Land space layout adjustment decision-making method based on planning conflict identification

Abstract

The invention discloses a territorial space layout adjustment decision method based on planning conflict identification, and belongs to the technical field of territorial space planning and management. Comprising the following steps: constructing a space-time conflict feature vector library containing multi-dimensional attributes; generating a semantic knowledge graph containing a causal relationship, a sequential relationship, a spatial relationship and an affiliation relationship; accurate prediction of influence intensity and duration of the conflict state along with time lapse is realized; trend analysis and risk level evaluation of a cross-scale conflict propagation path are realized; automatically identifying dominant conflicts in the current layout and potential conflicts based on propagation prediction, and intelligently classifying composite conflicts by using fuzzy clustering; a staged differentiation conflict intervention strategy recommendation scheme is automatically generated; solving a territorial space layout adjustment scheme; judging whether the layout adjustment scheme meets a preset conflict relieving standard or not;

Description

Technical Field

[0001] The present application relates to the technical field of land space planning and management, and more specifically, to a land space layout adjustment decision-making method based on planning conflict identification. Background Art

[0002] Currently, some land and space planning conflicts are handled through manual identification and empirical judgment. This presents challenges such as a single data dimension, limited identification accuracy, and delayed analysis results, making it difficult to meet the demands of dynamic monitoring and multi-scale management. Furthermore, once a conflict occurs, it often exhibits characteristics of cross-regional diffusion and delayed manifestation. Failure to identify and predict it in a timely manner often leads to cascading impacts on subsequent spatial layout adjustments and even exacerbates uncertainty in spatial governance. Furthermore, existing layout adjustment methods, which are mostly based on static optimization, fail to systematically consider the temporal nature of conflict evolution and the spatial hierarchical transmission mechanisms. This results in some adjustment plans being inadequately adapted and intervention measures being limited in effectiveness in practice. Therefore, there is an urgent need for a layout adjustment support tool that can integrate multi-source data, deeply analyze the causes of conflict, and possess predictive and intervention capabilities to enhance the foresight of planning and proactive governance.

[0003] To sum up, how to accurately identify and analyze national land space conflicts in a dynamic and complex spatial environment and formulate operational and adaptable layout adjustment decision-making plans has become a technical problem that needs to be solved urgently. Summary of the Invention

[0004] In order to overcome a series of defects in the existing technology, the purpose of this application is to provide a land space layout adjustment decision-making method based on planning conflict identification to address the above problems, which is applied to the land space planning decision-making system. The land space planning decision-making system includes a multi-source data fusion module, a spatiotemporal conflict analysis module, a conflict propagation prediction module, a land conflict knowledge graph construction module, a scheduling decision module and a layout optimization module, and includes the following steps.

[0005] Step 1: Use the multi-source data fusion module to perform spatiotemporal registration and semantic unification of multi-source heterogeneous spatial data, and automatically extract the spatial distribution characteristics, temporal evolution patterns, and semantic attribute characteristics of land use conflicts, and then construct a spatiotemporal conflict feature vector library containing multidimensional attributes.

[0006] Step 2: Through the territorial conflict knowledge graph construction module, based on the integrated multi-source data, automatically extract conflict event entities, conflict subject entities, spatial location entities and attribute feature entities, build a four-element semantic network, and identify the complete causal chain of the conflict causes, generating a semantic knowledge graph containing causal relationships, temporal relationships, spatial relationships and subordinate relationships.

[0007] Step 3: Based on the pre-trained spatiotemporal lag effect model and semantic enhancement of the land conflict knowledge graph, the spatiotemporal conflict analysis module is used to automatically capture and quantify the spatiotemporal propagation and lag effects of land use conflicts between different regions. Combined with the causal chain reasoning results in the knowledge graph, accurate prediction of the impact intensity and duration of the conflict status over time can be achieved.

[0008] Step 4: The conflict propagation prediction module intelligently identifies the optimal propagation path of land use conflicts at different spatial scales and quantifies the obstacles to conflict propagation caused by various influencing factors, thereby achieving trend analysis and risk level assessment of cross-scale conflict propagation paths.

[0009] Step 5: Based on the preset spatiotemporal hysteresis threshold and impact intensity threshold, the explicit conflicts in the current layout and the potential conflicts based on propagation prediction are automatically identified, and the complex conflicts are intelligently classified using fuzzy clustering.

[0010] Step 6: Through the scheduling decision module, based on the identified explicit and potential conflicts, the urgency of conflict mitigation, the rationality of intervention measures, and the existing resource allocation capabilities are comprehensively evaluated, and a phased and differentiated conflict intervention strategy recommendation is automatically generated, including strategy combinations and their priority rankings for the emergency response period, short-term governance period, mid-term adjustment period, and long-term consolidation period.

[0011] Step 7: Use the layout optimization module to build a multi-objective optimization model with the goals of conflict minimization, benefit maximization, and cost optimization, and integrate rigid rule constraints and time-space lag factors to solve the national land space layout adjustment plan.

[0012] Furthermore, the multi-source data fusion module adopts a hierarchical registration strategy during the spatiotemporal registration process: first, the spatial data in different coordinate systems are uniformly converted to the WGS84 geographic coordinate system to achieve consistent coordinate references; then, the common land features in the spatial data are identified through the feature point matching algorithm, and the data are geometrically corrected using the affine transformation matrix; finally, the timestamp alignment method is used to standardize the time series of data in different phases to ensure consistency in the time dimension; in the semantic unification process, a unified land use classification and coding system is constructed, and the semantic conversion between different data sources is realized through ontology mapping technology, and the confidence weighted fusion method is combined to handle semantic conflicts, ensuring that the fused data achieves spatial accuracy at the meter level on the basis of semantic consistency.

[0013] Furthermore, the multi-source data fusion module includes a data preprocessing unit, a coordinate conversion unit and a semantic mapping unit, among which: the data preprocessing unit is responsible for quality inspection and noise filtering of remote sensing image data, GIS vector data, statistical survey data and field measurement data from different sensor platforms; the coordinate conversion unit completes the precise coordinate transformation between multiple spatial reference systems based on high-precision geodetic datums and projection parameters, and adopts the seven-parameter Bursa model for unified processing of three-dimensional spatial coordinates; the semantic mapping unit constructs an ontology knowledge base based on industry standards, defines a standardized land use classification system and attribute description specifications, and realizes semantic alignment between heterogeneous data sources through semantic similarity calculation and concept hierarchy matching, ensuring that the semantic representation of the same geographic entity remains consistent in each data source.

[0014] Furthermore, the pre-trained spatiotemporal lag effect model adopts a deep recurrent neural network architecture, integrating an encoder-decoder structure and an attention mechanism module, wherein: the encoder part adopts a bidirectional long short-term memory network to capture the forward and backward dependency features in the time series; the decoder part uses a multi-head self-attention mechanism to dynamically learn the influence weights between different time steps; during the model training process, supervised learning samples are constructed based on historical conflict data, and a sliding time window is used to generate input sequence and target sequence pairs. The loss function is set as a weighted combination of mean square error and time decay weight, and the parameters are iteratively updated through the Adam optimization algorithm; the time series cross-validation method is used in the model verification stage to evaluate the prediction performance indicators including mean absolute error, root mean square error and correlation coefficient. At the same time, the optimal lag time window length and influence intensity attenuation parameter are determined through sensitivity analysis to ensure that the model has good prediction stability at multiple spatiotemporal scales.

[0015] Furthermore, the spatiotemporal conflict analysis module includes a conflict identification unit, an intensity calculation unit and a propagation analysis unit, among which: the conflict identification unit identifies land use type combinations with potential conflicts based on the land use compatibility matrix and spatial proximity criterion, and marks areas where potential conflicts may occur by setting spatial buffer thresholds and time interval parameters; the intensity calculation unit quantifies the conflict intensity using a multi-factor weighted evaluation method, comprehensively considering factors such as land use type differences, spatial overlapping area, population density, economic value and ecological sensitivity, and uses the hierarchical analysis method to determine the weight of each factor and establish a conflict intensity evaluation index system; the propagation analysis unit constructs a conflict propagation network based on graph theory and network analysis methods, with nodes representing spatial units and edges representing conflict propagation paths, and analyzes the spatial pattern and impact range of conflict propagation by calculating node centrality, clustering coefficient and path length.

[0016] Furthermore, the conflict propagation prediction module simulates the conflict propagation process in the spatial network based on the multi-agent modeling method. Each agent corresponds to a spatial unit and has state transition rules and interactive behavior patterns. The agent states include four types: no conflict, potential conflict, explicit conflict and conflict resolution. When the conflict intensity of adjacent agents exceeds the preset threshold, the state transition is triggered, and the propagation probability is determined by the distance attenuation function, terrain barrier factor and policy intervention intensity. Multiple random experiments are carried out through the Monte Carlo simulation method to statistically analyze the conflict propagation path, arrival time and impact range under different scenarios, generate probability distribution maps and risk level classifications, and identify the key parameters that have the greatest impact on the propagation process through sensitivity analysis.

[0017] Furthermore, the scheduling decision module includes an urgency assessment unit, a feasibility analysis unit, a resource allocation unit, a strategy generation unit, a planning scenario classification unit, an intelligent indicator adjustment unit and a real-time dynamic adjustment trigger unit, among which: the urgency assessment unit constructs an urgency evaluation index system based on the conflict propagation prediction results and the causal analysis of the knowledge graph; the feasibility analysis unit is used to evaluate the implementation conditions of the intervention measures; the resource allocation unit allocates the optimal resource combination for the intervention strategy based on the current available resource constraints; the strategy generation unit uses the urgency assessment, feasibility analysis and resource allocation results as decision-making conditions as inputs, and automatically generates a phased intervention strategy combination; the planning scenario classification unit divides the decision scenarios into four types: economic development orientation, ecological protection priority, social equity consideration and comprehensive coordination.

[0018] Furthermore, step 3 includes the following steps.

[0019] The quality of historical land use conflict event data was checked, and the regional data were mapped to a unified grid unit based on the spatial weight matrix. The sequences were then aligned according to the timestamps to generate a normalized spatiotemporal dataset.

[0020] The spatiotemporal conflict analysis module is used to calculate the conflict intensity index of each grid unit. Combining the neighborhood location characteristics and the semantic information in the territorial conflict knowledge graph, a multidimensional time series feature vector sequence integrating causal relationships is constructed based on a sliding time window.

[0021] The multi-dimensional time series feature vector sequence is input into the encoder part of the pre-trained spatiotemporal lag effect model, and a bidirectional long short-term memory network is used to capture the forward and backward associations in the sequence. Combined with the semantic enhancement information of the knowledge graph, the hidden state vector containing lag information and causal chain reasoning is output.

