A land space planning multi-source data fusion processing method and system

Abstract

The application relates to the technical field of space planning, and discloses a land space planning multi-source data fusion processing method and system. The method comprises the following steps: performing format analysis and semantic labeling on multi-source land space data to obtain standard land space data of land planning; performing hierarchical feature extraction on the standard land space data to obtain spatial features and attribute features of the land planning; performing adaptive feature fusion on the spatial features and the attribute features to obtain a multi-semantics fusion feature map of the land planning; constructing a spatial constraint rule library of the land planning based on use control rules and ecological protection red lines of the land planning; eliminating conflict patches in the multi-semantics fusion feature map based on the spatial constraint rule library, and performing semantic enhancement on the multi-semantics fusion feature map after elimination to obtain an optimized fusion result; and performing visual rendering on the optimized fusion result to obtain an auxiliary decision graph. The application can improve the efficiency of data fusion processing in land space.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of space planning, and particularly relates to a land space planning multi-source data fusion processing method and system. BACKGROUND

[0002] Land space planning needs to integrate multi-source heterogeneous data such as geographic grid data, vector layer data and text table data. The prior art lacks efficient format uniform parsing capability when processing these data, and does not establish a deep association mechanism with the land space planning terminology library, so it is impossible to accurately assign standard planning semantic tags to each data object. This makes the processed data frequently appear conflicts or missing invalid information, making it difficult to form standardized land space data, not only increasing the operation difficulty of subsequent feature extraction and fusion, but also greatly reducing the efficiency of the overall data processing process, and unable to meet the demand of land space planning for data processing timeliness.

[0003] In the feature fusion and conflict resolution link of multi-source data, the defects of the prior art are further highlighted. On the one hand, when the extracted spatial features and attribute features are fused, a fixed fusion mode is usually used, which cannot dynamically adjust the fusion weights of the two types of features according to the actual application requirements and core function priorities of land planning, resulting in that the fused feature map cannot accurately reflect the core demands of planning, and cannot provide effective support for subsequent planning analysis. On the other hand, the prior art lacks a systematic spatial constraint rule library based on the use control rules and ecological protection red lines, and it is difficult to efficiently and reasonably resolve the conflict patches in the multi-semantic fusion feature map, and the resolved data often has the problem of insufficient semantic integrity, ultimately resulting in low-quality auxiliary decision map generated, which cannot provide reliable data basis for land space planning decision. SUMMARY

[0004] The present application provides a land space planning multi-source data fusion processing method and system to solve the problems raised in the background art.

[0005] To achieve the above purpose, the present application provides a land space planning multi-source data fusion processing method, comprising:

[0006] S1, performing format analysis and semantic annotation on multi-source land space data to obtain standard land space data of land planning;

[0007] S2, performing hierarchical feature extraction on the standard land space data to obtain spatial features and attribute features of the land planning;

[0008] S3, adaptively fusing the spatial features and the attribute features to obtain a multi-semantic fusion feature map of the land planning;

[0009] S4, constructing a spatial constraint rule library of the territorial planning based on the purpose control rules and ecological protection red lines of the territorial planning;

[0010] S5, based on the spatial constraint rule library, resolving conflict patches in the multi-semantics fusion feature map, and performing semantic enhancement on the resolved multi-semantics fusion feature map to obtain an optimized fusion result of the territorial planning;

[0011] S6, visualizing and rendering the optimized fusion result to obtain an auxiliary decision graph of the territorial planning.

[0012] In a preferred embodiment, the format analysis and semantic annotation of the multi-source territorial spatial data to obtain the standard territorial spatial data of the territorial planning comprises:

[0013] The geographic grid data, vector layer data and text table data are collected into a multi-source data set of the territorial planning;

[0014] The multi-source data set is format-converted to obtain analyzed data of the multi-source data set;

[0015] Based on a pre-acquired territorial spatial planning term library, a planning semantic label is assigned to each data object in the analyzed data to obtain a semantic annotation result of the analyzed data;

[0016] Invalid data with conflicts and omissions in the semantic annotation result is removed to obtain the standard territorial spatial data of the territorial planning.

[0017] In a preferred embodiment, the hierarchical feature extraction of the standard territorial spatial data to obtain the spatial features and attribute features of the territorial planning comprises:

[0018] The spatial structure of the geographic features in the standard territorial spatial data is analyzed to obtain the spatial structure features of the standard territorial spatial data;

[0019] The class attribution, statistical characteristics and planning constraint conditions of the attribute information in the standard territorial spatial data are extracted to obtain the attribute semantic features of the standard territorial spatial data;

[0020] Based on the spatial structure features, spatial features describing the territorial spatial pattern of the territorial planning are constructed;

[0021] Based on the attribute semantic features, attribute features describing the planning attributes of the territorial planning are constructed.

[0022] In a preferred embodiment, the adaptive feature fusion of the spatial features and the attribute features to obtain the multi-semantics fusion feature map of the territorial planning comprises:

[0023] The geometric shape, spatial distribution and topological relationship features in the spatial features are semantically coded to obtain a spatial feature vector of the territorial planning;

[0024] The category attribution, statistical characteristics and planning constraint condition features in the attribute features are structurally organized to obtain an attribute feature vector of the territorial planning;

[0025] A corresponding relationship between the spatial features and the attribute features is established;

[0026] According to actual application requirements of the territorial planning, the corresponding relationship is weighted and fused to obtain a multi-semantics fused feature map of the territorial planning.

[0027] In a preferred embodiment, the corresponding relationship is weighted and fused according to actual application requirements of the territorial planning to obtain a multi-semantics fused feature map of the territorial planning, which comprises:

[0028] According to a priority of a core function in the territorial planning, an importance weight is assigned to the spatial feature vector and the attribute feature vector to obtain a weight configuration scheme in which the spatial feature vector and the attribute feature vector are assigned with importance weights;

[0029] Based on the weight configuration scheme, a preliminary fused feature of the territorial planning is generated, wherein a calculation formula of the preliminary fused feature is as follows:

[0030] ;

[0031] In the formula, is the preliminary fused feature, is the spatial feature vector, is a spatial factor in the weight configuration scheme, is the attribute feature vector, is an attribute factor in the weight configuration scheme;

[0032] The preliminary fused feature meeting a semantic constraint of territorial spatial planning is output as a multi-semantics fused feature map of the territorial planning.

