Land space planning multi-source data fusion processing method and system

Abstract

The invention relates to the technical field of space planning, and discloses a territorial space planning multi-source data fusion processing method and system, and the method comprises the steps: carrying out the format analysis and semantic annotation of multi-source territorial space data, and obtaining the standard territorial space data of territorial planning; performing hierarchical feature extraction on the standard territorial spatial data to obtain spatial features and attribute features of territorial planning; performing adaptive feature fusion on the spatial features and the attribute features to obtain a multi-semantic fusion feature map of territorial planning; constructing a spatial constraint rule base of territorial planning based on a use control rule and an ecological protection red line of territorial planning; based on a spatial constraint rule base, resolving conflict pattern spots in the multi-semantic fusion feature map, and performing semantic enhancement on the resolved multi-semantic fusion feature map to obtain an optimized fusion result; performing visual rendering on an optimization fusion result to obtain an auxiliary decision graph; according to the invention, the efficiency of data fusion processing in territorial space can be improved.

Description

Technical Field

[0001] This invention relates to the field of spatial planning technology, and in particular to a method and system for multi-source data fusion processing in land spatial planning. Background Technology

[0002] Territorial spatial planning requires the integration of heterogeneous data from multiple sources, including geographic raster data, vector layer data, and text table data. Current technologies lack efficient and standardized format parsing capabilities when processing this data, and have not established a deep association mechanism with the territorial spatial planning terminology database, making it impossible to accurately assign standardized planning semantic labels to each data object. This results in frequent conflicts or missing invalid information in the processed data, making it difficult to form standardized territorial spatial data. This not only increases the difficulty of subsequent feature extraction and fusion operations but also significantly reduces the efficiency of the overall data processing workflow, failing to meet the timeliness requirements of territorial spatial planning for data processing.

[0003] In the feature fusion and conflict resolution stages of multi-source data, the shortcomings of existing technologies become even more apparent. On the one hand, when fusing extracted spatial and attribute features, they often adopt fixed fusion patterns, failing to dynamically adjust the fusion weights of the two types of features according to the actual application needs and core functional priorities of land planning. This results in the fused feature map failing to accurately reflect the core requirements of planning and failing to provide effective support for subsequent planning analysis. On the other hand, existing technologies lack a systematic spatial constraint rule library based on land use control rules and ecological protection red lines. This makes it difficult to efficiently and reasonably resolve conflict patches appearing in multi-semantic fusion feature maps, and the resolved data often suffers from insufficient semantic integrity. Ultimately, this leads to low-quality auxiliary decision-making maps that cannot provide reliable data basis for land spatial planning decisions. Summary of the Invention

[0004] This invention provides a method and system for multi-source data fusion processing in land spatial planning to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a method for multi-source data fusion processing in land spatial planning, comprising: S1. Perform format parsing and semantic annotation on multi-source territorial spatial data to obtain standard territorial spatial data for territorial planning; S2. Perform hierarchical feature extraction on the standard land spatial data to obtain the spatial features and attribute features of the land planning; S3. Perform adaptive feature fusion on the spatial features and the attribute features to obtain the multi-semantic fusion feature map of the land use plan; S4. Based on the land use control rules and ecological protection red lines of the land use plan, construct a spatial constraint rule library for the land use plan; S5. Based on the spatial constraint rule base, conflict patches in the multi-semantic fusion feature map are resolved, and semantic enhancement is performed on the resolved multi-semantic fusion feature map to obtain the optimized fusion result of the land planning. S6. Visualize and render the optimized fusion results to obtain the auxiliary decision-making map of the land planning.

[0006] In a preferred embodiment, the step of performing format parsing and semantic annotation on multi-source territorial spatial data to obtain standard territorial spatial data for land planning includes: Geographic raster data, vector layer data, and text table data are combined into a multi-source data set for land planning; The format of the multi-source data set is converted to obtain the parsed data of the multi-source data set; Based on the pre-acquired territorial spatial planning terminology database, each data object in the parsed data is assigned a planning semantic label, and the semantic annotation result of the parsed data is obtained; By removing invalid data with conflicts and missing information from the semantic annotation results, standard land space data for land planning is obtained.

[0007] In a preferred embodiment, the step of performing hierarchical feature extraction on the standard land spatial data to obtain the spatial features and attribute features of the land planning includes: Spatial structure analysis is performed on the geographic elements in the standard land spatial data to obtain the spatial structure characteristics of the standard land spatial data. Extract the category classification, statistical characteristics, and planning constraints of the attribute information from the standard territorial spatial data to obtain the attribute semantic features of the standard territorial spatial data; Based on the aforementioned spatial structural features, spatial features describing the spatial pattern of the land use in the national land planning are constructed. Based on the aforementioned semantic features, attribute features describing the planning attributes in the national land planning are constructed.

[0008] In a preferred embodiment, the adaptive feature fusion of the spatial features and the attribute features to obtain the multi-semantic fusion feature map of the land use plan includes: Semantic encoding is performed on the geometric shape, spatial distribution, and topological relationship features in the spatial features to obtain the spatial feature vector of the land use plan. The category attribution, statistical characteristics, and planning constraint characteristics in the attribute features are structured and organized to obtain the attribute feature vector of the land planning. Establish the correspondence between the spatial features and the attribute features; Based on the actual application needs of the land use plan, the corresponding relationships are weighted and fused to obtain the multi-semantic fusion feature map of the land use plan.

[0009] In a preferred embodiment, the step of weightedly fusing the correspondences according to the actual application needs of the land use plan to obtain a multi-semantic fusion feature map of the land use plan includes: Based on the priority of the core functions in the land use plan, importance weights are assigned to the spatial feature vector and the attribute feature vector, resulting in a weight configuration scheme for assigning importance weights to the spatial feature vector and the attribute feature vector. Based on the weight configuration scheme, preliminary integration features of the land use plan are generated, wherein the calculation formula for the preliminary integration features is as follows: ; In the formula, For the aforementioned preliminary fusion features, The spatial feature vector, For the spatial factor in the weighting configuration scheme, The attribute feature vector, The attribute factors in the weight configuration scheme; The preliminary fusion features that conform to the semantic constraints of the national land spatial planning are output as the multi-semantic fusion feature map of the national land planning.

[0010] In a preferred embodiment, the step of constructing a spatial constraint rule base for the land use planning based on the land use control rules and ecological protection red lines includes: The permitted uses, restrictions, and intensity requirements of the land use control rules in the land use plan are extracted to obtain the structured land use constraints of the land use plan. By analyzing the data of the ecological protection red line delineation results in the land use plan, the ecological protection constraints of the land use plan are obtained; By logically analyzing the structured land use constraints and the ecological protection constraints, the constraints of the land use planning are obtained. The constraints are constructed into a spatial constraint rule library for the national land planning based on spatial location and rule type.

