Land and resource environment carrying capacity monitoring, dynamic evaluation and early warning method and system

Abstract

The application relates to the technical field of resources and environment, and particularly discloses a land and resource environment carrying capacity monitoring and dynamic evaluation and early warning method and system. The method comprises the following steps: firstly, based on the spatial utilization, resource environment consumption and ecological quality data of a target region, spatial clustering is carried out on the target region to obtain a monitoring and evaluation subregion; then, the above data tensor is reconstructed in the subregion to obtain a monitoring subregion index vector; subsequently, the index vector attribute is identified and the original index is mapped in combination with a preset land planning function subregion to generate a dynamic evaluation index matrix; the matrix is weighted and fused to obtain a multi-dimensional carrying capacity score; the score is used to diagnose the carrying pressure, quantify the nonlinear stress degree, determine the composite risk region and the coupling overload risk degree; finally, relevant information is structured and coded to generate a risk early warning report; and the application can improve the efficiency of land and resource environment carrying capacity monitoring and dynamic evaluation and early warning.

Description

Technical Field

[0001] This invention relates to the field of resource and environmental technology, and in particular to a method and system for monitoring, dynamic assessment and early warning of land and environmental carrying capacity. Background Technology

[0002] Existing technologies for monitoring and assessing the carrying capacity of land resources and the environment fail to integrate and analyze spatial utilization, resource and environmental consumption, and ecological quality data of the target area from multiple dimensions. Spatial clustering relies solely on a single data dimension for regional division, without feature embedding and correlation analysis of geographic grids. The basis for hierarchical reorganization lacks data feature support, resulting in insufficient matching between monitoring and assessment zones and the actual resource and environmental characteristics of the region. Subsequent analyses based on these zones lack a precise spatial foundation, and the utilization efficiency and value of monitoring data are both at a low level.

[0003] Existing technologies lack a systematic processing logic in carrying capacity assessment and risk early warning. Indicator identification does not incorporate targeted guidance and calibration based on land planning functional zoning. State-space mapping lacks clear guiding benchmark values ​​for reference. The weighted fusion method fails to reflect the actual differences between different zones and indicators. Risk diagnosis only performs simple threshold determination without conducting source analysis and nonlinear stress quantification for overloaded areas. Early warning reports also lack structured coding and prioritization of risk information, resulting in significant deviations between carrying capacity scores and actual conditions, inaccurate risk area identification, and a lack of practicality in early warning information. Consequently, they cannot provide effective decision-making basis for the refined management of land resources and the environment. Therefore, how to improve the efficiency of land resources and environmental carrying capacity monitoring and dynamic assessment and early warning has become an urgent problem to be solved. Summary of the Invention

[0004] This invention provides a method and system for monitoring, dynamic assessment and early warning of land and resources environmental carrying capacity, in order to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides a method for monitoring and dynamically assessing early warning of land and resources environmental carrying capacity, comprising: C1. Based on the spatial utilization data, resource and environmental consumption data, and ecological quality data of the target area, spatial clustering is performed on the target area to obtain the monitoring and evaluation zones of the target area; C2. Within the monitoring and assessment zone, the spatial use data, resource and environmental consumption data, and ecological quality data are reconstructed using tensors to obtain the monitoring zone index vector of the target area. C3. Based on the preset land planning functional zoning, attribute identification is performed on the monitoring zone indicator vector to obtain the indicator orientation type of the monitoring zone indicator vector. Based on the indicator orientation type, state space mapping is performed on the original indicators of the monitoring zone indicator vector to obtain the dynamic evaluation indicator matrix of the target area. C4. Weighted fusion of the dynamic evaluation index matrix yields a multidimensional carrying capacity score for the target area. C5. Based on the multidimensional bearing capacity score, the bearing pressure diagnosis of the target area is carried out to obtain the composite risk area of ​​the target area, and the nonlinear stress quantification of the composite risk area is carried out to obtain the degree of coupled overload risk of the composite risk area. C6. Structure the risk level of the composite risk area and the degree of coupled overload risk to obtain a risk warning report for the target area.

[0006] In a preferred embodiment, the step of spatially clustering the target area based on spatial utilization data, resource and environmental consumption data, and ecological quality data to obtain monitoring and evaluation zones for the target area includes: Acquire spatial utilization data, resource and environmental consumption data, and ecological quality data for the target area; The target area is spatially divided to obtain a geographic grid of the target area; Based on spatial utilization data, resource and environmental consumption data, and ecological quality data, feature embedding is performed on geographic grids to obtain a set of grid feature vectors for the target area. Correlation analysis is performed on the grid feature vector pairs in the grid feature vector set to obtain the correlation strength of the grid feature vector pairs; Based on the correlation strength, the geographic grid is hierarchically reorganized to obtain the monitoring and evaluation zones of the target area.

[0007] In a preferred embodiment, the step of performing tensor reconstruction on spatial use data, resource and environmental consumption data, and ecological quality data within the monitoring and assessment zone to obtain the monitoring zone index vector for the target area includes: Using the monitoring and assessment zones as spatial indexes, spatial utilization data, resource and environmental consumption data, and ecological quality data are mapped to the monitoring and assessment zones respectively, thus constructing a zoned dataset for the monitoring and assessment zones. The dimensionality of the partitioned dataset is transformed to obtain a multidimensional data tensor for the monitoring and evaluation partitions; Metadata parsing is performed on multidimensional data tensors to obtain the data type of the multidimensional data tensors; Based on data type, category fusion is performed on multidimensional data tensors to obtain data type aggregation vectors for monitoring and evaluation partitions; Variational inference is performed on the aggregated vector of data types to obtain the monitoring zoning indicator vector of the target area.

[0008] In a preferred embodiment, the step of identifying the attributes of the monitoring zone indicator vectors based on preset land planning functional zoning to obtain the indicator orientation type of the monitoring zone indicator vectors, and performing state-space mapping on the original indicators of the monitoring zone indicator vectors based on the indicator orientation type to obtain a dynamic evaluation indicator matrix for the target area, including: By associating and matching the preset land planning functional zones with the monitoring zone indicator vectors, the land planning functional zone type of the monitoring and evaluation zone is obtained; Based on the functional zoning type of land planning, the original indicators of the monitoring zone indicator vector are guided and calibrated to obtain the indicator guidance type of the monitoring zone indicator vector; Based on the monitoring zoning indicator vector, the guiding parameters of the land planning functional zoning are fitted to obtain the guiding benchmark value of the monitoring zoning indicator vector; Based on the guiding benchmark value, the covariance reduction of the original indicators in the monitoring zone indicator vector is performed to obtain the guiding benchmark deviation of the monitoring zone indicator vector. By reconstructing the spatial topology of the guideline deviation, a dynamic evaluation index matrix for the target area is obtained.

[0009] In a preferred embodiment, the step of fitting guidance parameters to the land planning functional zoning based on the monitoring zoning indicator vector to obtain the guidance benchmark value of the monitoring zoning indicator vector includes: The gridded feature vector of the monitoring zone index vector is obtained by performing gridded projection on the monitoring zone index vector. Based on the functional zoning type of land planning, the grid feature vectors are categorized to obtain a feature vector sample set for the functional zoning type of land planning. Density estimation is performed on the feature vector sample set to obtain the historical distribution characteristics of the indicators in the feature vector sample set. Based on the historical distribution characteristics of the indicators, tolerance analysis is performed on the evaluation indicators under the functional zoning type of land planning to obtain the stable numerical range of the evaluation indicators. The centrality of the stable numerical interval is measured to obtain the distribution center value of the stable numerical interval, and the distribution center value is used as the candidate value of the guiding benchmark for the evaluation index under the functional zoning type of land planning. The guide benchmark candidate values ​​are associated and bound with the evaluation indicators of the monitoring and evaluation zones to obtain the guide benchmark values ​​of the monitoring zone indicator vector.

[0010] In a preferred embodiment, the weighted fusion of the dynamic evaluation index matrix to obtain a multidimensional carrying capacity score for the target area includes: Entropy weight deconstruction is performed on the dynamic evaluation index matrix to obtain the monitoring zone index weights of the dynamic evaluation index matrix. The monitoring and evaluation zones in the dynamic evaluation index matrix are synthesized into comprehensive indices to obtain the evaluation indicators for the monitoring and evaluation zones. The weights of the monitoring zone indicators and the evaluation indicators are accumulated to obtain the monitoring zone carrying capacity score of the dynamic evaluation indicator matrix. Based on the spatial layout of the monitoring zones according to the dynamic evaluation index matrix, the carrying capacity scores of the monitoring zones are serialized and arranged to obtain the carrying capacity score sequence of the dynamic evaluation index matrix. By co-converging the carrying capacity score sequences, a multidimensional carrying capacity score for the target area is obtained.

