjust the intensity of the attention response and prevent high-frequency noise interference.

[0104] Then, a super-resolution reconstruction framework is obtained by adopting a phased training method.

[0105] Specifically, when pre-training the basic diffusion model, only use U-Net for super-resolution denoising training to ensure the initial convergence of the model. Then, fix the U-Net parameters and train the attention module alone to make it adapt to the multi-time step features of the diffusion process. Finally, unfreeze all parameters and jointly optimize the diffusion and attention modules to achieve end-to-end joint fine-tuning.

[0106] Among them, the optimizer and learning rate during the pre-training process can be configured. Among them, the optimizer can be Adam W, and the initial learning rate is 2e-4 to 5e-5. Along with different training stages, the learning rate is adaptively adjusted.

[0107] For example, in the warm-up stage: linearly increase the learning rate to the initial value in the first 500 - 1000 steps; decay strategy: Cosine annealing or linearly decay to 1e-6.

[0108] In some embodiments, the batch size, mixed progress training, etc. can also be configured.

[0109] It should be noted that during the training process, the receptive field of the attention module can also be adjusted according to the noise level of the time step. For example, local attention is used in the low-noise stage (close to the clear image), and global attention is used in the high-noise stage.

[0110] In addition, during the training process, pixel-level evaluation metrics such as PSNR and SSIM, as well as visual authenticity evaluation metrics of images such as LPIPS and FID, can be used to evaluate the performance of the super-resolution reconstruction framework.

[0111] In some embodiments, Dropout or random noise injection can also be introduced into the attention module to enhance the generalization ability, or gradient clipping or adaptive learning rate scheduling can be adopted.

[0112] C2, based on the bilinear attention mechanism, establish the feature maps corresponding to each high-resolution image, and determine the bilinear similarity matrix between the feature maps by capturing the similarity between the feature maps at different scales and different types of features.

[0113] Specifically, through the bilinear attention mechanism, the ability to represent the features of each high-resolution image, fine-grained feature extraction, adaptive feature selection, and context understanding ability can be enhanced, so that the complex interactions between the feature maps at different scales and different types of features can be better captured.

[0114] In the implementation process, based on the complex interactions between the feature maps at different scales and different types of features, calculate the bilinear similarity matrix between the feature maps, and then dynamically adjust the feature fusion weights based on this matrix. This method is particularly helpful for dealing with complex terrain structures in the geomorphology. For example, when dealing with the features at the intersection of a karst cave and an underground river, the system can intelligently fuse the information of the two geomorphological features to generate a more accurate reconstruction result.

[0115] C3. Determine the terrain complexity of the local area corresponding to the feature map according to the feature map, and adjust the parameters and attention weights of the diffusion model based on the terrain complexity to obtain the reconstruction result of the high-resolution image.

[0116] Specifically, by performing adaptive feature enhancement processing on the feature map (that is, adaptively selecting and enhancing important features according to the characteristics and context information of the feature map, thereby improving the expression ability and decision-making ability of the diffusion model), the terrain complexity of the local area corresponding to the feature map can be analyzed and determined. In this way, the parameters and attention weights (that is, the weights of different feature channels) of the diffusion model can be automatically adjusted, so that the diffusion steps and attention intensity can be adaptively changed to obtain a more refined reconstruction effect.

[0117] For example, for areas with relatively flat terrain, fewer diffusion steps are adopted to improve processing efficiency. Also, for areas with drastic terrain changes, the diffusion steps and attention intensity are increased to obtain a more refined reconstruction effect. Again, for areas with a deeper degree of corrosion, the weights of relevant feature channels are automatically enhanced to ensure that these important information can be accurately captured.

[0118] In some embodiments, a feature quality evaluation mechanism can also be established. By comparing the differences between the reconstruction result and the high-resolution reference data, the parameters of the diffusion model are continuously optimized, such as the number of time steps in the diffusion process, noise scheduling, etc.

[0119] C4. Use a multi-scale feature pyramid to determine the feature representations of different scales of the reconstruction result of the high-resolution image, and use the bilinear similarity matrix and bilinear attention mechanism between the feature maps to perform a fusion operation to determine the classification type of the standard surveying and mapping data.

[0120] Specifically, based on the reconstructed high-resolution features, fine-grained classification is performed using a multi-scale feature pyramid.