[0011] In a preferred embodiment, the step of resolving conflict patches in the multi-semantic fusion feature map based on the spatial constraint rule base includes: Identify regions with overlapping and contradictory planning uses in the multi-semantic fusion feature map to obtain the spatial location and conflict type of conflict patches in the multi-semantic fusion feature map; Based on the rule priority in the spatial constraint rule base, the rule clauses involved in the conflicting polygons are retrieved to obtain the resolution rules for the conflicting polygons; According to the resolution rules, the conflict patches are semantically reconstructed to obtain a preliminary resolution scheme for the multi-semantic fusion feature map; The rationality of the preliminary resolution scheme is verified, and the preliminary resolution scheme that passes the rationality verification is output as the resolved multi-semantic fusion feature map.

[0012] In a preferred embodiment, the step of semantically enhancing the resolved multi-semantic fusion feature map to obtain the optimized fusion result of the land use planning includes: Extract the core semantic features from the resolved multi-semantic fusion feature map; Based on knowledge in the field of territorial spatial planning, establish the logical relationships and hierarchical structure among the core semantic features; Based on the rule clauses in the spatial constraint rule base, the core semantic features for establishing logical relationships and hierarchical structures are optimized for consistency. The optimized semantic features are integrated into the multi-semantic fusion feature map, resulting in the optimized fusion of the land planning.

[0013] In a preferred embodiment, the step of visualizing and rendering the optimized fusion result to obtain the auxiliary decision-making map for land planning includes: The multi-semantic planning information in the optimized fusion results is converted into a visual data model to obtain the standardized rendering data of the land planning. According to the specifications of land and space planning maps, corresponding symbols, colors and annotation styles are configured for different planning elements in the standardized rendering data to obtain the symbolization configuration scheme of the standardized rendering data. Based on the symbolic configuration scheme, the standardized rendering data is rendered in layers to obtain the visualization layer of the land planning. The visualization layer is then refined to create the auxiliary decision-making map for land planning.

[0014] To address the aforementioned problems, the present invention also provides a multi-source data fusion processing system for land spatial planning, the system comprising: The data processing module is used to perform format parsing and semantic annotation on multi-source land spatial data to obtain standard land spatial data for land planning. The feature segmentation module is used to perform hierarchical feature extraction on the standard land spatial data to obtain the spatial features and attribute features of the land planning. The feature fusion module is used to adaptively fuse the spatial features and the attribute features to obtain the multi-semantic fusion feature map of the land use plan. The spatial planning constraint module is used to construct a spatial constraint rule library for the land use plan based on the land use control rules and ecological protection red lines of the land use plan. The map conflict resolution module is used to resolve conflict patches in the multi-semantic fusion feature map based on the spatial constraint rule library, and to perform semantic enhancement on the resolved multi-semantic fusion feature map to obtain the optimized fusion result of the land planning. The land planning auxiliary module is used to visualize and render the optimized fusion results to obtain the auxiliary decision map of the land planning.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention performs format parsing and semantic annotation on multi-source land spatial data, assigns standardized semantic labels to data objects using a land spatial planning terminology database, and removes conflicting, missing, and invalid data. This enables the efficient generation of standardized land spatial data, ensuring that multi-source data possesses a unified format and standardized planning semantics, significantly improving the consistency and usability of multi-source data. Simultaneously, by extracting spatial and attribute features from land spatial data in a layered manner, it accurately captures the spatial pattern and attribute information of land planning. Then, based on actual application needs, it adaptively weights and fuses these two types of features to accurately construct a multi-semantic fusion feature map, fully preserving the core value of the data and significantly improving the accuracy and relevance of data fusion, providing a high-quality data foundation for land spatial planning.

[0016] 2. This invention constructs a spatial constraint rule library based on land use control rules and ecological protection red lines. It can effectively resolve conflicting patches in multi-semantic fusion feature maps. At the same time, it establishes logical connections and hierarchical structures of core semantic features and optimizes consistency through semantic enhancement, significantly improving the planning rationality and semantic integrity of the fusion results. In addition, by transforming the optimized fusion results into standardized rendering data and performing layered rendering and embellishment processing in conjunction with planning map specifications, an intuitive auxiliary decision-making map is generated. This clearly presents complex planning information, making it easier for planners to quickly obtain key information, significantly improving the efficiency of land spatial planning data application, and providing direct and effective support for planning decisions. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a multi-source data fusion processing method for land spatial planning according to an embodiment of the present invention. Figure 2 A functional module diagram of a multi-source data fusion processing system for land spatial planning provided in an embodiment of the present invention; The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0018] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0019] This application provides a method for multi-source data fusion processing in land spatial planning. The executing entity of this method includes, but is not limited to, at least one of the following electronic devices that can be configured to execute the method provided in this application: a server, a terminal, etc. In other words, the method can be executed by software or hardware installed on a terminal device or a server device. The server includes, but is not limited to, a single server, a server cluster, a cloud server, or a cloud server cluster. The server can be an independent server or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0020] Reference Figure 1 The diagram shown is a flowchart illustrating a multi-source data fusion processing method for land spatial planning according to an embodiment of the present invention. In this embodiment, the multi-source data fusion processing method for land spatial planning includes: S1. Perform format parsing and semantic annotation on multi-source territorial spatial data to obtain standard territorial spatial data for territorial planning; In this embodiment of the invention, the step of performing format parsing and semantic annotation on multi-source territorial spatial data to obtain standard territorial spatial data for land planning includes: Geographic raster data, vector layer data, and text table data are combined into a multi-source data set for land planning; The format of the multi-source data set is converted to obtain the parsed data of the multi-source data set; Based on the pre-acquired territorial spatial planning terminology database, each data object in the parsed data is assigned a planning semantic label, and the semantic annotation result of the parsed data is obtained; By removing invalid data with conflicts and missing information from the semantic annotation results, standard land space data for land planning is obtained.

[0021] Specifically, the geographic raster data, vector layer data, and text table data are first organized separately. The geographic raster data is stored according to spatial resolution and coordinate system. The vector layer data is organized according to feature type, such as land parcels and roads. The text table data is organized according to data theme, such as land attributes and planning indicators. Then, the three types of organized raw data are uniformly imported into the same data storage container and labeled with data type and source, ultimately forming a multi-source data set for land planning.

[0022] Furthermore, for geographic raster data in the multi-source dataset, different formats such as TIFF and ENVI are converted to GeoTIFF format, preserving spatial reference information and verifying data values ​​pixel by pixel during the conversion; for vector layer data, different formats such as SHP and GeoJSON are converted to GeoJSON format, retaining geometric shape and attribute information and checking the accuracy of each feature; for text table data, different formats (such as Excel and CSV formats) are converted to CSV format, ensuring the integrity of the table header information and verifying the data row by row. After completing all format conversions, the data is integrated to obtain the parsed data of the multi-source dataset.