[0033] In a preferred embodiment, the spatial constraint rule library of the territorial planning is constructed based on the use control rules and the ecological protection red line of the territorial planning, which comprises:

[0034] The allowed use, restriction condition and intensity requirement of the use control rules in the territorial planning are extracted to obtain a structured use constraint condition of the territorial planning;

[0035] analyzing the ecological protection red line delineation result data in the national planning to obtain an ecological protection constraint condition of the national planning;

[0036] performing logical relationship analysis on the structured use constraint condition and the ecological protection constraint condition to obtain a constraint condition of the national planning;

[0037] constructing the constraint condition into a spatial constraint rule library of the national planning according to spatial positions and rule types.

[0038] In a preferred embodiment, based on the spatial constraint rule library, the conflict patches in the multi-semantics fusion feature map are resolved, including:

[0039] identifying areas of different planning uses that overlap and contradict in the multi-semantics fusion feature map to obtain spatial positions and conflict types of conflict patches in the multi-semantics fusion feature map;

[0040] According to the rule priority in the spatial constraint rule library, the rule clauses involved in the conflict patches are searched to obtain a resolution rule for the conflict patches;

[0041] According to the resolution rule, the conflict patches are semantically reconstructed to obtain a preliminary resolution scheme of the multi-semantics fusion feature map;

[0042] The preliminary resolution scheme is verified for planning rationality, and the preliminary resolution scheme that passes the planning rationality verification is output as a resolved multi-semantics fusion feature map.

[0043] In a preferred embodiment, the resolved multi-semantics fusion feature map is semantically enhanced to obtain an optimized fusion result of the national planning, including:

[0044] extracting core semantic features in the resolved multi-semantics fusion feature map;

[0045] Based on the knowledge in the field of national spatial planning, a logical association relationship and a hierarchical structure are established between the core semantic features;

[0046] According to the rule clauses in the spatial constraint rule library, the core semantic features establishing the logical association relationship and the hierarchical structure are optimized for consistency;

[0047] The semantic features that are optimized for consistency are integrated into the multi-semantics fusion feature map, and the optimized fusion result of the national planning.

[0048] In a preferred embodiment, the optimized fusion result is visually rendered to obtain an auxiliary decision-making atlas of the national planning, including:

[0049] Convert the multi-semantics planning information in the optimized fusion result into visual data model to obtain the standardized rendering data of the territorial planning;

[0050] According to the national space planning diagram specification, different planning elements in the standardized rendering data are configured with corresponding symbols, colors and note style to obtain a symbolization configuration scheme of the standardized rendering data;

[0051] Based on the symbolization configuration scheme, the standardized rendering data is subjected to hierarchical rendering to obtain a visual layer of the territorial planning;

[0052] The visual layer is subjected to decoration processing to obtain an auxiliary decision-making graph of the territorial planning.

[0053] In order to solve the above problems, the application further provides a territorial space planning multi-source data fusion processing system, the system comprises:

[0054] A data processing module is configured to perform format analysis and semantic annotation on multi-source territorial space data to obtain standardized territorial space data of territorial planning;

[0055] A feature division module is configured to perform hierarchical feature extraction on the standardized territorial space data to obtain spatial features and attribute features of the territorial planning;

[0056] A feature fusion module is configured to perform adaptive feature fusion on the spatial features and the attribute features to obtain a multi-semantics fusion feature map of the territorial planning;

[0057] A space planning constraint module is configured to construct a spatial constraint rule base of the territorial planning based on use control rules and ecological protection red lines of the territorial planning;

[0058] A graph conflict resolution module is configured to resolve conflict graph patches in the multi-semantics fusion feature map based on the spatial constraint rule base, and perform semantic enhancement on the resolved multi-semantics fusion feature map to obtain an optimized fusion result of the territorial planning;

[0059] A territorial planning auxiliary module is configured to perform visual rendering on the optimized fusion result to obtain an auxiliary decision-making graph of the territorial planning.

[0060] Compared with the prior art, the application has the following beneficial effects:

[0061] 1.The method can efficiently generate standardized land space data by carrying out format analysis and semantic annotation on multi-source land space data, combining land space planning terminology library to give data objects standard semantic labels, and eliminating invalid data with conflicts and omissions, ensure that multi-source data has unified format and standard planning semantics, greatly improve the consistency and availability of multi-source data; at the same time, by layering extracting spatial features and attribute features of land space data, accurately capturing the spatial pattern and attribute information of land planning, and based on the actual application demand, the two types of features are adaptively weighted and fused, the multi-semantics fusion feature map can be accurately constructed, the core value of data is fully retained, the accuracy and pertinence of data fusion are significantly improved, and high-quality data basis is provided for land space planning.

[0062] 2.The method can effectively eliminate the conflict patches in the multi-semantics fusion feature map based on the spatial constraint rule library constructed by land planning use control rules and ecological protection red line, and at the same time, the logical association and hierarchical structure of the core semantic features are established through semantic enhancement and the consistency is optimized, so that the planning rationality and semantic integrity of the fusion result are greatly improved; in addition, by converting the optimized fusion result into standardized rendering data, combining with planning pattern specification for hierarchical rendering and decoration processing, intuitive auxiliary decision-making atlas can be generated, complex planning information can be clearly presented, planning personnel can quickly obtain key information, the efficiency of land space planning data application is significantly improved, and direct and effective support is provided for planning decision. BRIEF DESCRIPTION OF DRAWINGS

[0063] Figure 1 A flowchart of a land space planning multi-source data fusion processing method provided by an embodiment of the application is shown.

[0064] Figure 2 A functional module diagram of a land space planning multi-source data fusion processing system provided by an embodiment of the application is shown.

[0065] The implementation of the application, functional characteristics and advantages will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0066] It should be understood that the specific embodiments described herein are only used to explain the application, and are not used to limit the application.

[0067] The embodiment of the present application provides a kind of land space planning multi-source data fusion processing method.The execution subject of the kind of land space planning multi-source data fusion processing method includes but is not limited to at least one of the electronic device that can be configured to execute the method provided by the embodiment of the present application, such as server, terminal etc.In other words, the kind of land space planning multi-source data fusion processing method can be executed by software or hardware installed in terminal device or server device.The server includes but is not limited to: single server, server cluster, cloud server or cloud server cluster etc.The server can be independent server, can also be cloud server that provides cloud service, cloud database, cloud computing, cloud function, cloud storage, network service, cloud communication, middleware service, domain name service, security service, content distribution network (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platform.

