Global land comprehensive improvement coupling evaluation and decision optimization method and system, medium and product

Abstract

The invention discloses a global land comprehensive improvement coupling evaluation and decision optimization method and system, a medium and a product, and relates to the field of land improvement evaluation. The method comprises the following steps: extracting first data of each suitability index from basic data of global land comprehensive improvement to obtain an improvement suitability index; calculating the change rate of each benefit index according to the second data before renovation and the third data after renovation so as to obtain a renovation benefit index; the coupling coordination degree of the target geographic unit is calculated based on the improvement suitability index and the improvement benefit index, and when the target geographic unit needs to be optimized, a differential improvement optimization strategy for the target geographic unit is matched and generated from a preset strategy knowledge base according to the coupling mismatch type to which the target geographic unit belongs; and generating a resource allocation scheme with the expected comprehensive benefit maximization under the renovation resource constraint condition input by the user. By implementing the technical scheme, the suitability and the benefit of global land comprehensive improvement can be scientifically evaluated.

Description

Technical Field

[0001] This application relates to the field of land consolidation evaluation, and in particular to a method, system, medium, and product for coupled evaluation and decision optimization of comprehensive land consolidation across the entire region. Background Technology

[0002] With rapid socio-economic development and accelerated urbanization, the rational utilization and management of land resources have become key factors in ensuring sustainable development. Comprehensive land consolidation, as a systematic land governance approach, aims to integrate various land resources, improve land use efficiency, enhance the ecological environment, and promote coordinated urban-rural development.

[0003] In existing technologies, the evaluation of the effectiveness of comprehensive land consolidation and decision-making mainly rely on single data sources and traditional evaluation methods. On the one hand, some evaluations are based on only a single type of data, such as geospatial data or ecological environment data, which is insufficient to comprehensively reflect the actual situation of comprehensive land consolidation. This limitation of a single data source makes the evaluation results inaccurate and incomplete, failing to provide sufficient basis for decision-making. On the other hand, traditional evaluation methods often focus on subjective judgment or single mathematical models, lacking comprehensive consideration of multiple factors. For example, relying solely on the analytic hierarchy process (AHP) for weight determination is easily influenced by human factors, leading to questions about the objectivity and scientific validity of the evaluation results.

[0004] Therefore, there is an urgent need for a more scientific and comprehensive evaluation and decision-making optimization method to improve the quality and efficiency of comprehensive land consolidation across the entire region. Summary of the Invention

[0005] This application provides a method, system, medium, and product for integrated land consolidation coupled evaluation and decision optimization, which can scientifically assess the suitability and benefits of integrated land consolidation, rationally determine the degree of coupling coordination, accurately generate differentiated consolidation optimization strategies, and achieve rational resource allocation to maximize expected comprehensive benefits.

[0006] Firstly, this application provides a method for coupled evaluation and decision optimization of comprehensive land consolidation across an entire region, the method comprising: Collect and integrate multi-source heterogeneous data from comprehensive land consolidation across the entire region to obtain basic data. The multi-source heterogeneous data includes remote sensing data, geospatial data, and ecological environment data. First data for each suitability indicator is extracted from the basic data. First weights for each suitability indicator are determined by a combined evaluation method combining the analytic hierarchy process and the entropy weight method. The remediation suitability index of the target geographic unit is obtained by weighted summation of the first data and the first weights. The second data and the third data of each benefit indicator before the remediation are extracted from the basic data. The change rate of each benefit indicator is calculated based on the second data and the third data. The second weight of each change rate is determined by the combined evaluation method. The remediation benefit index of the target geographical unit is obtained by weighted summation of the change rate and the second weight. The coupling coordination degree of the target geographic unit is calculated based on the remediation suitability index and the remediation benefit index, and whether the target geographic unit needs optimization is determined based on the remediation suitability index, the remediation benefit index, and the coupling coordination degree. When the target geographic unit needs optimization, a differentiated remediation and optimization strategy is generated from a preset strategy knowledge base based on the coupling mismatch type to which the target geographic unit belongs. In response to the user-inputted constraints on remediation resources, based on the differentiated remediation optimization strategy, the remediation priorities of multiple target geographical units within the target area are ranked, and a resource allocation scheme that maximizes the expected comprehensive benefits under the constraints is generated.

[0007] By employing the aforementioned technical solution, multi-source heterogeneous data from remote sensing, geospatial data, and ecological environment data are integrated. A scientific weighting method combining the analytic hierarchy process (AHP) and entropy weighting is used to calculate the suitability index and the effectiveness index for remediation, achieving a quantitative transformation from data to evaluation indicators and enhancing the objectivity and scientific rigor of the evaluation. Based on the coupling coordination degree calculated from the suitability index and the effectiveness index, the degree of matching between the two is identified, classifying remediation areas into types such as high suitability and high effectiveness, high suitability and low effectiveness, low suitability and high effectiveness, and low suitability and low effectiveness. This reveals the intrinsic relationship between remediation input and output, providing a basis for accurate diagnosis. Based on the automatic matching strategy knowledge base for coupling mismatch types, differentiated remediation optimization strategies are generated, achieving precise intervention with a "one-size-fits-all" approach, avoiding "one-size-fits-all" decisions, and improving the pertinence and effectiveness of remediation measures. After the user inputs resource constraints, the system can prioritize multiple geographical units for remediation, generating a resource allocation scheme that maximizes expected comprehensive benefits. This assists decision-makers in achieving optimal remediation benefits with limited resources, enhancing the systematic nature and operability of decision-making.

[0008] In some embodiments, the first weight of each of the suitability indicators is determined by the following formula: ; in, Indicates the first t The first evaluation cycle v The first weight of the suitability index, This represents the first generation obtained after processing by the analytic hierarchy process. t The first evaluation cycle vSubjective weights of suitability indicators This represents the first value obtained after processing with the entropy weight method. t The first evaluation cycle v The objective weight of each suitability indicator This represents the subjective weighting coefficient. ∈[0,1]; The second weight of each of the aforementioned rates of change is determined by the following formula: ; in, Indicates the first t The first evaluation cycle u The second weight of the rate of change of the term, This represents the first generation obtained after processing by the analytic hierarchy process. t The first evaluation cycle u Subjective weighting of the rate of change of the item This represents the first value obtained after processing with the entropy weight method. t The first evaluation cycle u Objective weight of the rate of change of the item This represents the subjective weighting coefficient. ∈[0,1].

[0009] By adopting the above technical solution, and introducing adjustable subjective weight coefficients, the subjective weights of the analytic hierarchy process (AHP) (reflecting expert experience) and the objective weights of the entropy weight method (reflecting data differences) are weighted and combined. This approach respects professional judgment while relying on data facts, avoiding the one-sidedness of a single weighting method. The change rates of suitability and benefit indicators use the same weighting fusion framework, ensuring methodological consistency between the two types of evaluations and facilitating the subsequent calculation and interpretation of coupling coordination. The weight calculation formula is explicitly linked to the "t-th evaluation period," indicating that the weights can be periodically updated over time, with data accumulation, or changes in policy orientation. This gives the evaluation system dynamic evolution capabilities, making it more aligned with actual management needs.

