Dynamic tracking and intelligent diagnosis system for land space planning implementation effect

Abstract

The application discloses a land space planning implementation effect dynamic tracking and intelligent diagnosis system, comprising the following modules: a data collection module, which accesses and fuses multi-source heterogeneous land space data. Thus, the application adopts a multi-model fusion scheme, sets up fine simulation scenarios covering different development strategies and policy interventions, provides reliable support for planning decision optimization, realizes objective quantification through a weighted aggregation function, and realizes automatic calculation of the evaluation process relying on standardized data support of the data collection module. The application can quickly quantify the compliance and overall benefits of planning implementation, truly reflect the planning implementation effectiveness, rely on spatiotemporal correlation rule mining and causal relationship inference model, realize deep correlation analysis of dynamic change information, evaluation results and planning knowledge graph, establish a risk grading early warning mechanism, and output a standardized diagnosis report containing a problem list, cause chain and implementable optimization strategy.

Description

Technical Field

[0001] This application relates to the technical field of geographic information, and in particular to a dynamic tracking and intelligent diagnosis system for the implementation effect of national spatial planning. Background Technology

[0002] Territorial spatial planning is a core means of controlling territorial spatial development and protection, optimizing spatial layout, and ensuring ecological security. Its implementation effect is directly related to the coordinated advancement of regional economic and social development and ecological environmental protection. With the advancement of the modernization of the territorial spatial governance system and governance capacity, traditional planning implementation monitoring and diagnosis models are no longer adequate to meet the management needs under the new circumstances and have many shortcomings.

[0003] Existing systems often use a single simulation model, with overly simplistic scenario settings. They fail to incorporate spatial constraint rules from the planning knowledge graph, making it impossible to accurately simulate the evolution trend of national land space under different development strategies and policy interventions. Consequently, the simulation results are out of touch with actual needs and cannot support the optimization of planning decisions.

[0004] Meanwhile, the existing system's evaluation focuses on single-dimensional indicators and lacks a multi-dimensional overall evaluation of compliance, achievement rate and comprehensive benefits. Moreover, the evaluation process relies on manual calculation, which makes it difficult to quickly and objectively quantify the compliance and overall benefits of the plan's implementation and to fully reflect the effectiveness of the plan's implementation.

[0005] Furthermore, existing systems cannot achieve in-depth correlation analysis between dynamically changing information, assessment results, and planning knowledge. They are not accurate in identifying risks during planning implementation, and diagnostic reports are mostly just data listings, lacking analysis of the causes of problems and feasible optimization strategies, thus failing to provide effective support for planning adjustments.

[0006] Application content

[0007] This application aims to address, at least to some extent, the technical problems in the related art.

[0008] To achieve the above objectives, this application proposes a dynamic tracking and intelligent diagnostic system for the implementation effects of territorial spatial planning, including the following modules:

[0009] The data collection module accesses and integrates multi-source heterogeneous land and space data, which includes at least planning target data, current status monitoring data, and socio-economic statistics data, forming a spatiotemporal database;

[0010] The knowledge base management module is connected to the data collection module to store and manage diagnostic rules, constraints, evaluation index models and historical case knowledge in the field of land and space planning, forming an updatable planning knowledge graph.

[0011] The spatiotemporal change perception module is connected to the data collection module. Based on the spatiotemporal database, it identifies and quantifies the dynamic changes in the structure, layout, and function of land space elements through spatiotemporal sequence analysis and change detection algorithms.

[0012] The simulation and deduction module is connected to the spatiotemporal change perception module and the knowledge base management module, receives the dynamic change information, and performs multi-scenario simulation and deduction of the future development trend of national land space based on the rules and models in the planning knowledge graph.

[0013] The implementation effect evaluation module is connected to the data collection module, the spatiotemporal change perception module, and the simulation and deduction module, respectively. It compares the dynamic change information and simulation and deduction results with the preset planning objectives, and calculates the compliance, achievement rate, and comprehensive benefit index of the planning implementation based on the evaluation index model in the knowledge base management module.