[0068] Referring to Figure 1 As shown in the figure, a kind of land space planning multi-source data fusion processing method provided by the embodiment of the present application is flow chart diagram.In the embodiment, the kind of land space planning multi-source data fusion processing method includes:

[0069] S1, the format analysis and semantic annotation of multi-source land space data are carried out, and the standard land space data of land planning is obtained;

[0070] In the embodiment of the present application, the format analysis and semantic annotation of multi-source land space data are carried out, and the standard land space data of land planning is obtained, including:

[0071] Geographical grid data, vector layer data and text table data are collected into the multi-source data set of land planning;

[0072] The format conversion is carried out to the multi-source data set, and the parsed data of the multi-source data set is obtained;

[0073] Based on the pre-acquired land space planning terminology library, each data object planning semantic label is given in the parsed data, and the semantic annotation result of the parsed data is obtained;

[0074] Invalid data with conflict and loss in the semantic annotation result is eliminated, and the standard land space data of land planning is obtained.

[0075] Specifically, the geographic raster data, vector layer data and text table data are sorted respectively, the geographic raster data is stored according to the spatial resolution and coordinate system, the vector layer data is sorted according to the feature type, such as land block and road, and the text table data is sorted according to the data theme, such as land attribute and planning index. Then, the three types of original data are uniformly imported into the same data storage container and labeled with data type and source, and finally a multi-source data set of land planning is formed.

[0076] Further, for the geographic raster data in the multi-source data set, different formats such as TIFF and ENVI are converted to GeoTIFF format, and the spatial reference information is kept unchanged and the data values are checked pixel by pixel; for the vector layer data, different formats such as SHP and GeoJSON are converted to GeoJSON format, and the geometric shape and attribute information are kept and the accuracy is checked for each feature; for the text table data, different formats such as Excel and CSV are converted to CSV format, and the header information is ensured to be complete and the data is checked line by line. After all the format conversion is completed, the parsed data of the multi-source data set is integrated.

[0077] Further, the pre-acquired land space planning terminology library includes standard terms such as “urban construction land” and “ecological protection red line”, each term corresponds to a definition and an applicable data type. For each data object of the parsed data, first determine its type such as raster, vector feature and table row object, and then match the corresponding standard term in the terminology library according to the attribute information of the data object such as the “land use property” field value of the vector land block or the spatial feature, and label the term as a planning semantic label in the data object attribute field, so that each data object has a unique label, and finally obtain the semantic labeling result of the parsed data.

[0078] Further, each data object in the semantic labeling result is checked, conflict data refers to the same data object being assigned multiple mutually exclusive labels such as a land block being labeled with “urban construction land” and “permanent basic farmland” at the same time, and conflict data is filtered and removed by comparing the mutually exclusive relationship of terms in the terminology library; missing data refers to data objects not being assigned any label, and missing data is filtered and removed by traversing the semantic label field. After removing all invalid data with conflicts and missing, the remaining data objects form the standard land space data of land planning.

[0079] In summary, this operation can effectively integrate multi-source heterogeneous data such as geographic raster data, vector layer data and text table data, eliminate the format differences of different data through format conversion, realize the format unification of multi-source data, clear the format obstacles for subsequent hierarchical feature extraction and feature fusion, and avoid processing interruption or errors caused by format incompatibility.

[0080] Overall, the pre-acquired national space planning term library is used to assign standard planning semantic labels to the parsed data, which can ensure the uniformity of semantic interpretation of each data object, solve the problem of semantic confusion of multi-source data, and improve the consistency of data semantics.

[0081] Overall, the invalid data in the elimination results can be directly filtered out to reduce the interference of invalid data on the subsequent process, significantly improve the availability and reliability of the standard national space data, provide high-quality initial support for subsequent data processing of national space planning, and ensure the efficiency and accuracy of the overall processing process.

[0082] S2, layering feature extraction is performed on the standard national space data to obtain spatial features and attribute features of the national planning;

[0083] In the embodiment of the application, the layering feature extraction on the standard national space data to obtain the spatial features and attribute features of the national planning comprises:

[0084] The spatial structure of the geographic elements in the standard national space data is analyzed to obtain the spatial structure features of the standard national space data;

[0085] The category attribution, statistical characteristics and planning constraint conditions of the attribute information in the standard national space data are extracted to obtain the attribute semantic features of the standard national space data;

[0086] The spatial structure features are used to construct spatial features describing the national space pattern of the national planning;

[0087] The attribute semantic features are used to construct attribute features describing the planning attributes in the national planning.

[0088] Specifically, the types of geographic elements in the standard national space data are identified, including land, roads and water systems. For each type of geographic element, the specific position in the geographic coordinate system and the relationship with adjacent elements are analyzed to determine the spatial distribution. The spatial form, boundary length, internal area and shape regularity are analyzed. The spatial association between different types of elements, such as the connection mode of roads and land boundaries, is analyzed. The spatial distribution, spatial form and spatial association of all geographic elements are integrated to obtain the spatial structure features of the standard national space data.

[0089] Further, first, the attribute information fields in the standard land space data are sorted, including land use property area, volume rate, and the like. For each attribute field, the category attribution is determined, such as land use property attribution, land use type category, area scale category, and development intensity category. The attribute values under each category are counted to obtain the characteristics, such as the proportion of each type of land use type category, the maximum value of area scale category, and the volume rate distribution of development intensity category. The planning constraints are extracted from the attribute fields, such as the volume rate of a certain land block not exceeding 2.5 and the area of cultivated land in a certain region not being lower than a certain value. The category attribution, statistical characteristics, and planning constraints of the attribute information are integrated to obtain the attribute semantic characteristics of the standard land space data.

[0090] Further, first, the core description dimensions of the land space pattern in land planning are determined, including the distribution of urban concentrated areas, the layout of ecological patches, and the architecture of traffic networks. The corresponding dimension information is extracted from the spatial structure characteristics, such as the range and land block density of urban concentrated areas from spatial distribution, the area of ecological patches from spatial form, and the connection degree of traffic networks from spatial correlation. The extracted dimension information is logically integrated according to the logic of the land space pattern to construct the spatial characteristics describing the land space pattern in land planning.