[0010] In some embodiments, calculating the coupling coordination degree of the target geographic unit based on the remediation suitability index and the remediation benefit index includes: The coupling coordination degree of the target geographic unit is calculated using the following formula: ; in, D Indicates the degree of coupling coordination. C Indicates the degree of coupling. T Indicates the comprehensive coordination index; The coupling degree is calculated using the following formula: ; in, SI Indicates the suitability index for remediation. BI Indicates the effectiveness index of the rectification efforts; The comprehensive coordination index is calculated using the following formula: T = α × SI + β × BI; Where α and β represent dynamic weighting coefficients; The suitability index for remediation is calculated using the following formula: ; in,( S v , t ) indicates the first t The first evaluation cycle v Suitableness indicators; The remediation benefit index is calculated using the following formula: ; in,( B u , t ) indicates the first t The first evaluation cycle u Rate of change of the item.

[0011] By employing the aforementioned technical solution, a multi-level computational framework comprising coupling degree, comprehensive coordination index, and final coupling coordination degree is constructed. This elevates the evaluation of suitability and benefits from simple numerical comparisons to a systematic assessment capable of quantifying the intensity of their interaction and coordination level. The coupling degree formula specifically measures the interaction intensity of two indicators, identifying their matching states (e.g., high matching, low matching, imbalance), providing direct evidence for analyzing whether a remediation project has achieved its intended benefits in a suitable location. The comprehensive coordination index formula allows for dynamic adjustment of the emphasis on suitability and benefits through weighted coefficients, enabling flexible configuration of the assessment according to different stage objectives (e.g., ecological priority, benefit priority), enhancing the targeted nature of decision-making. From the weighted summation of bottom-level indicators to the measurement of intermediate relationships, and finally to the synthesis of the final coordination degree, the model forms a rigorous, hierarchically integrated quantitative analysis path, ensuring that the evaluation results have clear mathematical logic and interpretability, facilitating their application to subsequent optimization decisions.

[0012] In some embodiments, before matching and generating differentiated remediation and optimization strategies for the target geographic unit from a preset strategy knowledge base based on the coupling mismatch type to which the target geographic unit belongs, the method further includes pushing cases based on the remediation suitability index, the remediation benefit index, and the coupling coordination degree, specifically including: Multiple feature attributes of the target geographic unit are obtained, and a target feature vector is constructed. The feature attributes include the remediation suitability index, the remediation benefit index, the coupling coordination degree, and the baseline indicators in the ecological dimension extracted from the basic data. Calculate the comprehensive similarity between the target feature vector and the feature vectors of historical cases in the preset strategy knowledge base; Based on the comprehensive similarity, a preset number of historical cases with the highest similarity are selected from the strategy knowledge base as recommended cases and pushed to the system, so that the recommended cases and associated historical remediation strategies can serve as a reference for generating differentiated remediation and optimization strategies for the target geographical unit.

[0013] By employing the aforementioned technical solution, a target vector comprising multi-dimensional features (suitability, effectiveness, coupling coordination, and ecological baseline indicators) is constructed, and its similarity to historical cases is calculated. This enables intelligent matching of the most relevant reference cases from past experience, transforming discrete historical data into a systematic decision-making knowledge base. The recommended cases and their associated historical remediation strategies provide a practically validated reference for differentiated remediation of the current target geographical unit. This ensures that the generated optimization strategies are not merely theoretical deductions, but are based on successful or unsuccessful experiences in similar situations, significantly improving the targeting of strategies and the credibility of decisions. The comprehensive similarity calculation not only considers core indicators of remediation effectiveness but also incorporates inherent attributes such as ecological baseline, ensuring that matched cases are comparable across multiple dimensions, including natural conditions, remediation potential, and performance, avoiding misleading recommendations due to similarity in only one aspect.

[0014] In some embodiments, calculating the comprehensive similarity between the target feature vector and the feature vectors of historical cases in a preset strategy knowledge base includes: The overall similarity is calculated using the following formula: ; in, X Represents the target feature vector. Y The feature vector representing historical cases, x j Represents the first in the target feature vector j One attribute, y j Represents the th element in the eigenvector. j One attribute, Sim ( X , Y The expression represents the comprehensive similarity between the target feature vector and the feature vector. w j Indicates the first j The weight of each attribute, d ( x j , y j ) represents the target feature vector and the feature vector at the th digit.j Normalized Euclidean distance on each attribute, where M is the total number of feature attributes; The target feature vector and the feature vector at the th moment are calculated using the following formula. j Normalized Euclidean distance over each attribute: ; in, max ( y j () indicates that all historical cases in the strategy knowledge base are in the first... j The maximum value of each attribute min ( y j () indicates that all historical cases in the strategy knowledge base are in the first... j The minimum value across all attributes.

[0015] By adopting the above technical solution, the formula introduces weighting coefficients, allowing for differentiated processing of the importance of different characteristic attributes (such as suitability index, benefit index, and ecological baseline indicators), making similarity calculation more aligned with actual decision-making needs, rather than a simple equal-weighted average. Through the normalized Euclidean distance formula, all attribute values ​​are mapped to the [0, 1] interval, effectively eliminating the bias caused by differences in units, scales, or numerical ranges of different attributes in similarity calculation, ensuring the fairness and accuracy of cross-attribute comparisons. The comprehensive similarity formula, based on a weighted sum of distances, directly reflects the degree of similarity (the larger the value, the more similar), making it not only computationally efficient but also possessing intuitive mathematical and physical meaning, facilitating decision-makers' understanding of the matching logic.

[0016] In some embodiments, the step of matching and generating differentiated remediation and optimization strategies for the target geographic unit from a preset strategy knowledge base based on the coupling mismatch type to which the target geographic unit belongs includes: Based on the remediation suitability index, the remediation efficiency index, and the coupling coordination degree, the target geographical unit is divided into at least one of the following coupling mismatch types through a preset threshold rule: high suitability-low efficiency potential unreleased area, low suitability-high efficiency over-performance area, and low suitability-low efficiency inefficient area. Based on the determined coupling mismatch type, all associated primary remediation strategies are selected from the strategy knowledge base to form a first strategy set; The historical rectification strategies are matched and weighted with the first set of strategies to form a second set of strategies, wherein the similarity of the recommended cases is used as the fusion weight of the associated historical rectification strategies. The strategies in the second strategy set are adjusted based on the real-time natural background conditions of the target geographic unit extracted from the basic data to generate the differentiated remediation and optimization strategy.

[0017] By employing the aforementioned technical solution, the remediation units are finely categorized through preset threshold rules (such as high suitability-low efficiency, low suitability-high efficiency, and low suitability-low efficiency). This allows strategy matching to directly target specific "causes" (coupling mismatch types), achieving precise intervention with a "one-policy-per-category" approach, significantly improving the strategy's relevance. A first set of primary strategies is selected from the strategy knowledge base, and then weighted and fused with historical strategies from recommended cases to form a second set. This ensures both the theoretical foundation and systematic nature of the strategies while incorporating empirically tested wisdom, resulting in strategies that are both standardized and effective. The similarity of recommended cases is used as the fusion weight for historical remediation strategies, ensuring that the more similar a case is to the current situation, the greater its associated strategy's contribution to the final optimized strategy. This mechanism enables the strategy generation process to have adaptive learning capabilities, rather than simply piling up rules. Before the final strategy is generated, a secondary adjustment is made based on the real-time natural background conditions of the target units extracted from the basic data (such as soil, hydrology, and vegetation status). This ensures that the recommended strategies not only meet the typological requirements but also adapt to the specific and dynamic natural constraints of the local area, improving the feasibility of strategy implementation.