[0022] The decoder performs weighted aggregation of hidden state vectors through the attention mechanism, integrates the causal chain reasoning results in the knowledge graph, and maps the weight distribution of different time steps into the prediction parameters of the conflict impact intensity and duration at the current moment, thereby achieving accurate prediction of the conflict status over time.

[0023] Based on the hysteresis coefficient and spatial propagation probability in the decoder output, combined with the semantic enhancement analysis of the knowledge graph, the prediction results are mapped back to the geographic grid, automatically capturing and quantifying the spatiotemporal propagation paths and corresponding time delays of land use conflicts between regions, thereby generating a spatiotemporal propagation trajectory map that includes propagation and hysteresis effects.

[0024] The predicted conflict intensity and duration are compared with the measured data for error analysis; if the prediction error exceeds the set threshold, the lag window length or spatial weight parameter in the model is dynamically adjusted based on the sensitivity analysis results and knowledge graph feedback, and iterative optimization is performed until the prediction accuracy meets the set standards.

[0025] Furthermore, step 4 includes the following steps.

[0026] At the three spatial levels of region, county, and plot, conflict propagation networks are constructed based on grid units or administrative boundary units, where nodes represent corresponding spatial units and edge weights are determined by the conflict transmission probability and distance decay function between adjacent nodes to ensure accurate mapping of network structures at different scales.

[0027] A multi-agent model is introduced at each network level to simulate the diffusion process of conflicts. Agents migrate between nodes according to preset state transition rules. At the same time, the shortest path algorithm is used to automatically extract the optimal propagation path of conflicts from the simulation results.

[0028] The resistance value corresponding to the comprehensive barrier factor is calculated for each edge on the path, and the path cost weight is assigned after normalization to achieve accurate quantification of multiple influencing factors.

[0029] The optimal propagation paths and their resistance costs identified in each level of the network are summarized. By comparing the path length, accumulated resistance value and propagation time delay, the cross-scale propagation trend characteristics are extracted, providing a quantitative analysis basis for the trend differences between the macro and micro levels.

[0030] Based on the total value of path resistance and the transmission probability, combined with the threshold quantile method, a risk score is implemented for each transmission path, and it is divided into three risk levels: low, medium, and high, so as to identify potential key conflict diffusion corridors and high-risk sections.

[0031] The optimal propagation path, resistance distribution, and risk level are displayed as map layers, and trend analysis and risk assessment reports are automatically generated, including cross-scale path comparison charts, resistance factor contribution bar charts, and risk area distribution heat maps.

[0032] Furthermore, the decision-making method for adjusting the national land space layout also includes the following steps.

[0033] Step 8: During the layout adjustment plan generation process, the impact of the plan on future conflict evolution is evaluated in real time through the spatiotemporal fitness evaluation function. The conflict propagation prediction results and the spatiotemporal lag effect analysis results are combined to determine whether the layout adjustment plan meets the preset conflict mitigation standards.

[0034] Step 9: If the layout adjustment solution does not meet the preset conflict mitigation criteria, return to the multi-objective optimization model and solve again until the conflict mitigation criteria are met.

[0035] Step 10: If the layout adjustment plan has met the preset conflict mitigation standards, a Pareto optimal solution set that takes into account both current conflict mitigation and future risk prevention and control is generated, and the final national land space layout adjustment decision plan is output.

[0036] Furthermore, step 8 includes the following steps.

[0037] The spatial structure parameters, land use type distribution and adjustment range of the current layout adjustment plan are input into the spatiotemporal fitness evaluation function, and combined with the future conflict situation characteristics output by the conflict propagation prediction module to extract the key impact indicators of the layout plan on the conflict evolution process.

[0038] The evaluation indicators of the layout plan in three dimensions, namely conflict mitigation effect, future development adaptability and implementation rationality, are calculated respectively, and a comprehensive evaluation vector is constructed based on them.

[0039] According to the predetermined expert weight system, each indicator is weighted, and the comprehensive fitness score of the scheme is generated by weighted summation.

[0040] The obtained fitness score is compared with the set conflict mitigation standard to quantitatively determine whether the current layout plan meets the minimum threshold requirements of conflict intensity reduction, conflict area reduction, and propagation path blocking indicators.

[0041] Combined with the results of the spatiotemporal lag effect analysis, the time delay and persistence changes in the conflict propagation process after the layout adjustment are tested to further verify whether the control effect of the scheme on the conflict evolution trend at different time nodes in the future is in line with expectations.

[0042] Compared with the existing technology, this application has the following beneficial effects: This application constructs a land conflict knowledge graph that integrates multi-source heterogeneous data, combines a pre-trained spatiotemporal lag effect model with multi-agent propagation simulation, and realizes causal chain analysis of land use conflicts, cross-scale propagation path prediction, and intelligent layout optimization, thereby providing refined and evolvable conflict intervention and adjustment decision support for land space planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 A flowchart of a land space layout adjustment decision-making method based on planning conflict identification disclosed in an embodiment of the present application. DETAILED DESCRIPTION

[0044] To make the objectives, technical solutions, and advantages of the present invention more apparent, the technical solutions in the embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Throughout the drawings, identical or similar reference numerals represent identical or similar elements or elements having identical or similar functions. The described embodiments are only some, not all, of the embodiments of the present invention.

[0045] Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative work shall fall within the scope of protection of the present invention.

[0046] The embodiments and directional terms described below with reference to the accompanying drawings are exemplary and intended to be used to explain the present invention, but should not be construed as limiting the present invention.

[0047] like Figure 1 As shown, a land space layout adjustment decision-making method based on planning conflict identification is applied to a land space planning decision-making system. The land space planning decision-making system includes a multi-source data fusion module, a spatiotemporal conflict analysis module, a conflict propagation prediction module, a land conflict knowledge graph construction module, a scheduling decision module and a layout optimization module. The method includes the following steps.

[0048] Step 1: Use the multi-source data fusion module to perform spatiotemporal registration and semantic unification of multi-source heterogeneous spatial data, and automatically extract the spatial distribution characteristics, temporal evolution patterns, and semantic attribute characteristics of land use conflicts, and then construct a spatiotemporal conflict feature vector library containing multidimensional attributes.

[0049] Step 2: Through the territorial conflict knowledge graph construction module, based on the integrated multi-source data, automatically extract conflict event entities, conflict subject entities, spatial location entities and attribute feature entities, build a four-element semantic network, and identify the complete causal chain of the conflict causes, generating a semantic knowledge graph containing causal relationships, temporal relationships, spatial relationships and subordinate relationships.

[0050] Step 3: Based on the pre-trained spatiotemporal lag effect model and semantic enhancement of the land conflict knowledge graph, the spatiotemporal conflict analysis module is used to automatically capture and quantify the spatiotemporal propagation and lag effects of land use conflicts between different regions. Combined with the causal chain reasoning results in the knowledge graph, accurate prediction of the impact intensity and duration of the conflict status over time can be achieved.

[0051] Step 4: The conflict propagation prediction module intelligently identifies the optimal propagation path of land use conflicts at different spatial scales and quantifies the obstacles to conflict propagation caused by various influencing factors, thereby achieving trend analysis and risk level assessment of cross-scale conflict propagation paths.

[0052] Step 5: Based on the preset spatiotemporal hysteresis threshold and impact intensity threshold, the explicit conflicts in the current layout and the potential conflicts based on propagation prediction are automatically identified, and the complex conflicts are intelligently classified using fuzzy clustering.

[0053] Step 6: Through the scheduling decision module, based on the identified explicit and potential conflicts, the urgency of conflict mitigation, the rationality of intervention measures, and the existing resource allocation capabilities are comprehensively evaluated, and a phased and differentiated conflict intervention strategy recommendation is automatically generated, including strategy combinations and their priority rankings for the emergency response period, short-term governance period, mid-term adjustment period, and long-term consolidation period.

[0054] Step 7: Use the layout optimization module to build a multi-objective optimization model with the goals of conflict minimization, benefit maximization, and cost optimization, and integrate rigid rule constraints and time-space lag factors to solve the national land space layout adjustment plan.

[0055] Step 8: During the layout adjustment plan generation process, the impact of the plan on future conflict evolution is evaluated in real time through the spatiotemporal fitness evaluation function. The conflict propagation prediction results and the spatiotemporal lag effect analysis results are combined to determine whether the layout adjustment plan meets the preset conflict mitigation standards.

[0056] Step 9: If the layout adjustment solution does not meet the preset conflict mitigation criteria, return to the multi-objective optimization model and solve again until the conflict mitigation criteria are met.

[0057] Step 10: If the layout adjustment plan has met the preset conflict mitigation standards, a Pareto optimal solution set that takes into account both current conflict mitigation and future risk prevention and control is generated, and the final national land space layout adjustment decision plan is output.

[0058] By introducing a multi-module collaborative mechanism, this method addresses the decision-making challenges associated with overlapping conflicts, spatiotemporal mismatches, and resource constraints in land spatial planning, significantly enhancing the scientific nature and foresight of planning adjustments. Specifically, a multi-source data fusion module is first used to perform spatiotemporal unification and semantic standardization on heterogeneous spatial data, effectively extracting the spatial distribution and evolutionary characteristics of land use conflicts and constructing a high-dimensional feature library to enhance the accuracy and comprehensiveness of conflict identification. Subsequently, a knowledge graph of land conflicts is constructed, organically linking conflict subjects, events, spaces, and attribute entities to form a multidimensional causal network, enabling structured extraction and visual representation of conflict causes. Furthermore, a spatiotemporal lag effect model, combined with a semantically enhanced knowledge graph, quantitatively analyzes conflict propagation paths and intensities, enabling accurate prediction of conflict dynamics and providing a scientific basis for subsequent intervention measures. Furthermore, different conflict types are intelligently classified to improve the efficiency of analyzing and responding to complex conflicts. Subsequently, based on the level and urgency of the conflict, a multi-stage intervention strategy is matched, taking into account both emergency response and long-term governance, forming a targeted strategy combination, and enhancing the flexibility and adaptability of spatial governance. At the layout optimization level, a multi-objective optimization model is constructed, taking into account benefits, costs and rule constraints, and deducing the layout adjustment effects under different intervention strategies. The fitness function is used to dynamically evaluate the inhibitory effect of the scheme on the evolution of future conflicts, thereby achieving iterative optimization of the planning scheme. Finally, under the condition of meeting the conflict mitigation threshold, a Pareto optimal solution set that takes into account current and future risk prevention and control is output, providing a comprehensive decision-making plan with scientific support and operability for the actual national land space layout. Overall, this method realizes a complete closed loop from conflict identification, propagation prediction to scheduling decision-making and optimized execution, breaking through the problems of traditional national land space adjustment methods that are static, isolated and dependent on experience.