[0091] Further, first, the core description directions of the planning attributes in land planning are determined, including land use control requirements, development intensity levels, and resource constraint standards. The corresponding direction information is extracted from the attribute semantic characteristics, such as the land use control type division from the category attribution, the overall state of development intensity from the statistical characteristics, and the resource constraint values from the planning constraints. The extracted direction information is logically integrated according to the logic of the planning attributes to construct the attribute characteristics describing the planning attributes in land planning.

[0092] In summary, this operation can accurately split the core information dimensions of the standard land space data. By spatial structure analysis of geographic features in the data, spatial structure characteristics are extracted and spatial characteristics reflecting the land space pattern are constructed, which can clearly capture key spatial information such as geometric form, spatial distribution, and topological relationship in land planning, ensuring accurate portrayal of land space layout and providing data support for subsequent understanding of planning space logic.

[0093] In summary, by extracting the category attribution, statistical characteristics, and planning constraints of attribute information, attribute semantic characteristics are obtained and attribute characteristics describing planning attributes are constructed, which can clearly determine the planning attribute connotation and constraint requirements behind the data and avoid feature distortion caused by confusion between attribute information and spatial information.

[0094] In summary, this hierarchical extraction method can make spatial characteristics and attribute characteristics independent and complete, laying a foundation for subsequent establishment of the corresponding relationship between the two types of characteristics and implementation of adaptive weighted fusion, effectively improving the pertinence and effectiveness of feature extraction, ensuring the accuracy of subsequent data fusion steps, and providing feature data support with clear levels and complete information for land space planning.

[0095] S3, adaptively fusing the spatial features and the attribute features to obtain a multi-semantics fusion feature map of the territorial planning;

[0096] In the embodiment of the present application, the adaptively fusing the spatial features and the attribute features to obtain a multi-semantics fusion feature map of the territorial planning comprises:

[0097] semantically encoding geometric morphology, spatial distribution and topological relationship features in the spatial features to obtain a spatial feature vector of the territorial planning;

[0098] structurally organizing category attribution, statistical characteristics and planning constraint condition features in the attribute features to obtain an attribute feature vector of the territorial planning;

[0099] establishing a corresponding relationship between the spatial features and the attribute features;

[0100] according to actual application requirements of the territorial planning, performing weighted fusion on the corresponding relationship to obtain a multi-semantics fusion feature map of the territorial planning.

[0101] In the embodiment of the present application, the according to actual application requirements of the territorial planning, performing weighted fusion on the corresponding relationship to obtain a multi-semantics fusion feature map of the territorial planning comprises:

[0102] according to a priority of a core function in the territorial planning, assigning importance weights to the spatial feature vector and the attribute feature vector to obtain a weight configuration scheme of the spatial feature vector and the attribute feature vector assigning importance weights;

[0103] based on the weight configuration scheme, generating a preliminary fusion feature of the territorial planning, wherein a calculation formula of the preliminary fusion feature is as follows:

[0104] ;

[0105] In the formula, f is the preliminary fusion feature, is the preliminary fusion feature, is the spatial feature vector, is a spatial factor in the weight configuration scheme, is the attribute feature vector, is an attribute factor in the weight configuration scheme;

[0106] outputting the preliminary fusion feature meeting semantics constraints of territorial spatial planning as the multi-semantics fusion feature map of the territorial planning.

[0107] Specifically, the geometric shape feature in the spatial feature is first decomposed into boundary length, internal area, shape regularity, the spatial distribution feature is geographic coordinate range, element density, and the topological relationship feature is adjacent element type, connection mode. Each feature item is assigned a unique digital code, such as boundary length coded as 101, geographic coordinate range coded as 201, and adjacent element type coded as 301. Then the specific values of each feature item corresponding to each geographic element are extracted, and a one-dimensional data sequence is formed in the order of coding to obtain the spatial feature vector of the land planning.

[0108] Further, the category attribution in the attribute feature 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 the number of each category, the numerical maximum and minimum value, and the distribution interval, and the planning constraint conditions are divided into structured fields such as the upper limit of the volume rate and the lower limit of the cultivated land protection area. The specific content of each attribute information corresponding to the field is extracted and converted into a unified format of text or value. A one-dimensional data sequence is formed in the order of the field of category attribution, statistical characteristics, and planning constraint conditions to obtain the attribute feature vector of the land planning.

[0109] Further, a unique identification number is assigned to each geographic element in the standard land space data, which is associated with the spatial feature and attribute feature corresponding to the geographic element. Each feature item in the spatial feature vector and each feature item in the attribute feature vector of the same geographic element are matched one by one through the identification number, and the association relationship between each spatial feature item and the corresponding attribute feature item is recorded to form an association table containing identification number, spatial feature item, and attribute feature item, and the corresponding relationship between the spatial feature and the attribute feature is established.

[0110] Further, the weight distribution rule is determined according to the actual application requirements of the land planning, such as setting the volume rate weight in the planning constraint condition and the topological relationship weight in the spatial feature to a higher value under the demand of urban development planning, and setting the weight of other feature items to a lower value. According to the rule, a fixed weight value is assigned to each spatial feature item and attribute feature item in the corresponding relationship. The value of the spatial feature item in the same corresponding relationship is multiplied by the corresponding weight value, and the value of the attribute feature item is multiplied by the corresponding weight value. The sum of the two products is the fusion value. The fusion values of all geographic elements are marked on the geographic base map according to their spatial positions. The association information between the fusion value and the corresponding feature item is retained during the marking to obtain the multi-semantic fusion feature map of the land planning.

[0111] Specifically, first, the core functions in the national land planning are combed, including ecological protection, urban construction, agricultural production, etc. The priorities of each core function are determined according to the national land space planning document, for example, ecological protection is set as the highest priority, and urban construction is set as the second priority. Then, each core function is associated with the feature items in the spatial feature vector, such as the spatial distribution of ecological patches, the geometric shape of urban blocks, and the feature items in the attribute feature vector, such as the planning constraints of ecological land and the development intensity statistical characteristics of urban land. The feature items associated with the core functions with high priority are assigned higher importance weights, and the feature items associated with the core functions with low priority are assigned lower importance weights. Finally, the weights of each feature item in the spatial feature vector and the attribute feature vector, as well as the corresponding feature item names, are arranged into a table to obtain the weight configuration scheme of the importance weights of the spatial feature vector and the attribute feature vector.

[0112] Further, the spatial feature vector and the attribute feature vector corresponding to each geographic element are extracted from the standard national land space data, and the importance weight corresponding to each feature item is found according to the weight configuration 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, and the weighted result of each feature item in the attribute feature vector is calculated in the same way. The weighted results of all spatial feature items and the weighted results of all 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, and all one-dimensional data sequences of the geographic elements together form the preliminary fusion features of the national land planning.