[0018] In some embodiments, the step of filtering all associated primary remediation strategies from the strategy knowledge base to form a first strategy set based on the determined coupling mismatch type specifically includes: Based on the coupling mismatch type, one or more remediation failure modes are matched in the preset strategy failure mode library. Starting from the matched remediation failure mode, all remediation strategy nodes marked as avoiding the remediation failure mode are retrieved in the remediation strategy knowledge graph constructed in the strategy knowledge base, thus forming a basic set of risk resistance strategies. For each strategy in the aforementioned risk mitigation strategy base set, a secondary failure chain derived from external interference or internal execution deviation during implementation is simulated. A risk propagation model trained using historical case data is used to quantify and extrapolate the probability of the occurrence of the secondary failure chain and the estimated negative impact on the remediation benefit index, and the comprehensive risk exposure value of each strategy is calculated. Obtain the average benefit improvement data of each strategy in the historical application of the risk resistance strategy base set as the benchmark return expectation, construct a risk-return trade-off function, and calculate the comprehensive risk exposure value and the benchmark return expectation to obtain the initial screening priority score of each strategy. The strategies are sorted according to the initial screening priority score, and a preset number of top-ranked strategies are selected to form the first strategy set.

[0019] Using the aforementioned technical solution, starting with the matched "failure mode," all strategy nodes aimed at avoiding that failure mode are retrieved backwards from the strategy knowledge graph, forming a "basic set of risk-resistant strategies." This problem (failure)-oriented screening logic upgrades the strategy library's invocation from simple "functional matching" to "risk prevention," embedding proactive risk management thinking from the initial stage of strategy generation. A risk propagation model simulates secondary failure chains for each strategy, quantifies their probability of occurrence and the degree of negative impact, and calculates the comprehensive risk exposure value. This breaks through the limitations of traditional strategy evaluation, which only considers expected returns or static risks, and can proactively identify dynamic and cascading risks that may arise during strategy execution, greatly enhancing the depth and predictability of strategy robustness assessment.

[0020] In a second aspect, embodiments of this application provide a computer system including a memory, a processor, and a computer program stored in the memory; the processor executes the computer program to implement the steps of the method described in any possible implementation of the first aspect.

[0021] Thirdly, embodiments of this application provide a computer-readable storage medium having a computer program / instructions stored thereon, which, when executed by a processor, implement the steps of the method described in any possible implementation of the first aspect.

[0022] Fourthly, embodiments of this application provide a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the method described in any possible implementation of the first aspect.

[0023] It is understood that the computer system provided in the second aspect, the storage medium provided in the third aspect, and the computer program product provided in the fourth aspect are all used to execute the method provided in this application. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. By integrating heterogeneous data from multiple sources, including remote sensing, geospatial data, and ecological environment data, a unified and reliable basic data foundation is formed, solving the problems of scattered data sources and inconsistent standards in traditional evaluations. Geographic units are scientifically and quantitatively evaluated from two dimensions—"remediation potential" and "remediation effect"—using both remediation suitability index and remediation benefit index, making the evaluation results more comparable and interpretable. 2. Based on the coupling mismatch type, the system automatically matches the strategy knowledge base to generate differentiated governance strategies for each type, avoiding "one-size-fits-all" decisions and improving the pertinence and effectiveness of measures. Through similarity calculation, the system pushes historical similar cases and their strategies to provide experience reference for current decisions, realize knowledge accumulation and intelligent reuse, and supports user input of resource constraints. The system automatically prioritizes multiple geographical units and generates a resource allocation plan that maximizes expected comprehensive benefits, assisting decision-makers in making the best choice with limited resources. 3. The system adopts a combined weighting method that combines the analytic hierarchy process (AHP) and the entropy weighting method, taking into account both expert experience and data objectivity. The weights can be dynamically adjusted with the evaluation cycle to enhance adaptability. The system provides interactive functions such as scenario simulation, dynamic parameter adjustment, and case push, enabling decision-makers to actively participate in strategy formulation and improve the transparency and participation of the decision-making process. Attached Figure Description

[0025] Figure 1 This is a flowchart illustrating the method for coupled evaluation and decision optimization of comprehensive land consolidation in this application embodiment; Figure 2 This is a schematic diagram of the architecture of the integrated land consolidation coupled evaluation and decision optimization system in this application embodiment; Figure 3 This is a schematic diagram of an exemplary hardware structure of a computer system in an embodiment of this application. Detailed Implementation

[0026] The terminology used in the following embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. As used in the specification and appended claims of this application, the singular expressions “a,” “an,” “the,” “the,” “the,” and “this” are intended to include the plural expressions as well, unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used in this application refers to any or all possible combinations including one or more of the listed items.

[0027] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as implying or suggesting relative importance or implicitly indicating the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature, and in the description of the embodiments of this application, unless otherwise stated, "multiple" means two or more.

[0028] The following is combined Figure 1 The method of the embodiments of this application will be described below.

[0029] Figure 1This is a flowchart illustrating the coupled evaluation and decision optimization method for comprehensive land consolidation in this application embodiment, as shown below. Figure 1 As shown, the method includes the following steps: S101. Collect and integrate multi-source heterogeneous data from comprehensive land consolidation across the entire region to obtain basic data. The multi-source heterogeneous data includes remote sensing data, geospatial data, and ecological environment data. S102. Extract the first data of each suitability indicator from the basic data, determine the first weight of each suitability indicator by a combined evaluation method combining the analytic hierarchy process and the entropy weight method, and obtain the remediation suitability index of the target geographical unit by performing a weighted summation operation on the first data and the first weight. S103. Extract the second data of each benefit indicator before the remediation and the third data after the remediation from the basic data. Calculate the rate of change of each benefit indicator based on the second data and the third data. Determine the second weight of each rate of change through the combined evaluation method. Obtain the remediation benefit index of the target geographical unit by performing a weighted summation operation on the rate of change and the second weight. S104. Calculate the coupling coordination degree of the target geographic unit based on the remediation suitability index and the remediation benefit index, and determine whether the target geographic unit needs optimization based on the remediation suitability index, the remediation benefit index, and the coupling coordination degree. S105. When the target geographic unit needs to be optimized, a differentiated remediation and optimization strategy for the target geographic unit is generated by matching from a preset strategy knowledge base according to the coupling mismatch type to which the target geographic unit belongs. S106. In response to the user-inputted resource constraints, based on the differentiated remediation optimization strategy, prioritize the remediation of multiple target geographical units within the target area, and generate a resource allocation scheme that maximizes the expected comprehensive benefits under the constraints.

[0030] Figure 2 This is a schematic diagram of the architecture of the integrated land consolidation coupled evaluation and decision optimization system in this application embodiment, as shown below. Figure 2 As shown, the system includes a multi-source data fusion module, a coupled evaluation module, and an optimization decision-making module connected in sequence. The multi-source data fusion module is used to collect and fuse multi-source heterogeneous data related to comprehensive land consolidation across the entire region, constructing a data base with unified spatiotemporal benchmarks and semantic associations. The coupled evaluation module is used to construct and calculate suitability and benefit indices based on the data base, and analyze their matching relationship through a coupled coordination degree model. The optimization decision-making module is used to visualize the coupled evaluation results and provide interactive decision support for users.

[0031] The following is combined Figure 2The embodiments of this application will be described.