[0059] Furthermore, the multi-source data fusion module adopts a hierarchical registration strategy during the spatiotemporal registration process: first, the spatial data in different coordinate systems are uniformly converted to the WGS84 geographic coordinate system to achieve consistent coordinate references; then, the common land features in the spatial data are identified through the feature point matching algorithm, and the data are geometrically corrected using the affine transformation matrix; finally, the timestamp alignment method is used to standardize the time series of data in different phases to ensure consistency in the time dimension; in the semantic unification process, a unified land use classification and coding system is constructed, and the semantic conversion between different data sources is realized through ontology mapping technology, and the confidence weighted fusion method is combined to handle semantic conflicts, ensuring that the fused data achieves spatial accuracy at the meter level on the basis of semantic consistency.

[0060] In this embodiment, a hierarchical registration strategy is used to achieve high-precision fusion of heterogeneous spatial data. Based on a unified coordinate system, time base, and semantic encoding, this effectively addresses the challenges of inconsistent coordinate bases, large timestamp discrepancies, and semantic classification conflicts across multi-source data. Spatial alignment accuracy is enhanced through affine transformation matrices and feature point matching techniques. Combined with semantic ontology mapping and a confidence-weighted mechanism, the accuracy and robustness of semantic fusion are enhanced, ultimately achieving comprehensive unification of the fused data across time, space, and semantic levels, providing a high-quality data foundation for subsequent conflict analysis and decision optimization.

[0061] Furthermore, the multi-source data fusion module includes a data preprocessing unit, a coordinate conversion unit and a semantic mapping unit, among which: the data preprocessing unit is responsible for quality inspection and noise filtering of remote sensing image data, GIS vector data, statistical survey data and field measurement data from different sensor platforms; the coordinate conversion unit completes the precise coordinate transformation between multiple spatial reference systems based on high-precision geodetic datums and projection parameters, and adopts the seven-parameter Bursa model for unified processing of three-dimensional spatial coordinates; the semantic mapping unit constructs an ontology knowledge base based on industry standards, defines a standardized land use classification system and attribute description specifications, and realizes semantic alignment between heterogeneous data sources through semantic similarity calculation and concept hierarchy matching, ensuring that the semantic representation of the same geographic entity remains consistent in each data source.

[0062] This embodiment effectively improves the coordination and consistency between different data sources through the multi-source data fusion module. The preprocessing unit ensures the reliability and availability of raw data and reduces noise interference. The coordinate conversion unit uses a seven-parameter model to unify spatial references and enhance three-dimensional positioning accuracy. The semantic mapping unit normalizes the semantics of various data by establishing an ontology knowledge base, resolving the issue of divergent semantic representations of geographic entities and providing unified, high-quality data support for subsequent conflict analysis and spatial reasoning.

[0063] Furthermore, the territorial conflict knowledge graph construction module includes an entity extraction unit, a relationship recognition unit, a knowledge fusion unit and a causal reasoning unit, among which: the entity extraction unit is used to automatically identify four types of core entities from the fused multi-source data, the conflict event entity includes attributes such as conflict type, occurrence time, duration, and impact range, the conflict subject entity includes stakeholders and their role attributes, the spatial location entity includes geographical identifiers such as administrative division code, plot code, latitude and longitude coordinates, and spatial hierarchy, and the attribute feature entity includes quantitative attributes such as economic indicators, environmental indicators, social indicators, and policy indicators; the relationship recognition unit is used to automatically identify four types of semantic relationships between entities, the causal relationship is represented by semantic labels such as "lead", "influence", "promote", and "hinder", the temporal relationship is represented by time labels such as "prior to", "simultaneously", "after", and "continuous", the spatial relationship is represented by spatial labels such as "adjacent", "include", "overlap", and "separate", and the subordinate relationship is represented by It is represented by organizational labels such as "affiliation", "jurisdiction", "responsibility", and "participation", and each relationship is assigned a confidence weight in the range of 0-1; the knowledge fusion unit identifies the same entity from different data sources by calculating the semantic similarity and structural similarity between entities, and merges entities using clustering algorithms and expert rules. At the same time, it ensures the integrity and consistency of the knowledge graph through relationship consistency verification and conflict resolution mechanism; the causal reasoning unit adopts a hybrid reasoning method, combining rule-based symbolic reasoning and statistics-based probabilistic reasoning. Symbolic reasoning constructs a causal rule library based on domain expert knowledge, "If condition A and condition B, then the probability of result C is P", and discovers potential causal relationships through forward chain reasoning and backward chain reasoning. Probabilistic reasoning uses the Bayesian network model to model causal relationships as conditional probability distributions, and calculates the joint probability of complex causal chains through the conditional independence assumption between variables. Fuzzy logic and evidence theory are introduced to deal with incomplete and uncertain causal evidence.

[0064] This embodiment provides systematic and reasonable knowledge support for planning and decision-making by constructing a clearly structured and semantically complete knowledge graph of land conflicts. The entity extraction unit accurately identifies conflict events, subjects, locations, and attributes, comprehensively reconstructing conflict scenarios. The relationship identification unit reveals causal, temporal, spatial, and subordinate relationships between entities, enhancing the logical connectivity of data. The knowledge fusion unit effectively resolves redundancy and conflicts in cross-source data, ensuring the accuracy and consistency of the graph structure. The causal reasoning unit combines symbolic logic and probabilistic models to automatically construct and evolve causal chains under uncertain conditions, significantly improving the intelligent level of conflict cause analysis and risk prediction.

[0065] Furthermore, the construction process of the spatiotemporal conflict feature vector library includes the following steps: first, the spatial autocorrelation index, landscape fragmentation index and boundary complexity index of land use conflict are calculated, and by setting different time windows, the periodic patterns, trend characteristics and abnormal changes of conflict evolution are analyzed; then, based on expert knowledge combined with statistical analysis, a subset of key features with a high influence on conflict prediction is screened out; then, continuous features are standardized, discrete features are one-hot encoded, and time series features are differentially transformed, and finally a standardized feature vector representation is constructed; at the same time, a mapping index between feature vectors and corresponding spatial positions and timestamps is established to achieve efficient spatiotemporal feature query and management.

[0066] This embodiment achieves multi-dimensional feature extraction and structured expression of land use conflicts by constructing a standardized spatiotemporal conflict feature vector library. By introducing indicators such as spatial autocorrelation, fragmentation, and boundary complexity, the spatial distribution and morphological characteristics of conflicts are quantified; combined with time window analysis of evolution trends and abnormal fluctuations, the ability to perceive the dynamic evolution of conflicts is improved. Feature screening and standardization ensure the validity and comparability of vector data, and differential transformation enhances the expressiveness of temporal changes; finally, the established spatiotemporal mapping index enables rapid positioning and management of feature data, providing efficient and accurate basic support for conflict prediction and decision-making.

[0067] Furthermore, the pre-trained spatiotemporal lag effect model adopts a deep recurrent neural network architecture, integrating an encoder-decoder structure and an attention mechanism module, wherein: the encoder part adopts a bidirectional long short-term memory network to capture the forward and backward dependency features in the time series; the decoder part uses a multi-head self-attention mechanism to dynamically learn the influence weights between different time steps; during the model training process, supervised learning samples are constructed based on historical conflict data, and a sliding time window is used to generate input sequence and target sequence pairs. The loss function is set as a weighted combination of mean square error and time decay weight, and the parameters are iteratively updated through the Adam optimization algorithm; the time series cross-validation method is used in the model verification stage to evaluate the prediction performance indicators including mean absolute error, root mean square error and correlation coefficient. At the same time, the optimal lag time window length and influence intensity attenuation parameter are determined through sensitivity analysis to ensure that the model has good prediction stability at multiple spatiotemporal scales.

[0068] This embodiment uses a deep recurrent neural network architecture, integrating a bidirectional memory mechanism and an attention mechanism, to achieve accurate modeling of the lag effect of land use conflicts in the temporal evolution process. The encoder can effectively extract the time-dependent features before and after, and the decoder dynamically assigns weights to each time step, improving the model's ability to identify the impact of conflict delays. During the training process, historical data and sliding windows are combined to generate samples, and the loss function design introduces a time decay mechanism to better fit the actual evolution process. During the verification phase, multiple error indicators and sensitivity analysis are used to ensure that the model has robust prediction capabilities at different spatiotemporal scales, providing reliable support for subsequent communication analysis and decision-making interventions.

[0069] Furthermore, the spatiotemporal conflict analysis module includes a conflict identification unit, an intensity calculation unit and a propagation analysis unit, among which: the conflict identification unit identifies land use type combinations with potential conflicts based on the land use compatibility matrix and spatial proximity criterion, and marks areas where potential conflicts may occur by setting spatial buffer thresholds and time interval parameters; the intensity calculation unit quantifies the conflict intensity using a multi-factor weighted evaluation method, comprehensively considering factors such as land use type differences, spatial overlapping area, population density, economic value and ecological sensitivity, and uses the hierarchical analysis method to determine the weight of each factor and establish a conflict intensity evaluation index system; the propagation analysis unit constructs a conflict propagation network based on graph theory and network analysis methods, with nodes representing spatial units and edges representing conflict propagation paths, and analyzes the spatial pattern and impact range of conflict propagation by calculating node centrality, clustering coefficient and path length.

[0070] This embodiment achieves accurate identification, quantitative assessment, and analysis of land use conflicts through the construction of a systematic conflict analysis process. The conflict identification unit utilizes a compatibility matrix and the principle of spatial proximity, combined with buffer zones and time parameters, to effectively screen potential conflict areas. The intensity calculation unit quantifies the severity of conflicts through a multi-factor weighting approach, taking into account spatial, social, economic, and ecological dimensions to enhance the objectivity and applicability of the evaluation results. The propagation analysis unit incorporates graph theory methods to construct a propagation network, revealing the spatial diffusion paths and clustering characteristics of conflicts, providing a clear basis for subsequent risk assessment and intervention strategy formulation.