[0121] More specifically, use a multi-scale feature pyramid to construct feature representations of different scales, and then adaptively fuse these features through a bilinear attention mechanism to finally generate a high-precision classification result.

[0122] In some embodiments, when determining the classification result of the standard surveying and mapping data, the classification result can also be optimized and corrected based on empirical rules.

[0123] For example, by introducing a post-processing module based on expert knowledge in the cloud platform, the classification result is optimized and corrected by combining the empirical rules of geological experts.

[0124] In short, the above solution constructs an adaptive classification optimization mechanism that can accurately determine the classification type of standard mapping data.

[0125] For example, based on the refined classification framework of super-resolution reconstruction, the above solution performs super-resolution reconstruction on low-resolution remote sensing image data, significantly improving the clarity of image details. Then, using the high-resolution features after reconstruction, it classifies the landforms of standard mapping data at multiple levels to determine the landforms of standard mapping data.

[0126] In some embodiments, the multi-level classification may include: 1) Surface morphology classification: stone forests, stone buds, stalagmites, etc.; 2) Underground structure classification: karst caves, underground rivers, subterranean rivers, etc.; 3) Ecological environment classification: vegetation cover, hydrological features, etc.; 4) Geological disaster risk classification: karst collapse, landslide-prone areas, etc.

[0127] And based on the classification type, it is also beneficial to subsequently establish a multi-dimensional data indexing system to support data retrieval and management in multiple dimensions such as classification type, geological features, and risk level. At the same time, the system also provides a visualization display function, which can intuitively display the three-dimensional structure and spatial distribution characteristics of different landforms, providing decision-making support for geological research and engineering planning.

[0128] In some embodiments, the accuracy of the classification results can also be continuously monitored to automatically adjust the network parameters and attention weights, continuously improving the classification accuracy. At the same time, the system also establishes a verification feedback mechanism for the classification results, and through the auxiliary verification of the expert knowledge base, ensures the reliability of the classification results.

[0129] In some embodiments, a data hierarchical access control mechanism can also be established, and according to the classification type, determine the access permission levels of each standard mapping data, and record the data access process.

[0130] Specifically, for users with different permission levels, the access permission levels they have are different. For example, the permission level is only to view basic standard mapping data; while for users with the highest permission level, they can view or modify all standard mapping data.

[0131] In this way, after determining the user's permission level, standard mapping data adapted to the user's role and permission level can be provided according to the user's role.

[0132] In summary, first, this solution creatively applies the bidirectional channel attention network to landform feature extraction, improving the recognition ability of complex landforms; second, a lightweight feature enhancement module is designed to ensure the accuracy of feature extraction while maintaining high processing efficiency; third, a refined classification framework based on super-resolution reconstruction is implemented, significantly improving the classification accuracy; fourth, an adaptive classification optimization mechanism is established to ensure the continuous improvement of the system's classification performance; fifth, it provides a powerful tool for the research and management of special terrains, making this refined management solution based on deep learning not only improve the management efficiency of landform data but also provide a technical example for the data management of other special terrains.

[0133] That is, by combining advanced image processing techniques with geological expertise, the system realizes the intelligent management of complex landforms and provides important support for geological research and engineering practice.

[0134] D. Establish a data directory for the standard mapping data based on the classification type corresponding to the standard mapping data.

[0135] Specifically, the classification type reflects the type of the area represented by the standard mapping data. In this way, for standard mapping data with the same classification type, a summary operation can be performed to form a data directory for characterizing the same clustering result.

[0136] In this embodiment, the efficient convolutional sparse coding and double decoder segmentation technology of the local competition algorithm can be applied to the construction process of the data directory.

[0137] More specifically, refer to Figure 3 the flowchart of constructing a data directory in an embodiment of the present invention shown in Figure 3 As shown, the following steps can be performed:

[0138] D1. Based on the classification type, use the efficient convolutional sparse coding with the local competition algorithm to construct the feature representation of the data directory.

[0139] Specifically, this coding mechanism introduces a competition mechanism in the local area, enabling the mapping data of different classification types to generate more unique and distinguishable feature representations.

[0140] Specifically, first, the mapping data is converted into a high-dimensional feature space, and then the local feature patterns of the high-dimensional feature space are extracted through convolutional operations.