[0032] The multi-source data fusion module comprises a data access layer, a cleaning and governance layer, a fusion processing layer, and an application interface layer. The application interface layer provides standardized data access interfaces, supporting data interaction between different modules. The data access layer integrates various types of data from different departments (natural resources, agriculture and rural areas, ecological environment, etc.) and different time periods (before planning, during implementation, and after remediation) through distributed acquisition technology. This primarily includes remote sensing data, geospatial data, ecological environment data, and socioeconomic data. Remote sensing data, such as satellite imagery and UAV oblique photography data, is used to monitor land cover changes and project progress. Geospatial data, such as 3D reality models, topography, and land use change survey data, is used to analyze spatial patterns and natural baselines. Ecological environment data, such as soil quality, vegetation cover, biodiversity, and hydrological conditions data, is used to assess ecological status and sensitivity. Socioeconomic data, such as population distribution, industrial layout, and infrastructure data, is used to analyze socioeconomic benefits. The cleaning and governance layer standardizes multi-source heterogeneous data, unifying data formats (such as GeoJSON), eliminating data contradictions, filling missing values, removing outliers, and performing unified spatiotemporal benchmark conversion. The fusion processing layer employs deep learning and other methods to perform spatiotemporal alignment and semantic association of multi-source data, establishing a dynamic database covering the entire chain of planning, implementation, acceptance, and maintenance, forming a knowledge graph for remediation that can be analyzed and queried. From the fused basic data, data required to construct a suitability evaluation index system is extracted. This system encompasses multiple dimensions, including natural, economic, social, and ecological dimensions. Natural dimensions: topography slope, soil fertility, and climate conditions. Economic dimensions: land value, current utilization efficiency, and location conditions. Social dimensions: population density and infrastructure accessibility. Ecological dimensions: ecological sensitivity and ecosystem service value. The remediation suitability index (SI) is calculated through the suitability evaluation submodule within the coupled evaluation module, and the remediation benefit index (BI) is calculated through the benefit evaluation submodule. A combined weighting method, combining the analytic hierarchy process (AHP, reflecting expert subjective judgment) and the entropy weighting method (reflecting objective data differences), is used to determine the importance (weight) of each indicator in the evaluation. This process is not fixed and can be dynamically adjusted with the evaluation cycle or data updates. After standardizing the values ​​of each indicator in each unit, a weighted sum is calculated based on their corresponding weights to obtain the unit's suitability index for remediation. A higher SI value indicates that the unit's natural and socio-economic conditions are more suitable for priority remediation. Benefit indicators are extracted from the basic data for both before remediation (second data) and after remediation (or the expected target value, i.e., third data). These indicators are also multi-dimensional, including economic, social, and ecological benefits. Economic benefits include: land output rate, increase in farmers' income, and changes in land transfer revenue. Social benefits include: improvement in the living environment, coverage of public service facilities, and public satisfaction. Ecological benefits include: vegetation cover change rate, improvement in soil and water conservation capacity, and increase in carbon sequestration.For each benefit indicator, the rate of change (the magnitude of change) from before to after the remediation is calculated to quantify the direct impact of the remediation action. Similar to the steps above, the AHP-entropy weight combination method is used to determine the weights of each benefit rate of change. Then, the remediation benefit index of the unit is calculated by weighted summation. The higher the BI value, the more significant the comprehensive benefits brought by the remediation. Based on the calculated SI and BI values, the coupling coordination degree model (composed of coupling degree and comprehensive coordination index) is used to calculate the coupling coordination degree (D) of the unit. The D value reflects the level of mutual promotion and coordinated development between suitability and benefit. According to the preset threshold rules, combined with the SI, BI, and D values, the geographical units are divided into different types, for example: High suitability-high benefit (high-quality area): no optimization required. High suitability-low benefit (unreleased potential area): optimization is required, and there may be problems with project management and post-maintenance. Low suitability-high benefit (extraordinary performance area): attention is required, experience should be summarized but promotion should be cautious. Low suitability-low benefit (inefficient area): optimization or even reassessment of the necessity of remediation is required. By optimizing the visualization rendering layer of the decision-making module, the system visually displays suitability zones, benefit zones, and coupling coordination zones on a 3D reality map using different colors (e.g., green for high-quality areas, yellow for areas with exceptional performance, orange for areas with untapped potential, and red for inefficient areas) and symbols (e.g., stars for high-efficiency areas and triangles for low-efficiency areas). The 3D map construction is based on UAV oblique photogrammetry and 5G communication technology, supporting high-precision and high-efficiency 3D visualization, enabling decision-makers to clearly identify different area types, reducing decision identification time by 40% compared to traditional methods. The interactive service layer provides scenario simulation functionality, allowing users to adjust the weights of suitability or benefit evaluation indicators through a RESTful API interface and dynamically view changes in coupling results. It also provides a case study push function, calculating regional similarity based on the KNN algorithm combined with multi-dimensional indicators such as SI, BI, and D values, and pushing similar successful or failed cases for reference. The system automatically determines whether a geographic unit needs optimization and what type of optimization is required based on the classification type (especially the latter three mismatch types). Based on the determined coupling mismatch type (e.g., high suitability - low efficiency), it links to a preset strategy knowledge base. The system simultaneously calculates the similarity between the current unit and cases in the historical case library, and pushes the historical case with the highest similarity and its implemented strategies as important references. Based on the coupling analysis results, the decision support layer automatically generates optimization suggestions. Combining general strategy rules in the strategy knowledge base and the historical practical experience of the pushed cases, and considering the real-time natural background conditions of the target unit (such as current soil moisture and vegetation status), the system filters, integrates, and localizes strategies, ultimately generating differentiated remediation optimization strategies for that specific unit. For example, for "untapped potential areas," it might suggest "strengthening project supervision and fund auditing." Users (decision-makers) input overall or specific remediation resource constraints (such as total investment limits and annual remediation area targets).Based on the differentiated optimization strategies generated for each target unit and their expected benefit improvement potential, combined with resource cost estimation, the system comprehensively ranks all geographical units requiring remediation and determines the priority order of implementation. Under the resource constraints input by the user, the system simulates different resource allocation schemes to automatically generate the optimal resource allocation scheme with the goal of maximizing the expected comprehensive benefits within the target area.

[0033] In some embodiments, the first weight of each of the suitability indicators is determined by the following formula: ; in, Indicates the first t The first evaluation cycle v The first weight of the suitability index, This represents the first generation obtained after processing by the analytic hierarchy process. t The first evaluation cycle v Subjective weights of suitability indicators This represents the first value obtained after processing with the entropy weight method. t The first evaluation cycle v The objective weight of each suitability indicator This represents the subjective weighting coefficient. ∈[0,1]; The second weight of each of the aforementioned rates of change is determined by the following formula: ; in, Indicates the first t The first evaluation cycle u The second weight of the rate of change of the term, This represents the first generation obtained after processing by the analytic hierarchy process. t The first evaluation cycle u Subjective weighting of the rate of change of the item This represents the first value obtained after processing with the entropy weight method. t The first evaluation cycle u Objective weight of the rate of change of the item This represents the subjective weighting coefficient. ∈[0,1].