[0071] Furthermore, the intensity calculation unit also includes an ecological value change rate calculation subunit and a social and cultural value assessment subunit: the ecological value change rate calculation subunit includes four assessment function blocks: supply service, regulation service, cultural service and support service, among which: the supply service function block calculates the value gains and losses of food production, fresh water supply, forest products, genetic resources, etc., and adopts a pricing method that combines the alternative cost method and the market price method to establish a unit area service value coefficient table covering different ecosystem types such as farmland, forests, wetlands, and grasslands; the regulation service function block evaluates the value changes of climate regulation, hydrological regulation, soil conservation, pollution purification, etc., and adopts the shadow price method and cost-effectiveness method to calculate the carbon sequestration, runoff regulation, soil The value of soil erosion control is evaluated by introducing spatiotemporal differentiation adjustment coefficients to consider the marginal value differences of regulatory services in different locations; the cultural service function block adopts the conditional value method and selection experiment method to evaluate the value of landscape aesthetics, cultural heritage, and leisure and entertainment, establishes a cultural service value assessment model based on the public's willingness to pay, and constructs a cultural service importance grading system at the national (weight 1.0), provincial (0.8), municipal (0.6), and county (0.4) levels; the supporting service function block evaluates the value of basic ecological processes such as biodiversity maintenance, soil formation, and nutrient cycling, adopts the production function method and protection cost method to calculate the indirect economic value of supporting services, and establishes an ecosystem health evaluation model to quantify the stability changes of supporting services. The social and cultural value assessment sub-unit includes three assessment functional blocks: social equity impact, cultural landscape value, and social cohesion change. Among them, the social equity impact functional block establishes the Gini coefficient change rate indicator to evaluate the impact of layout adjustment on regional development equity, calculates the changes in benefit distribution among different income groups, introduces the spatial justice index to evaluate the fairness changes in the accessibility of public service facilities, and sets the vulnerable group protection weight coefficient to give higher weight to the impact on low-income groups and the elderly group; the cultural landscape value functional block constructs a landscape value evaluation system based on historical and cultural elements, and uses the hierarchical analysis method to determine the weights of historical buildings, traditional villages, cultural routes, and intangible cultural heritage carriers; the social cohesion change functional block evaluates the impact of changes in community network structure on social capital and calculates the community stability index.

[0072] This implementation quantifies the impact of land and space adjustments on regional comprehensive functions through a dual approach of ecological and socio-cultural value assessment. Firstly, a value calculation system based on multiple assessment methods and ecosystem types is constructed, focusing on four types of ecological services: provision, regulation, culture, and support, to improve the accuracy of quantifying ecological value changes. Secondly, indicators such as social equity, cultural landscape, and social cohesion are introduced to comprehensively assess the potential impact of planning schemes on cultural heritage and social stability. Overall, this achieves a systematic quantification of multi-dimensional values, which will help optimize spatial layout and enhance ecological security and social harmony.

[0073] Furthermore, a semantic enhancement mechanism is established between the spatiotemporal conflict analysis module and the territorial conflict knowledge graph construction module. Through the causal relationships and semantic attributes provided by the knowledge graph, the conflict identification results are semantically annotated and the causes are explained. The entity matching and relationship reasoning of the knowledge graph are introduced into the conflict identification process to improve the accuracy of conflict type judgment. The causal weights and impact paths of the knowledge graph are incorporated into the intensity calculation process to enhance the scientific nature of the assessment of the degree of conflict impact. The spatial and temporal relationships of the knowledge graph are combined in the communication analysis process to optimize the construction of the communication network and path analysis, realizing the transformation from simple data statistical analysis to semantic understanding and knowledge reasoning.

[0074] This embodiment improves the explanatory power and intelligence of conflict identification and assessment by linking the spatiotemporal conflict analysis module with the knowledge graph. During the identification phase, the causal relationships and semantic labels in the graph are introduced to assign semantic meaning to conflict areas, enabling precise type judgment and automated cause tracing. In intensity calculation, the causal chains and impact weights in the graph are combined to enhance the logical consistency and scientific basis of conflict intensity assessment. In propagation analysis, the spatial and temporal relationships in the graph are utilized to assist in network structure construction, making the conflict propagation path more consistent with actual evolutionary characteristics, thereby achieving a shift from a data-driven to a knowledge-driven analysis model and enhancing intelligent reasoning capabilities and analytical depth.

[0075] Furthermore, the conflict propagation prediction module simulates the conflict propagation process in the spatial network based on the multi-agent modeling method. Each agent corresponds to a spatial unit and has state transition rules and interactive behavior patterns. The agent states include four types: no conflict, potential conflict, explicit conflict and conflict resolution. When the conflict intensity of adjacent agents exceeds the preset threshold, the state transition is triggered, and the propagation probability is determined by the distance attenuation function, terrain barrier factor and policy intervention intensity. Multiple random experiments are carried out through the Monte Carlo simulation method to statistically analyze the conflict propagation path, arrival time and impact range under different scenarios, generate probability distribution maps and risk level classifications, and identify the key parameters that have the greatest impact on the propagation process through sensitivity analysis.

[0076] This example utilizes a multi-agent modeling approach to simulate the spatial spread of conflict, demonstrating the dynamic nature of conflict evolution. Each agent represents a geographic unit, with clear state definitions and response rules. It can transition states based on conflict pressures in neighboring regions, reflecting the cascading effects of conflict spread in the real world. The probability of conflict spread is modulated by factors such as spatial distance, terrain conditions, and policy interventions, enhancing the model's relevance to real-world scenarios. Monte Carlo simulation and multi-scenario statistics quantify the uncertainty of conflict spread and generate a risk level map, providing data support for risk prediction and intervention strategies.

[0077] Furthermore, the scheduling decision module adopts a multi-criteria decision analysis framework, including an urgency assessment unit, a feasibility analysis unit, a resource allocation unit and a strategy generation unit, among which: the urgency assessment unit constructs an urgency evaluation index system including the speed of expansion of the conflict impact range, the scale of potential economic losses, the level of social stability risk, and the degree of ecological environmental degradation based on the conflict propagation prediction results and the causal analysis of the knowledge graph, adopts the hierarchical analysis method to determine the weight of each indicator, and calculates the comprehensive urgency score through the fuzzy comprehensive evaluation method. According to the score range, it is divided into four levels: urgent (≥0.8), emergency (0.6-0.8), general (0.4-0.6), and delayed (<0.4); the feasibility analysis unit evaluates the implementation conditions of intervention measures from four perspectives: technical feasibility, economic feasibility, policy feasibility, and social feasibility. Technical feasibility considers factors such as the maturity of existing technology, professional personnel deployment, and equipment conditions support. Economic feasibility evaluates investment costs, operating costs, expected returns, and difficulty in raising funds. Policy feasibility analyzes the completeness of laws and regulations, the convenience of administrative approval, and policy The feasibility level is generated by comprehensively considering factors such as the level of support, public acceptance of social feasibility assessments, difficulty in coordinating stakeholders, and the scope of social impact. The resource allocation unit uses a resource allocation optimization algorithm that combines linear programming and integer programming to allocate optimal resource combinations for intervention strategies with different urgency and feasibility levels based on the current available resource constraints, including the total amount of fiscal funds and allocation ratio, the number and professional structure of professional and technical personnel, the type and usage status of technical equipment, and the implementation time window and schedule. This ensures that the intervention effect is maximized within resource constraints. The strategy generation unit uses a decision tree algorithm and expert system method, taking the urgency assessment, feasibility analysis, and resource allocation results as decision-making inputs. Through a rule-matching mechanism based on the principle of "if urgency is X, feasibility is Y, and resource conditions are Z, then recommend strategy W," it automatically generates a phased intervention strategy combination. The strategy content includes specific intervention measures, implementation schedule, division of labor among responsible parties, expected effect indicators, risk prevention and control measures, and other elements. The overall effect of the strategy combination is optimized through a heuristic search algorithm.

[0078] This embodiment achieves the scientific formulation of conflict intervention strategies and the rational allocation of resources through multi-criteria analysis. The urgency assessment unit comprehensively considers four indicators: the speed of conflict spread, economic losses, social risks, and environmental degradation, to quantify the urgency of conflict resolution and ensure that high-risk issues are resolved first. The feasibility analysis comprehensively evaluates the implementation conditions of intervention measures from technical, economic, policy, and social perspectives to ensure the practical operability of the plan. The resource allocation unit combines financial funds, personnel structure, equipment status, and time schedule to use optimization algorithms to achieve the optimal allocation of limited resources and improve intervention efficiency. The strategy generation unit relies on decision trees and expert systems to automatically formulate phased intervention plans through rule matching, covering the content of measures, time nodes, division of responsibilities, and risk control, and uses heuristic search to optimize the overall effect to ensure that the strategy is both scientific and reasonable and feasible.

[0079] Furthermore, the scheduling decision module also includes a planning scenario classification unit, an intelligent indicator adjustment unit and a real-time dynamic adjustment trigger unit: the planning scenario classification unit divides the decision scenarios into four types: economic development orientation, ecological protection priority, social equity and comprehensive coordination. The indicator weight configuration of the economic development orientation scenario is economic benefit (0.5) > social benefit (0.3) > ecological benefit (0.2); the weight configuration of the ecological protection priority scenario is ecological benefit (0.5) > social benefit (0.3) > economic benefit (0.2); the weight configuration of the social equity scenario is social benefit (0.4) > ecological benefit (0.35) > economic benefit (0.25); the weight configuration of the comprehensive coordination scenario is economic benefit (0.35) = ecological benefit (0.35) = social benefit Benefit (0.3); The intelligent indicator adjustment unit adopts a dual mechanism of weight optimization based on machine learning and weight adjustment based on feedback learning. The machine learning weight optimization takes historical conflict data, planning implementation effects, and expert evaluation results as input, extracts key influencing factors and effect indicators through feature engineering, automatically updates indicator weights based on prediction accuracy, and outputs a scenario-based dynamic weight matrix; feedback learning weight adjustment adjusts weights according to the difference between actual implementation effects and expected goals, and uses the particle swarm optimization algorithm to find the optimal weight combination; when there is a significant conflict between different goals, the weight coordination program is started, the TOPSIS method is used to evaluate the comprehensive effect of different weight combinations, the Pareto frontier analysis is introduced to find the optimal balance point between multiple goals, and a consistency verification mechanism for weight adjustment is established to ensure logical rationality. The real-time dynamic adjustment trigger unit establishes a triple mechanism of threshold triggering, periodic evaluation and learning evolution. Among them, the threshold trigger mechanism is configured to achieve: automatic triggering of weight adjustment when the key indicator deviates from the expected value by more than 20%, initiating policy adaptive weight adjustment when a new major policy is released, and activating the emergency weight adjustment mode when an emergency environmental or economic event occurs; the periodic evaluation mechanism is configured to achieve: quarterly applicability evaluation of the indicator system, semi-annual weight validity test, and annual comprehensive indicator system optimization and upgrade; the learning evolution mechanism is configured to achieve: accumulation of best practice cases and lessons learned in different scenarios, forming an adaptive learning intelligent evaluation mechanism to continuously improve evaluation accuracy and practicality.

[0080] This embodiment achieves scenario adaptation and dynamic weight optimization for planning and scheduling decisions. By configuring indicator weights based on classified scenarios and dynamically adjusting decision preferences using machine learning and feedback algorithms, it is possible to flexibly switch between different development goals and automatically trigger the adjustment mechanism based on real-time data changes. The triple trigger mechanism ensures the timeliness and adaptability of planning responses and supports emergency response and policy adaptation. Overall, it enhances the intelligence, flexibility, and practicality of national land space scheduling strategies and improves the scientific nature of decision-making under multi-objective coordination.