[0023] Furthermore, the pre-acquired territorial spatial planning terminology database includes standard terms such as "urban construction land" and "ecological protection red line." Each term corresponds to a definition and applicable data type. For each data object in the parsed data, its type is first determined, such as raster, vector feature, or table row object. Then, based on the attribute information of the data object, such as the "land use nature" field value or spatial characteristics of the vector plot, the corresponding standard term is matched in the terminology database. This term is then used as a planning semantic label and marked in the attribute field of the data object to ensure that each data object has a unique label, ultimately obtaining the semantic labeling result of the parsed data.

[0024] Furthermore, each data object in the semantic annotation results is examined. Conflicting data refers to the same data object being assigned multiple mutually exclusive labels, such as a plot of land being labeled as both "urban construction land" and "permanent basic farmland". Conflicting data is filtered and removed by comparing the mutual exclusion relationships of terms in the terminology database. Missing data refers to data objects that have not been assigned any labels. Missing data is filtered and removed by traversing the semantic label fields. After removing all conflicting and missing invalid data, the remaining data objects constitute the standard land space data for land planning.

[0025] In summary, this operation can effectively integrate heterogeneous data from multiple sources, such as geographic raster data, vector layer data, and text table data. By converting the formats of different data, it eliminates the format differences between the different data and achieves the unification of the formats of multi-source data. This removes format obstacles for subsequent steps such as hierarchical feature extraction and feature fusion, and avoids processing interruptions or errors caused by format incompatibility.

[0026] In summary, assigning standardized planning semantic labels to the parsed data based on the pre-acquired territorial spatial planning terminology database can ensure the consistency of semantic interpretation of various data objects, solve the problem of semantic confusion in multi-source data, and improve the semantic consistency of data.

[0027] In summary, removing conflicting and missing invalid data from the results allows for the direct selection of high-quality data, reducing the interference of invalid data on subsequent processes, significantly improving the usability and reliability of standard territorial spatial data, providing high-quality initial support for subsequent data processing in territorial spatial planning, and ensuring the efficiency and accuracy of the overall processing flow.

[0028] S2. Perform hierarchical feature extraction on the standard land spatial data to obtain the spatial features and attribute features of the land planning; In this embodiment of the invention, the step of performing hierarchical feature extraction on the standard land spatial data to obtain the spatial features and attribute features of the land planning includes: Spatial structure analysis is performed on the geographic elements in the standard land spatial data to obtain the spatial structure characteristics of the standard land spatial data. Extract the category classification, statistical characteristics, and planning constraints of the attribute information from the standard territorial spatial data to obtain the attribute semantic features of the standard territorial spatial data; Based on the aforementioned spatial structural features, spatial features describing the spatial pattern of the land use in the national land planning are constructed. Based on the aforementioned semantic features, attribute features describing the planning attributes in the national land planning are constructed.

[0029] Specifically, the types of geographic elements in the standard land space data are first identified, including land parcels, roads, and water systems. For each geographic element, its spatial distribution is analyzed to determine its specific location in the geographic coordinate system and its relationship with adjacent elements. Its spatial morphology is analyzed to measure the boundary length, internal area, and shape regularity. Its spatial association is analyzed to clarify the connection methods between different types of elements, such as the boundary connection between roads and land parcels. The spatial distribution, spatial morphology, and spatial association of all geographic elements are integrated to obtain the spatial structure characteristics of the standard land space data.

[0030] Furthermore, we first sort out the attribute information fields in the standard territorial spatial data, including land use, area, and plot ratio. For each attribute field, we determine its category, such as land use as land type, area as scale, and plot ratio as development intensity. We then statistically analyze the attribute values ​​under each category to obtain characteristics, such as the proportion of each type in the land use type category, the maximum and minimum values ​​of the area in the scale category, and the distribution of the plot ratio in the development intensity category. We extract planning constraints from the attribute fields, such as the plot ratio of a certain plot not exceeding 2.5, and the cultivated land area of ​​a certain area not being lower than a specific value. By integrating the category classification, statistical characteristics, and planning constraints of the attribute information, we obtain the attribute semantic features of the standard territorial spatial data.

[0031] Furthermore, we first clarify that the core descriptive dimensions of the land spatial pattern in the national land planning include the distribution of urban concentrated areas, the layout of ecological patches, and the transportation network architecture. We then extract corresponding dimensional information from spatial structural characteristics, such as the scope and density of urban concentrated areas from spatial distribution, the area of ​​ecological patches from spatial morphology, and the degree of connectivity of the transportation network from spatial correlation. We then integrate the extracted dimensional information according to the logic of the national land spatial pattern to construct the spatial characteristics that describe the land spatial pattern in the national land planning.

[0032] Furthermore, the core descriptive directions of planning attributes in land use planning are first determined, including land use control requirements, development intensity levels, and resource constraint standards. Corresponding directional information is extracted from the semantic features of the attributes, such as extracting land use control type classification from category attribution, extracting the overall status of development intensity from statistical characteristics, and extracting resource constraint values ​​from planning constraints. The extracted directional information is then integrated according to the planning attribute logic to construct attribute features that describe planning attributes in land use planning.

[0033] In summary, this operation can accurately break down the core information dimensions of standard land and space data. By analyzing the spatial structure of geographic elements in the data, it can extract spatial structural features and construct spatial features that reflect the spatial pattern of the land. It can clearly capture key spatial information such as geometric shape, spatial distribution and topological relationship in land planning, ensuring accurate depiction of the land spatial layout and providing data support for subsequent understanding of the spatial logic of planning.

[0034] In summary, by extracting the category classification, statistical characteristics, and planning constraints of attribute information, we can obtain the semantic features of attributes and construct attribute features that describe planning attributes. This can clarify the connotation and constraints of planning attributes behind the data and avoid feature distortion caused by confusion between attribute information and spatial information.

[0035] In summary, this hierarchical extraction method enables spatial features and attribute features to be independent and complete, laying the foundation for establishing the correspondence between the two types of features and achieving adaptive weighted fusion. It effectively improves the pertinence and effectiveness of feature extraction, ensures the accuracy of subsequent data fusion, and provides clear and complete feature data support for territorial spatial planning.