[0034] Define the current evaluation period as t (e.g., annual or quarterly evaluation), and specify the set of all indicators used to evaluate "suitability of land consolidation" or "change in benefits" within this period. For example, suitability indicators might include soil quality and slope; benefit change rate indicators might include grain yield increase rate and vegetation coverage increase rate. Invite experts in land consolidation, agriculture, ecology, and economics to construct a judgment matrix questionnaire. The core of the questionnaire is to ask experts to compare any two indicators at the same level pairwise and determine their relative importance. Collect all expert scores, typically using the geometric mean method to synthesize expert opinions and form the final judgment matrix. Perform a consistency test on the judgment matrix. After passing the test, use mathematical methods such as the eigenvalue method to calculate the subjective weight of each indicator. This weight reflects the degree of importance that the expert group considers each indicator to be in the evaluation system based on their knowledge and experience. Collect actual data on each indicator for all evaluated geographical units within the current evaluation period. For example, collect measured soil quality and slope values ​​(for suitability assessment) for all plots to be evaluated, or data on grain yield and vegetation cover before and after remediation for all remediated plots (for calculating the rate of change in benefits). Since the dimensions and orders of magnitude of each indicator differ, the raw data needs to be standardized (e.g., using the range method, Z-score method, etc.) to eliminate the influence of dimensions. Based on the standardized data, calculate the information entropy for each indicator. Information entropy reflects the degree of difference in the indicator data across different geographical units. The greater the data difference, the more information the indicator provides in distinguishing different units. Calculate the difference coefficient based on the information entropy; the larger the difference coefficient, the more important the indicator. Finally, normalize the difference coefficients of each indicator to obtain the objective weight of each indicator. This weight is entirely determined by the dispersion of the data and is not influenced by human judgment. Decision-makers or system administrators need to determine a subjective weight coefficient between 0 and 1 for the current evaluation period. The value of the subjective weight coefficient is not fixed and can be dynamically adjusted according to the evaluation purpose. For example, during periods with high-quality data and abundant historical cases, the subjective weighting coefficient can be lowered, placing greater trust in the data; conversely, in the initial stages of new policy implementation or significant changes in evaluation standards, the subjective weighting coefficient can be increased, relying more on expert experience for guidance. Through the calculation using the above formula, a dynamically adjustable final weight (first weight or second weight) integrating subjective and objective information is calculated for each evaluation indicator (whether it's a suitability indicator or a rate of change in benefits indicator). This weight will be directly used in subsequent weighted summations to calculate the suitability index and the benefits index of the remediation efforts.

[0035] In some embodiments, calculating the coupling coordination degree of the target geographic unit based on the remediation suitability index and the remediation benefit index includes: The coupling coordination degree of the target geographic unit is calculated using the following formula: ; in, D Indicates the degree of coupling coordination. C Indicates the degree of coupling. T Indicates the comprehensive coordination index; The coupling degree is calculated using the following formula: ; in, SI Indicates the suitability index for remediation. BI Indicates the effectiveness index of the rectification efforts; The comprehensive coordination index is calculated using the following formula: T = α × SI + β × BI; Where α and β represent dynamic weighting coefficients; The suitability index for remediation is calculated using the following formula: ; in,( S v , t ) indicates the first t The first evaluation cycle v Suitableness indicators; The remediation benefit index is calculated using the following formula: ; in,( B u , t ) indicates the first t The first evaluation cycle u Rate of change of the item.

[0036] Specify that this is the t-th evaluation (e.g., the 2024 evaluation), and list all indicators used to assess "suitability," such as: soil quality indicators (S1, t), topographic slope indicators (S2, t), infrastructure accessibility indicators (S3, t), ecological sensitivity indicators (S4, t), etc. For the v-th indicator, perform the following: extract the specific value of this indicator for the geographic unit from the basic data, denoted as (S... v This value needs to be standardized (e.g., converted to a score between 0 and 1). Using the previously introduced AHP-entropy weight fusion method, the final weight of this indicator in the current evaluation period t is obtained, denoted as . The weighted summation calculation of SI involves multiplying the standardized value of each indicator by its corresponding combined weight, and then summing the products of all indicators. Suitability Index (SI) = (Weight of Indicator 1 × Standardized Value of Indicator 1) + (Weight of Indicator 2 × Standardized Value of Indicator 2) + ... + (Weight of Indicator v × Standardized Value of Indicator v). SI is a value between 0 and 1. The closer the value is to 1, the more suitable the land conditions of the unit are for priority remediation; the lower the value, the weaker the natural or socio-economic foundation, and the greater the difficulty or potential for remediation. This is also based on the t-th evaluation period. List all indicators used to assess benefits, such as: grain yield per mu change rate (B1, t), farmer per capita income change rate (B2, t), vegetation coverage increase rate (B3, t), public satisfaction increase rate (B4, t), etc. For the u-th benefit indicator, its change rate needs to be calculated. Extract the data before remediation (second data) and the data after remediation (third data) from the basic data. Change rate (B u The value of t is usually expressed as "(post-remediation value - pre-remediation value) / pre-remediation value", or other standardization methods are used to ultimately convert it into a standard score. Similarly, the AHP-entropy weighted fusion method is used to determine the weight of this rate of change in efficiency indicator, denoted as […]. Weighted summation calculation of BI: Similar to the calculation of SI, the change rate score of each benefit indicator is multiplied by its weight and then summed. Remediation Benefit Index (BI) = (Weight of Change Rate Indicator 1 × Score of Change Rate 1) + (Weight of Change Rate Indicator 2 × Score of Change Rate 2) + ... + (Weight of Change Rate Indicator u × Score of Change Rate u). BI is also a value between 0 and 1. The closer the value is to 1, the more significant the comprehensive benefits brought about by the remediation; the lower the value, the less significant the benefits are. Substitute the SI and BI obtained above into the coupling degree calculation formula. The value of C also ranges from 0 to 1. When the C value is close to 1, it indicates that both SI and BI are high or low, and the values ​​are close, indicating that "potential" and "effect" are in a high-strength coupling state, and their development pace is highly correlated. When the C value is small, it indicates that the development of the two systems is loose or uncoordinated, and the correlation is weak. This indicator reflects the magnitude of the interaction force between the two. Two dynamic weighting coefficients, α and β, are determined. α represents the degree of emphasis on "suitability (potential)" of the remediation, and β represents the degree of emphasis on "benefits (effects)" of the remediation. Typically, α + β = 1. Managers can adjust these coefficients according to policy orientations at different stages. For example, in the planning and site selection stage, potential may be emphasized more (α set higher); in the performance evaluation stage, effectiveness may be emphasized more (β set higher). The T-value is also a comprehensive score, reflecting the overall performance level of the unit in terms of "potential" and "effectiveness" under specific policy weights. The higher the T-value, the better the overall development level. Substituting the calculated C and T into the coupling coordination degree calculation formula yields the coupling coordination degree D. Based on the calculated D value, and combined with the original scores of SI and BI, geographic units can be precisely classified as follows: High suitability-high efficiency (high-quality area, D≥0.8 and SI≥0.7), Low suitability-high efficiency (area with exceptional performance, D≥0.6 and BI≥0.8), High suitability-low efficiency (area with untapped potential, D≥0.6 and SI≥0.7), and Low suitability-low efficiency (inefficient area, D≤0.3 and SI≤0.4).

[0037] In some embodiments, before matching and generating differentiated remediation and optimization strategies for the target geographic unit from a preset strategy knowledge base based on the coupling mismatch type to which the target geographic unit belongs, the method further includes pushing cases based on the remediation suitability index, the remediation benefit index, and the coupling coordination degree, specifically including: Multiple feature attributes of the target geographic unit are obtained, and a target feature vector is constructed. The feature attributes include the remediation suitability index, the remediation benefit index, the coupling coordination degree, and the baseline indicators in the ecological dimension extracted from the basic data. Calculate the comprehensive similarity between the target feature vector and the feature vectors of historical cases in the preset strategy knowledge base; Based on the comprehensive similarity, a preset number of historical cases with the highest similarity are selected from the strategy knowledge base as recommended cases and pushed to the system, so that the recommended cases and associated historical remediation strategies can serve as a reference for generating differentiated remediation and optimization strategies for the target geographical unit.