[0113] Further, first, the semantic constraints of the national land space planning are determined, including rules such as "no urban construction attribute can be marked within the ecological protection red line" and "permanent basic farmland cannot be marked with industrial land category attribution". Then, 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, for example, the urban development intensity feature is included in the fusion result of the ecological protection red line, the fusion result of the 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. When marking, the key information in the fusion features is presented synchronously, such as the weighted area of the ecological patch and the weighted volume rate of the urban block. Finally, the multi-semantic fusion feature map of the national land planning is output.

[0114] Specifically, That is, the spatial feature vector, which is derived from the semantic encoding of the geometric shape, spatial distribution, and topological relationship features in the spatial features of the national land planning. Specifically, it is a one-dimensional data sequence formed by arranging the feature items of each geographic element, such as boundary length, geographic coordinate range, and adjacent element type, in the order of encoding.

[0115] Further, i.e. the spatial factor in the weight configuration scheme, which is derived from the weight configuration scheme formulated according to the priority of the core function in the land planning, and specifically the importance weight assigned to each feature item in the spatial feature vector, for example, when the priority of the ecological protection core function is high, the feature item weight corresponding to the spatial distribution of the ecological patch is a component of .

[0116] Further, i.e. the attribute feature vector, which is derived from the results of structurally organizing the category attribution, statistical characteristics and planning constraint condition features in the attribute features of the land planning, and specifically a one-dimensional data sequence formed by arranging the feature items such as the land use type, the proportion of the number of each type, and the upper limit of the volume rate of each geographic element in the field order.

[0117] Further, i.e. the attribute factor in the weight configuration scheme, which is derived from the weight configuration scheme formulated according to the priority of the core function in the land planning, and specifically the importance weight assigned to each feature item in the attribute feature vector, for example, when the priority of the urban construction core function is high, the feature item weight corresponding to the statistical characteristics of the urban land development intensity is a component of .

[0118] Further, the meaning of the formula is to obtain the weighted results of the spatial features by multiplying the spatial feature vector and the spatial factor in the weight configuration scheme, and to obtain the weighted results of the attribute features by multiplying the attribute feature vector and the attribute factor in the weight configuration scheme, and then to add the two weighted results to integrate the weighted information of the spatial features and the attribute features, and finally to generate the preliminary fusion features of the land planning corresponding to each geographic element, and the values of the spatial factor and the attribute factor in this process reflect the influence degree of the priority of the core function in the land planning on the two types of features.

[0119] Further, when the spatial factor in the weight configuration scheme increases and the spatial feature vector remains unchanged, the product of the spatial feature vector and the spatial factor will increase, and then the preliminary fusion features will increase, at this time the influence degree of the spatial features in the preliminary fusion features is enhanced.

[0120] Further, when the attribute factor in the weight configuration scheme increases and the attribute feature vector remains unchanged, the product of the attribute feature vector and the attribute factor will increase, and then the preliminary fusion features will increase, at this time the influence degree of the attribute features in the preliminary fusion features is enhanced.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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;

[0127] 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:

[0128] 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.

[0129] 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;

[0130] The structured use constraint condition and the ecological protection constraint condition are logically combed to obtain the constraint condition of the territorial planning;

[0131] The constraint condition is constructed into a spatial constraint rule library of the territorial planning according to spatial positions and rule types.

[0132] Specifically, use control rules are extracted from a use control chapter in a territorial planning text and special use control files, allowed uses corresponding to each land plot or region are identified one by one, construction or utilization types such as urban residential construction and agricultural planting that can be carried out are determined, restriction conditions corresponding to each allowed use are extracted, activities prohibited in association such as allowing residential construction but prohibiting supporting high-noise facilities are determined, intensity requirements of each use are extracted, and quantitative standards of development or utilization such as an upper limit of a volume rate of residential construction and an upper limit of a building height are determined, the extracted allowed uses, restriction conditions and intensity requirements are arranged into a table according to a structure of 'land plot number-allowed use-restriction condition-intensity requirement', and the structured use constraint condition of the territorial planning is obtained.

[0133] Further, ecological protection red line delimitation achievement data of the territorial planning is obtained, the data includes vector boundary data of the red line region and a red line control description file, the vector boundary data is analyzed first to determine a geographic coordinate range of each red line region such as an east longitude interval and a north latitude interval, the control description file is analyzed to determine human activities prohibited in each red line region such as prohibition of industrial project construction and mineral resource exploitation and human activities allowed in each red line region such as ecological restoration engineering, the geographic coordinate range of each red line region is associated and arranged with corresponding control requirements, and the ecological protection constraint condition of the territorial planning is obtained.

[0134] Further, spatial ranges of the structured use constraint condition and the ecological protection constraint condition are compared first to find out regions spatially overlapped such as a land plot both in a commercial development range of the use control and in the ecological protection red line, constraint priorities are determined according to priority rules of the territorial planning, it is determined that the ecological protection constraint condition has a higher priority than the structured use constraint condition, if there is a conflict between the two types of constraints in the overlapped region such as the use control allowing commercial development but the ecological protection prohibiting construction, the ecological protection constraint condition is used as a criterion, constraint conditions without spatial overlap and without conflict are directly reserved, and the constraint contents after conflict processing and without conflict are integrated, and the constraint condition of the territorial planning is obtained.

[0135] Further, first, the constraint conditions are classified according to spatial positions, and all constraint conditions in the same administrative street or grid are classified into a group in units of administrative streets or geographical grids, each group is marked with a corresponding spatial position identifier such as a street name or grid number, then the constraint conditions in each group are classified according to rule types, and are divided into use restriction type, ecological protection type and intensity control type, the use restriction type includes use permission and prohibition related constraints, the ecological protection type includes red line area regulation constraints, and the intensity control type includes volume rate and building density related constraints, then the entry structure of the spatial constraint rule library is constructed, each entry includes a spatial position identifier, a rule type, constraint specific content and effective start and end time, and the classified constraint conditions are entered one by one according to the structure to construct the spatial constraint rule library of the land planning.