[0141] Among them, during the feature extraction process, the local competition algorithm ensures that only the most significant features are retained. This mechanism not only reduces the redundancy of features but also improves the efficiency of data retrieval. For example, when processing remote sensing image data, it can automatically identify and retain the most representative ground object features, providing a more accurate indexing basis for subsequent data retrieval.

[0142] D2, realizes the segmented management of surveying and mapping data through a dual-decoder architecture, including: decoding the spatial attributes of surveying and mapping data through the first decoder, and processing the temporal attributes of surveying and mapping data through the second decoder.

[0143] Specifically, in this step, a dual-decoder architecture is introduced to realize the segmented management of surveying and mapping data.

[0144] More specifically, this architecture contains two independent but collaborative decoders. Among them, the first decoder is responsible for decoding the spatial attributes of surveying and mapping data, and the second decoder focuses on processing the temporal attributes of surveying and mapping data.

[0145] In other words, through this dual-decoder structure, it is possible to better understand and organize surveying and mapping data with spatio-temporal characteristics. And in practical applications, the dual-decoder can not only accurately restore the original features of surveying and mapping data but also generate intermediate representations suitable for retrieval, greatly improving the organization efficiency of the data catalog.

[0146] D3, through an intelligent classification framework based on sparse coding, uses the local competition algorithm to determine the hierarchical relationship between different features based on the spatial and temporal attributes of the surveying and mapping data, and constructs a hierarchical data catalog structure using the hierarchical relationship between different features.

[0147] Specifically, the intelligent classification framework based on sparse coding uses the feature representation generated by convolutional sparse coding and combines the output of the dual-decoder to achieve multi-dimensional classification of surveying and mapping data.

[0148] Specifically, through the local competition algorithm, the most representative features are selected, and then these features are used to construct a hierarchical data catalog structure.

[0149] At the same time, the system also establishes a feature update mechanism that can dynamically adjust the weights of features according to the data access pattern to ensure that the data catalog structure always reflects the actual usage of the data.

[0150] In some embodiments, when constructing the hierarchical data catalog structure, the classification results are optimized and corrected.

[0151] In summary, first, this solution innovatively introduces the local competition algorithm into the convolutional sparse coding process, improving the distinctiveness of feature representation; second, a dual decoder architecture is designed to achieve refined management of spatio-temporal data; third, an intelligent classification framework based on sparse coding is established to enhance the efficiency of data organization; fourth, it is conducive to implementing a hierarchical retrieval optimization mechanism, significantly improving the retrieval performance; fifth, an adaptive data directory maintenance framework is developed to ensure the continuous and efficient operation of the system.

[0152] In other words, this solution that combines the efficient convolutional sparse coding with local competition algorithm and the dual decoder not only improves the performance and reliability of the mapping data directory service, but also provides a new technical idea for the management of large-scale spatial data. By combining advanced deep learning technologies with traditional data management methods, the system realizes the intelligent management and efficient retrieval of mapping data, providing users with more convenient and accurate data services.

[0153] E. Construct a multi-dimensional spatial index for the standard mapping data.

[0154] Specifically, by establishing a multi-dimensional spatial index, retrieval of the standard mapping data can be achieved from multiple different dimensions, making this hierarchical retrieval strategy significantly improve the retrieval efficiency, especially showing obvious advantages when dealing with a large amount of mapping data.

[0155] In this embodiment, the linear deformable cross-attention mechanism of the Kalman filter can be fused with the traditional spatial index structure to construct a multi-dimensional spatial index.

[0156] More specifically, refer to Figure 4 the flowchart of constructing a multi-dimensional spatial index in an embodiment of the present invention shown in Figure 4 As shown, the following steps can be executed:

[0157] E1. Based on the linear variability cross-attention mechanism of the Kalman filter, model the dynamic features of the spatial objects corresponding to the standard mapping data, and determine the target areas of each standard mapping data.

[0158] Specifically, the linear deformable cross-attention mechanism based on the Kalman filter is introduced to enhance the intelligent construction of the spatial index.

[0159] Specifically, this mechanism models the dynamic features of the spatial data to predict and update the state information of the spatial objects corresponding to the data directory in real time.