[0014] The intelligent diagnostic module is connected to the implementation effect evaluation module, the knowledge base management module, and the spatiotemporal change perception module, respectively. Based on the evaluation results of the planning implementation, it combines the dynamic change information and the planning knowledge graph to perform correlation analysis and reasoning, automatically identify key issues, conflicts, and risks in the planning implementation, and generate an intelligent diagnostic report containing causal analysis and optimization suggestions.

[0015] In addition, the application may also include the following additional technical features:

[0016] Specifically, the data collection module includes: a data interface unit that connects to data sources such as land surveys, remote sensing monitoring, real-time sensing, government approvals, and statistical yearbooks; and a data fusion unit that performs spatiotemporal registration, format conversion, and semantic mapping on multi-source heterogeneous data to form a spatiotemporal database with a unified spatiotemporal benchmark.

[0017] Specifically, the knowledge base management module includes: a rule extraction unit, which automatically extracts diagnostic rules and constraints from planning texts, technical specifications, and case libraries; and a knowledge update unit, which updates the rule weights and case libraries in the planning knowledge graph based on dynamic changes and evaluation results.

[0018] Specifically, the spatiotemporal change perception module employs spatiotemporal sequence analysis methods including: change vector analysis based on multi-period remote sensing images and land use transfer matrix calculation; and change detection algorithms including semantic segmentation change detection based on deep learning and object-oriented post-classification comparison methods.

[0019] Specifically, the simulation and deduction module includes: a scenario setting unit, which sets multiple sets of simulation scenarios under different development strategies, policy interventions, or external environmental parameters; and a deduction engine unit, which, based on cellular automata, multi-agent models, or land use change simulation models, and combined with spatial constraint rules in the planning knowledge graph, deduces the evolution trend of the national land spatial pattern under different scenarios.

[0020] Specifically, in the implementation effect evaluation module: the compliance index reflects the spatial consistency ratio between the actual space use and the planned space use; the achievement rate index is used to measure the phased completion ratio of each planning sub-project objective; and the comprehensive benefit index is calculated by a weighted aggregation function of economic benefits, social benefits, and ecological benefits.

[0021] Specifically, the intelligent diagnostic module includes: an association analysis unit, which identifies abnormal associations between dynamic change information, evaluation results, and planning knowledge graph based on spatiotemporal association rule mining and causal relationship inference; a risk identification unit, which provides graded early warnings for planning implementation risks such as exceeding limits, conflict overlap, and delayed response; and a report generation unit, which uses natural language generation technology to output a diagnostic report containing a problem list, spatial distribution map, causal chain, and targeted optimization strategies.

[0022] Specifically, it also includes a visualization module, comprising: a spatial visualization unit, which renders and overlays the key issues, risk areas and their spatial distribution in the intelligent diagnostic report in the form of thematic maps, heat maps or spatiotemporal animations; and a report push unit, which pushes the structured diagnostic report and visualization results to planning management, supervision and execution and public query terminals according to preset user roles and permissions, and provides interactive query functions based on maps and charts.

[0023] In summary, the beneficial effects of the proposed dynamic tracking and intelligent diagnosis system for the implementation of territorial spatial planning are as follows:

[0024] 1. This application adopts a multi-model fusion scheme, setting up refined simulation scenarios covering different development strategies and policy interventions. The simulation process combines spatial constraint rules and dynamic change data in the planning knowledge graph, which can accurately simulate the evolution trend of national land space and provide reliable support for the optimization of planning decisions.

[0025] 2. A multi-dimensional and standardized evaluation index system has been constructed, covering compliance, achievement rate and comprehensive benefit index indicators. Objective quantification is achieved through weighted aggregation function. At the same time, relying on the standardized data support of the data collection module, the evaluation process is automated, which can quickly quantify the compliance and overall benefits of the planning implementation and truly reflect the effectiveness of the planning implementation.