[0136] In general, the operation can convert the scattered use regulation rules and ecological protection red line data in the land planning into systematic constraint bases. By extracting the permitted use, limitation condition and intensity requirement of the use regulation rules, structured use constraint conditions are formed, and by analyzing the ecological protection red line delineation results, ecological protection constraint conditions are obtained, which effectively avoids the problem of scattered and fragmented two types of core constraint information, and realizes the centralized integration of key constraint elements of the planning.

[0137] In general, on this basis, the logical relationship between the two types of constraint conditions is sorted out, which can eliminate contradictions or redundancies between constraints, ensure the internal consistency of the spatial constraint rule library, and avoid decision deviation caused by rule conflicts in subsequent applications. And constructing the rule library according to spatial positions and rule types can make the constraint rule classification clear and positioning accurate, facilitate fast retrieval and matching of rules when processing conflict patches, and improve the efficiency of rule calling.

[0138] In general, the finally constructed spatial constraint rule library can accurately meet the core control needs of land planning, provide compliant and reliable constraint support for subsequent conflict resolution and semantic enhancement of multi-semantic fusion feature maps, ensure that the optimized fusion results meet the control requirements of land planning, and help improve the compliance and scientificity of planning results.

[0139] S5, based on the spatial constraint rule library, resolving conflict patches 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 of the land planning;

[0140] In the embodiment of the application, based on the spatial constraint rule library, the conflict patches in the multi-semantic fusion feature map are resolved, which includes:

[0141] Identifying regions with overlapping and contradictory planning uses in the multi-semantic fusion feature map to obtain the spatial position and conflict type of the conflict patches in the multi-semantic fusion feature map;

[0142] According to the rule priority in the space constraint rule library, rule clauses involved in the conflict patch are searched to obtain a resolution rule of the conflict patch;

[0143] According to the resolution rule, semantic reconstruction is performed on the conflict patch to obtain a preliminary resolution scheme of the multi-semantics fusion feature map;

[0144] The preliminary resolution scheme is subjected to planning rationality verification, and the preliminary resolution scheme with a passed planning rationality verification result is output as a resolved multi-semantics fusion feature map.

[0145] In the embodiment of the application, semantic enhancement is performed on the resolved multi-semantics fusion feature map to obtain an optimized fusion result of the territorial planning, which comprises:

[0146] Core semantic features in the resolved multi-semantics fusion feature map are extracted;

[0147] Based on the knowledge in the field of territorial spatial planning, a logical association relationship and a hierarchical structure among the core semantic features are established;

[0148] According to the rule clauses in the space constraint rule library, the core semantic features with the established logical association relationship and hierarchical structure are subjected to consistency optimization;

[0149] The semantic features subjected to the consistency optimization are integrated into the multi-semantics fusion feature map, and the optimized fusion result of the territorial planning.

[0150] Specifically, planning use information of all patches in the multi-semantics fusion feature map is extracted, each patch corresponds to a unique planning use label such as urban residential land, ecological protection land and industrial land, patches adjacent to or overlapping in a spatial range are subjected to use comparison, if patches in the same spatial range are labeled with different uses, it is determined as an overlapping area, if the use of a patch is contrary to the default planning use of the area, such as a patch in an ecological protection red line labeled with industrial land, it is determined as a conflict area, specific spatial ranges of the overlapping and conflict areas are recorded through geographic coordinates of the patches, conflict types are classified according to “overlapping area, conflict area”, and spatial positions and conflict types of conflict patches in the multi-semantics fusion feature map are obtained.

[0151] Further, the preset rule priority ranking in the spatial constraint rule library is first called, which clearly indicates that the priority of ecological protection class rules is higher than that of urban construction class rules, and the priority of urban construction class rules is higher than that of agricultural production class rules. All rule clauses corresponding to the spatial region in the rule library are retrieved according to the spatial position of the conflict plot, and then the clauses related to the conflict are filtered in combination with the conflict type. For example, when the overlapping region involves residential and commercial use, the use compatibility clause in the urban construction class is retrieved; when the conflicting region involves ecology and industrial use, the prohibition clause in the ecological protection class is retrieved. The rule with the highest priority is reserved as the resolution rule of the conflict plot, and the resolution rule of the conflict plot is obtained.

[0152] Further, the semantic information of the conflict plot is adjusted according to the resolution rule. If the resolution rule is “industrial use is prohibited within the ecological protection red line”, the semantic label of industrial use of the conflict plot is deleted, and the semantic label of ecological protection use is supplemented. The attribute information of the plot is updated synchronously, such as deleting the industrial development intensity related data and adding the ecological protection requirement data. If the resolution rule is “residential and commercial use overlapping region is controlled according to residential use priority”, the semantic label of the overlapping region plot is unified as residential land, and the commercial use related attribute is adjusted as residential supporting attribute. It is ensured that the semantic of the adjusted plot is completely consistent with the resolution rule, and there is no new conflict between the spatial position and the surrounding non-conflict plots. The preliminary resolution scheme of the multi-semantic fusion feature map is obtained.

[0153] Further, the region function positioning in the overall scheme of territorial planning is checked, such as the positioning of a region as an ecological conservation area. It is checked whether the region plots in the preliminary resolution scheme meet the ecological use requirements. It is checked whether the plot attributes in the preliminary resolution scheme meet all the clauses of the spatial constraint rule library, such as whether the plot area meets the restriction. If the positioning and the clauses meet, it is determined that the planning rationality verification result is passed. If there are items that do not meet, the semantic reconstruction is returned to be re-performed. All plots in the preliminary resolution scheme with the verification result passed are integrated according to the original spatial position to form a complete multi-semantic fusion feature map, which is output as the resolved multi-semantic fusion feature map.

[0154] Specifically, the core semantic features in the field knowledge of territorial spatial planning are first sorted out, including function division type, land use property, development intensity index, and ecological protection level. The logical association among the core semantic features is determined according to the field knowledge. For example, when the function division type is urban built-up area, the land use property can include residential land and commercial land, and the development intensity index needs to match the urban construction requirements. When the function division type is ecological protection area, the land use property is only ecological land, and the development intensity index is set to the minimum value. The hierarchical structure of the core semantic features is further divided, the top layer is the function division type, the middle layer is the land use property, and the bottom layer is the development intensity index and the ecological protection level. The structural framework is established according to the “top layer-middle layer-bottom layer” subordinate relationship, and the logical association relationship and hierarchical structure among the core semantic features are formed.