[0081] Furthermore, a hierarchical analysis method was used to analyze the trend of cross-scale conflict transmission paths. The study area was divided into three spatial levels: regional scale, county scale, and plot scale, and corresponding grid resolutions and analysis units were configured for different levels. At the regional scale, macro-analysis was used to identify inter-regional conflict transmission trends and main transmission corridors, with a grid size of 5 km × 5 km. At the county scale, meso-analysis was conducted to identify local conflict hotspots and transmission nodes, with a grid size of 1 km × 1 km. At the plot scale, detailed analysis was used to identify specific conflict locations and their transmission paths, with a grid accuracy of 100 m × 100 m. Information transmission and feedback mechanisms were used between scales to achieve top-down coordination, ensuring the consistency and accuracy of conflict transmission path analysis in multi-scale space.

[0082] This implementation utilizes hierarchical analysis to identify conflict transmission paths across different scales. Appropriate grid resolutions are employed at each spatial level, from regions (5 km x 5 km) to counties (1 km x 1 km) and finally to plots (100 m x 100 m), ensuring a balanced consideration of both macro-trends and micro-details. Information sharing and feedback mechanisms coordinate across these levels, ensuring the continuity and accuracy of transmission path identification. This fully reveals the patterns of conflict diffusion at different spatial scales, providing a reliable basis for the formulation of scientific, tiered intervention strategies.

[0083] Furthermore, the preset spatiotemporal lag threshold is determined based on the statistical analysis results of historical conflict data: by calculating the spatiotemporal lag distribution characteristics of historical conflict events, the threshold is set using the percentile method, where the time lag threshold is taken as the 75th percentile of the historical data, and the spatial lag threshold is taken as the 80th percentile of the historical propagation distance; the impact intensity threshold is based on the conflict impact degree classification standard, and is divided into four intensity levels of mild, moderate, severe and extremely severe using the quartile method, and the optimal split point is determined through ROC curve analysis to ensure that the threshold can not only effectively identify key conflicts, but also avoid misjudgment due to excessive sensitivity.

[0084] This example uses a systematic statistical analysis of historical conflict data to scientifically determine thresholds for temporal and spatial lags and impact intensity. The temporal lag threshold uses the 75th percentile, reflecting the typical time range over which most conflicts spread; the spatial lag threshold uses the 80th percentile, covering the propagation distances of most conflicts. The impact intensity threshold is based on a grading standard for conflict severity, combining quartile analysis and receiver operating characteristic (ROC) curve optimization to ensure accurate classification and practical application. This threshold setting method effectively balances sensitivity and accuracy, providing a robust basis for conflict identification and risk assessment.

[0085] Furthermore, the phased intervention strategy is formulated through dynamic planning based on the time priority matrix and resource constraints, and the intervention measures are divided into four implementation phases according to the urgency of implementation and the intensity of resource demand: the emergency response period (0-3 months) is mainly aimed at conflicts rated as extremely urgent and urgent, and temporary rapid response measures are adopted, including the establishment of spatial control buffer zones, the implementation of temporary use restrictions, the activation of emergency response plans, and the coordination of relevant departments. The key goal is to quickly control the spread of conflicts and stabilize the situation; the short-term governance period (3-12 months) is to implement direct intervention measures for identified explicit conflicts, including local land use adjustments, relocation and transformation of conflict facilities, restoration of damaged ecological environment, and coordination and negotiation among stakeholders. The key goal is to eliminate current prominent contradictions and restore normal order; the mid-term adjustment period is mainly aimed at conflicts rated as extremely urgent and urgent, and temporary rapid response measures are adopted, including the establishment of spatial control buffer zones, the implementation of temporary use restrictions, the activation of emergency response plans, and the coordination of relevant departments. The key goal is to quickly control the spread of conflicts and stabilize the situation. During the entire period (1 to 3 years), systematic structural adjustment measures will be implemented based on the results of layout optimization, including regional function repositioning, industrial structure optimization and upgrading, infrastructure network reconstruction, and improvement of institutional mechanisms. The key goals are to establish a long-term governance mechanism and enhance system stability. During the long-term consolidation period (more than 3 years), institutional construction and capacity enhancement measures will be implemented, including improving the relevant legal and regulatory system, establishing an intelligent monitoring and early warning system, enhancing the collaborative governance capabilities of multiple departments, and cultivating a sustainable development model. The key goal is to achieve the organic unity of conflict prevention and sustainable development. A dynamic adjustment mechanism will be established in the strategy formulation process at each stage. Through real-time monitoring of changes in key indicators and evaluation of intervention effects, the strategy correction procedure will be automatically triggered when the actual implementation results deviate from the expected goals, ensuring the scientific nature and adaptability of the phased strategy.

[0086] This implementation plan is scientifically divided into four phases, taking into account time priorities and resource constraints, to ensure targeted and continuous intervention measures. The emergency response phase focuses on high-urgency conflicts, swiftly implementing temporary control and emergency measures to prevent their spread. The short-term governance phase targets overt conflicts, implementing specific adjustments and repairs to restore regional order. The mid-term adjustment phase promotes structural optimization and institutional improvement to strengthen the governance system. The long-term consolidation phase focuses on institutional development and capacity enhancement to achieve sustainable development. A dynamic adjustment mechanism runs throughout the entire process, flexibly revising strategies based on real-time monitoring and evaluation to ensure the effective connection and continuous optimization of intervention measures at each stage.

[0087] Furthermore, the identification of explicit conflicts adopts a multi-criteria decision analysis method, which comprehensively considers the spatial overlap, functional incompatibility, environmental impact and socio-economic loss factors of the conflicts, and uses a weighted comprehensive evaluation model to calculate the conflict severity index; the identification of potential conflicts is based on the propagation prediction results, and the probability threshold method is used to judge that the area where the propagation probability exceeds the set threshold is a potential conflict area. At the same time, combined with the propagation time window and the impact range, a spatiotemporal buffer zone is set for early warning; the identification results include conflict location, conflict type, impact level, probability of occurrence and expected time information, which are visualized through the geographic information system.

[0088] In this embodiment, explicit conflict identification utilizes a multi-criteria comprehensive evaluation, incorporating factors such as spatial overlap, functional compatibility, environmental impact, and socioeconomic losses. A weighted model is constructed to quantify conflict severity, ensuring comprehensive and scientific assessment results. Potential conflicts are identified using probability thresholds based on propagation predictions to identify areas with a high likelihood of propagation. This, combined with the establishment of spatiotemporal buffer zones, enables early warning. The final identification results include the specific location, type, impact intensity, probability of occurrence, and estimated time of the conflict. These results are intuitively displayed through a GIS platform, enabling decision-makers to promptly understand conflict dynamics and formulate targeted measures.

[0089] Furthermore, in the objective function design of the multi-objective optimization model, the conflict minimization goal comprehensively considers the severity and handling costs of various conflicts through weighted summation; the benefit maximization goal covers three sub-goals: economic benefits, ecological benefits, and social benefits; the cost optimization goal covers land consolidation costs, infrastructure construction costs, and ecological restoration costs; the weights of each objective function are determined by combining the hierarchical analysis method and the Delphi method, and field experts are invited to judge the weights, and the rationality of the weight setting is ensured through consistency testing; the model is solved using a classic genetic algorithm, and an elite retention strategy is introduced to balance the convergence and diversity of the solution. The parameters are set as: population size 50, crossover probability 0.8, mutation probability 0.1, and maximum evolutionary generations 200 generations.

[0090] This embodiment integrates the three goals of conflict minimization, benefit maximization, and cost optimization through weighted methods, taking into account the key needs in land use adjustment. Conflict minimization focuses on measuring the severity of conflicts and the cost of responses. Benefit targets cover multiple levels of economy, ecology, and society, while cost targets are refined to aspects such as land consolidation, infrastructure, and ecological restoration. Weights are determined by combining hierarchical analysis with the Delphi method, and experts are invited to review and conduct consistency tests to ensure that the weight distribution is scientific and reasonable. The genetic algorithm is used for solution, combined with the elite retention strategy, to effectively balance search efficiency and solution diversity. The parameters are reasonably configured to ensure stable and high-quality optimization results within 200 generations.

[0091] Furthermore, the multi-objective optimization model dynamically adjusts the objective function structure and constraint settings according to different planning scenarios. In the economic development-oriented scenario, the weight of the conflict minimization objective is reduced to 0.3, the weight of the benefit maximization objective is increased to 0.5, and the weight of the cost optimization objective is set to 0.2. At the same time, some ecological constraints are relaxed, allowing moderate development under the premise of strict environmental impact assessment; in the ecological protection priority scenario, the weight of the conflict minimization objective is increased to 0.5, the weight of the benefit maximization objective is reduced to 0.2, and the weight of the cost optimization objective is set to 0.3, strengthening the ecological protection red line and environmentally sensitive areas. Rigid constraints, adding a bottom line constraint that the ecosystem service function will not be reduced; in the scenario of taking social equity into consideration, a social equity target sub-function is added to the objective function, and the weight configuration is adjusted to conflict minimization (0.35), benefit maximization (0.3), cost optimization (0.2), and social equity (0.15). The constraints are added to the balanced configuration of public service facilities and the protection of the basic rights and interests of vulnerable groups; in the comprehensive coordination scenario, a dynamic balance mechanism of three objectives is established, and the weights of each objective are fine-tuned within the range of ±10% based on the real-time evaluation results to ensure the coordinated development of economic, ecological, and social benefits. When the planning scenario changes, the objective function is gradually adjusted through the weight interpolation method to avoid the solution space jump caused by sudden switching. The interpolation formula is: W new (t)=W old ×(1-t)+W target ×t, where: W old Indicates the currently used optimization weight configuration, that is, the set of objective function weight values ​​before the scene switch occurs; W target W represents the new weight configuration target to be achieved after the planning scenario changes, that is, the set of weight values ​​that different objective functions should have in the new planning scenario; new (t) represents the current iterative weight vector in the transition phase, which is used to achieve the transition from W old To W target A smooth transition is achieved; t is the transition progress parameter, which increases linearly from 0 to 1, and the transition period is set to 5-10 optimization iteration cycles; when the optimization result deviates significantly from the goal orientation of the selected scenario, the constraints are automatically adjusted or the target weights are reconfigured to ensure the consistency of the final solution with the scenario expectations; at the same time, corresponding optimization solutions are generated for different scenarios, and multiple options are provided to decision makers through comparative analysis. A scenario sensitivity analysis function is also established to evaluate the impact of changes in key parameters on the optimization results in different scenarios.