[0038] The system extracts key attributes from four main categories to construct feature vectors based on a predefined scientific framework: suitability index (representing the unit's remediation potential); remediation benefit index (representing the unit's remediation effect); coupling coordination degree (representing the health status of the match between potential and effect); and key ecological background indicators, extracted from the fused basic data to reflect the unit's inherent natural conditions, such as soil type and texture, average annual precipitation, main vegetation type, altitude, and slope. All these attribute values ​​are arranged in a fixed order to form a multidimensional array, which is the target feature vector for the unit. For example, the target feature vector might be represented as [SI=0.85, BI=0.45, D=0.60, soil type=red soil, average slope=8°, annual precipitation=1200mm, ...]. Each historical remediation case stored in the strategy knowledge base has its historical feature vector pre-constructed and stored according to the same attribute framework, along with the historical remediation strategies adopted and the final effects. The system compares the target feature vector with the feature vectors of each historical case in the knowledge base. This comparison is not a simple equality check, but rather calculates a quantified comprehensive similarity score using a mathematical formula (such as the weighted normalized Euclidean distance formula). The calculation process considers the differences in importance of different attributes (for example, "coupling coordination" might be considered more important than a specific background indicator), reflecting this by assigning different weights to different attributes. Simultaneously, the calculation eliminates the influence of different attribute units (e.g., standardizing precipitation and slope values ​​to the same scale) to ensure fairness in the comparison. After calculation, the system generates a list showing the similarity scores of all historical cases with the current unit. The scores typically range from 0 to 1, with higher scores indicating greater similarity. The generated similarity list is then sorted in descending order, with the most similar cases at the top. Based on a preset number (e.g., Top 3 or Top 5), a corresponding number of historical cases are selected from the top of the sorted list. These selected cases are the recommended cases. The system does not simply push the name or ID of a case, but pushes a complete information package for each recommended case. This information package typically includes: the case's basic feature vector (so that decision-makers understand why it was selected), the type of coupling mismatch the case faced at the time (compared to the current unit), the remediation strategy ultimately adopted by the case (core reference content), the effect record after the implementation of the strategy (successful, partially successful, or unsuccessful experiences), and key background information (such as year, region, etc.).

[0039] In some embodiments, calculating the comprehensive similarity between the target feature vector and the feature vectors of historical cases in a preset strategy knowledge base includes: The overall similarity is calculated using the following formula: ; in, X Represents the target feature vector. Y The feature vector representing historical cases, x j Represents the first in the target feature vector j One attribute, y j Represents the th element in the eigenvector. j One attribute, Sim ( X , Y The expression represents the comprehensive similarity between the target feature vector and the feature vector. w j Indicates the first j The weight of each attribute, d ( x j , y j ) represents the target feature vector and the feature vector at the th digit. j Normalized Euclidean distance on each attribute, where M is the total number of feature attributes; The target feature vector and the feature vector at the th moment are calculated using the following formula. j Normalized Euclidean distance over each attribute: ; in, max ( y j () indicates that all historical cases in the strategy knowledge base are in the first... j The maximum value of each attribute min ( y j () indicates that all historical cases in the strategy knowledge base are in the first... j The minimum value across all attributes.

[0040] Specify the M features used for comparison. For example, M=7. A feature vector containing 7 attributes might be: [Suitability index for remediation, benefit index for remediation, coupling coordination degree, soil type code, average slope, annual precipitation, vegetation cover index]. Target feature vector X: X=[x1, x2, x3, ..., x M [ ], which refers to the numerical values ​​of the geographical unit for which a strategy needs to be formulated, across various attributes. Historical case feature vector Y: Y = [y1, y2, y3, ..., y M[ ], which refers to the numerical values ​​of a historical case in the knowledge base across various attributes. A weight is assigned to each attribute. The determination of weights is usually based on expert experience or data analysis, reflecting the importance of that attribute in judging similarity. The sum of all weights should be 1. For the first... j One attribute, max ( y j This represents the maximum value of this attribute across all historical cases in the strategy knowledge base. min ( y j This represents the minimum value, which defines a range of historical experience. For the ... j Each attribute is used to calculate the target value. x j With case value y j The absolute difference between the values ​​is then divided by the historical experience range mentioned above. Example: Suppose we are comparing average slope attributes (unit: degrees). In the historical case library, the minimum slope of all plots is 0° and the maximum is 25°. Therefore, max(y-slope) - min(y-slope) = 25 - 0 = 25. The slope of the target plot... x j =5°, the slope of historical cases y j =10°. The absolute difference is |5-10|=5. The normalized distance is d (slope)=5 / 25=0.20. d ( x j , y j The result of the calculation is a unitless value between 0 and 1. d=0 indicates that the two are completely identical in this attribute, d=1 indicates that the two are extremely different in this attribute, one at its historical minimum and the other at its historical maximum. The smaller the value, the closer the two are in this specific attribute. The normalized distance calculated for each attribute... d ( x j , y j ), multiplied by its corresponding weight w j We obtain the weighted distance for each of the M attributes. Then, we sum the weighted distances of all M attributes to get the total weighted distance. This value reflects the overall difference between the two vectors across all attributes, taking into account the importance of different attributes. The smaller the value, the smaller the overall difference. A smaller distance value represents greater similarity, while people are generally more accustomed to higher scores representing greater similarity. Therefore, we use the above comprehensive similarity formula to convert the total weighted distance into a comprehensive similarity score.

[0041] In some embodiments, the step of matching and generating differentiated remediation and optimization strategies for the target geographic unit from a preset strategy knowledge base based on the coupling mismatch type to which the target geographic unit belongs includes: Based on the remediation suitability index, the remediation efficiency index, and the coupling coordination degree, the target geographical unit is divided into at least one of the following coupling mismatch types through a preset threshold rule: high suitability-low efficiency potential unreleased area, low suitability-high efficiency over-performance area, and low suitability-low efficiency inefficient area. Based on the determined coupling mismatch type, all associated primary remediation strategies are selected from the strategy knowledge base to form a first strategy set; The historical rectification strategies are matched and weighted with the first set of strategies to form a second set of strategies, wherein the similarity of the recommended cases is used as the fusion weight of the associated historical rectification strategies. The strategies in the second strategy set are adjusted based on the real-time natural background conditions of the target geographic unit extracted from the basic data to generate the differentiated remediation and optimization strategy.