[0160] For example, the Kalman filter continuously optimizes the position estimation of spatial objects through prediction steps and update steps, reducing the uncertainty in spatial queries. On this basis, the linear deformable property allows the index structure to be dynamically adjusted according to the data distribution characteristics, enabling the index structure to better adapt to the local characteristics of spatial data.

[0161] E2, based on the node splitting and merging operations of the R-tree index, identifies the associations between different spatial objects, and organizes the storage spaces with an association greater than the set threshold in the same R-tree node.

[0162] Specifically, apply the cross-attention mechanism to the R-tree index construction process.

[0163] By calculating the attention weights between spatial objects, it is possible to identify a set of objects with closer spatial relationships. In this way, the node splitting and merging operations of the R-tree no longer rely solely on geometric distance, but also consider the semantic associations between objects.

[0164] For example, when processing urban building data, buildings with similar functional attributes will be preferentially organized in the same R-tree node, thereby improving the subsequent spatial query efficiency.

[0165] E3, according to the distribution characteristics of spatial objects on the R-tree nodes, dynamically adjusts the node capacity and splitting threshold of the B+-tree to generate a hybrid index structure.

[0166] Specifically, optimize the attribute index structure of the B+-tree through the linear deformable mechanism.

[0167] This mechanism can dynamically adjust the node capacity and splitting threshold of the B+-tree according to the distribution characteristics of attribute values, enabling the index structure to better adapt to the statistical characteristics of the data. At the same time, the introduction of the cross-attention mechanism enables the system to capture the potential associations between attribute values, providing better support for multi-condition combination queries.

[0168] E4, establish a mapping relationship between the hybrid index structure and the target areas of each standard surveying and mapping data to serve as a multi-dimensional spatial index.

[0169] Specifically, a fusion mechanism is designed to combine the results predicted by the Kalman filter with the spatial index structure. When performing a spatial query, the system first determines the possible target areas based on the prediction results of the Kalman filter, and then uses the hybrid index structure of the R-tree and B+-tree to perform an accurate search within this area. This approach significantly reduces the retrieval space and improves the query efficiency.

[0170] In summary, first, applying the linear deformable cross-attention mechanism of Kalman filtering to spatial index construction improves the intelligence level of the index structure; second, innovatively combining the attention mechanism with traditional spatial indexes realizes semantic-based spatial data organization; third, designing an adaptive index optimization mechanism ensures that the system can continuously maintain high retrieval performance; fourth, realizing prediction-driven spatial query optimization significantly reduces the computational overhead of retrieval; fifth, establishing a dynamic index maintenance mechanism enables the system to better adapt to changes in data distribution.

[0171] In short, this fusion solution significantly improves the retrieval efficiency and adaptability of the system by combining modern intelligent algorithms with traditional spatial index technologies, providing an innovative solution for the efficient management of massive spatial data. At the same time, the adaptive characteristics of this solution also ensure that the system can maintain stable performance in the face of continuous changes in data scale and distribution.

[0172] In some embodiments, it is also possible to establish a mapping relationship between the multi-dimensional spatial index and the data directory to access the data directory through the multi-dimensional spatial index.

[0173] Moreover, by constructing an efficient spatial index and realizing multi-dimensional data management and retrieval functions to provide users with convenient surveying and mapping data access services is one of the core functional modules of the entire system.

[0174] In some embodiments, constructing the multi-dimensional spatial index for the standard surveying and mapping data includes: dividing the spatial objects corresponding to the standard surveying and mapping data according to the minimum bounding rectangle to establish a hierarchical tree index structure; using a B+ tree index structure to establish a B+ tree index for the spatial objects corresponding to the standard surveying and mapping data; and fusing the tree index structure and the B+ tree index to generate the multi-dimensional spatial index.

[0175] F. Set a service interface layer on the cloud storage architecture, and the service interface layer is used to provide a unified data access interface to query the standard surveying and mapping data through the multi-dimensional spatial index or the data directory.

[0176] Specifically, by setting the service interface layer, real-time sharing of standard surveying and mapping data can be achieved.

[0177] More specifically, by constructing a data service interface layer, providing a unified data access interface, and realizing a data sharing service based on WebService, it can support online conversion of multiple data formats.