[0092] This embodiment achieves adaptive optimization and adjustment of planning objectives under different scenarios. By dynamically changing the objective function structure and constraints, it ensures a balance between economic, ecological, and social goals. A weighted interpolation method ensures continuity during scenario switching and avoids fluctuations in the solution space. The system automatically adjusts the optimization path based on the degree of deviation and generates multiple optimization solutions for comparison and selection, enhancing the flexibility, robustness, and interpretability of planning decisions while improving adaptability to complex scenario changes.

[0093] Furthermore, a collaborative optimization mechanism is established between the layout optimization module and the scheduling decision module. The phased intervention strategy output by the scheduling decision module is used as the constraint condition and guiding principle for layout optimization. A strategy consistency constraint is added to the multi-objective optimization model to ensure the coordination and unity of the optimization results and the phased intervention strategy. At the same time, the strategy implementation cost and time benefit terms are introduced into the objective function. The cost-benefit ratio and time value of strategies at different stages are comprehensively considered. A hierarchical solution strategy is adopted in the optimization process. The key constraint variables are first determined according to the emergency and short-term strategy requirements. Then, the medium- and long-term layout plan is optimized on this basis to achieve an organic combination of short-term emergency response and long-term system optimization, thereby improving the overall scientificity and operability of the layout adjustment plan.

[0094] This example incorporates phased intervention strategies into the optimization model's constraints, ensuring consistency between the layout adjustment plan and intervention measures. By introducing cost-effectiveness and time-effectiveness metrics for strategy implementation, the economic feasibility and timeliness of strategies at different stages are comprehensively evaluated. The optimization employs a hierarchical approach, first satisfying the key constraints of emergency and short-term strategies, then advancing the design of medium- and long-term solutions, achieving an organic integration of short-term response and long-term planning.

[0095] Furthermore, rigid rule restrictions include legal and regulatory constraints, ecological protection constraints, infrastructure constraints and safety protection constraints, among which: legal and regulatory constraints include land use nature and development intensity restrictions determined by statutory plans such as the land use master plan, urban master plan, and environmental protection plan; ecological protection constraints include strict protection requirements for ecological protection red lines, environmentally sensitive areas, water source protection areas, and nature reserves; infrastructure constraints include safety protection distances and functional guarantee requirements for important transportation facilities, energy facilities, water conservancy facilities, communication facilities, and other infrastructure; safety protection constraints include development and construction restrictions in areas prone to geological disasters, flood risk areas, and hazardous chemical production and storage areas; spatiotemporal lag factors are embedded in the optimization model through dynamic weight adjustment: when the layout plan violates the soft constraints, punitive weights are assigned to the relevant items in the objective function, and the weight adjustment range is calculated in grades based on the degree of deviation and the duration of the impact, thereby achieving a coordinated balance between the strict implementation of hard constraints and the flexible guidance of soft constraints.

[0096] In this example, rigid rule restrictions encompass four key areas: laws and regulations, ecological protection, infrastructure, and safety. These clearly define land use, development intensity, and protection requirements to ensure planning compliance and environmental safety. Legal and regulatory constraints ensure that land use complies with statutory plans at all levels; ecological protection constraints strictly limit development activities in ecologically sensitive areas; infrastructure constraints maintain safe distances and proper functionality of critical facilities; and safety protection constraints guard against geological disasters, flood risks, and hazardous chemical safety hazards. Temporal and spatial lag factors are incorporated into the optimization model as dynamic weights, imposing graded penalties for violations of soft constraints. Weight adjustments are based on the magnitude and duration of deviations, achieving a flexible balance between strict adherence to rigid rules and flexible guidance.

[0097] Furthermore, a spatiotemporal fitness evaluation function is constructed based on a multi-criteria decision analysis method, covering three dimensions: conflict mitigation effect, future development adaptability, and rationality of program implementation. In terms of conflict mitigation effect evaluation, the direct effectiveness of the program in reducing conflicts is quantified by calculating the conflict intensity change rate, conflict area reduction rate, and conflict propagation blocking rate before and after layout adjustment. In terms of future development adaptability evaluation, a scenario analysis method is used to set various development scenarios such as rapid economic development, stable population growth, and environmental protection priority, and the adaptability score and robustness index of the program under each scenario are evaluated to reflect the program's ability to cope with future uncertainties. In terms of program implementation rationality evaluation, the implementation cost, technical difficulty, policy support, public acceptance and other factors are comprehensively considered, and the feasibility is quantitatively evaluated using a fuzzy comprehensive evaluation method. The overall spatiotemporal fitness score is obtained by weighted aggregation of the evaluation results of the three dimensions, and sensitivity analysis and uncertainty analysis mechanisms are introduced to improve the robustness and explanatory power of the evaluation results.

[0098] In this embodiment, the spatiotemporal fitness evaluation function integrates the three dimensions of conflict mitigation effect, future development adaptability, and rationality of program implementation to comprehensively evaluate the layout adjustment program. In terms of conflict mitigation, the direct governance effectiveness of the program is quantified by analyzing the change in conflict intensity and area and the effect of blocking transmission. Future adaptability uses scenario analysis to examine the stability and adaptability of the program under different economic, demographic, and environmental development backgrounds. The evaluation of implementation rationality combines cost, technical difficulty, policy support, and public recognition, and adopts fuzzy comprehensive evaluation to achieve quantification. The results of the three parts are weighted and integrated to generate an overall fitness score, supplemented by sensitivity and uncertainty analysis to ensure that the evaluation results are scientific and have practical guiding value.

[0099] Furthermore, the conflict mitigation standards include quantitative standards and qualitative standards, among which: the quantitative standards judge whether the plan meets the basic requirements by setting minimum thresholds for the conflict intensity reduction rate, conflict area reduction rate, and conflict propagation blocking rate. The conflict intensity reduction rate is required to be no less than 10%, the reference value for the conflict area reduction rate is no less than 8%, and the reference value for the conflict propagation blocking rate is no less than 15%; the qualitative standards comprehensively judge the rationality and acceptability of the plan through expert evaluation and stakeholder participation. The evaluation content includes whether it is in line with the regional development strategy, whether it meets the people's livelihood needs, whether it fully considers ecological and environmental protection, and whether the conditions for implementation are met; the fuzzy reasoning method is introduced in the standard judgment process to convert the quantitative indicators and qualitative evaluation results into fuzzy membership, and the comprehensive judgment results are obtained through the fuzzy rule base and reasoning engine; when the quantitative and qualitative standards are met at the same time, the plan is judged to be passed, otherwise it is necessary to return to the optimization process and solve it again.

[0100] In this embodiment, conflict mitigation criteria encompass both quantitative and qualitative aspects. Quantitative criteria set thresholds for conflict intensity reduction (≥10%), conflict area reduction (≥8%), and conflict propagation interruption (≥15%) to measure the effectiveness of the solution in actual conflict management. Qualitative criteria, through expert review and stakeholder engagement, comprehensively assess whether the solution aligns with regional development strategies, meets public needs, balances ecological protection, and meets implementation requirements. The evaluation process utilizes fuzzy reasoning, converting quantitative indicators and subjective evaluations into fuzzy membership degrees. The solution's eligibility is then comprehensively assessed using a rule base and inference engine. A solution is accepted only if both quantitative and qualitative criteria are met; otherwise, it undergoes rollback and optimization to ensure that the final solution is both scientifically effective and feasible.

[0101] Furthermore, the re-solution process of the multi-objective optimization model adopts a parameter fine-tuning strategy, and appropriately adjusts the parameters according to the quality of the current solution and the search status, including adjusting the population size between 40-60, the crossover probability between 0.7-0.9, and the mutation probability between 0.05-0.15; in the re-solution process, a multi-population parallel evolution mechanism is adopted, the main population is divided into 3-5 sub-populations for parallel search, and the optimal individuals are migrated between populations every 10 generations; in the solution process, a convergence judgment criterion is set: when the objective function improvement for twenty consecutive generations is less than 0.001, it is judged to be converged.

[0102] In this example, when resolving the multi-objective optimization model, a parameter fine-tuning strategy was employed to dynamically adjust the population size (40-60), crossover probability (0.7-0.9), and mutation probability (0.05-0.15) to adapt to the search progress and improve the quality of the solution. A multi-population parallel evolution mechanism was introduced, dividing the main population into 3-5 subpopulations for simultaneous search, enhancing the algorithm's diversity and global exploration capabilities. The optimal individual was migrated every 10 generations to promote information sharing. Convergence was determined based on the improvement in the objective function; the algorithm was considered converged if the improvement was less than 0.001 for 20 consecutive generations, ensuring an efficient and stable solution process.

[0103] Furthermore, the strategy of balancing current conflict mitigation and future risk prevention and control adopts a time-weighted approach, assigning different weights to the impact of conflicts in different periods through an exponentially decaying time decay function, with high weights assigned to recent conflicts and low weights assigned to long-term conflicts; the risk prevention and control strategy is based on scenario analysis, setting three types of future development scenarios: conventional scenarios, challenge scenarios, and opportunity scenarios, and formulating corresponding response measures for each scenario; the strategy dynamic adjustment mechanism relies on real-time optimization of feedback information during the implementation process, and by monitoring changes in key node indicators, triggering the strategy adjustment procedure when the indicators deviate from the expected range; the strategy effectiveness evaluation adopts a cost-benefit analysis method, comprehensively comparing input costs and expected returns, while considering social and environmental benefits to ensure the economic feasibility and sustainability of the strategy.

[0104] This embodiment uses a time-weighted approach and an exponential decay function to assign differentiated weights to the impact of conflicts at different time stages, prioritizing the resolution of near-term conflicts while also taking into account the prevention of long-term risks. Risk prevention and control integrates scenario analysis, setting three future scenarios: routine, challenge, and opportunity. Targeted response measures are then formulated to enhance the flexibility and relevance of the strategy. A dynamic adjustment mechanism optimizes strategies in real time based on implementation feedback, monitors changes in key indicators, and promptly corrects deviations to ensure the continued effectiveness of intervention measures. Strategy evaluation utilizes cost-benefit analysis, comprehensively considering economic input, social impact, and environmental benefits to ensure the economic rationale and long-term sustainability of the plan.

[0105] Furthermore, the final decision-making plan for adjusting the spatial layout of the national land includes four parts: a spatial layout adjustment map, an implementation timetable, a policy measure proposal, and an effect evaluation report. Among them: the spatial layout adjustment map is drawn using standard map making specifications, including the current layout map, the planned layout map, the adjustment comparison map, and the detailed map of key areas. The map scale is set according to the needs of different levels: 1:25,000 to 1:50,000 for the city and county level, 1:5,000 to 1:10,000 for the township level, and 1:1000 to 1:2000 for key areas; the implementation timetable is set according to the degree of urgency, implementation difficulty, and The funding demand factor is used to formulate a phased implementation plan, including short-term implementation projects, medium-term implementation projects and long-term implementation projects. Each project clearly defines the implementation entity, implementation time, funding source and expected results; the policy measure proposal puts forward specific policy suggestions based on the policy needs of the program implementation, including suggestions on the improvement of laws and regulations, funding guarantee measures, technical support conditions and organizational management system; the effect evaluation report adopts a combination of quantitative and qualitative evaluation methods, sets up an evaluation index system and evaluation methods, and establishes a tracking and monitoring mechanism for implementation effects, providing a scientific basis for the dynamic adjustment and continuous improvement of the program.