[0036] S3. Perform adaptive feature fusion on the spatial features and the attribute features to obtain the multi-semantic fusion feature map of the land use plan; In this embodiment of the invention, the adaptive feature fusion of the spatial features and the attribute features to obtain the multi-semantic fusion feature map of the land use plan includes: Semantic encoding is performed on the geometric shape, spatial distribution, and topological relationship features in the spatial features to obtain the spatial feature vector of the land use plan. The category attribution, statistical characteristics, and planning constraint characteristics in the attribute features are structured and organized to obtain the attribute feature vector of the land planning. Establish the correspondence between the spatial features and the attribute features; Based on the actual application needs of the land use plan, the corresponding relationships are weighted and fused to obtain the multi-semantic fusion feature map of the land use plan.

[0037] In this embodiment of the invention, the step of weightedly fusing the corresponding relationships according to the actual application needs of the land use plan to obtain a multi-semantic fusion feature map of the land use plan includes: Based on the priority of the core functions in the land use plan, importance weights are assigned to the spatial feature vector and the attribute feature vector, resulting in a weight configuration scheme for assigning importance weights to the spatial feature vector and the attribute feature vector. Based on the weight configuration scheme, preliminary integration features of the land use plan are generated, wherein the calculation formula for the preliminary integration features is as follows: ; In the formula, For the aforementioned preliminary fusion features, The spatial feature vector, For the spatial factor in the weighting configuration scheme, The attribute feature vector, The attribute factors in the weight configuration scheme; The preliminary fusion features that conform to the semantic constraints of the national land spatial planning are output as the multi-semantic fusion feature map of the national land planning.

[0038] Specifically, the spatial features are first broken down into geometric features such as boundary length, internal area, and shape regularity; spatial distribution features such as geographic coordinate range and element density; and topological relationship features such as adjacent element types and connection methods. A unique numerical code is assigned to each feature item, such as boundary length being coded as 101, geographic coordinate range as 201, and adjacent element type as 301. Then, the specific values ​​of the feature items corresponding to each geographic element are extracted and arranged in the order of the codes to form a one-dimensional data sequence, thus obtaining the spatial feature vector of the land planning.

[0039] Furthermore, the category attribution in the attribute features is first divided into structured fields such as land use type, scale type, and development intensity type; the statistical characteristics are divided into structured fields such as the proportion of each category, maximum and minimum values, and distribution range; and the planning constraints are divided into structured fields such as the upper limit of plot ratio and the lower limit of cultivated land protection area. The specific content of the corresponding field of each attribute information is extracted and converted into text or numerical values ​​in a unified format. The fields are arranged in the order of category attribution, statistical characteristics, and planning constraints to form a one-dimensional data sequence, thus obtaining the attribute feature vector of land planning.

[0040] Furthermore, a unique identifier is assigned to each geographic element in the standard territorial spatial data. This identifier is associated with both the spatial features and attribute features of the geographic element. By using the identifier, each feature item in the spatial feature vector of the same geographic element is matched one by one with each feature item in the attribute feature vector. The association between each spatial feature item and the corresponding attribute feature item is recorded, forming an association table containing the identifier, spatial feature items, and attribute feature items, thus establishing the correspondence between spatial features and attribute features.

[0041] Furthermore, weight allocation rules are determined based on the actual application needs of land planning. For example, under the needs of urban development planning, the weight of plot ratio in planning constraints and the weight of topological relationship in spatial features are set to higher values, while the weights of other feature items are set to lower values. According to this rule, fixed weight values ​​are assigned to spatial feature items and attribute feature items in each correspondence. The spatial feature item value of the same correspondence is multiplied by the corresponding weight value, and the attribute feature item value is multiplied by the corresponding weight value. The two product results are added to obtain the fused value. The fused values ​​of all geographic elements are marked on the geographic base map according to their spatial location. When marking, the association information between the fused value and the corresponding feature item is retained to obtain the multi-semantic fused feature map of land planning.

[0042] Specifically, the core functions of land use planning are first identified, including ecological protection, urban construction, and agricultural production. The priority of each core function is then clarified based on the land use planning documents, for example, setting ecological protection as the highest priority and urban construction as the second highest priority. Next, each core function is correlated with features in the spatial feature vector, such as the spatial distribution of ecological patches and the geometric shape of urban plots, and features in the attribute feature vector, such as planning constraints on ecological land and statistical characteristics of urban land development intensity. Higher importance weights are assigned to features associated with high-priority core functions, and lower importance weights are assigned to features associated with low-priority core functions. Finally, the weights of each feature in the spatial feature vector, the weights of each feature in the attribute feature vector, and the corresponding feature names are compiled into a table to obtain a weighting scheme for allocating importance weights to the spatial feature vector and the attribute feature vector.

[0043] Furthermore, spatial feature vectors and attribute feature vectors corresponding to each geographic element are extracted from standard land spatial data. The importance weight corresponding to each feature item is found according to the weighting scheme. The specific value of each feature item in the spatial feature vector is multiplied by the corresponding weight to obtain the weighted result of the feature item. Similarly, the weighted result of each feature item in the attribute feature vector is calculated. The weighted results of all spatial feature items and attribute feature items of the same geographic element are arranged in the order of "spatial feature item weighted result first, attribute feature item weighted result second" to form a one-dimensional data sequence of the geographic element. The one-dimensional data sequences of all geographic elements together constitute the preliminary integrated features of land planning.

[0044] Furthermore, the semantic constraints of the land and space planning are first clarified, including rules such as "urban construction attributes shall not be marked within the ecological protection red line" and "the industrial land category shall not be marked on permanent basic farmland." The fusion results of each geographic element in the preliminary fusion features are checked one by one to determine whether they meet the semantic constraints. If the fusion result of a geographic element violates the semantic constraints, such as the fusion result of a plot within the ecological protection red line containing urban development intensity characteristics, the fusion result of that geographic element is removed. The preliminary fusion features that meet the semantic constraints are marked on the geographic base map according to the actual spatial location of the geographic elements. During the marking, key information in the fusion features, such as the weighted area of ​​ecological patches and the weighted plot ratio of urban plots, are presented simultaneously. The final output is a multi-semantic fusion feature map of the land and space planning.

[0045] Specifically, The spatial feature vector is the result of semantically encoding the geometric shape, spatial distribution and topological relationship features in the spatial features of land planning. Specifically, it is a one-dimensional data sequence formed by arranging the boundary length, geographic coordinate range, and adjacent element types of each geographic element in the coding order.

[0046] Furthermore, The spatial factors in the weighting scheme originate from the weighting scheme formulated based on the priority of core functions in land use planning. Specifically, they are the importance weights assigned to each feature item in the spatial feature vector. For example, when the core function of ecological protection has a high priority, the weight of the feature item corresponding to the spatial distribution of ecological patches is... Components of.

[0047] Furthermore, The attribute feature vector is the result of structuring the category classification, statistical characteristics and planning constraints of the attribute features of land planning. Specifically, it is a one-dimensional data sequence formed by arranging the land use type, the proportion of each type, the maximum floor area ratio and other feature items of each geographic element in the order of fields.