[0178] In short, the innovation of the present invention is mainly reflected in the following aspects: First, the adoption of a hybrid index structure of R-tree and B+-tree significantly improves the retrieval efficiency of spatial data. Second, the data catalog service implemented based on a distributed architecture provides reliable support for the efficient management of massive data. Third, a multi-level data classification system is designed to achieve refined management of surveying and mapping data. In addition, by introducing a caching mechanism and query optimization strategies, the response performance of the system is greatly improved. Finally, the design of rich data display methods greatly enhances the user experience of the system.

[0179] Or rather, for the construction of the data catalog service, first, a distributed database is used to store metadata information, and a data catalog synchronization and update mechanism is established to ensure the timeliness and consistency of the data catalog. Second, a multi-dimensional retrieval function is implemented to support users to flexibly retrieve according to multiple dimensions such as spatial range, time range, data type, and keywords. In addition, the system provides rich data preview functions, including thumbnail preview, attribute information preview, and online map preview, etc., to facilitate users to quickly understand the data content.

[0180] In some embodiments, the method for storing and sharing surveying and mapping data based on a cloud platform further satisfies one or more of the following:

[0181] Optimize the query process of the standard surveying and mapping data, including at least one of the following: adopt a consistent hashing algorithm to balance the load of different query requests and dynamically adjust the load of service nodes; based on the Redis caching mechanism, cache the hot data in the surveying and mapping data; configure parallel query processing, query plan optimization, and batch data query functions. This can improve the query performance.

[0182] Visualize the query results, including: providing display methods in the form of lists, map visualization, and statistical charts, and supporting multi-condition combination filtering, sorting functions, and data export functions.

[0183] Establish a monitoring mechanism, including: real-time monitoring of storage capacity and access traffic metrics.

[0184] In summary, the present invention constructs a unified platform for storing and sharing surveying and mapping data, realizing the standardized storage, efficient management, and convenient sharing of massive heterogeneous surveying and mapping data.

[0185] The embodiments of the present invention also provide a device corresponding to the method for storing and sharing surveying and mapping data based on a cloud platform, as Figure 5 shown in the structural schematic diagram of a device for storing and sharing surveying and mapping data based on a cloud platform in an embodiment of the present invention, as Figure 5 shown, the device 100 for storing and sharing surveying and mapping data based on a cloud platform may include:

[0186] Building module 110 for building a cloud storage architecture;

[0187] Data processing module 120, which performs format conversion and standardization processing on heterogeneous surveying and mapping data stored in the cloud storage architecture based on a pre-established surveying and mapping data format standard and metadata specification to obtain standard surveying and mapping data;

[0188] Data management module 130 for performing reconstruction processing on the standard surveying and mapping data, determining the classification type corresponding to the standard surveying and mapping data, and establishing a data directory for the standard surveying and mapping data based on the classification type corresponding to the standard surveying and mapping data, and constructing a multi-dimensional space index for the standard surveying and mapping data;

[0189] Access module 140 for querying the standard surveying and mapping data through a multi-dimensional space index or data directory by setting a service interface layer on the cloud storage architecture, where the service interface layer is used to provide a unified data access interface.

[0190] Among them, the specific working processes and principles of the building module 110, data processing module 120, data management module 130, and access module 140 can refer to the relevant descriptions in the foregoing examples.

[0191] It can be understood that the above division of each module is only a division of logical functions. In actual implementation, it can be fully or partially integrated into a physical entity, or physically separated. In addition, the above units can be implemented in the form of a processor calling software.

[0192] The present invention also provides a computer system suitable for implementing a method for storing and sharing surveying and mapping data based on a cloud platform. Among them, the computer system includes a central processing unit (CPU), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) or a program loaded from a storage part into a random access memory (RAM), such as executing the method described in the above embodiments. In the RAM, various programs and data required for system operation are also stored. The CPU, ROM, and RAM are connected to each other through a bus. An input / output (I / O) interface is also connected to the bus.

[0193] The following components are connected to the I / O interface: an input part including a keyboard, a mouse, etc.; an output part including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage part including a hard disk, etc.; and a communication part including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication part performs communication processing via a network such as the Internet. The drive 310 is also connected to the I / O interface as required. Removable media such as magnetic disks, optical disks, magneto-optical disks, semiconductor memories, etc. are installed on the drive as required so that a computer program read from thereon is installed into the storage part as required.

[0194] Specifically, according to an embodiment of the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), various functions defined in the system of the present application are executed.