[0011] In a preferred embodiment, the calculation formula for the multidimensional bearing capacity score is as follows: ; In the formula, For multi-dimensional load-bearing capacity scoring, The serial number of the monitoring and evaluation zone. To monitor and evaluate the serial numbers of the evaluation indicators in the designated zones, For the dynamic evaluation index matrix, the first The partition weights of each monitoring and evaluation partition. To monitor and evaluate the total number of zones, To monitor and evaluate the total number of evaluation indicators within the zoning area, For the dynamic evaluation index matrix, the first The first monitoring and assessment zone The weight of each evaluation indicator, For the dynamic evaluation index matrix, the first The first monitoring and assessment zone The values ​​of each evaluation indicator.

[0012] In a preferred embodiment, the step of performing bearing pressure diagnosis on the target area based on multidimensional bearing capacity scoring to obtain the composite risk area of ​​the target area, and performing nonlinear stress quantification on the composite risk area to obtain the coupled overload risk degree of the composite risk area, includes: The multidimensional carrying capacity score and the monitoring and evaluation zone are aggregated in a dimension-reducing manner to obtain the zone carrying capacity score of the monitoring and evaluation zone; Based on the preset bearing capacity baseline and the zoning bearing capacity score, the monitoring and evaluation zoning ... Overload source diagnosis is performed on overloaded zones to obtain the spatial location and overload type of overloaded zones. Based on the spatial location and overload type, the boundaries of overloaded zones are marked to obtain the initial risk area of ​​the target area. The performance parameters of the assessment indicators for the initial risk area are inverted to obtain the actual indicator values. Based on actual indicator values ​​and guiding benchmark values, the initial risk area is determined to obtain the composite risk area of ​​the target area; The contribution of the composite risk region is analyzed to obtain the deviation of the overload index and the index weight of the composite risk region. The deviation of the overload index and the index weight are combined with heterogeneous information to obtain the degree of coupled overload risk of the composite risk region.

[0013] In a preferred embodiment, the step of structurally encoding the composite risk region and the degree of coupled overload risk to obtain a risk warning report for the target region includes: By performing field deconstruction on the complex risk area, the spatial distribution information of the complex risk area can be obtained; By nesting and fusing spatial distribution information with the degree of coupled overload risk, a composite risk information set for the target area is obtained. Based on the degree of coupled overload risk, the composite risk information set is prioritized to obtain the risk information sequence of the composite risk information set. The risk information sequence is semantically encapsulated to obtain a risk warning report for the target area.

[0014] To address the aforementioned problems, this invention also provides a land resources and environmental carrying capacity monitoring and dynamic assessment early warning system, the system comprising: The spatial clustering and partitioning module is used to perform spatial clustering on the target area based on spatial utilization data, resource and environmental consumption data, and ecological quality data, so as to obtain the monitoring and evaluation partitions of the target area. The tensor reconstruction index module is used to reconstruct spatial utilization data, resource and environmental consumption data, and ecological quality data within the monitoring and evaluation zone, so as to obtain the monitoring zone index vector of the target area. The dynamic evaluation construction module is used to identify the attributes of the monitoring zone indicator vectors based on the preset land planning functional zoning, obtain the indicator orientation type of the monitoring zone indicator vectors, and perform state space mapping on the original indicators of the monitoring zone indicator vectors based on the indicator orientation type to obtain the dynamic evaluation indicator matrix of the target area. The carrying capacity scoring module is used to perform weighted fusion of the dynamic evaluation index matrix to obtain a multi-dimensional carrying capacity score for the target area. The risk area diagnosis module is used to diagnose the bearing pressure of the target area based on multi-dimensional bearing capacity scoring, obtain the composite risk area of ​​the target area, and perform nonlinear stress quantification on the composite risk area to obtain the degree of coupled overload risk of the composite risk area. The early warning report generation module is used to perform structured coding of composite risk areas and coupled overload risk levels to obtain risk early warning reports for the target area.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. This invention relies on multi-dimensional data to conduct spatial clustering analysis. It completes the division of monitoring and assessment zones through geographic grid feature embedding and correlation analysis, and then uses the zones as indexes to reconstruct the data tensors. Combined with the preset land planning functional zones, it completes the attribute identification and state space mapping of indicator vectors. This allows the construction of the dynamic assessment indicator matrix to fit the regional resource and environmental characteristics and planning positioning, realizing the multi-dimensional integration and refined analysis of monitoring data. It significantly improves the accuracy and pertinence of land resource and environmental carrying capacity monitoring and assessment, and provides clear spatial and indicator basis for the technical processing of each link.

[0016] 2. This invention achieves weighted fusion of dynamic assessment index matrices through entropy weight decomposition, obtaining a multi-dimensional carrying capacity score that fits the actual situation of the region. Then, through dimensionality reduction aggregation and source tracing diagnosis, the precise definition of composite risk areas is completed. At the same time, nonlinear stress quantification is carried out on the risk areas to determine the degree of coupled overload risk. Finally, a hierarchical risk warning report is generated through structured coding, realizing a systematic technical connection between carrying capacity assessment and risk warning, improving the accuracy of risk identification and the practicality of warning information, and forming a complete technical closed loop between dynamic assessment of land and resources environmental carrying capacity and risk warning, effectively improving the efficiency of overall technical application and decision support value. Attached Figure Description

[0017] Figure 1 A flowchart illustrating a method for monitoring, dynamic assessment, and early warning of land and resources environmental carrying capacity according to an embodiment of the present invention; Figure 2 A functional module diagram of a land resources and environmental carrying capacity monitoring and dynamic assessment early warning system provided in an embodiment of the present invention; Figure 3 An example diagram of land and resources environmental carrying capacity scoring for a land and resources environmental carrying capacity monitoring and dynamic assessment and early warning method 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 monitoring and dynamically assessing early warning of land and resources carrying capacity. 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 cluster of cloud servers. The server can be an independent server or a cloud server that provides 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 (CDN), and big data and artificial intelligence platforms.

[0020] Reference Figure 1 The diagram shown is a flowchart illustrating a method for monitoring and dynamically assessing early warning of land and resources environmental carrying capacity according to an embodiment of the present invention. In this embodiment, the method includes: C1. Based on the spatial utilization data, resource and environmental consumption data, and ecological quality data of the target area, spatial clustering is performed on the target area to obtain the monitoring and evaluation zones of the target area; In this embodiment of the invention, the step of spatially clustering the target area based on spatial utilization data, resource and environmental consumption data, and ecological quality data to obtain monitoring and evaluation zones for the target area includes: Acquire spatial utilization data, resource and environmental consumption data, and ecological quality data for the target area; The target area is spatially divided to obtain a geographic grid of the target area; Based on spatial utilization data, resource and environmental consumption data, and ecological quality data, feature embedding is performed on geographic grids to obtain a set of grid feature vectors for the target area. Correlation analysis is performed on the grid feature vector pairs in the grid feature vector set to obtain the correlation strength of the grid feature vector pairs; Based on the correlation strength, the geographic grid is hierarchically reorganized to obtain the monitoring and evaluation zones of the target area.

[0021] Spatial utilization data, resource and environmental consumption data, and ecological quality data covering the entire target area are extracted from the territorial spatial planning management database, resource and environmental monitoring platform, and ecological environment quality monitoring network. The extracted three types of data are processed to unify the data format, and missing and invalid values ​​are removed to form a standardized set of spatial utilization data, resource and environmental consumption data, and ecological quality data for the target area.

[0022] Based on the geographic boundary coordinates and topographic features of the target area, and in accordance with the preset equal-area spatial division rules, the entire geographic space of the target area is divided into uniformly sized regular geographic units. Each regular geographic unit is treated as an independent geographic grid, and all geographic grids are uniquely identified by geographic codes. By integrating all geographic grids with unique geographic codes, the geographic grid of the target area is obtained.

[0023] Using the unique geocode of each geographic grid as the matching basis, standardized spatial utilization data, resource and environmental consumption data, and ecological quality data are matched one by one with the corresponding geographic grids. All feature information of the three types of data corresponding to each geographic grid is extracted. The extracted feature information is transformed into a standardized feature representation form according to a preset dimension arrangement. A feature representation vector is generated for each geographic grid. The feature representation vectors of all geographic grids are integrated to obtain the grid feature vector set of the target area.