[0048] Furthermore, The attribute factors in the weighting scheme originate from the weighting scheme formulated based on the priority of core functions in land use planning. Specifically, they are the importance weights assigned to each feature item in the attribute feature vector. For example, when the core function of urban construction has a high priority, the weight of the feature item corresponding to the statistical characteristic of urban land development intensity is... Components of.

[0049] Furthermore, the significance of this formula is that by multiplying the spatial feature vector with the spatial factors in the weighting scheme, a weighted result of the spatial features is obtained. At the same time, by multiplying the attribute feature vector with the attribute factors in the weighting scheme, a weighted result of the attribute features is obtained. Then, the two weighted results are added together to integrate the weighted information of the spatial features and attribute features, and finally, the preliminary integrated features of the land planning corresponding to each geographic element are generated. In this process, the values ​​of the spatial factors and attribute factors reflect the degree of influence of the core functional priority of land planning on the two types of features.

[0050] Furthermore, when the spatial factor in the weight configuration scheme increases while the spatial feature vector remains unchanged, the product of the spatial feature vector and the spatial factor will increase, which in turn leads to an increase in the initial fusion feature. At this time, the influence of the spatial feature in the initial fusion feature is enhanced.

[0051] Furthermore, when the attribute factor in the weight configuration scheme increases while the attribute feature vector remains unchanged, the product of the attribute feature vector and the attribute factor will increase, which in turn leads to an increase in the initial fusion feature. At this time, the influence of the attribute feature in the initial fusion feature is enhanced.

[0052] Furthermore, when the spatial feature vector increases and the spatial factor in the weight configuration scheme remains unchanged, the product of the spatial feature vector and the spatial factor will increase, which in turn leads to an increase in the initial fusion feature. At this time, the contribution of the change in the spatial feature value itself to the initial fusion feature increases.

[0053] Furthermore, when the attribute feature vector increases and the attribute factors in the weight configuration scheme remain unchanged, the product of the attribute feature vector and the attribute factors will increase, which in turn leads to an increase in the initial fusion feature. At this time, the contribution of the change in the value of the attribute feature itself to the initial fusion feature increases.

[0054] In summary, this operation can effectively break down the information barriers between spatial features and attribute features. By semantically encoding spatial features and structurally organizing attribute features, the two types of features are transformed into standardized feature vectors. This solves the problem that different types of features have large differences in form and are difficult to fuse directly, laying a unified data foundation for subsequent fusion operations and ensuring the smoothness of the fusion process.

[0055] In summary, by establishing a correspondence between spatial features and attribute features, a deep connection between land spatial pattern information and planning attribute information is achieved, avoiding the one-sidedness of features caused by the separation of the two types of information, and ensuring that the fusion results can fully cover the core information dimensions of land planning.

[0056] In summary, it uses a weighted fusion method based on the actual application needs of land planning and the priority of core functions. It can dynamically adjust the importance weights of the two types of features, so that the fusion results can accurately match specific planning requirements. This avoids the problem of insufficient demand adaptability caused by fixed fusion modes. The resulting multi-semantic fusion feature map has both spatial logic and attribute constraints, providing high-quality and highly adaptable feature data support for subsequent conflict resolution and auxiliary decision-making map construction.

[0057] S4. Based on the land use control rules and ecological protection red lines of the land use plan, construct a spatial constraint rule library for the land use plan; In this embodiment of the invention, the step of constructing a spatial constraint rule base for the land use planning based on the land use control rules and ecological protection red lines includes: The permitted uses, restrictions, and intensity requirements of the land use control rules in the land use plan are extracted to obtain the structured land use constraints of the land use plan. By analyzing the data of the ecological protection red line delineation results in the land use plan, the ecological protection constraints of the land use plan are obtained; By logically analyzing the structured land use constraints and the ecological protection constraints, the constraints of the land use planning are obtained. The constraints are constructed into a spatial constraint rule library for the national land planning based on spatial location and rule type.

[0058] Specifically, land use control rules are extracted from the land use control chapters and special land use control documents in the land use planning documents. First, the permitted uses corresponding to each plot or area are identified one by one, and the types of construction or utilization that can be carried out, such as urban residential construction and agricultural planting, are clarified. Then, the restrictions corresponding to each permitted use are extracted, and the prohibited activities are clarified, such as allowing residential construction but prohibiting the installation of high-noise facilities. Next, the intensity requirements for each use are extracted, and the quantitative standards for development or utilization are clarified, such as the upper limit of plot ratio and the upper limit of building height for residential construction. The extracted permitted uses, restrictions, and intensity requirements are organized into a table according to the structure of "plot number - permitted use - restriction conditions - intensity requirements" to obtain the structured land use constraints of the land use planning.

[0059] Furthermore, the data on the delineation of ecological protection red lines in the national land planning is obtained. This data includes vector boundary data of the red line areas and red line control documents. First, the vector boundary data is analyzed to determine the geographical coordinate range of each red line area, such as a certain degree of east longitude and a certain degree of north latitude. Then, the control documents are analyzed to clarify the prohibited human activities in each red line area, such as the prohibition of industrial project construction and mineral resource mining, and the permitted human activities, such as ecological restoration projects. The geographical coordinate range of each red line area is correlated and organized with the corresponding control requirements to obtain the ecological protection constraints of the national land planning.

[0060] Furthermore, the spatial scope of structured land use constraints and ecological protection constraints is compared first to identify areas where they overlap, such as a plot of land that is both within the commercial development area of ​​land use control and within the ecological protection red line. Then, the priority of constraints is determined according to the land planning priority rules, clarifying that the ecological protection constraints have a higher priority than the structured land use constraints. If there is a conflict between the two types of constraints in the overlapping area, such as land use control allowing commercial development but ecological protection prohibiting construction, then the ecological protection constraints shall prevail. Constraints that do not overlap spatially and do not conflict are directly retained. The constraints after conflict resolution are integrated with the non-conflicting constraints to obtain the constraints of land planning.

[0061] Furthermore, constraints are first categorized by spatial location, using administrative streets or geographic grids as units. All constraints within the same administrative street or grid are grouped together, with each group labeled with a corresponding spatial location identifier such as street name and grid number. Then, constraints within each group are categorized by rule type into three categories: use restriction, ecological protection, and intensity control. Use restriction includes constraints related to permitted and prohibited uses, ecological protection includes red line area control constraints, and intensity control includes constraints related to plot ratio and building density. Next, an entry structure for the spatial constraint rule library is constructed, with each entry containing a spatial location identifier, rule type, specific constraint content, and effective start and end time. The categorized constraints are then entered one by one according to this structure to construct the spatial constraint rule library for land planning.