[0106] In this example, the final decision-making plan for adjusting the national land spatial layout consists of four parts: a spatial layout adjustment map, an implementation schedule, policy and measure recommendations, and an effectiveness evaluation report. The spatial layout adjustment map is drawn according to standard cartographic specifications and covers the current situation, planned areas, adjustment comparisons, and detailed maps of key areas. The scales are set at 1:25,000–1:50,000 at the city and county level, 1:5,000–1:10,000 at the township level, and 1:1,000–1:2,000 for key areas. The implementation schedule is divided into short-term, medium-term, and long-term projects based on urgency, implementation difficulty, and funding needs. It clearly defines the implementing entities, timelines, funding sources, and expected results. The policy and measure recommendations address implementation needs, including specific recommendations for improving regulations, funding guarantees, technical support, and management system development. The effectiveness evaluation report integrates both quantitative and qualitative indicators and establishes a tracking and monitoring mechanism to ensure dynamic evaluation and continuous optimization of the plan's implementation.

[0107] Furthermore, step 3 includes the following steps.

[0108] The quality of historical land use conflict event data was checked, and the regional data were mapped to a unified grid unit based on the spatial weight matrix. The sequences were then aligned according to the timestamps to generate a normalized spatiotemporal dataset.

[0109] The spatiotemporal conflict analysis module is used to calculate the conflict intensity index of each grid unit. Combining the neighborhood location characteristics and the semantic information in the territorial conflict knowledge graph, a multidimensional time series feature vector sequence integrating causal relationships is constructed based on a sliding time window.

[0110] The multi-dimensional time series feature vector sequence is input into the encoder part of the pre-trained spatiotemporal lag effect model, and a bidirectional long short-term memory network is used to capture the forward and backward associations in the sequence. Combined with the semantic enhancement information of the knowledge graph, the hidden state vector containing lag information and causal chain reasoning is output.

[0111] The decoder performs weighted aggregation of hidden state vectors through the attention mechanism, integrates the causal chain reasoning results in the knowledge graph, and maps the weight distribution of different time steps into the prediction parameters of the conflict impact intensity and duration at the current moment, thereby achieving accurate prediction of the conflict status over time.

[0112] Based on the hysteresis coefficient and spatial propagation probability in the decoder output, combined with the semantic enhancement analysis of the knowledge graph, the prediction results are mapped back to the geographic grid, automatically capturing and quantifying the spatiotemporal propagation paths and corresponding time delays of land use conflicts between regions, thereby generating a spatiotemporal propagation trajectory map that includes propagation and hysteresis effects.

[0113] The predicted conflict intensity and duration are compared with the measured data for error analysis; if the prediction error exceeds the set threshold, the lag window length or spatial weight parameter in the model is dynamically adjusted based on the sensitivity analysis results and knowledge graph feedback, and iterative optimization is performed until the prediction accuracy meets the set standards.

[0114] This embodiment generates a unified and standardized spatiotemporal dataset by strictly quality-checking and spatial mapping historical land use conflict data, ensuring data consistency and accuracy. With the help of the spatiotemporal conflict analysis module, combined with the characteristics of neighboring areas and the semantic information of the knowledge graph, a temporal feature vector integrating causal relationships is constructed to achieve an in-depth characterization of the evolution of the conflict. The feature sequence is input into the pre-trained model, and through the bidirectional long short-term memory network and attention mechanism, the temporal correlation and causal relationship of the conflict are accurately captured, and the intensity and duration of the conflict impact are predicted. The prediction results are mapped back to the geographic grid, and the propagation path and time delay of the conflict are automatically quantified to form a detailed spatiotemporal propagation trajectory. By comparing the prediction with the measured data, the model parameters are dynamically adjusted, the prediction accuracy is continuously optimized, and the understanding and early warning capabilities of the spatiotemporal evolution of land use conflicts are improved.

[0115] Furthermore, step 4 includes the following steps.

[0116] At the three spatial levels of region, county, and plot, conflict propagation networks are constructed based on grid units or administrative boundary units, where nodes represent corresponding spatial units and edge weights are determined by the conflict transmission probability and distance decay function between adjacent nodes to ensure accurate mapping of network structures at different scales.

[0117] A multi-agent model is introduced at each network level to simulate the diffusion process of conflicts. Agents migrate between nodes according to preset state transition rules. At the same time, the shortest path algorithm is used to automatically extract the optimal propagation path of conflicts from the simulation results.

[0118] The resistance value corresponding to the comprehensive barrier factor is calculated for each edge on the path, and the path cost weight is assigned after normalization to achieve accurate quantification of multiple influencing factors.

[0119] The optimal propagation paths and their resistance costs identified in each level of the network are summarized. By comparing the path length, accumulated resistance value and propagation time delay, the cross-scale propagation trend characteristics are extracted, providing a quantitative analysis basis for the trend differences between the macro and micro levels.

[0120] Based on the total value of path resistance and the transmission probability, combined with the threshold quantile method, a risk score is implemented for each transmission path, and it is divided into three risk levels: low, medium, and high, so as to identify potential key conflict diffusion corridors and high-risk sections.

[0121] The optimal propagation path, resistance distribution, and risk level are displayed as map layers, and trend analysis and risk assessment reports are automatically generated, including cross-scale path comparison charts, resistance factor contribution bar charts, and risk area distribution heat maps.

[0122] In this embodiment, step 4 covers three spatial levels: regions, counties, and plots, and constructs a corresponding conflict propagation network. Nodes represent spatial units, and edge weights are determined by conflict transmission probability and distance attenuation. The multi-agent model is used to simulate conflict diffusion, and the shortest path algorithm is used to extract the optimal propagation path. The barrier factors of the path edges are quantified and assigned cost weights. The cross-scale path length, resistance, and propagation delay are comprehensively analyzed to reveal differences in propagation trends. Based on path resistance and propagation probability, a threshold method is used to perform risk scoring, divide risk areas into low, medium, and high levels, and identify key diffusion corridors. Finally, the propagation path, resistance distribution, and risk level are displayed in the form of a map layer, and a trend and risk assessment report is generated.

[0123] Furthermore, step 8 includes the following steps.

[0124] The spatial structure parameters, land use type distribution and adjustment range of the current layout adjustment plan are input into the spatiotemporal fitness evaluation function, and combined with the future conflict situation characteristics output by the conflict propagation prediction module to extract the key impact indicators of the layout plan on the conflict evolution process.

[0125] The evaluation indicators of the layout plan in three dimensions, namely conflict mitigation effect, future development adaptability and implementation rationality, are calculated respectively, and a comprehensive evaluation vector is constructed based on them.

[0126] According to the predetermined expert weight system, each indicator is weighted, and the comprehensive fitness score of the scheme is generated by weighted summation.

[0127] The obtained fitness score is compared with the set conflict mitigation standard to quantitatively determine whether the current layout plan meets the minimum threshold requirements of conflict intensity reduction, conflict area reduction, and propagation path blocking indicators.

[0128] Combined with the results of the spatiotemporal lag effect analysis, the time delay and persistence changes in the conflict propagation process after the layout adjustment are tested to further verify whether the control effect of the scheme on the conflict evolution trend at different time nodes in the future is in line with expectations.

[0129] This implementation uses the spatial structural parameters and land use adjustments of the layout plan as inputs to a spatiotemporal fitness evaluation function. This function, combined with future conflict dynamics, extracts key influencing indicators. Evaluations are calculated for conflict mitigation effectiveness, future adaptability, and implementation rationality, and a comprehensive fitness score is generated based on expert weighting. This score is then compared with conflict mitigation criteria to determine whether the plan meets the minimum requirements for reducing conflict intensity, reducing area, and interrupting conflict transmission. Furthermore, the spatiotemporal lag effect is incorporated to verify the plan's effectiveness in controlling the delay and duration of conflict transmission, ensuring compliance with intended objectives.

[0130] Finally, it should be noted that the above embodiments are intended only to illustrate the technical solutions of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art will appreciate that modifications may be made to the technical solutions described in the above embodiments, or that some of the technical features may be replaced with equivalents; such modifications or replacements do not deviate from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A land space layout adjustment decision-making method based on planning conflict identification, applied to a land space planning decision-making system, characterized by: The national land space planning decision-making system includes a multi-source data fusion module, a spatiotemporal conflict analysis module, a conflict propagation prediction module, a national land conflict knowledge graph construction module, a scheduling decision module, and a layout optimization module, including the following steps: Step 1: Use the multi-source data fusion module to perform spatiotemporal registration and semantic unification of multi-source heterogeneous spatial data, and automatically extract the spatial distribution characteristics, temporal evolution patterns, and semantic attribute characteristics of land use conflicts, thereby constructing a spatiotemporal conflict feature vector library containing multidimensional attributes; Step 2: Through the territorial conflict knowledge graph construction module, based on the fused multi-source data, the conflict event entities, conflict subject entities, spatial location entities, and attribute feature entities are automatically extracted to construct a four-element semantic network. The complete causal chain of the conflict causes is identified, and a semantic knowledge graph containing causal relationships, temporal relationships, spatial relationships, and subordinate relationships is generated. Step 3: Based on the pre-trained spatiotemporal lag effect model and semantic enhancement of the land conflict knowledge graph, the spatiotemporal conflict analysis module automatically captures and quantifies the spatiotemporal propagation and lag effects of land use conflicts between different regions. Combined with the causal chain reasoning results in the knowledge graph, it achieves accurate prediction of the impact intensity and duration of the conflict status over time. Step 4: The conflict propagation prediction module intelligently identifies the optimal propagation paths of land use conflicts across different spatial scales and quantifies the impact of various factors on conflict propagation, thereby enabling trend analysis and risk level assessment of cross-scale conflict propagation paths. Step 5: Automatically identify explicit conflicts in the current layout and potential conflicts based on propagation predictions based on preset spatiotemporal hysteresis thresholds and impact intensity thresholds, and intelligently classify complex conflicts using fuzzy clustering. Step 6: Based on the identified explicit and potential conflicts, the scheduling decision-making module comprehensively evaluates the urgency of conflict mitigation, the rationality of intervention measures, and the available resource allocation capabilities. It then automatically generates phased, differentiated conflict intervention strategy recommendations, including strategy combinations and their priority rankings for the emergency response period, short-term governance period, mid-term adjustment period, and long-term consolidation period. Step 7: Use the layout optimization module to build a multi-objective optimization model with the goals of conflict minimization, benefit maximization, and cost optimization, and integrate rigid rule constraints and time-space lag factors to solve the national land space layout adjustment plan.