[0155] Further, all rule clauses are extracted from the spatial constraint rule library, including land use property restrictions in different functional divisions, upper limits of development intensity, and control requirements corresponding to ecological protection levels. The core semantic features with established logical associations and hierarchical structures are matched with rule clauses one by one. If the value of a certain core semantic feature violates the corresponding clause, such as the development intensity index of a certain plot in the urban built-up area exceeding the upper limit of the development intensity in the rule library for that area, the value of the core semantic feature is adjusted to meet the clause requirements. If the logical associations between core semantic features conflict with rule clauses, such as the association of residential land use property with ecological protection area plots, the association is revised to only associate ecological land use property with ecological protection area plots according to the rule clause. After adjusting all core semantic features, the consistency-optimized semantic features are obtained.

[0156] Further, all the patches in the multi-semantic fusion feature map are obtained, each patch corresponding to a unique spatial location identifier. The consistency-optimized semantic features are matched with the patches according to the spatial location identifier. The optimized "ecological protection area-ecological land-lowest development intensity" semantic features are assigned to the patches corresponding to the spatial location, updating the original semantic information of the patches to ensure that the semantic features of each patch are completely consistent with the consistency-optimized results. All updated patches are integrated while maintaining the spatial location relationships between the patches unchanged to form a complete multi-semantic fusion feature map containing the optimized semantic features, which is the optimization fusion result of the land planning.

[0157] In summary, this operation can accurately identify conflict patches with overlapping and conflicting planning uses in the multi-semantic fusion feature map. It relies on the rule priority retrieval and matching of the spatial constraint rule library to resolve rules, and then filters compliant solutions through planning rationality verification, effectively solving patch conflict problems, avoiding planning data deviations caused by conflicts, ensuring that the fusion results strictly meet the requirements of land use control and ecological protection red line in land planning, and reducing the risk of planning violations.

[0158] In summary, by extracting the core semantic features of the resolved feature map and establishing logical associations and hierarchical structures based on the knowledge in the field of land spatial planning, and then optimizing semantic consistency according to the spatial constraint rules, the semantic gaps that may exist in the resolved data can be filled, the semantic integrity and logical coherence can be improved, and semantic confusion or discontinuity can be avoided.

[0159] In summary, the final optimization fusion result has compliance and high-quality semantics, providing reliable data support for subsequent visual rendering to generate an auxiliary decision-making atlas, ensuring the accuracy of land planning data application.

[0160] S6, visualizing and rendering the optimization fusion result to obtain an auxiliary decision-making atlas of the land planning.

[0161] In the embodiment of the present application, the visualization rendering of the optimization fusion result is performed to obtain the auxiliary decision graph of the territorial planning, which comprises:

[0162] The multi-semantics planning information in the optimization fusion result is converted into a visualization data model to obtain standardized rendering data of the territorial planning;

[0163] According to the national space planning graph specification, the corresponding symbol, color and note style are configured for different planning elements in the standardized rendering data to obtain a symbolization configuration scheme of the standardized rendering data;

[0164] Based on the symbolization configuration scheme, the standardized rendering data is rendered in layers to obtain a visualization layer of the territorial planning;

[0165] The visualization layer is processed to obtain the auxiliary decision graph of the territorial planning.

[0166] In general, the operation first converts the optimization fusion result into a visualization data model, converts abstract multi-semantics planning information into concrete data, breaks the barrier of "difficult to read data", and makes complex territorial planning data easier to understand. Then, according to the national space planning graph specification, the exclusive symbol, color and note style are configured for different planning elements in the standardized rendering data to ensure the professionalism and uniformity of the visualization presentation, and to avoid information misreading caused by element identification confusion.

[0167] In general, then, the visualization layer is generated by layer rendering, so that various elements such as territorial space pattern and planning attribute constraints are clearly separated and organically integrated, which facilitates the planning personnel to quickly locate and check target information. After the finishing processing, the details of the graph are improved to further improve the information integrity. The finally generated auxiliary decision graph can intuitively present the planning core logic and key information, help the planning personnel to efficiently obtain effective data, provide intuitive and accurate support for territorial space planning decision, and improve the decision efficiency and accuracy.

[0168] As shown in Figure 2 Fig. 1 is a functional module diagram of a territorial space planning multi-source data fusion processing system according to an embodiment of the present application.

[0169] The land space planning multi-source data fusion processing system 100 can be installed in an electronic device. According to the functions implemented, the land space planning multi-source data fusion processing system 100 can include a data processing module 101, a feature division module 102, a feature fusion module 103, a space planning constraint module 104, a graph conflict resolution module 105, and a land planning auxiliary module 106. The modules disclosed in the present application can also be referred to as units, which refer to a series of computer program segments that can be executed by an electronic device processor and can complete a fixed function, which are stored in the memory of the electronic device.

[0170] In the present embodiment, the functions of each module / unit are as follows:

[0171] The data processing module 101 is configured to perform format analysis and semantic annotation on multi-source land space data to obtain standard land space data for land planning.

[0172] The feature division module 102 is configured to perform hierarchical feature extraction on the standard land space data to obtain spatial features and attribute features of the land planning.

[0173] The feature fusion module 103 is configured to perform adaptive feature fusion on the spatial features and the attribute features to obtain multi-semantics fusion feature graphs of the land planning.

[0174] The space planning constraint module 104 is configured to construct a spatial constraint rule base of the land planning based on use control rules and ecological protection red lines of the land planning.

[0175] The graph conflict resolution module 105 is configured to resolve conflict graph patches in the multi-semantics fusion feature graphs based on the spatial constraint rule base, and perform semantic enhancement on the resolved multi-semantics fusion feature graphs to obtain an optimized fusion result of the land planning.

[0176] The land planning auxiliary module 106 is configured to perform visual rendering on the optimized fusion result to obtain an auxiliary decision graph of the land planning.

[0177] In several embodiments provided in the present application, it should be understood that the disclosed methods and systems can be implemented in other ways. For example, the system embodiments described above are only illustrative, for example, the division of the modules is only a logical function division, and another division method can be used in actual implementation.

[0178] The modules described as separate components may or may not be physically separate, and the components displayed as modules may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0179] In addition, each functional module in various embodiments of the application can be integrated in one processing unit, or each unit can exist physically independently, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0180] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0181] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence is to use digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, obtain knowledge and use knowledge to obtain the best results.