[0062] In summary, this operation can transform the scattered land use control rules and ecological protection red line data in land use planning into a systematic set of constraints. By extracting the permitted uses, restrictions, and intensity requirements from the land use control rules, structured land use constraints are formed. At the same time, ecological protection constraints are obtained by analyzing the ecological protection red line delineation data. This effectively avoids the problem of fragmented and scattered information on these two types of core constraints, and achieves centralized integration of key planning constraints.

[0063] In summary, clarifying the logical relationships between the two types of constraints can eliminate contradictions or redundancies between constraints, ensuring the inherent consistency of the spatial constraint rule base and avoiding decision-making biases caused by rule conflicts in subsequent applications. Furthermore, constructing the rule base according to spatial location and rule type makes the constraint rules clearly categorized and accurately positioned, facilitating rapid retrieval of matching rules when processing conflicting features and improving rule invocation efficiency.

[0064] In summary, the final spatial constraint rule library can accurately meet the core control needs of land planning, providing compliant and reliable constraint support for subsequent multi-semantic fusion feature map conflict resolution and semantic enhancement, ensuring that the optimized fusion results meet the control requirements of land planning, and helping to improve the compliance and scientific nature of planning results.

[0065] S5. Based on the spatial constraint rule base, conflict patches in the multi-semantic fusion feature map are resolved, and semantic enhancement is performed on the resolved multi-semantic fusion feature map to obtain the optimized fusion result of the land planning. In this embodiment of the invention, the step of resolving conflict patches in the multi-semantic fusion feature map based on the spatial constraint rule base includes: Identify regions with overlapping and contradictory planning uses in the multi-semantic fusion feature map to obtain the spatial location and conflict type of conflict patches in the multi-semantic fusion feature map; Based on the rule priority in the spatial constraint rule base, the rule clauses involved in the conflicting polygons are retrieved to obtain the resolution rules for the conflicting polygons; According to the resolution rules, the conflict patches are semantically reconstructed to obtain a preliminary resolution scheme for the multi-semantic fusion feature map; The rationality of the preliminary resolution scheme is verified, and the preliminary resolution scheme that passes the rationality verification is output as the resolved multi-semantic fusion feature map.

[0066] In this embodiment of the invention, the step of semantically enhancing the resolved multi-semantic fusion feature map to obtain the optimized fusion result of the land planning includes: Extract the core semantic features from the resolved multi-semantic fusion feature map; Based on knowledge in the field of territorial spatial planning, establish the logical relationships and hierarchical structure among the core semantic features; Based on the rule clauses in the spatial constraint rule base, the core semantic features for establishing logical relationships and hierarchical structures are optimized for consistency. The optimized semantic features are integrated into the multi-semantic fusion feature map, resulting in the optimized fusion of the land planning.

[0067] Specifically, the planned use information of all map patches is extracted from the multi-semantic fusion feature map. Each map patch corresponds to a unique planned use label, such as urban residential land, ecological protection land, or industrial land. Adjacent or spatially overlapping map patches are compared in terms of use. If map patches in the same spatial range are labeled with different uses, they are determined to be overlapping areas. If the use of a map patch contradicts the default planned use of the area, such as a map patch within the ecological protection red line labeled as industrial land, it is determined to be a conflicting area. The specific spatial range of overlapping and conflicting areas is recorded through the geographic coordinates of the map patches. The conflict type is clarified by classifying the areas as "overlapping areas" and "conflicting areas", thus obtaining the spatial location and conflict type of conflicting map patches in the multi-semantic fusion feature map.

[0068] Furthermore, the system first retrieves the preset rule priority ranking from the spatial constraint rule base. This ranking clearly prioritizes ecological protection rules over urban construction rules, which in turn prioritize agricultural production rules. Based on the spatial location of the conflicting map features, the system searches the rule base for all rule clauses corresponding to the spatial area. Then, it filters clauses related to the conflict type. For example, when the overlapping area involves residential and commercial uses, the system searches for use compatibility clauses in the urban construction category. When the conflicting area involves ecological and industrial uses, the system searches for prohibition clauses in the ecological protection category. Based on the rule priority, the highest priority clause is retained as the resolution rule for the conflicting map features, thus obtaining the resolution rule for the conflicting map features.

[0069] Furthermore, the semantic information of conflicting patches is adjusted according to the resolution rules. If the resolution rule is "industrial use is prohibited within the ecological protection red line", the industrial use semantic label of the conflicting patches is deleted, the ecological protection use semantic label is added, and the attribute information of the patches is updated simultaneously, such as deleting data related to industrial development intensity and adding data on ecological protection requirements. If the resolution rule is "overlapping areas of residential and commercial use are prioritized for residential use management", the semantic label of the overlapping area patches is unified as residential land, and the commercial use related attributes are adjusted to residential supporting attributes. This ensures that the semantics of the adjusted patches are completely consistent with the resolution rules, and that there are no new conflicts between the spatial location and the surrounding non-conflicting patches, thus obtaining a preliminary resolution scheme for the multi-semantic fusion feature map.

[0070] Furthermore, by comparing the regional functional positioning in the overall national land planning scheme (e.g., if a certain area is positioned as an ecological conservation area), it is checked whether all the map patches in the preliminary resolution scheme meet the requirements for ecological use. The map patch attributes in the preliminary resolution scheme are checked to see if they meet all the clauses of the spatial constraint rule library, such as whether the plot ratio and building height meet the restrictions. If the positioning and clauses are met, the rationality verification result of the planning is determined to be passed. If there are any unmet items, it is returned to re-semantic reconstruction. All map patches in the preliminary resolution scheme with the verification result passed are integrated according to their original spatial locations to form a complete multi-semantic fusion feature map. The output is the resolved multi-semantic fusion feature map.

[0071] Specifically, we first sort out the core semantic features in the field of land and space planning, including functional zoning types, land use nature, development intensity indicators, and ecological protection levels. Based on the knowledge of the field, we determine the logical relationship between each core semantic feature. For example, when the functional zoning type is an urban built-up area, the land use nature can include residential land and commercial land, and the development intensity indicator must match the urban construction requirements. When the functional zoning type is an ecological protection area, the land use nature is only ecological land, and the development intensity indicator is set to the minimum value. Then, we divide the hierarchical structure of the core semantic features. The top layer is the functional zoning type, the middle layer is the land use nature, and the bottom layer is the development intensity indicator and ecological protection level. We establish a structural framework according to the subordinate relationship of "top-middle-bottom layer" to form the logical relationship and hierarchical structure between the core semantic features.