[0195] It should be noted that the computer-readable medium shown in the embodiments of the present application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the above two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (ERPOM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0196] In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable computer program. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wired, etc., or any suitable combination of the above.

[0197] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Among them, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code, and the above-mentioned module, program segment, or part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order from that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram or flowchart, and the combination of blocks in the block diagram or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0198] The units involved in the embodiments of the present invention can be implemented in software or in hardware, and the described units can also be provided in a processor. Among them, the names of these units do not constitute a limitation to the unit itself in some cases.

[0199] According to one aspect of the present application, a computer program product or a computer program is provided, and the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above various alternative implementation manners.

[0200] As another aspect, the present application also provides a computer-readable medium, which may be included in the electronic device described in the above embodiments; or may exist alone without being assembled into the electronic device. The above computer-readable medium carries one or more programs, and when the above one or more programs are executed by an electronic device, the electronic device implements the method described in the above embodiments.

[0201] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present application, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0202] Through the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (such as a personal computer, a server, a touch terminal, or a network device, etc.) to execute the method according to the embodiments of the present application.

[0203] Although the present specification discloses the above, the present invention is not limited thereto. Any person skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the protection scope of the present invention should be subject to the scope defined by the claims.

Claims

1. A method for storing and sharing surveying and mapping data based on a cloud platform, characterized in that: include: Build cloud storage architecture; Based on pre-established surveying and mapping data format standards and metadata specifications, format conversion and standardization processing are performed on heterogeneous surveying and mapping data stored in the cloud storage architecture to obtain standard surveying and mapping data; Reconstructing the standard surveying and mapping data to determine the classification type corresponding to the standard surveying and mapping data; Based on the classification type corresponding to the standard surveying and mapping data, establishing a data directory for the standard surveying and mapping data; Constructing a multidimensional spatial index for the standard surveying and mapping data; A service interface layer is provided on the cloud storage architecture, wherein the service interface layer is used to provide a unified data access interface so as to query the standard surveying and mapping data through the multidimensional spatial index or data directory; The step of establishing a data directory for the standard surveying and mapping data based on the classification type corresponding to the standard surveying and mapping data includes: Based on the classification type, efficient convolutional sparse coding with a local competition algorithm is used to construct a feature representation of the data directory, including: converting the surveying and mapping data into a high-dimensional feature space; extracting a local feature pattern of the high-dimensional feature space as a feature representation of the data directory through a convolution operation; Segment management of surveying and mapping data is achieved through a dual decoder architecture, including: decoding the spatial attributes of the surveying and mapping data through a first decoder, and processing the temporal attributes of the surveying and mapping data through a second decoder; Through an intelligent classification framework based on sparse coding and utilizing a local competition algorithm, the hierarchical relationship between different features is determined based on the spatial attributes and temporal attributes of the surveying and mapping data, and a hierarchical data directory structure is constructed using the hierarchical relationship between different features.

2. The method for storing and sharing surveying and mapping data according to claim 1, characterized in that: The cloud storage architecture construction includes: The Hadoop distributed file system is used as the underlying storage architecture to achieve distributed storage of surveying and mapping data; Build a distributed database cluster to support the storage and management of structured and unstructured surveying and mapping data.

3. The method for storing and sharing surveying and mapping data according to claim 1, characterized in that: The reconstructing the standard surveying and mapping data to determine the classification type corresponding to the standard surveying and mapping data includes: According to a super-resolution reconstruction framework based on a diffusion model and efficient bilinear attention fusion, an image containing the standard mapping data is enhanced to generate a high-resolution image, including: adding Gaussian noise to an image below a preset resolution, and gradually restoring and enhancing image details through a multi-step iterative back diffusion process to generate multiple high-resolution images; Based on the bilinear attention mechanism, the feature maps corresponding to each high-resolution image are established, and the bilinear similarity matrix between the feature maps is determined by capturing the similarity between the features of different scales and different types. Determining the terrain complexity of the local area corresponding to the feature map according to the feature map, and adjusting the parameters and attention weights of the diffusion model based on the terrain complexity to obtain a reconstruction result of a high-resolution image; A multi-scale feature pyramid is used to determine feature representations of different scales of the reconstruction result of the high-resolution image, and a bilinear similarity matrix and a bilinear attention mechanism between feature maps are used to perform a fusion operation to determine the classification type of the standard surveying and mapping data.