[0182] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application and are not limiting. Although the present application has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A land space planning multi-source data fusion processing method, characterized in that, The method comprises: S1, format analysis and semantic annotation of multi-source national space data to obtain standard national space data of national planning; S2, hierarchical feature extraction of the standard national space data to obtain spatial features and attribute features of the national planning; S3, adaptive feature fusion of the spatial features and the attribute features to obtain multi-semantics fusion feature map of the national planning; S4, based on the use control rules and ecological protection red line of the national planning, a spatial constraint rule base of the national planning is constructed; S5, based on the spatial constraint rule base, conflict patches in the multi-semantics fusion feature map are resolved, and the resolved multi-semantics fusion feature map is semantically enhanced to obtain an optimized fusion result of the national planning, including: identifying areas of different planning uses overlap and conflict in the multi-semantics fusion feature map to obtain the spatial position and conflict type of the conflict patches in the multi-semantics fusion feature map; according to the rule priority in the spatial constraint rule base, the rule clauses involved in the conflict patches are searched to obtain the resolution rules of the conflict patches; according to the resolution rules, the conflict patches are semantically reconstructed to obtain a preliminary resolution scheme of the multi-semantics fusion feature map; the preliminary resolution scheme is verified for planning rationality, and the preliminary resolution scheme that passes the planning rationality verification is output as the resolved multi-semantics fusion feature map; the core semantic features in the resolved multi-semantics fusion feature map are extracted; based on the knowledge in the field of national space planning, a logical association relationship and a hierarchical structure are established between the core semantic features; according to the rule clauses in the spatial constraint rule base, the core semantic features with the logical association relationship and the hierarchical structure are optimized for consistency; the semantically consistent features are integrated into the multi-semantics fusion feature map, and the optimized fusion result of the national planning is obtained; S6, the optimized fusion result is visualized and rendered to obtain an auxiliary decision graph of the national planning.

2. The method of claim 1, wherein the method further comprises: The format analysis and semantic annotation of multi-source national space data to obtain standard national space data of national planning comprises: geographical grid data, vector layer data and text table data are collected into a multi-source data set of national planning; the multi-source data set is format-converted to obtain parsed data of the multi-source data set; based on a pre-acquired national space planning term base, each data object in the parsed data is given a planning semantic label to obtain a semantic annotation result of the parsed data; invalid data with conflicts and omissions in the semantic annotation result are removed to obtain standard national space data of national planning.

3. The method of claim 1, wherein the method further comprises: The hierarchical feature extraction of the standard national space data to obtain spatial features and attribute features of the national planning comprises: spatial structure analysis of geographical elements in the standard national space data to obtain spatial structure features of the standard national space data; extracting the category attribution, statistical characteristics and planning constraint conditions of attribute information in the standard national space data to obtain attribute semantic features of the standard national space data; constructing a spatial feature of the land spatial pattern of the land planning based on the spatial structure feature; constructing an attribute feature of the planning attribute in the land planning based on the attribute semantic feature.

4. The method of claim 1, wherein The adaptive feature fusion of the spatial feature and the attribute feature obtains a multi-semantics fusion feature map of the land planning, including: semantic coding of geometric morphology, spatial distribution, and topological relationship features in the spatial feature to obtain a spatial feature vector of the land planning; structured organization of category attribution, statistical characteristics, and planning constraint condition features in the attribute feature to obtain an attribute feature vector of the land planning; establishing a corresponding relationship between the spatial feature and the attribute feature; weighted fusion of the corresponding relationship according to actual application requirements of the land planning to obtain a multi-semantics fusion feature map of the land planning.

5. The method of claim 4, wherein the method further comprises: The weighted fusion of the corresponding relationship according to actual application requirements of the land planning to obtain a multi-semantics fusion feature map of the land planning, including: allocating importance weights to the spatial feature vector and the attribute feature vector according to a priority of a core function in the land planning to obtain a weight configuration scheme of the spatial feature vector and the attribute feature vector allocating importance weights; generating a preliminary fusion feature of the land planning based on the weight configuration scheme, wherein a calculation formula of the preliminary fusion feature is as follows: ； wherein is the preliminary fusion feature, is the spatial feature vector, is a spatial factor in the weight configuration scheme, is the attribute feature vector, is an attribute factor in the weight configuration scheme; outputting the preliminary fusion feature meeting semantic constraints of land spatial planning as a multi-semantics fusion feature map of the land planning.

6. The method of claim 1, wherein the method further comprises: The spatial constraint rule base of the land planning is constructed based on the land use control rules and the ecological protection red line of the land planning, including: extracting allowed use, restriction conditions, and intensity requirements of the land use control rules in the land planning to obtain structured use constraint conditions of the land planning; analyzing the ecological protection red line delineation result data in the land planning to obtain ecological protection constraint conditions of the land planning; combing logical relationships of the structured use constraint conditions and the ecological protection constraint conditions to obtain constraint conditions of the land planning; constructing the constraint conditions into a spatial constraint rule base of the land planning according to spatial positions and rule types.

7. The method of claim 1, wherein the method further comprises: The visualization rendering of the optimization fusion result obtains an auxiliary decision graph of the land planning, including: converting multi-semantics planning information in the optimization fusion result into a visualization data model to obtain standardized rendering data of the land planning; configuring corresponding symbols, colors, and note styles for different planning elements in the standardized rendering data according to land spatial planning graph specification to obtain a symbolization configuration scheme of the standardized rendering data; layered rendering of the standardized rendering data based on the symbolization configuration scheme to obtain a visualization layer of the land planning; finishing processing of the visualization layer to obtain the auxiliary decision graph of the land planning.

8. A land spatial planning multi-source data fusion processing system for implementing the land spatial planning multi-source data fusion processing method in claim 1, the system comprising: A data processing module is configured to perform format analysis and semantic annotation on multi-source national space data to obtain standard national space data for national planning. A feature division module is configured to perform hierarchical feature extraction on the standard national space data to obtain spatial features and attribute features of the national planning. A feature fusion module is configured to perform adaptive feature fusion on the spatial features and the attribute features to obtain multi-semantics fusion feature maps of the national planning. A spatial planning constraint module is configured to construct a spatial constraint rule base of the national planning based on use control rules and ecological protection red lines of the national planning. A graph conflict resolution module is configured to resolve conflict graph patches in the multi-semantics fusion feature maps based on the spatial constraint rule base, and perform semantic enhancement on the resolved multi-semantics fusion feature maps to obtain an optimized fusion result of the national planning. A national planning assistance module is configured to perform visual rendering on the optimized fusion result to obtain an assistance decision graph of the national planning.

Images