[0072] Furthermore, all rule clauses are extracted from the spatial constraint rule base, including land use restrictions for different functional zones, development intensity limits, and control requirements corresponding to ecological protection levels. The core semantic features with established logical relationships and hierarchical structures are matched one by one with the rule clauses. If the value of a core semantic feature violates the corresponding clause, such as the development intensity index of a plot in an urban built-up area exceeding the development intensity limit for that area in the rule base, the value of the core semantic feature is adjusted to meet the clause requirements. If the logical relationship between core semantic features conflicts with the rule clauses, such as an ecological protection zone plot being associated with residential land use, the relationship is corrected according to the rule clauses so that the ecological protection zone plot is only associated with ecological land use. After adjusting all core semantic features, a consistent and optimized semantic feature is obtained.

[0073] Furthermore, all the map patches in the multi-semantic fusion feature map are obtained, and each map patch corresponds to a unique spatial location identifier. The semantic features optimized for consistency are matched with the map patches according to the spatial location identifier. The optimized semantic features of "ecological protection zone - ecological land - minimum development intensity" are assigned to the map patches with the corresponding spatial locations, and the original semantic information of the map patches is updated to ensure that the semantic features of each map patch are completely consistent with the results of consistency optimization. All updated map patches are integrated, and the spatial location relationship between map patches remains unchanged to form a complete multi-semantic fusion feature map containing optimized semantic features. This map is the optimized fusion result of land planning.

[0074] In summary, this operation can accurately identify conflicting map features with overlapping or contradictory planned uses in multi-semantic fusion feature maps. It relies on the rule priority retrieval and matching rules in the spatial constraint rule base to resolve conflicts, and then filters compliant solutions through planning rationality verification. This effectively solves the problem of map feature conflicts, avoids planning data deviations caused by conflicts, ensures that the fusion results strictly comply with the requirements of land use control and ecological protection red lines, and reduces the risk of planning violations.

[0075] In summary, by extracting the core semantic features of the deconstructed feature map, establishing its logical connections and hierarchical structure in conjunction with knowledge from the field of land spatial planning, and then optimizing semantic consistency based on spatial constraint rules, we can make up for possible semantic gaps in the deconstructed data, improve semantic integrity and logical coherence, and avoid semantic confusion or discontinuity.

[0076] In summary, the final optimized and integrated results combine compliance with high-quality semantics, providing reliable data support for subsequent visualization rendering and generation of auxiliary decision-making maps, and ensuring the accuracy of land planning data applications.

[0077] S6. Visualize and render the optimized fusion results to obtain the auxiliary decision-making map of the land planning.

[0078] In this embodiment of the invention, the step of visualizing and rendering the optimized fusion result to obtain the auxiliary decision-making map for land planning includes: The multi-semantic planning information in the optimized fusion results is converted into a visual data model to obtain the standardized rendering data of the land planning. According to the specifications of land and space planning maps, corresponding symbols, colors and annotation styles are configured for different planning elements in the standardized rendering data to obtain the symbolization configuration scheme of the standardized rendering data. Based on the symbolic configuration scheme, the standardized rendering data is rendered in layers to obtain the visualization layer of the land planning. The visualization layer is then refined to create the auxiliary decision-making map for land planning.

[0079] In summary, this process first transforms the optimized fusion results into a visual data model, converting abstract, multi-semantic planning information into concrete data, breaking down the barrier of "difficult-to-interpret data" and making complex land planning data easier to understand. Then, based on the land spatial planning map specifications, it assigns unique symbols, colors, and annotation styles to different planning elements in the standardized rendering data, ensuring the professionalism and consistency of the visualization and avoiding misinterpretation of information due to confusing element identification.

[0080] In summary, the subsequent layered rendering generates visual layers, clearly separating yet organically integrating various elements such as land spatial patterns and planning attribute constraints, facilitating planners' quick location and access to target information. Further refinement and detailing enhances the map's completeness. The resulting decision support map intuitively presents the core planning logic and key information, helping planners efficiently acquire effective data and providing intuitive and accurate support for land spatial planning decisions, thereby improving decision-making efficiency and accuracy.

[0081] like Figure 2The diagram shown is a functional module diagram of a multi-source data fusion processing system for land spatial planning provided by an embodiment of the present invention.

[0082] The multi-source data fusion processing system 100 for land spatial planning described in this invention can be installed in an electronic device. Depending on the functions implemented, the multi-source data fusion processing system 100 for land spatial planning may include a data processing module 101, a feature segmentation module 102, a feature fusion module 103, a spatial planning constraint module 104, a map conflict resolution module 105, and a land planning auxiliary module 106. The modules described in this invention can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and can perform a fixed function, and are stored in the memory of the electronic device.

[0083] In this embodiment, the functions of each module / unit are as follows: The data processing module 101 is used to perform format parsing and semantic annotation on multi-source territorial spatial data to obtain standard territorial spatial data for territorial planning. The feature segmentation module 102 is used to perform hierarchical feature extraction on the standard land space data to obtain the spatial features and attribute features of the land planning. The feature fusion module 103 is used to perform adaptive feature fusion on the spatial features and the attribute features to obtain the multi-semantic fusion feature map of the land planning. The spatial planning constraint module 104 is used to construct a spatial constraint rule library for the land use plan based on the land use control rules and ecological protection red lines of the land use plan. The map conflict resolution module 105 is used to resolve conflict patches in the multi-semantic fusion feature map based on the spatial constraint rule library, and to perform semantic enhancement on the resolved multi-semantic fusion feature map to obtain the optimized fusion result of the land planning. The land planning auxiliary module 106 is used to visualize and render the optimization and fusion results to obtain the auxiliary decision map of the land planning.

[0084] In the several embodiments provided by this invention, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and other division methods may be used in actual implementation.

[0085] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0086] Furthermore, the functional modules in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or in the form of hardware plus software functional modules.

[0087] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0088] The embodiments of this application can acquire and process relevant data based on artificial intelligence technology. Artificial intelligence is the theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use that knowledge to obtain optimal results.

[0089] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention.

Claims

1. A method for fusing and processing multi-source data in land spatial planning, characterized in that, The method includes: S1. Perform format parsing and semantic annotation on multi-source territorial spatial data to obtain standard territorial spatial data for territorial planning; S2. Perform hierarchical feature extraction on the standard land spatial data to obtain the spatial features and attribute features of the land planning; S3. Perform adaptive feature fusion on the spatial features and the attribute features to obtain the multi-semantic fusion feature map of the land use plan; S4. Based on the land use control rules and ecological protection red lines of the land use plan, construct a spatial constraint rule library for the land use plan; S5. Based on the spatial constraint rule base, conflict patches in the multi-semantic fusion feature map are resolved, and semantic enhancement is performed on the resolved multi-semantic fusion feature map to obtain the optimized fusion result of the land planning. S6. Visualize and render the optimized fusion results to obtain the auxiliary decision-making map of the land planning.