4. The method for storing and sharing surveying and mapping data according to claim 3, characterized in that: Meet one or more of the following: Optimize and correct the classification results based on empirical rules; Establish a data hierarchical access control mechanism, and determine the access permission level for each standard surveying and mapping data based on the classification type, and log the data access process.

5. The method for storing and sharing surveying and mapping data according to claim 1, characterized in that: The constructing of a multidimensional spatial index for the standard surveying and mapping data comprises: Dividing the spatial objects corresponding to the standard surveying and mapping data according to the minimum circumscribed rectangle to establish a hierarchical tree index structure; Using a B+ tree index structure, a B+ tree index is established for the spatial object corresponding to the standard surveying and mapping data; The tree index structure and the B+ tree index are integrated to generate the multidimensional space index.

6. The method for storing and sharing surveying and mapping data according to claim 1, characterized in that: The constructing of a multidimensional spatial index for the standard surveying and mapping data comprises: Based on the cross-attention mechanism of the linear variability of the Kalman filter, the dynamic characteristics of the spatial objects corresponding to the standard surveying and mapping data are modeled to determine the target area of ​​each standard surveying and mapping data; Based on the node splitting and merging operations of the R-tree index, the association between different spatial objects is identified, and the storage spaces with association greater than the set threshold are organized in the same R-tree node; According to the distribution characteristics of spatial objects on R-tree nodes, the node capacity and split threshold of B+ tree are dynamically adjusted to generate a hybrid index structure. A mapping relationship between the hybrid index structure and the target area of ​​each standard surveying and mapping data is established to serve as a multi-dimensional spatial index.

7. The method for storing and sharing surveying and mapping data according to claim 1, characterized in that: Meet one or more of the following: Optimizing the query process of the standard surveying and mapping data, including at least one of the following: using a consistent hashing algorithm to balance the load of different query requests and dynamically adjusting the load of service nodes; caching hot data in the surveying and mapping data based on a Redis cache mechanism; Configure parallel query processing, query plan optimization, and batch data query capabilities; Visual query results, including: providing display methods including list form, map visualization and statistical charts, and supporting multi-condition combination filtering and sorting functions and data export functions; Establish a monitoring mechanism, including real-time monitoring of storage capacity and access traffic indicators.

8. A cloud platform-based surveying and mapping data storage and sharing device, characterized in that: include: Building blocks for constructing cloud storage architecture; A data processing module, which performs format conversion and standardization processing on the heterogeneous surveying and mapping data stored in the cloud storage architecture based on pre-established surveying and mapping data format standards and metadata specifications to obtain standard surveying and mapping data; A data management module, used to reconstruct the standard surveying and mapping data, determine the classification type corresponding to the standard surveying and mapping data, and establish a data directory for the standard surveying and mapping data based on the classification type corresponding to the standard surveying and mapping data, and construct a multidimensional spatial index for the standard surveying and mapping data; An access module, configured to query the standard surveying and mapping data through the multidimensional spatial index or data directory by setting a service interface layer on the cloud storage architecture, wherein the service interface layer is configured to provide a unified data access interface; The step of establishing a data directory for the standard surveying and mapping data based on the classification type corresponding to the standard surveying and mapping data includes: Based on the classification type, efficient convolutional sparse coding with a local competition algorithm is used to construct a feature representation of the data directory, including: converting the surveying and mapping data into a high-dimensional feature space; extracting a local feature pattern of the high-dimensional feature space as a feature representation of the data directory through a convolution operation; Segment management of surveying and mapping data is achieved through a dual decoder architecture, including: decoding the spatial attributes of the surveying and mapping data through a first decoder, and processing the temporal attributes of the surveying and mapping data through a second decoder; Through an intelligent classification framework based on sparse coding and utilizing a local competition algorithm, the hierarchical relationship between different features is determined based on the spatial attributes and temporal attributes of the surveying and mapping data, and a hierarchical data directory structure is constructed using the hierarchical relationship between different features.

9. An electronic device, characterized in that: include: A processor and a memory, wherein the memory stores one or more computer executable instructions, and the processor calls the one or more computer executable instructions to execute the steps of the surveying and mapping data storage and sharing method as described in any one of claims 1 to 7.

Images