[0024] Select any two different grid feature vectors from the set of grid feature vectors in the target region to form a grid feature vector pair. Perform a dimension-by-dimensional similarity comparison on the feature representation content in each grid feature vector pair. Determine the similarity value of each grid feature vector pair based on the comprehensive result of the dimension-by-dimensional similarity comparison. Use this similarity value directly as the association strength of the corresponding grid feature vector pair. After completing the similarity comparison of all grid feature vector pairs in the target region, obtain the association strength of the grid feature vector pairs.

[0025] Three sets of association strength grading thresholds are preset. The association strength of all grid feature vector pairs is compared with the preset grading thresholds one by one. Based on the comparison results, the geographic grid is divided into three different association levels: high, medium and low. Spatial adjacency verification is carried out on geographic grids within the same association level. Spatially adjacent geographic grids in the same association level are merged and recombined. Spatially non-adjacent geographic grids in the same level retain their independent division status. All combinations of geographic grids that have been merged and recombined and those that retain their independent status are used as independent monitoring and evaluation zones. All independent monitoring and evaluation zones are integrated to obtain the monitoring and evaluation zones of the target area.

[0026] The beneficial effects include: standardizing the three types of basic data in the target area to ensure data validity; completing spatial division based on the equal area rule and geographic boundaries to ensure a unified standard for the formation of geographic grids; achieving precise association and feature embedding between data and geographic grids through unique geographic codes, allowing the grid feature vector set to fully represent the actual data characteristics of each grid; determining the association strength of grid feature vector pairs through dimensional similarity comparison; and completing the hierarchical reorganization of geographic grids by combining preset hierarchical thresholds and spatial adjacency verification. This ensures that the generated monitoring and assessment zones are highly matched with the actual spatial characteristics of spatial utilization, resource and environmental consumption, and ecological quality in the target area. The entire implementation process has clear operating rules and judgment criteria, making the generation of monitoring and assessment zones reproducible and improving the accuracy and rationality of monitoring and assessment zone division. This lays a precise and realistic spatial data foundation for subsequent monitoring and assessment work related to the carrying capacity of land resources and the environment.

[0027] C2. Within the monitoring and assessment zone, the spatial use data, resource and environmental consumption data, and ecological quality data are reconstructed using tensors to obtain the monitoring zone index vector of the target area. In this embodiment of the invention, the step of performing tensor reconstruction on spatial utilization data, resource and environmental consumption data, and ecological quality data within the monitoring and evaluation zone to obtain the monitoring zone index vector of the target area includes: Using the monitoring and assessment zones as spatial indexes, spatial utilization data, resource and environmental consumption data, and ecological quality data are mapped to the monitoring and assessment zones respectively, thus constructing a zoned dataset for the monitoring and assessment zones. The dimensionality of the partitioned dataset is transformed to obtain a multidimensional data tensor for the monitoring and evaluation partitions; Metadata parsing is performed on multidimensional data tensors to obtain the data type of the multidimensional data tensors; Based on data type, category fusion is performed on multidimensional data tensors to obtain data type aggregation vectors for monitoring and evaluation partitions; Variational inference is performed on the aggregated vector of data types to obtain the monitoring zoning indicator vector of the target area.

[0028] Using the unique spatial geocode of each monitoring and assessment zone as a spatial index, the standardized spatial utilization data, resource and environmental consumption data, and ecological quality data are matched one by one to the corresponding monitoring and assessment zone according to their geospatial affiliation. The three types of data matched in each monitoring and assessment zone are classified, collected, and organized to form a dataset exclusive to each monitoring and assessment zone. By integrating the exclusive datasets of all monitoring and assessment zones, the partition dataset of the monitoring and assessment zone is obtained.

[0029] For the monitoring and evaluation partition dataset, according to the preset three-dimensional partitioning rules of spatial dimension, data type dimension, and time dimension, the various discrete data in each monitoring and evaluation partition are decomposed and rearranged in terms of dimensions. The decomposed data are then filled into the corresponding three-dimensional framework, so that the partition dataset of each monitoring and evaluation partition is transformed into a regular data volume with a three-dimensional structure. By integrating the three-dimensional structure data volumes of all monitoring and evaluation partitions, a multidimensional data tensor of the monitoring and evaluation partition is obtained.

[0030] Metadata information of all data in the multidimensional data tensor of the monitoring and evaluation partition is extracted. The metadata information includes three core contents: data collection source, data representation object, and data measurement unit. According to the preset metadata classification and judgment rules, each extracted metadata information is classified one by one. Metadata information with the same representation object and the same measurement unit is classified into the same data type. After completing the classification and judgment of all metadata information, all data categories contained in the multidimensional data tensor are determined, and the data type of the multidimensional data tensor is obtained.

[0031] Based on the data type of the multidimensional data tensor obtained from the analysis, all data content corresponding to the same data type is extracted from the multidimensional data tensor. The extracted data content of the same type is integrated without redundancy. According to the preset one-dimensional vector arrangement rules, the integrated data content corresponding to each type of data is transformed into a one-dimensional feature vector with a fixed dimension length. Each data type generates a unique one-dimensional feature vector. The one-dimensional feature vectors corresponding to all data types are integrated to form an ordered vector set, thus obtaining the data type aggregation vector of the monitoring and evaluation partition.

[0032] Core features are extracted from the one-dimensional feature vectors in the data type aggregation vectors of the monitoring and assessment zones. Key data information that can characterize the core features of the land resources and environment of the monitoring and assessment zones is retained in each vector, while redundant data information that is only used for auxiliary characterization is removed. According to the preset arrangement rules of land resources and environment monitoring indicators, the retained key data information is re-integrated and standardized. The integrated key data information is transformed into feature vectors of a unified specification. By integrating the feature vectors of this unified specification of all monitoring and assessment zones, the monitoring zone indicator vector of the target area is obtained.

[0033] The beneficial effects include: using the unique spatial geocode of the monitoring and assessment zone as an index to achieve accurate spatial mapping of three types of data, providing a clear geographical basis for the construction of the zone dataset; pre-setting three-dimensional dimensional rules to complete the dimensional transformation of the zone dataset, enabling the multi-dimensional data tensor to form a regular dimensional structure; extracting core metadata information and classifying and parsing data types according to pre-set rules, ensuring a unified standard and accurate results for data type determination; completing data integration and vector transformation based on data types to obtain data type aggregation vectors, making data representation more systematic; and completing variational inference through core feature extraction and pre-set indicator dimensional rules, enabling the monitoring zone indicator vectors to accurately represent the core characteristics of land and resources environment of each monitoring and assessment zone in the target area. The entire implementation process has clear operating rules and judgment criteria, achieving the reproducibility of the technical solution, while improving the regularity and accuracy of data processing, allowing the monitoring zone indicator vectors to provide a reliable and realistic indicator data foundation for subsequent attribute identification and dynamic assessment.

[0034] C3. Based on the preset land planning functional zoning, attribute identification is performed on the monitoring zone indicator vector to obtain the indicator orientation type of the monitoring zone indicator vector. Based on the indicator orientation type, state space mapping is performed on the original indicators of the monitoring zone indicator vector to obtain the dynamic evaluation indicator matrix of the target area. In this embodiment of the invention, the step of identifying the attributes of the monitoring zone indicator vectors based on preset land planning functional zoning to obtain the indicator guidance type of the monitoring zone indicator vectors, and performing state-space mapping on the original indicators of the monitoring zone indicator vectors based on the indicator guidance type to obtain the dynamic evaluation indicator matrix of the target area, includes: By associating and matching the preset land planning functional zones with the monitoring zone indicator vectors, the land planning functional zone type of the monitoring and evaluation zone is obtained; Based on the functional zoning type of land planning, the original indicators of the monitoring zone indicator vector are guided and calibrated to obtain the indicator guidance type of the monitoring zone indicator vector; Based on the monitoring zoning indicator vector, the guiding parameters of the land planning functional zoning are fitted to obtain the guiding benchmark value of the monitoring zoning indicator vector; Based on the guiding benchmark value, the covariance reduction of the original indicators in the monitoring zone indicator vector is performed to obtain the guiding benchmark deviation of the monitoring zone indicator vector. By reconstructing the spatial topology of the guideline deviation, a dynamic evaluation index matrix for the target area is obtained.

[0035] The process of fitting guidance parameters between the land use planning functional zones and the monitoring zoning indicator vectors to obtain the guidance benchmark values ​​for the monitoring zoning indicator vectors includes: The gridded feature vector of the monitoring zone index vector is obtained by performing gridded projection on the monitoring zone index vector. Based on the functional zoning type of land planning, the grid feature vectors are categorized to obtain a feature vector sample set for the functional zoning type of land planning. Density estimation is performed on the feature vector sample set to obtain the historical distribution characteristics of the indicators in the feature vector sample set. Based on the historical distribution characteristics of the indicators, tolerance analysis is performed on the evaluation indicators under the functional zoning type of land planning to obtain the stable numerical range of the evaluation indicators. The centrality of the stable numerical interval is measured to obtain the distribution center value of the stable numerical interval, and the distribution center value is used as the candidate value of the guiding benchmark for the evaluation index under the functional zoning type of land planning. The guide benchmark candidate values ​​are associated and bound with the evaluation indicators of the monitoring and evaluation zones to obtain the guide benchmark values ​​of the monitoring zone indicator vector.