[0042] The preset policy knowledge base is a structured database, and each remediation policy in it is labeled with the applicable coupling mismatch type. The system automatically retrieves and extracts all policy entries labeled as applicable to this type from the knowledge base based on the determined coupling mismatch type (such as high suitability - low benefit). These policies are usually general and principle-based suggestions. For areas where potential has not been released, the policies that may be retrieved include: conducting post-project evaluation audits, strengthening project supervision and acceptance, establishing long-term management and protection mechanisms, optimizing the fund appropriation process, etc. The set of these policies constitutes the first policy set. It is a preliminary solution library formed based on theory and general experience. From the previous case push step, multiple recommended cases most similar to the current unit are obtained, and each case is associated with the historical remediation policies actually adopted at that time. The system does not simply add the historical policies to the first set, but performs weighted fusion. The more similar a historical case is to the current unit, the greater the reference value of its success (or failure) experience for the current decision. The case similarity is used as the fusion weight for the associated historical remediation policies. For a case with a similarity of 0.95, its historical policy will be given extremely high importance during fusion, and for a case with a similarity of 0.70, the importance of its historical policy will be relatively low. The system matches, de-duplicates, and integrates the general policies in the first policy set with these weighted historical policies. Each policy in the finally formed second policy set may be assigned a confidence level or priority mark based on historical experience. This set combines theoretical correctness and practical relevance. The system extracts the specific and dynamic natural background conditions of this unit from the latest basic data floor, which includes but is not limited to: the current soil moisture and fertility status, the current vegetation coverage and growth conditions, the recent climate and water regime data, and the micro-topography details within the plot. The system automatically adjusts the policies in the second policy set based on these real-time data. For example, a general policy is to apply organic fertilizer. After integrating historical experience, the recommended dosage of this policy in the second set may be a kilograms per mu. However, when the system detects that the current soil organic matter content in this unit is already relatively high, or it is in a state after flooding, it will automatically adjust the recommended dosage to b kilograms per mu (b < a), or suggest changing to "drain waterlogging first, and then apply fertilizer". After this round of adjustment, the finally output is the differentiated remediation and optimization policies specifically targeted at this target geographical unit.

[0043] In some embodiments, screening out all associated primary remediation policies from the policy knowledge base according to the determined coupling mismatch type to form the first policy set specifically includes: Based on the coupling mismatch type, matching one or more remediation failure modes in the preset policy failure mode library, and starting from the matched remediation failure mode, retrieving all remediation policy nodes labeled as avoiding the remediation failure mode in the remediation policy knowledge graph constructed by the policy knowledge base to form the anti-risk policy base set; For each strategy in the aforementioned risk mitigation strategy base set, a secondary failure chain derived from external interference or internal execution deviation during implementation is simulated. A risk propagation model trained using historical case data is used to quantify and extrapolate the probability of the occurrence of the secondary failure chain and the estimated negative impact on the remediation benefit index, and the comprehensive risk exposure value of each strategy is calculated. Obtain the average benefit improvement data of each strategy in the historical application of the risk resistance strategy base set as the benchmark return expectation, construct a risk-return trade-off function, and calculate the comprehensive risk exposure value and the benchmark return expectation to obtain the initial screening priority score of each strategy. The strategies are sorted according to the initial screening priority score, and a preset number of top-ranked strategies are selected to form the first strategy set.

[0044] The strategy failure mode library is an independent knowledge base that systematically summarizes and defines common failure types and their causes in land consolidation across the entire region. Examples include: "misappropriation of funds and ineffective supervision," "deviation in the implementation of engineering and technical standards," "lack of responsibility for post-construction maintenance," and "mismatch between ecological restoration measures and local conditions." Based on the determined coupling mismatch type, the system automatically associates one or more consolidation failure modes most likely to lead to such results. For example, for areas with high suitability but low efficiency (unreleased potential), the system may prioritize matching "engineering supervision failure mode" and "lack of post-construction maintenance mode." The system uses the matched failure modes as "query clues" to search the consolidation strategy knowledge graph. Each strategy node in this knowledge graph is labeled with failure modes that it can "avoid" or "cope with." The system retrieves all strategy nodes labeled "avoidable [engineering supervision failure]" and / or "copeable [lack of post-construction maintenance]." All retrieved strategy nodes constitute the basic set of risk mitigation strategies. For each candidate strategy in the basic set of risk mitigation strategies, the system initiates a simulation. It no longer views strategies as static solutions, but rather simulates their implementation process, analyzing new problem chains that may arise due to external interference (such as extreme weather, market fluctuations) or internal execution deviations (such as substandard construction quality, low farmer participation). For example, the strategy "introducing third-party full-process supervision" (to avoid regulatory failure). Secondary failure chain simulation: High supervision costs may → squeeze direct project costs → lead to material downgrading → potential project quality issues → ultimately failing to meet benefits. Application of a risk propagation model: The system invokes a risk propagation model trained on a large amount of historical case data. This model can estimate the probability of each step in the above secondary failure chain being triggered, and estimate the negative impact on the remediation benefit index (BI) if the failure chain ultimately occurs (e.g., causing a 15% decrease in the expected BI value). The model can also combine the probability of occurrence and the degree of negative impact to calculate a comprehensive risk exposure value for the strategy. The higher this value, the greater the potential risk inherent in implementing the strategy itself. The system uses historical data to statistically analyze the average benefit improvement (e.g., an average increase in BI value of 0.1) of each strategy in the risk mitigation strategy base set when applied in similar past projects. This serves as the baseline expected return for that strategy. A risk-return trade-off function is constructed: the system establishes a mathematical function whose core objective is to maximize returns while controlling risk. A typical simplified function form might be: Initial screening priority score = Baseline expected return × (1 - Overall risk exposure), or a more complex normalized form: Score = (Standardized return value) / (Risk exposure value + Smoothing constant). Substituting the baseline expected return and overall risk exposure value of each strategy into the trade-off function, the initial screening priority score for each strategy is calculated. High-scoring strategies: These indicate high returns and low risk, making them ideal priority choices. Low-scoring strategies: These may have low returns, excessively high risks, or both.The system sorts all strategies in descending order of their initial screening priority score. Based on a preset threshold (e.g., "only the top 10") or quantity (e.g., "select the Top 5"), a corresponding number of strategies are selected from the top of the sorted list. These selected strategies ultimately form the first strategy set. This set is the essence of the risk-resistance strategy base set after two rigorous screening processes: risk quantification assessment and risk-return trade-off.

[0045] The above describes the method for coupled evaluation and decision optimization of comprehensive land consolidation in this application. The computer system in this application will be described in detail below in conjunction with the above method for coupled evaluation and decision optimization of comprehensive land consolidation.

[0046] Please see Figure 3 This is a schematic diagram of an exemplary hardware structure of a computer system in an embodiment of this application.

[0047] In some embodiments, the computer system 300 includes a computer device, which may be a terminal device. The computer device includes a processor 301, a memory 302, a sensor module 303, a communication module 304, an input device 305, and an output device 306 connected via a system bus. The processor 301 of the computer device provides computing and control capabilities. The memory 302 of the computer device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The database is used to store data.

[0048] Those skilled in the art will understand that Figure 3 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0049] In some embodiments of this application, a computer-readable storage medium is provided, including instructions that, when executed on the computer system 300, cause the computer system 300 to execute the integrated land consolidation coupled evaluation and decision optimization method of the embodiments of this application.

[0050] In some embodiments of this application, a computer program product is also provided, which, when run on a computer system 300, causes the computer system 300 to execute the integrated land consolidation coupled evaluation and decision optimization method of the embodiments of this application.

[0051] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit it. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.

[0052] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that integrates one or more available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive), etc.

[0053] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. This program can be stored in a computer-readable storage medium, and when executed, it can include the processes described in the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM or random access memory (RAM), magnetic disks, or optical disks.