2. The method for multi-source data fusion processing in land spatial planning as described in claim 1, characterized in that, The process of parsing and semantically annotating multi-source territorial spatial data to obtain standard territorial spatial data for land planning includes: Geographic raster data, vector layer data, and text table data are combined into a multi-source data set for land planning; The format of the multi-source data set is converted to obtain the parsed data of the multi-source data set; Based on the pre-acquired territorial spatial planning terminology database, each data object in the parsed data is assigned a planning semantic label, and the semantic annotation result of the parsed data is obtained; By removing invalid data with conflicts and missing information from the semantic annotation results, standard land space data for land planning is obtained.

3. The method for multi-source data fusion processing in land spatial planning as described in claim 1, characterized in that, The step of performing hierarchical feature extraction on the standard land spatial data to obtain the spatial features and attribute features of the land planning includes: Spatial structure analysis is performed on the geographic elements in the standard land spatial data to obtain the spatial structure characteristics of the standard land spatial data. Extract the category classification, statistical characteristics, and planning constraints of the attribute information from the standard territorial spatial data to obtain the attribute semantic features of the standard territorial spatial data; Based on the aforementioned spatial structural features, spatial features describing the spatial pattern of the land use in the national land planning are constructed. Based on the aforementioned semantic features, attribute features describing the planning attributes in the national land planning are constructed.

4. The method for multi-source data fusion processing in land spatial planning as described in claim 1, characterized in that, The adaptive feature fusion of the spatial features and the attribute features to obtain the multi-semantic fusion feature map of the land use plan includes: Semantic encoding is performed on the geometric shape, spatial distribution, and topological relationship features in the spatial features to obtain the spatial feature vector of the land use plan. The category attribution, statistical characteristics, and planning constraint characteristics in the attribute features are structured and organized to obtain the attribute feature vector of the land planning. Establish the correspondence between the spatial features and the attribute features; Based on the actual application needs of the land use plan, the corresponding relationships are weighted and fused to obtain the multi-semantic fusion feature map of the land use plan.

5. The method for multi-source data fusion processing in land spatial planning as described in claim 4, characterized in that, The step of weightedly fusing the corresponding relationships according to the actual application needs of the land use plan to obtain a multi-semantic fusion feature map of the land use plan includes: Based on the priority of the core functions in the land use plan, importance weights are assigned to the spatial feature vector and the attribute feature vector, resulting in a weight configuration scheme for assigning importance weights to the spatial feature vector and the attribute feature vector. Based on the weight configuration scheme, preliminary integration features of the land use plan are generated, wherein the calculation formula for the preliminary integration features is as follows: ； In the formula, For the aforementioned preliminary fusion features, The spatial feature vector, For the spatial factor in the weighting configuration scheme, The attribute feature vector, The attribute factors in the weight configuration scheme; The preliminary fusion features that conform to the semantic constraints of the national land spatial planning are output as the multi-semantic fusion feature map of the national land planning.

6. The method for multi-source data fusion processing in land spatial planning as described in claim 1, characterized in that, The spatial constraint rule base for the land use planning, based on the land use control rules and ecological protection red lines, includes: The permitted uses, restrictions, and intensity requirements of the land use control rules in the land use plan are extracted to obtain the structured land use constraints of the land use plan. By analyzing the data of the ecological protection red line delineation results in the land use plan, the ecological protection constraints of the land use plan are obtained; By logically analyzing the structured land use constraints and the ecological protection constraints, the constraints of the land use planning are obtained. The constraints are constructed into a spatial constraint rule library for the national land planning based on spatial location and rule type.

7. The method for multi-source data fusion processing in land spatial planning as described in claim 1, characterized in that, The process of resolving conflict patches in the multi-semantic fusion feature map based on the spatial constraint rule base includes: Identify regions with overlapping and contradictory planning uses in the multi-semantic fusion feature map to obtain the spatial location and conflict type of conflict patches in the multi-semantic fusion feature map; Based on the rule priority in the spatial constraint rule base, the rule clauses involved in the conflicting polygons are retrieved to obtain the resolution rules for the conflicting polygons; According to the resolution rules, the conflict patches are semantically reconstructed to obtain a preliminary resolution scheme for the multi-semantic fusion feature map; The rationality of the preliminary resolution scheme is verified, and the preliminary resolution scheme that passes the rationality verification is output as the resolved multi-semantic fusion feature map.

8. The method for multi-source data fusion processing in land spatial planning as described in claim 7, characterized in that, The semantic enhancement of the resolved multi-semantic fusion feature map to obtain the optimized fusion result of the land use planning includes: Extract the core semantic features from the resolved multi-semantic fusion feature map; Based on knowledge in the field of territorial spatial planning, establish the logical relationships and hierarchical structure among the core semantic features; Based on the rule clauses in the spatial constraint rule base, the core semantic features for establishing logical relationships and hierarchical structures are optimized for consistency. The optimized semantic features are integrated into the multi-semantic fusion feature map, resulting in the optimized fusion of the land planning.

9. The method for multi-source data fusion processing in land spatial planning as described in claim 1, characterized in that, The visualization rendering of the optimized fusion results to obtain the auxiliary decision-making map for land planning includes: The multi-semantic planning information in the optimized fusion results is converted into a visual data model to obtain the standardized rendering data of the land planning. According to the specifications of land and space planning maps, corresponding symbols, colors and annotation styles are configured for different planning elements in the standardized rendering data to obtain the symbolization configuration scheme of the standardized rendering data. Based on the symbolic configuration scheme, the standardized rendering data is rendered in layers to obtain the visualization layer of the land planning. The visualization layer is then refined to create the auxiliary decision-making map for land planning.

10. A multi-source data fusion processing system for land spatial planning, characterized in that, The system includes: The data processing module is used to perform format parsing and semantic annotation on multi-source land and space data to obtain standard land and space data for land planning. The feature segmentation module is used to perform hierarchical feature extraction on the standard land spatial data to obtain the spatial features and attribute features of the land planning. The feature fusion module is used to adaptively fuse the spatial features and the attribute features to obtain the multi-semantic fusion feature map of the land use plan. The spatial planning constraint module is used to construct a spatial constraint rule library for the land use plan based on the land use control rules and ecological protection red lines of the land use plan. The map conflict resolution module is used to resolve conflict patches in the multi-semantic fusion feature map based on the spatial constraint rule library, and to perform semantic enhancement on the resolved multi-semantic fusion feature map to obtain the optimized fusion result of the land planning. The land planning auxiliary module is used to visualize and render the optimized fusion results to obtain the auxiliary decision map of the land planning.

Images