[0036] Spatial overlay analysis is performed on the spatial geographic boundaries of the pre-set land planning functional zones and the spatial geographic boundaries of each monitoring and evaluation zone. The matching criterion is that the spatial overlap ratio is not less than 90%. The pre-set land planning functional zones that meet the criterion are identified as the matching objects of the corresponding monitoring and evaluation zones. Each monitoring and evaluation zone is labeled with the corresponding land planning functional zone category name and unique code. The matching and labeling results of all monitoring and evaluation zones are integrated to obtain the land planning functional zone type of the monitoring and evaluation zone.

[0037] A fixed mapping relationship table between the types of land planning functional zones and the types of indicator orientations is pre-set. This table clearly defines the three types of orientation attributes corresponding to each original indicator under each type of land planning functional zone: development, protection, and control. Based on this mapping relationship table, the orientation attributes of all original indicators in each monitoring zone indicator vector are matched and labeled one by one. The labeled original indicators are classified and integrated according to their orientation attributes. The corresponding combination of indicator orientation types is determined for each monitoring zone indicator vector, thus obtaining the indicator orientation type of the monitoring zone indicator vector.

[0038] Using the completed geographic grids within the monitoring and evaluation zone as the spatial carrier, the original indicator values ​​in the indicator vector of the monitoring zone are allocated and projected one by one according to the unique geographic code of the geographic grid. Each geographic grid is assigned a corresponding complete indicator value feature, and the indicator value features of each geographic grid are arranged according to a preset dimension and transformed into a vector representation. By integrating the vectors of this type of all geographic grids within the monitoring and evaluation zone, the grid feature vector of the monitoring and evaluation zone is obtained.

[0039] According to the land planning functional zoning type marked by the monitoring and evaluation zoning, the grid feature vectors of all monitoring and evaluation zoning ...

[0040] The numerical distribution of all vector data in the feature vector sample set is analyzed for each evaluation indicator. The proportion of the number of samples in each interval to the total number of samples is counted according to the equal interval. The core interval is determined with the proportion of the number of samples not less than 80%. The core interval of the numerical distribution of each evaluation indicator is determined. The density of the feature vector sample set is estimated and the historical distribution characteristics of the indicators are obtained. Based on the historical distribution characteristics of the indicators, the rationality of the numerical fluctuation range of each evaluation indicator under the land planning functional zoning type is screened. Abnormal values ​​outside the core interval are eliminated, and the core interval is determined as the stable numerical interval of the evaluation indicator.

[0041] The midpoint of the stable numerical range of the evaluation indicators is calculated, and this midpoint is used as the distribution center value of the stable numerical range. The distribution center value is directly determined as the guiding benchmark candidate value of the evaluation indicator under the corresponding land planning functional zoning type, and the corresponding guiding benchmark candidate value is matched and labeled for each evaluation indicator.

[0042] Based on the land planning functional zoning type of the monitoring and evaluation zone, the candidate values ​​of the guidance benchmarks of each evaluation indicator are bound one-to-one with the original evaluation indicators in the monitoring zone indicator vector. A fixed candidate value of guidance benchmark is assigned to each original indicator in the monitoring zone indicator vector. The bound candidate values ​​of guidance benchmark are determined as the final numerical reference standard, and the guidance benchmark value of the monitoring zone indicator vector is obtained.

[0043] Using the guiding benchmark as a fixed numerical benchmark, the numerical difference between the actual value of each original indicator in the monitoring zone indicator vector and the corresponding guiding benchmark value is calculated. The overall dispersion of the numerical difference results of all original indicators is normalized, unreasonable difference values ​​caused by extreme abnormal values ​​are eliminated, and the numerical difference results that can truly reflect the deviation of the original indicators from the benchmark value are retained. The normalized numerical difference results are integrated into an ordered set to obtain the guiding benchmark deviation of the monitoring zone indicator vector.

[0044] Based on the spatial topological adjacency relationship of each monitoring and evaluation zone within the target area, the row dimension of the matrix is ​​set as the unique code of the monitoring and evaluation zone, and the column dimension is set as the fixed sequence number of the original indicator in the indicator vector of the monitoring zone. The deviation of the guidance benchmark of each monitoring and evaluation zone is filled into the corresponding position of the matrix one by one according to the correspondence between the row and the column, thus completing the matrix arrangement and integration of the deviation of the guidance benchmark of all monitoring and evaluation zones, and obtaining the dynamic evaluation indicator matrix of the target area.

[0045] The beneficial effects of this implementation process are achieved by using specific thresholds for spatial overlap ratios to accurately correlate and match land use planning functional zones with monitoring and evaluation zones. This provides clear and reproducible standards for determining functional zone types. Standardized calibration of indicator guidance types is achieved through a pre-set fixed mapping table, avoiding subjectivity in guidance determination. Gridded projection of monitoring zone indicator vectors is completed using a geographic grid, making feature representations more closely aligned with spatial distribution characteristics. Density estimation and tolerance analysis are performed using an 80% sample proportion threshold as the core, providing objective evidence for determining stable numerical ranges. Guidance that aligns with the functional positioning of land use planning is obtained through centrality measurement and correlation binding. The baseline value, after covariance reduction and normalization, accurately reflects the actual state of the indicators. Finally, the dynamic evaluation indicator matrix, based on spatial topological relationships, retains the spatial attributes of the monitoring and evaluation zones while accurately presenting the deviation characteristics of each indicator. Each step of the process has clearly defined operating rules and judgment conditions, improving the accuracy and standardization of indicator attribute identification and state space mapping. This allows the generated dynamic evaluation indicator matrix to provide a realistic, standardized, and spatially-attribute indicator data foundation for the subsequent weighted integration and scoring of land and resources environmental carrying capacity, while also ensuring the reproducibility of the entire technical solution.

[0046] C4. Weighted fusion of the dynamic evaluation index matrix yields a multidimensional carrying capacity score for the target area. In this embodiment of the invention, the step of weighted fusion of the dynamic evaluation index matrix to obtain a multidimensional carrying capacity score for the target area includes: Entropy weight deconstruction is performed on the dynamic evaluation index matrix to obtain the monitoring zone index weights of the dynamic evaluation index matrix. The monitoring and evaluation zones in the dynamic evaluation index matrix are synthesized into comprehensive indices to obtain the evaluation indicators for the monitoring and evaluation zones. The carrying capacity score of the monitoring zone is obtained by accumulating the weights of the monitoring zone indicators and the evaluation indicators into a dynamic evaluation indicator matrix. Based on the spatial layout of the monitoring zones according to the dynamic evaluation index matrix, the carrying capacity scores of the monitoring zones are serialized and arranged to obtain the carrying capacity score sequence of the dynamic evaluation index matrix. By co-converging the carrying capacity score sequences, a multidimensional carrying capacity score for the target area is obtained.

[0047] The calculation formula for the multidimensional bearing capacity score is as follows: ; In the formula, For multi-dimensional load-bearing capacity scoring, The serial number of the monitoring and evaluation zone. To monitor and evaluate the serial numbers of the evaluation indicators in the designated zones, For the dynamic evaluation index matrix, the first The partition weights of each monitoring and evaluation partition. To monitor and evaluate the total number of zones, To monitor and evaluate the total number of evaluation indicators within the zoning area, For the dynamic evaluation index matrix, the first The first monitoring and assessment zone The weight of each evaluation indicator, For the dynamic evaluation index matrix, the first The first monitoring and assessment zone The values ​​of each evaluation indicator.

[0048] Data standardization and normalization were carried out on the deviation of the guiding benchmark for all monitoring and assessment zones within the dynamic assessment indicator matrix. Invalid data with a value of zero and abnormal data exceeding three times the range of stable values ​​were removed. Based on the technical specifications for assessment of land and resources environmental carrying capacity, a three-level judgment threshold for information entropy was preset: 0 to 0.3 is the high dispersion interval, 0.3 to 0.7 is the medium dispersion interval, and 0.7 to 1 is the low dispersion interval. The normalized data was analyzed for numerical dispersion and matched with the corresponding information entropy interval. The indicators were weighted according to the principle that the lower the information entropy, the higher the indicator weight. The weighted values ​​were then normalized so that the sum of all indicator weights was 1. The original indicators of each monitoring and assessment zone were matched with corresponding normalized weight values. The indicator weight results of all monitoring and assessment zones were integrated to obtain the monitoring zone indicator weights of the dynamic assessment indicator matrix.