Claims

1. A method for coupled evaluation and decision optimization of comprehensive land consolidation, characterized in that, include: Collect and integrate multi-source heterogeneous data from comprehensive land consolidation across the entire region to obtain basic data. The multi-source heterogeneous data includes remote sensing data, geospatial data, and ecological environment data. First data for each suitability indicator is extracted from the basic data. First weights for each suitability indicator are determined by a combined evaluation method combining the analytic hierarchy process and the entropy weight method. The remediation suitability index of the target geographic unit is obtained by weighted summation of the first data and the first weights. The second data and the third data of each benefit indicator before the remediation are extracted from the basic data. The change rate of each benefit indicator is calculated based on the second data and the third data. The second weight of each change rate is determined by the combined evaluation method. The remediation benefit index of the target geographical unit is obtained by weighted summation of the change rate and the second weight. The coupling coordination degree of the target geographic unit is calculated based on the remediation suitability index and the remediation benefit index, and whether the target geographic unit needs optimization is determined based on the remediation suitability index, the remediation benefit index, and the coupling coordination degree. When the target geographic unit needs optimization, a differentiated remediation and optimization strategy is generated from a preset strategy knowledge base based on the coupling mismatch type to which the target geographic unit belongs. In response to the user-inputted constraints on remediation resources, based on the differentiated remediation optimization strategy, the remediation priorities of multiple target geographical units within the target area are ranked, and a resource allocation scheme that maximizes the expected comprehensive benefits under the constraints is generated.

2. The method for coupled evaluation and decision optimization of comprehensive land consolidation according to claim 1, characterized in that, The first weight of each of the aforementioned suitability indicators is determined by the following formula: ； in, Indicates the first t The first evaluation cycle v The first weight of the suitability index, This represents the first generation obtained after processing by the analytic hierarchy process. t The first evaluation cycle v Subjective weights of suitability indicators This represents the first value obtained after processing with the entropy weight method. t The first evaluation cycle v The objective weight of each suitability indicator This represents the subjective weighting coefficient. ∈[0,1]; The second weight of each of the aforementioned rates of change is determined by the following formula: ； in, Indicates the first t The first evaluation cycle u The second weight of the rate of change of the term, This represents the first generation obtained after processing by the analytic hierarchy process. t The first evaluation cycle u Subjective weighting of the rate of change of the item This represents the first value obtained after processing with the entropy weight method. t The first evaluation cycle u Objective weight of the rate of change of the item This represents the subjective weighting coefficient. ∈[0,1].

3. The method for coupled evaluation and decision optimization of comprehensive land consolidation according to claim 2, characterized in that, The calculation of the coupling coordination degree of the target geographic unit based on the remediation suitability index and the remediation benefit index includes: The coupling coordination degree of the target geographic unit is calculated using the following formula: ； in, D Indicates the degree of coupling coordination. C Indicates the degree of coupling. T Indicates the comprehensive coordination index; The coupling degree is calculated using the following formula: ； in, SI Indicates the suitability index for remediation. BI Indicates the effectiveness index of the rectification efforts; The comprehensive coordination index is calculated using the following formula: T = α × SI + β × BI; Where α and β represent dynamic weighting coefficients; The suitability index for remediation is calculated using the following formula: ； in,( S v , t ) indicates the first t The first evaluation cycle v Suitableness indicators; The remediation benefit index is calculated using the following formula: ； in,( B u , t ) indicates the first t The first evaluation cycle u Rate of change of the item.

4. The method for coupled evaluation and decision optimization of comprehensive land consolidation according to claim 1, characterized in that, Before matching and generating differentiated remediation and optimization strategies for the target geographic unit from a preset strategy knowledge base based on the coupling mismatch type to which the target geographic unit belongs, the process further includes case recommendation based on the remediation suitability index, the remediation benefit index, and the coupling coordination degree, specifically including: Multiple feature attributes of the target geographic unit are obtained, and a target feature vector is constructed. The feature attributes include the remediation suitability index, the remediation benefit index, the coupling coordination degree, and the baseline indicators in the ecological dimension extracted from the basic data. Calculate the comprehensive similarity between the target feature vector and the feature vectors of historical cases in the preset strategy knowledge base; Based on the comprehensive similarity, a preset number of historical cases with the highest similarity are selected from the strategy knowledge base as recommended cases and pushed to the system, so that the recommended cases and associated historical remediation strategies can serve as a reference for generating differentiated remediation and optimization strategies for the target geographical unit.

5. The method for coupled evaluation and decision optimization of comprehensive land consolidation according to claim 4, characterized in that, The calculation of the comprehensive similarity between the target feature vector and the feature vectors of historical cases in the preset strategy knowledge base includes: The overall similarity is calculated using the following formula: ； in, X Represents the target feature vector. Y The feature vector representing historical cases, x j Represents the first in the target feature vector j One attribute, y j Represents the th element in the eigenvector. j One attribute, Sim ( X , Y The expression represents the comprehensive similarity between the target feature vector and the feature vector. w j Indicates the first j The weight of each attribute, d ( x j , y j ) represents the target feature vector and the feature vector at the th digit. j Normalized Euclidean distance on each attribute, where M is the total number of feature attributes; The target feature vector and the feature vector at the th moment are calculated using the following formula. j Normalized Euclidean distance over each attribute: ； in, max ( y j () indicates that all historical cases in the strategy knowledge base are in the first... j The maximum value of each attribute min ( y j () indicates that all historical cases in the strategy knowledge base are in the first... j The minimum value across all attributes.

6. The method for coupled evaluation and decision optimization of comprehensive land consolidation according to claim 4, characterized in that, The step of matching and generating differentiated remediation and optimization strategies for the target geographic unit from a preset strategy knowledge base based on the coupling mismatch type to which the target geographic unit belongs includes: Based on the remediation suitability index, the remediation efficiency index, and the coupling coordination degree, the target geographical unit is divided into at least one of the following coupling mismatch types through a preset threshold rule: high suitability-low efficiency potential unreleased area, low suitability-high efficiency over-performance area, and low suitability-low efficiency inefficient area. Based on the determined coupling mismatch type, all associated primary remediation strategies are selected from the strategy knowledge base to form a first strategy set; The historical rectification strategies are matched and weighted with the first set of strategies to form a second set of strategies, wherein the similarity of the recommended cases is used as the fusion weight of the associated historical rectification strategies. The strategies in the second strategy set are adjusted based on the real-time natural background conditions of the target geographic unit extracted from the basic data to generate the differentiated remediation and optimization strategy.

7. The method for coupled evaluation and decision optimization of comprehensive land consolidation according to claim 6, characterized in that, Based on the determined coupling mismatch type, all associated primary remediation strategies are selected from the strategy knowledge base to form a first strategy set, specifically including: Based on the coupling mismatch type, one or more remediation failure modes are matched in the preset strategy failure mode library. Starting from the matched remediation failure mode, all remediation strategy nodes marked as avoiding the remediation failure mode are retrieved in the remediation strategy knowledge graph constructed in the strategy knowledge base, thus forming a basic set of risk resistance strategies. For each strategy in the aforementioned risk mitigation strategy base set, a secondary failure chain derived from external interference or internal execution deviation during implementation is simulated. A risk propagation model trained using historical case data is used to quantify and extrapolate the probability of the occurrence of the secondary failure chain and the estimated negative impact on the remediation benefit index, and the comprehensive risk exposure value of each strategy is calculated. Obtain the average benefit improvement data of each strategy in the historical application of the risk resistance strategy base set as the benchmark return expectation, construct a risk-return trade-off function, and calculate the comprehensive risk exposure value and the benchmark return expectation to obtain the initial screening priority score of each strategy. The strategies are sorted according to the initial screening priority score, and a preset number of top-ranked strategies are selected to form the first strategy set.

8. A computer system comprising a memory, a processor, and a computer program stored in the memory, characterized in that, The processor executes the computer program to implement the steps of the method according to any one of claims 1-7.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-7.

10. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps of the method described in any one of claims 1-7.

Images