2. The method for adjusting the national land space layout based on planning conflict identification according to claim 1 is characterized in that: The multi-source data fusion module adopts a hierarchical registration strategy in the process of spatiotemporal registration: first, the spatial data in different coordinate systems are uniformly converted to the WGS84 geographic coordinate system to achieve consistent coordinate references; Then, the common land features in the spatial data are identified through the feature point matching algorithm, and the data is geometrically corrected using the affine transformation matrix; finally, the timestamp alignment method is used to standardize the time series of data in different phases to ensure the consistency of the time dimension; in the process of semantic unification, a unified land use classification and coding system is constructed, and the semantic conversion between different data sources is realized through ontology mapping technology. The confidence-weighted fusion method is combined to deal with semantic conflicts, ensuring that the fused data achieves spatial accuracy at the meter level on the basis of semantic consistency.

3. The method for adjusting the national land space layout based on planning conflict identification according to claim 1 is characterized in that: The multi-source data fusion module includes a data preprocessing unit, a coordinate conversion unit, and a semantic mapping unit. The data preprocessing unit is responsible for quality inspection and noise filtering of remote sensing image data, GIS vector data, statistical survey data, and field measurement data from different sensor platforms. The coordinate conversion unit completes precise coordinate transformation between multiple spatial reference systems based on high-precision geodetic datums and projection parameters, and uses the seven-parameter Bursa model for unified processing of three-dimensional spatial coordinates. The semantic mapping unit constructs an ontology knowledge base based on industry standards, defines a standardized land use classification system and attribute description specifications, and achieves semantic alignment between heterogeneous data sources through semantic similarity calculation and concept hierarchy matching, ensuring that the semantic representation of the same geographic entity remains consistent in each data source.

4. The method for adjusting the national land space layout based on planning conflict identification according to claim 1 is characterized in that: The pre-trained spatiotemporal lag effect model adopts a deep recurrent neural network architecture, integrating an encoder-decoder structure and an attention mechanism module. Among them, the encoder part adopts a bidirectional long short-term memory network to capture the forward and backward dependency features in the time series; the decoder part uses a multi-head self-attention mechanism to dynamically learn the influence weights between different time steps; during the model training process, supervised learning samples are constructed based on historical conflict data, and a sliding time window is used to generate input sequence and target sequence pairs. The loss function is set as a weighted combination of mean square error and time decay weight, and the parameters are iteratively updated through the Adam optimization algorithm; the time series cross-validation method is used in the model verification stage to evaluate the prediction performance indicators including mean absolute error, root mean square error and correlation coefficient. At the same time, the optimal lag time window length and influence intensity attenuation parameter are determined through sensitivity analysis to ensure that the model has good prediction stability at multiple spatiotemporal scales.

5. The method for adjusting the national land space layout based on planning conflict identification according to claim 1 is characterized in that: The spatiotemporal conflict analysis module includes a conflict identification unit, an intensity calculation unit, and a propagation analysis unit. Among them, the conflict identification unit identifies land use type combinations with potential conflicts based on the land use compatibility matrix and spatial proximity criterion, and marks areas where potential conflicts may occur by setting spatial buffer thresholds and time interval parameters; the intensity calculation unit quantifies the conflict intensity using a multi-factor weighted evaluation method, comprehensively considering factors such as land use type differences, spatial overlap area, population density, economic value, and ecological sensitivity, and uses the hierarchical analysis method to determine the weight of each factor and establish a conflict intensity evaluation index system; the propagation analysis unit constructs a conflict propagation network based on graph theory and network analysis methods, with nodes representing spatial units and edges representing conflict propagation paths. The spatial pattern and impact range of conflict propagation are analyzed by calculating node centrality, clustering coefficient, and path length.

6. The method for adjusting the national land space layout based on planning conflict identification according to claim 1 is characterized in that: The scheduling decision module includes an urgency assessment unit, a feasibility analysis unit, a resource allocation unit, a strategy generation unit, a planning scenario classification unit, an intelligent indicator adjustment unit, and a real-time dynamic adjustment trigger unit. Among them: the urgency assessment unit constructs an urgency evaluation index system based on the conflict propagation prediction results and causal analysis of the knowledge graph; the feasibility analysis unit is used to evaluate the implementation conditions of intervention measures; the resource allocation unit allocates the optimal resource combination for the intervention strategy based on the current available resource constraints; the strategy generation unit uses the urgency assessment, feasibility analysis, and resource allocation results as decision-making inputs to automatically generate a phased intervention strategy combination; the planning scenario classification unit divides the decision scenarios into four types: economic development orientation, ecological protection priority, social equity consideration, and comprehensive coordination.

7. The method for adjusting the national land space layout based on planning conflict identification according to claim 1 is characterized in that: The conflict propagation prediction module simulates the conflict propagation process in the spatial network based on the multi-agent modeling method. Each agent corresponds to a spatial unit and has state transition rules and interactive behavior patterns. The agent states include four types: no conflict, potential conflict, explicit conflict and conflict resolution. When the conflict intensity of adjacent agents exceeds the preset threshold, the state transition is triggered. The propagation probability is determined by the distance attenuation function, terrain barrier factor and policy intervention intensity. Multiple random experiments are carried out through the Monte Carlo simulation method to statistically analyze the conflict propagation path, arrival time and impact range under different scenarios, generate probability distribution maps and risk level classifications, and identify the key parameters that have the greatest impact on the propagation process through sensitivity analysis.

8. The method for decision-making on land space layout adjustment based on planning conflict identification according to claim 1 is characterized in that: Step 3 includes the following steps: The quality of historical land use conflict event data was checked, and the regional data were mapped to a unified grid unit based on the spatial weight matrix. The sequences were then aligned according to the timestamps to generate a normalized spatiotemporal dataset. The spatiotemporal conflict analysis module is used to calculate the conflict intensity index of each grid cell. Combining the neighborhood location characteristics with the semantic information in the territorial conflict knowledge graph, a multidimensional temporal feature vector sequence integrating causal relationships is constructed based on a sliding time window. The multi-dimensional time series feature vector sequence is input into the encoder part of the pre-trained spatiotemporal lag effect model. A bidirectional long short-term memory network is used to capture the forward and backward associations in the sequence. Combined with the semantic enhancement information of the knowledge graph, the hidden state vector containing lag information and causal chain reasoning is output. The decoder uses the attention mechanism to perform weighted aggregation on the hidden state vector, integrates the causal chain reasoning results in the knowledge graph, and maps the weight distribution of different time steps into the prediction parameters of the conflict impact intensity and duration at the current moment, thus achieving accurate prediction of the conflict status over time. Based on the hysteresis coefficient and spatial propagation probability in the decoder output, combined with semantic enhancement analysis of the knowledge graph, the prediction results are mapped back to the geographic grid, automatically capturing and quantifying the spatiotemporal propagation paths and corresponding time delays of land use conflicts between regions, thereby generating a spatiotemporal propagation trajectory map that includes propagation and hysteresis effects. The predicted conflict intensity and duration are compared with the measured data for error analysis; if the prediction error exceeds the set threshold, the lag window length or spatial weight parameter in the model is dynamically adjusted based on the sensitivity analysis results and knowledge graph feedback, and iterative optimization is performed until the prediction accuracy meets the set standards.

9. The method for adjusting the national land space layout based on planning conflict identification according to claim 1 is characterized in that: Step 4 includes the following steps: At the regional, county, and land parcel levels, conflict propagation networks are constructed based on grid units or administrative boundary units, where nodes represent corresponding spatial units and edge weights are determined by the conflict transmission probability between adjacent nodes and the distance decay function to ensure accurate mapping of network structures at different scales. A multi-agent model is introduced at each network level to simulate the diffusion process of conflicts. Agents migrate between nodes according to preset state transition rules. At the same time, the shortest path algorithm is used to automatically extract the optimal conflict propagation path from the simulation results. The resistance value corresponding to the comprehensive barrier factor is calculated for each edge on the path, and after normalization, the path cost weight is assigned to achieve accurate quantification of multiple influencing factors; The optimal propagation paths and their resistance costs identified in each layer of the network are summarized. By comparing path lengths, accumulated resistance values, and propagation time delays, cross-scale propagation trend characteristics are extracted, providing a quantitative analysis basis for trend differences between macro and micro levels. Based on the total path resistance and transmission probability, combined with the threshold quantile method, each transmission path is scored for risk and divided into three risk levels: low, medium, and high. This helps identify potential key conflict diffusion corridors and high-risk sections. The optimal propagation path, resistance distribution, and risk level are displayed as map layers, and trend analysis and risk assessment reports are automatically generated, including cross-scale path comparison charts, resistance factor contribution bar charts, and risk area distribution heat maps.

10. The method for decision-making on land space layout adjustment based on planning conflict identification according to claim 1, characterized in that: The decision-making method for adjusting the national land spatial layout also includes the following steps: Step 8: During the generation of the layout adjustment plan, the impact of the plan on future conflict evolution is evaluated in real time using the spatiotemporal fitness evaluation function. The conflict propagation prediction results and spatiotemporal lag effect analysis results are combined to determine whether the layout adjustment plan meets the preset conflict mitigation standards. Specifically, the spatial structural parameters, land use type distribution, and adjustment range of the current layout adjustment plan are input into the spatiotemporal fitness evaluation function. Combined with the future conflict situation characteristics output by the conflict propagation prediction module, the key influencing indicators of the layout plan on the conflict evolution process are extracted. Evaluation indicators of the layout plan in terms of conflict mitigation effect, future development adaptability, and implementation rationality are calculated, and a comprehensive evaluation vector is constructed based on these indicators. Each indicator is weighted according to a predetermined expert weight system, and a comprehensive fitness score is generated through weighted summation. The obtained fitness score is compared with the set conflict mitigation standards to quantitatively determine whether the current layout plan meets the minimum threshold requirements for conflict intensity reduction, conflict area reduction, and propagation path blocking indicators. Combined with the spatiotemporal lag effect analysis results, the time delay and persistence changes in the conflict propagation process after the layout adjustment are tested to further verify whether the plan's control effect on conflict evolution trends at different future time points meets expectations. Step 9: If the layout adjustment solution does not meet the preset conflict mitigation criteria, return to the multi-objective optimization model and solve again until the conflict mitigation criteria are met; Step 10: If the layout adjustment plan has met the preset conflict mitigation standards, a Pareto optimal solution set that takes into account both current conflict mitigation and future risk prevention and control is generated, and the final national land space layout adjustment decision plan is output.

Images