[0049] Based on the deviation of the guiding benchmark of each monitoring and assessment zone in the dynamic evaluation index matrix as the core data foundation, and according to the pre-set index synthesis hierarchy rules of the control focus of the territorial spatial planning functional zoning, the original indicators of each zone are first divided into three categories of indicator groups according to spatial utilization, resource and environmental consumption, and ecological quality, and the numerical integration within each group is completed. Then, a fixed structural proportion of the three categories of indicator groups is preset for different territorial spatial planning functional zones: 50% for ecological quality indicators, 20% for spatial utilization indicators, and 30% for resource and environmental consumption indicators in ecological protection zones; 50% for spatial utilization indicators, 30% for resource and environmental consumption indicators, and 20% for ecological quality indicators in urban construction zones; and 50% for resource and environmental consumption indicators, 20% for spatial utilization indicators, and 30% for ecological quality indicators in agricultural production zones. The integration results of the three categories of indicator groups are comprehensively collected according to the corresponding proportions, and the collected single value is determined as the exclusive value of the corresponding monitoring and assessment zone. By integrating the exclusive values ​​of all monitoring and assessment zones, the evaluation indicators of the monitoring and assessment zones are obtained.

[0050] Each individual indicator weight in each monitoring and evaluation zone is matched and combined with the corresponding indicator value one by one. A pre-set numerical verification rule is used to identify and remove results whose combined values ​​exceed the stable numerical range of the monitoring and evaluation zone as outliers. The remaining valid combined results are accumulated sequentially according to the indicator group order. The accumulated result is retained to four valid digits to complete the numerical normalization. Each monitoring and evaluation zone corresponds to a verified and normalized accumulated value, which is the carrying capacity score of the corresponding monitoring and evaluation zone. The carrying capacity scores of all monitoring and evaluation zones are integrated to obtain the monitoring zone carrying capacity score of the dynamic evaluation indicator matrix.

[0051] Based on the geocoding standard of national land spatial surveying, and taking the spatial topological adjacency relationship of the monitoring and assessment zones within the target area as the core, a pre-set spatial order rule for sequential arrangement is established. The monitoring and assessment zones are arranged sequentially from east to west and from north to south according to their unique geocodes. The carrying capacity scores of each monitoring and assessment zone are arranged one by one according to this rule. During the arrangement process, each score is labeled with the corresponding unique geocode and specific spatial location information of the monitoring and assessment zone, forming an ordered list containing score data and spatial attribute information. This list is the carrying capacity score sequence of the dynamic assessment index matrix.

[0052] Based on the pre-set collaborative aggregation weighting rules for the control priority of the land and resources environmental carrying capacity of the target area, the aggregation weight of the core ecological zone monitoring and assessment zone is 0.4, the aggregation weight of the urban construction zone monitoring and assessment zone is 0.3, and the aggregation weight of the agricultural production zone monitoring and assessment zone is 0.3. The carrying capacity scores of each zone in the carrying capacity scoring sequence are matched and combined with the corresponding aggregation weights. All the combined results are accumulated as a whole. The accumulated results are normalized and mapped to the pre-set scoring range of 0 to 100 to obtain a single value that can represent the overall land and resources environmental carrying capacity status of the target area. This value is the multi-dimensional carrying capacity score of the target area.

[0053] The source of the parameters in the formula, The serial number of the monitoring and evaluation zone is a unique numerical number assigned to the monitoring and evaluation zones obtained by spatial clustering of the target area, in accordance with the spatial topological orientation from east to west and from north to south. The starting value of the number is 1 and increases sequentially. The serial number of the assessment indicator in the monitoring and assessment zone is a unique numerical number assigned to the original indicators of each monitoring and assessment zone in the dynamic assessment indicator matrix, according to a fixed category order of spatial utilization data indicators, resource and environmental consumption data indicators, and ecological quality data indicators. The starting value of the number is 1 and increases sequentially. For the dynamic evaluation index matrix, the first The weights of each monitoring and assessment zone are determined by pre-setting weight rules based on the control priority of the land and resources environmental carrying capacity of the target area. Basic weight values ​​are assigned according to the zone type: core ecological zone, urban construction zone, and agricultural production zone. All basic weight values ​​are then normalized so that the sum of the weights of all monitoring and assessment zones in the target area is 1. The processed values ​​are then directly assigned to the corresponding monitoring and assessment zone. The total number of monitoring and evaluation zones is the actual number obtained by counting each monitoring and evaluation zone obtained by spatial clustering of the target area. This value is a non-negative integer and is completely consistent with the actual number of monitoring and evaluation zones. The total number of evaluation indicators within a monitoring and evaluation zone is the actual number obtained by counting all the original evaluation indicators in a single monitoring and evaluation zone in the dynamic evaluation indicator matrix. The total number of evaluation indicators in each monitoring and evaluation zone within the target area remains consistent. For the dynamic evaluation index matrix, the first The first monitoring and assessment zone The weights of each evaluation indicator are determined by standardizing and normalizing the deviation data of the guiding benchmark within the dynamic evaluation indicator matrix, removing invalid data with values ​​of zero and abnormal data exceeding three times the range of stable values, analyzing the dispersion of the normalized data and matching it with a preset information entropy range, assigning initial weights to each indicator according to the principle that the lower the information entropy, the higher the indicator weight, and then normalizing the initial weights within a single monitoring and evaluation zone so that the sum of the weights of all indicators within the zone is 1, and using the processed values ​​as the indicator weights of the corresponding indicators. For the dynamic evaluation index matrix, the first The first monitoring and assessment zone The value of the evaluation indicator is the value of the first indicator in the monitoring zone indicator vector. Within the monitoring and assessment zone, the first After calculating the numerical difference between the actual value of each original indicator and the corresponding guiding benchmark value, the guiding benchmark deviation value is obtained by eliminating unreasonable difference values ​​through covariance reduction. This value is directly extracted from the corresponding position in the dynamic evaluation indicator matrix. The multidimensional carrying capacity score is obtained by calculating each parameter in the formula layer by layer. The calculation results are normalized and mapped to a preset scoring range of 0 to 100, which serves as the final value representing the overall land resource and environmental carrying capacity status of the target area.

[0054] This formula is the core quantitative implementation of obtaining a multi-dimensional carrying capacity score for a target area by weighted fusion of a dynamic assessment indicator matrix. It directly inherits the technical product of constructing the dynamic assessment indicator matrix and accurately implements the technical operational requirements of accumulating the weights of monitoring zone indicators and assessment indicator components within the dynamic assessment indicator matrix, and then collaboratively aggregating the carrying capacity score sequence. The formula adopts a hierarchical calculation logic: first calculating the weighted values ​​of each assessment indicator within a single monitoring and assessment zone, and then calculating the weighted sum of values ​​from all monitoring and assessment zones. This logic matches the spatial layout characteristics of the monitoring and assessment zones and the structural characteristics of the assessment indicators, thus achieving... This reflects the differences in control priorities among different monitoring and assessment zones in the assessment of land resources and environmental carrying capacity, and also through... This reflects the varying importance of different assessment indicators within a single monitoring and assessment zone, ensuring that the weighted fusion result accurately reflects the actual characteristics of each monitoring and assessment zone and each assessment indicator within the target area. The formula calculates a multidimensional carrying capacity score for the target area. This value serves as the core quantitative basis for subsequent carrying capacity pressure diagnosis and identification of complex risk areas based on the multidimensional carrying capacity score. It achieves a technical transformation from indicator data in a dynamic assessment indicator matrix to an overall carrying capacity score, providing a precise and standardized quantitative data foundation for all subsequent carrying capacity analysis and risk warning processes.

[0055] The beneficial effects of this implementation process are based on clear numerical thresholds and industry technical specifications to conduct entropy weight analysis, ensuring the objectivity and standardization of the allocation of indicator weights for monitoring zones, avoiding the bias of subjective assignment. Combined with the control priorities of land planning functional zones, differentiated index synthesis rules are preset, ensuring that the assessment indicators of the monitoring and evaluation zones are highly aligned with the regional functional positioning. Pre-set numerical verification rules complete the accumulation of the weights of monitoring zone indicators and assessment indicators, effectively eliminating outliers and ensuring the accuracy of the carrying capacity score for the monitoring zones. Serialization is performed based on geocoding standards and spatial topological relationships, preserving clear spatial attributes in the carrying capacity score sequence. Then, convergence weights are preset according to control priorities to complete collaborative convergence, ensuring that the generated multi-dimensional carrying capacity score reflects both the differentiated characteristics of each zone and accurately represents the overall carrying capacity status of the target area. Each step of the process has clear operating rules, quantitative thresholds, and judgment standards, ensuring the reproducibility of the technical solution and significantly improving the standardization of the weighted fusion process and the accuracy of the results. This provides a reliable and practical scoring data foundation for subsequent diagnosis and risk warning of land resource and environmental carrying capacity pressure.

[0056] C5. Based on the multidimensional bearing capacity score, the bearing pressure diagnosis of the target area is carried out to obtain the composite risk area of ​​the target area, and the nonlinear stress quantification of the composite risk area is carried out to obtain the degree of coupled overload risk of the composite risk area. In this embodiment of the invention, the step of performing load-bearing pressure diagnosis on the target area based on multi-dimensional load-bearing capacity scoring to obtain the composite risk area of ​​the target area, and performing nonlinear stress quantification on the composite risk area to obtain the coupled overload risk degree of the composite risk area, includes: The multidimensional carrying capacity score and the monitoring and evaluation zone are aggregated in a dimension-reducing manner to obtain the zone carrying capacity score of the monitoring and evaluation zone; Based on the preset bearing capacity baseline and the zoning bearing capacity score, the monitoring and evaluation zoning ... Overload source diagnosis is performed on overloaded zones to obtain the spatial location and overload type of overloaded zones. Based on the spatial location and overload type, the boundaries of overloaded zones are marked to obtain the initial risk area of ​​the target area. The performance parameters of the assessment indicators for the initial risk area are inverted to obtain the actual indicator values. Based on actual indicator values ​​and guiding benchmark values, the initial risk area is determined to obtain the composite risk area of ​​the target area; Contribution analysis is performed on the composite risk region to obtain the overload index deviation and index weight of the composite risk region. The overload index deviation and index weight are then combined with heterogeneous information to obtain the coupled overload risk level of the composite risk region.

[0057] The multidimensional carrying capacity score is precisely linked to the unique geographic code of the monitoring and assessment zone. The multidimensional carrying capacity score is decomposed and allocated according to the proportion of land area of ​​each monitoring and assessment zone in the target area. The decomposed values ​​are normalized and regularized by combining the carrying capacity score sequence values ​​of each monitoring and assessment zone. Invalid values ​​caused by extreme differences in area proportion are eliminated. A single normalized value is matched for each monitoring and assessment zone. The values ​​of this type of all monitoring and assessment zones are integrated to obtain the zone carrying capacity score of the monitoring and assessment zone.

[0058] Figure 3 This is a schematic diagram of the load-bearing capacity benchmark and scoring curve provided in an embodiment of the present invention. Figure 3 The document displays the carrying capacity baseline, scoring curve, and warning line values ​​for ecological functional zones, urban construction zones, agricultural production zones, and general areas. The carrying capacity baseline for ecological functional zones is 84.0 points / day / square kilometer, the scoring curve is 84.0 points / day / square kilometer, and the warning line is 60 points / day / square kilometer; the carrying capacity baseline for urban construction zones is 80.5 points / day / square kilometer, the scoring curve is 79.5 points / day / square kilometer, and the warning line is 60 points / day / square kilometer; the carrying capacity baseline for agricultural production zones is 77.0 points / day / square kilometer, the scoring curve is 76.0 points / day / square kilometer, and the warning line is 60 points / day / square kilometer; the carrying capacity baselines for general areas are 82.0 points / day / square kilometer and 81.0 points / day / square kilometer, respectively, with corresponding scoring curves of 81.0 points / day / square kilometer and 80.0 points / day / square kilometer, and the warning line is uniformly set at 60 points / day / square kilometer. The carrying capacity baselines for each functional zone in the diagram are set based on the land spatial planning control objectives and historical data distribution characteristics. The scoring curves reflect the changing trends of the actual carrying capacity scores of each zone, and the warning lines serve as the critical thresholds for early warning of carrying capacity pressure. By comparing the carrying capacity scores of zones with the corresponding carrying capacity baselines, overloaded zones with scores below the baselines can be intuitively identified, providing a quantitative basis for subsequent overload source tracing and diagnosis, and the determination of complex risk areas. Figure 3 This reflects the differentiated configuration of the load-bearing capacity benchmarks for different functional zones, improving the accuracy and operability of load-bearing pressure diagnosis.

[0059] The carrying capacity baseline is set based on the control objectives of the functional zoning of the national land space planning. It is combined with the stable numerical range of the evaluation indicators of various types of zoning after central measurement and normalization. Different national land planning functional zones correspond to exclusive carrying capacity baseline values. The carrying capacity score of each monitoring and evaluation zone is compared with the carrying capacity baseline of its respective national land planning functional zone. Monitoring and evaluation zones with scores lower than the corresponding baseline values ​​are marked with an overload exclusive label. All monitoring and evaluation zones with overload exclusive labels are integrated to obtain the overloaded zones.

[0060] The unique geographic codes, spatial topological boundaries, and monitoring zone indicator vector data of overloaded zones are extracted. Indicators whose deviation from the guiding benchmark exceeds the stable value range are identified as overload inducing indicators. Overload types are classified according to the spatial utilization, resource and environmental consumption, and ecological quality indicators to which the overload inducing indicators belong. Based on the geographic grid boundary of the overloaded zone, spatial boundary fitting is performed in combination with the actual spatial distribution range of the overload inducing indicators to accurately calibrate the actual impact boundary of the overloaded zone. All overloaded zones with completed boundary calibration are integrated to obtain the initial risk area of ​​the target region.

[0061] Based on the monitoring zoning indicator vector of the initial risk area as the basic data, and combined with the raw data collected by real-time monitoring of land resources and environment, the deviation values ​​of the guiding benchmark of each assessment indicator in the initial risk area are reversed and restored. The normalization correction values ​​added in the previous data processing stage are removed, and the original monitoring values ​​of the indicators are restored. The equipment monitoring range is verified on the restored original monitoring values, and invalid values ​​that exceed the range are removed. The valid original monitoring values ​​after verification are determined as the actual values ​​of the corresponding assessment indicators. All such values ​​of assessment indicators are integrated to obtain the actual indicator values ​​of the assessment indicators.

[0062] The actual values ​​of each assessment indicator within the initial risk area are compared one by one with the corresponding guiding benchmark values. The deviation ratio of the actual indicator value from the guiding benchmark value is calculated. A 50% threshold is preset as the severe deviation judgment threshold. When the deviation ratio of a single indicator reaches or exceeds this threshold, it is judged as a severe deviation indicator. When there are two or more different types of severe deviation indicators within the initial risk area, the initial risk area is judged as a composite risk area. All areas judged as composite risk areas are integrated to obtain the composite risk area of ​​the target area.

[0063] Extract the actual index values ​​and guiding benchmark values ​​of all severely deviated indicators within the composite risk area. Calculate the specific deviation value of each indicator relative to the guiding benchmark value. This value represents the overload index deviation degree of the composite risk area. Simultaneously extract the index weights corresponding to each severely deviated indicator in the dynamic evaluation index matrix. Use the index weights as coefficients to perform weighted aggregation of the deviation degrees of each overload indicator. First, complete the aggregation within each group according to the index category, and then conduct overall aggregation. Normalize the aggregated values ​​and map them to the value range of 0 to 1. The normalized values ​​within this range represent the coupled overload risk degree of the composite risk area. The value is positively correlated with the risk degree. Integrate these values ​​from all composite risk areas to obtain the coupled overload risk degree of the composite risk area.

[0064] The beneficial effects of this implementation process are achieved by using the proportion of land area to complete the dimensionality reduction and aggregation of multi-dimensional carrying capacity scores. This ensures that the zoning carrying capacity scores are highly consistent with the actual carrying capacity status of each monitoring and assessment zone. Differentiated carrying capacity baselines are preset based on functional zoning control targets, providing clear and reproducible quantitative criteria for marking overloaded zones. Overload source diagnosis accurately identifies the spatial location and type of overloaded zones. Initial risk area labeling is completed by combining spatial boundary fitting, ensuring that the spatial range of risk areas matches the actual impact of overload. Performance parameter inversion is performed based on real-time monitoring raw data, restoring the true numerical state of the assessment indicators. Using a specific threshold of 50% for the determination of severe deviation indicators, the identification of complex risk areas has standardized operating rules. By extracting the deviation degree and weight of overload indicators through contribution analysis and completing the coordination of heterogeneous information, the degree of coupled overload risk can accurately reflect the actual contribution difference of each indicator to the complex risk. Each step of the entire process has set clear operating standards, quantitative thresholds and judgment conditions, ensuring the reproducibility of the technical solution, greatly improving the accuracy of load-bearing pressure diagnosis and the scientific nature of complex risk quantification, and providing a practical, accurate and standardized risk data foundation for subsequent risk information structured coding and early warning report generation.

[0065] C6. Structure the risk level of the composite risk area and the degree of coupled overload risk to obtain a risk warning report for the target area.

[0066] In this embodiment of the invention, the step of structurally encoding the composite risk region and the degree of coupled overload risk to obtain a risk warning report for the target region includes: By performing field deconstruction on the complex risk area, the spatial distribution information of the complex risk area can be obtained; By nesting and fusing spatial distribution information with the degree of coupled overload risk, a composite risk information set for the target area is obtained. Based on the degree of coupled overload risk, the composite risk information set is prioritized to obtain the risk information sequence of the composite risk information set. The risk information sequence is semantically encapsulated to obtain a risk warning report for the target area.

[0067] For complex risk areas, extract their unique geographic codes, spatial topological boundaries, monitoring and assessment zoning numbers, corresponding land planning functional zoning types, and spatially adjacent area information. Based on the standardized expression specifications of land spatial basic surveying and mapping, transform the extracted information into standardized text information containing latitude and longitude ranges, administrative affiliation levels, and spatial morphological characteristics. At the same time, mark the spatial boundary markers between each complex risk area and the surrounding normal areas. Integrate this type of standardized text information of all complex risk areas to obtain the spatial distribution information of complex risk areas.

[0068] The spatial distribution information of composite risk areas is accurately associated and matched with the corresponding coupled overload risk level using a unique geocode. The coupled overload risk level value and its corresponding risk interval are marked at the core position of the corresponding spatial distribution information. The associated information is integrated into units according to a fixed hierarchical structure of "spatial basic attributes - risk level value - risk interval division". Each composite risk area corresponds to an independent and complete risk information unit. By integrating the risk information units of all composite risk areas, the composite risk information set of the target area is obtained.

[0069] Based on the technical specifications for risk early warning of land and resources environmental carrying capacity, a three-level classification threshold for coupled overload risk is preset: 0.7 to 1 is the high-risk range, 0.3 to 0.7 is the medium-risk range, and 0 to 0.3 is the low-risk range. The composite risk information set of the target area is first divided into high, medium, and low risk ranges. Within the same risk range, the risk information units are arranged in descending order of the coupled overload risk level. During the arrangement process, all the contents of each risk information unit are completely retained without deletion, forming an ordered risk information arrangement list, and thus obtaining the risk information sequence of the composite risk information set.

[0070] Based on the current standards for compiling early warning reports on land and resources environmental carrying capacity, a standardized structured report template is pre-set. The template includes five fixed modules: risk area overview, risk level classification, spatial distribution characteristics, core causes of overload, and early warning and control recommendations. Each module has clear content filling specifications and expression requirements. The ordered content in the risk information sequence is filled into the template one by one according to the module division requirements. The technical information is standardized and semantically transformed, redundant professional expressions are eliminated and core information is retained. Standardized hierarchical titles and content descriptions are added to each module of the template. All completed and standardized module content is integrated to form a complete text report, resulting in a risk early warning report for the target area.

[0071] The beneficial effects of this implementation process are as follows: Based on the national land space basic surveying and mapping specifications, the process deconstructs the field of complex risk areas, ensuring the standardization and uniformity of spatial distribution information and guaranteeing the comparability of spatial information in different complex risk areas. Through unique geocoding, it achieves precise nesting and fusion of spatial distribution information and coupled overload risk levels, ensuring that each unit of the complex risk information set possesses complete spatial and risk attributes. Pre-defined quantitative thresholds are used to prioritize the risk information set, providing an objective and reproducible basis for the arrangement of risk information sequences and intuitively reflecting differences in risk levels. Semantic encapsulation using pre-defined structured templates according to industry standards ensures that the risk warning report has a clear structure and standardized expression. After removing redundant technical information, it better meets the actual needs of management and decision-making. Every step of the process follows industry technical specifications and sets clear operational standards, improving the standardization and accuracy of risk information structured coding. The generated risk warning report provides clear, comprehensive, and practical information support for risk management and decision-making regarding the carrying capacity of land resources and the environment, achieving a complete technical closed loop from risk area diagnosis to warning report generation.

[0072] like Figure 2 The diagram shown is a functional block diagram of a land resources and environmental carrying capacity monitoring and dynamic assessment early warning system provided in an embodiment of the present invention.

[0073] The land and resources environmental carrying capacity monitoring and dynamic assessment early warning system 100 of this invention can be installed in an electronic device. Depending on the functions implemented, the land and resources environmental carrying capacity monitoring and dynamic assessment early warning system 100 may include a spatial clustering and partitioning module 101, a tensor reconstruction index module 102, a dynamic assessment construction module 103, a carrying capacity scoring module 104, a risk area diagnosis module 105, and an early warning report generation module 106. The module described in this invention can also be called a unit, which refers to 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.

[0074] In this embodiment, the functions of each module / unit are as follows: The spatial clustering and partitioning module 101 is used to perform spatial clustering on the target area based on the spatial utilization data, resource and environmental consumption data and ecological quality data of the target area, so as to obtain the monitoring and evaluation partition of the target area. The tensor reconstruction index module 102 is used to reconstruct spatial utilization data, resource and environmental consumption data, and ecological quality data into tensors within the monitoring and evaluation zone to obtain the monitoring zone index vector of the target area. The dynamic evaluation construction module 103 is used to identify the attributes of the monitoring zone indicator vector based on the preset land planning functional zoning, obtain the indicator orientation type of the monitoring zone indicator vector, and perform state space mapping on the original indicators of the monitoring zone indicator vector based on the indicator orientation type to obtain the dynamic evaluation indicator matrix of the target area. The carrying capacity scoring module 104 is used to perform weighted fusion of the dynamic evaluation index matrix to obtain a multi-dimensional carrying capacity score of the target area. The risk area diagnosis module 105 is used to diagnose the bearing pressure of the target area based on the multi-dimensional bearing capacity score, obtain the composite risk area of ​​the target area, and perform nonlinear stress quantification on the composite risk area to obtain the degree of coupled overload risk of the composite risk area. The early warning report generation module 106 is used to perform structured encoding of the composite risk area and the degree of coupled overload risk to obtain a risk early warning report for the target area.

[0075] 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.

[0076] 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.

[0077] 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.

[0078] 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.

[0079] This application embodiment 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.

[0080] 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 monitoring, dynamic assessment, and early warning of land and resources environmental carrying capacity, characterized in that, The method includes: C1. Based on the spatial utilization data, resource and environmental consumption data, and ecological quality data of the target area, spatial clustering is performed on the target area to obtain the monitoring and evaluation zones of the target area; C2. Within the monitoring and assessment zone, the spatial use data, resource and environmental consumption data, and ecological quality data are reconstructed using tensors to obtain the monitoring zone index vector of the target area. C3. Based on the preset land planning functional zoning, attribute identification is performed on the monitoring zone indicator vector to obtain the indicator orientation type of the monitoring zone indicator vector. Based on the indicator orientation type, state space mapping is performed on the original indicators of the monitoring zone indicator vector to obtain the dynamic evaluation indicator matrix of the target area. C4. Weighted fusion of the dynamic evaluation index matrix yields a multidimensional carrying capacity score for the target area. C5. Based on the multidimensional bearing capacity score, the bearing pressure diagnosis of the target area is carried out to obtain the composite risk area of ​​the target area, and the nonlinear stress quantification of the composite risk area is carried out to obtain the degree of coupled overload risk of the composite risk area. C6. Structure the risk level of the composite risk area and the degree of coupled overload risk to obtain a risk warning report for the target area.

2. The method for monitoring and dynamic assessment and early warning of land and resources environmental carrying capacity as described in claim 1, characterized in that, Based on spatial utilization data, resource and environmental consumption data, and ecological quality data of the target area, spatial clustering is performed on the target area to obtain monitoring and evaluation zones for the target area, including: Acquire spatial utilization data, resource and environmental consumption data, and ecological quality data for the target area; The target area is spatially divided to obtain a geographic grid of the target area; Based on spatial utilization data, resource and environmental consumption data, and ecological quality data, feature embedding is performed on geographic grids to obtain a set of grid feature vectors for the target area. Correlation analysis is performed on the grid feature vector pairs in the grid feature vector set to obtain the correlation strength of the grid feature vector pairs; Based on the correlation strength, the geographic grid is hierarchically reorganized to obtain the monitoring and evaluation zones of the target area.

3. The method for monitoring and dynamic assessment and early warning of land and resources environmental carrying capacity as described in claim 1, characterized in that, Within the monitoring and assessment zone, spatial use data, resource and environmental consumption data, and ecological quality data are reconstructed using tensors to obtain the monitoring zone indicator vector for the target area, including: Using the monitoring and assessment zones as spatial indexes, spatial utilization data, resource and environmental consumption data, and ecological quality data are mapped to the monitoring and assessment zones respectively, thus constructing a zoned dataset for the monitoring and assessment zones. The dimensionality of the partitioned dataset is transformed to obtain a multidimensional data tensor for the monitoring and evaluation partitions; Metadata parsing is performed on multidimensional data tensors to obtain the data type of the multidimensional data tensors; Based on data type, category fusion is performed on multidimensional data tensors to obtain data type aggregation vectors for monitoring and evaluation partitions; Variational inference is performed on the aggregated vector of data types to obtain the monitoring zoning indicator vector of the target area.

4. The method for monitoring, dynamic assessment, and early warning of land and resources environmental carrying capacity as described in claim 1, characterized in that, The method involves identifying the attributes of the monitoring zone indicator vectors based on preset land planning functional zoning, obtaining the indicator orientation type of the monitoring zone indicator vectors, and performing state-space mapping on the original indicators of the monitoring zone indicator vectors based on the indicator orientation type to obtain the dynamic evaluation indicator matrix of the target area, including: By associating and matching the preset land planning functional zones with the monitoring zone indicator vectors, the land planning functional zone type of the monitoring and evaluation zone is obtained; Based on the functional zoning type of land planning, the original indicators of the monitoring zone indicator vector are guided and calibrated to obtain the indicator guidance type of the monitoring zone indicator vector; Based on the monitoring zoning indicator vector, the guiding parameters of the land planning functional zoning are fitted to obtain the guiding benchmark value of the monitoring zoning indicator vector; Based on the guiding benchmark value, the covariance reduction of the original indicators in the monitoring zone indicator vector is performed to obtain the guiding benchmark deviation of the monitoring zone indicator vector. Spatial topological reconstruction of the guideline deviation is performed to obtain the dynamic evaluation index matrix of the target area.

5. The method for monitoring, dynamic assessment, and early warning of land and resources environmental carrying capacity as described in claim 4, characterized in that, The process of fitting guidance parameters to the land planning functional zones based on the monitoring zoning indicator vectors to obtain the guidance benchmark values ​​of the monitoring zoning indicator vectors includes: The gridded feature vector of the monitoring zone index vector is obtained by performing gridded projection on the monitoring zone index vector. Based on the functional zoning type of land planning, the grid feature vectors are categorized to obtain a feature vector sample set for the functional zoning type of land planning. Density estimation is performed on the feature vector sample set to obtain the historical distribution characteristics of the indicators in the feature vector sample set. Based on the historical distribution characteristics of the indicators, tolerance analysis is performed on the evaluation indicators under the functional zoning type of land planning to obtain the stable numerical range of the evaluation indicators. The centrality of the stable numerical interval is measured to obtain the distribution center value of the stable numerical interval, and the distribution center value is used as the candidate value of the guiding benchmark for the evaluation index under the functional zoning type of land planning. The guide benchmark candidate values ​​are associated and bound with the evaluation indicators of the monitoring and evaluation zones to obtain the guide benchmark values ​​of the monitoring zone indicator vector.

6. The method for monitoring and dynamic assessment and early warning of land and resources environmental carrying capacity as described in claim 1, characterized in that, The weighted fusion of the dynamic evaluation index matrix yields a multi-dimensional carrying capacity score for the target area, including: Entropy weight deconstruction is performed on the dynamic evaluation index matrix to obtain the monitoring zone index weights of the dynamic evaluation index matrix. The monitoring and evaluation zones in the dynamic evaluation index matrix are synthesized into comprehensive indices to obtain the evaluation indicators for the monitoring and evaluation zones. The carrying capacity score of the monitoring zone is obtained by accumulating the weights of the monitoring zone indicators and the evaluation indicators into a dynamic evaluation indicator matrix. Based on the spatial layout of the monitoring zones according to the dynamic evaluation index matrix, the carrying capacity scores of the monitoring zones are serialized and arranged to obtain the carrying capacity score sequence of the dynamic evaluation index matrix. By co-converging the carrying capacity score sequences, a multidimensional carrying capacity score for the target area is obtained.

7. The method for monitoring and dynamic assessment and early warning of land and resources environmental carrying capacity as described in claim 6, characterized in that, The calculation formula for the multidimensional bearing capacity score is as follows: ; In the formula, For multi-dimensional load-bearing capacity scoring, The serial number of the monitoring and evaluation zone. To monitor and evaluate the serial numbers of the evaluation indicators in the designated zones, For the dynamic evaluation index matrix, the first The partition weights of each monitoring and evaluation partition. To monitor and evaluate the total number of zones, To monitor and evaluate the total number of evaluation indicators within the zoning area, For the dynamic evaluation index matrix, the first The first monitoring and assessment zone The weight of each evaluation indicator, For the dynamic evaluation index matrix, the first The first monitoring and assessment zone The values ​​of each evaluation indicator.

8. The method for monitoring and dynamic assessment and early warning of land and resources environmental carrying capacity as described in claim 4, characterized in that, The method of performing bearing pressure diagnosis on the target area based on multidimensional bearing capacity scoring to obtain the composite risk area of ​​the target area, and performing nonlinear stress quantification on the composite risk area to obtain the coupled overload risk degree of the composite risk area, including: The multidimensional carrying capacity score and the monitoring and evaluation zone are aggregated in a dimension-reducing manner to obtain the zone carrying capacity score of the monitoring and evaluation zone; Based on the preset bearing capacity baseline and the zoning bearing capacity score, the monitoring and evaluation zoning ... Overload source diagnosis is performed on overloaded zones to obtain the spatial location and overload type of overloaded zones. Based on the spatial location and overload type, the boundaries of overloaded zones are marked to obtain the initial risk area of ​​the target area. The performance parameters of the assessment indicators for the initial risk area are inverted to obtain the actual indicator values. Based on actual indicator values ​​and guiding benchmark values, the initial risk area is determined to obtain the composite risk area of ​​the target area; The contribution of the composite risk region is analyzed to obtain the deviation of the overload index and the index weight of the composite risk region. The deviation of the overload index and the index weight are combined with heterogeneous information to obtain the degree of coupled overload risk of the composite risk region.

9. The method for monitoring and dynamic assessment and early warning of land and resources environmental carrying capacity as described in claim 1, characterized in that, The structured coding of the composite risk area and the degree of coupled overload risk yields a risk warning report for the target area, including: By performing field deconstruction on the complex risk area, the spatial distribution information of the complex risk area can be obtained; By nesting and fusing spatial distribution information with the degree of coupled overload risk, a composite risk information set for the target area is obtained. Based on the degree of coupled overload risk, the composite risk information set is prioritized to obtain the risk information sequence of the composite risk information set. The risk information sequence is semantically encapsulated to obtain a risk warning report for the target area.

10. A monitoring and dynamic assessment early warning system for land and resources environmental carrying capacity, characterized in that, The system for implementing the land and resources environmental carrying capacity monitoring, dynamic assessment and early warning method as described in claim 1, comprises: The spatial clustering and partitioning module is used to perform spatial clustering on the target area based on spatial utilization data, resource and environmental consumption data, and ecological quality data, so as to obtain the monitoring and evaluation partitions of the target area. The tensor reconstruction index module is used to reconstruct spatial utilization data, resource and environmental consumption data, and ecological quality data within the monitoring and evaluation zone, so as to obtain the monitoring zone index vector of the target area. The dynamic evaluation construction module is used to identify the attributes of the monitoring zone indicator vectors based on the preset land planning functional zoning, obtain the indicator orientation type of the monitoring zone indicator vectors, and perform state space mapping on the original indicators of the monitoring zone indicator vectors based on the indicator orientation type to obtain the dynamic evaluation indicator matrix of the target area. The carrying capacity scoring module is used to perform weighted fusion of the dynamic evaluation index matrix to obtain a multi-dimensional carrying capacity score for the target area. The risk area diagnosis module is used to diagnose the bearing pressure of the target area based on multi-dimensional bearing capacity scoring, obtain the composite risk area of ​​the target area, and perform nonlinear stress quantification on the composite risk area to obtain the degree of coupled overload risk of the composite risk area. The early warning report generation module is used to perform structured coding of composite risk areas and coupled overload risk levels to obtain risk early warning reports for the target area.

Images