[0026] 3. Based on spatiotemporal correlation rule mining and causal relationship inference models, we can achieve in-depth correlation analysis of dynamic change information, evaluation results and planning knowledge graph, establish a risk classification and early warning mechanism, accurately identify various risks in planning implementation and manage them in a graded manner, and output standardized diagnostic reports containing problem lists, causal chains and implementable optimization strategies. Attached Figure Description

[0027] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0028] Figure 1 This is a flowchart of the dynamic tracking and intelligent diagnosis system for the implementation effect of the territorial spatial planning in this application;

[0029] Figure 2 This is a flowchart of the simulation and deduction module of the dynamic tracking and intelligent diagnosis system for the implementation effect of the territorial spatial planning in this application;

[0030] Figure 3 This is a flowchart of the intelligent diagnosis module of the dynamic tracking and intelligent diagnosis system for the implementation effect of the territorial spatial planning in this application. Detailed Implementation

[0031] To make the technical means, inventive features, objectives, and effects of this application easier to understand, the application is further described below with reference to specific illustrations. It should be noted that, unless otherwise specified, the embodiments and features described in these embodiments can be combined with each other.

[0032] The present application will now be described in further detail with reference to the accompanying drawings.

[0033] like Figures 1-3 As shown in the embodiment of this application, the dynamic tracking and intelligent diagnosis system for the implementation effect of land and space planning includes the following modules: a data collection module, which accesses and integrates multi-source heterogeneous land and space data, including at least planning target data, current status monitoring data and socio-economic statistics data, to form a spatiotemporal database.

[0034] It should be noted that the planning target data covers the contents of land and space planning documents, planning maps, indicator decomposition schemes, and control requirements at all levels. The current status monitoring data relies on a variety of technologies such as remote sensing monitoring, UAV aerial surveying, ground monitoring stations, and GIS spatial data acquisition to obtain real-time information on the current status of spatial elements such as land use, mineral resource development, and ecological environment quality. The data formats cover a variety of types, including vector data, raster data, and image data. The socio-economic statistics data are collected from relevant units such as statistics departments, development and reform departments, and housing and urban-rural development departments, including statistics on population size and distribution, total GDP and structure, industrial layout, and urban and rural construction investment.

[0035] This module integrates multi-source heterogeneous data through preprocessing operations such as data cleaning, format standardization, spatiotemporal alignment, and redundancy removal to build a unified spatiotemporal database. This provides data support for the operation of subsequent modules and supports real-time data updates and incremental imports, ensuring the timeliness and integrity of the database.

[0036] The knowledge base management module, connected to the data collection module, stores and manages diagnostic rules, constraints, evaluation index models, and historical case knowledge in the field of land and space planning, forming an updatable planning knowledge graph.

[0037] It should be noted that the diagnostic rules cover compliance rules, rationality rules, and coordination rules in the implementation process of territorial spatial planning, such as the rules for judging the compliance of land use type conversion, the rules for the control of ecological protection red lines, and the rules for the constraint of planning indicator implementation.

[0038] The constraints include ecological protection red lines, permanent basic farmland, urban development boundaries, as well as hard requirements such as resource and environmental carrying capacity and suitability assessment for land development.

[0039] The evaluation index model includes a system of various indicators, indicator weights, calculation methods, and evaluation standards for evaluating the effectiveness of planning implementation. It covers multiple dimensions such as resource utilization efficiency, ecological environment quality, coordinated urban and rural development, and achievement of planning goals, and can be flexibly adjusted according to different regions and different planning types.

[0040] Historical case knowledge collection includes successful cases, lessons learned, and countermeasures of land and space planning implementation in different regions and periods at home and abroad, establishing a case database and classifying and labeling it.

[0041] Knowledge graphs use techniques such as association rule mining and knowledge reasoning to organically link various types of knowledge. At the same time, they establish a knowledge update mechanism that can continuously enrich the content of the knowledge graph by manually inputting new knowledge or automatically mining and refining new planning practices and monitoring data. This provides solid knowledge support for system simulation, effect evaluation and intelligent diagnosis.

[0042] The spatiotemporal change perception module, connected to the data collection module, identifies and quantifies the dynamic changes in the structure, layout, and function of land and space elements based on a spatiotemporal database through spatiotemporal sequence analysis and change detection algorithms.

[0043] It should be noted that, firstly, historical and real-time data in the spatiotemporal database are sorted out to construct a spatiotemporal sequence dataset of land and space elements, covering the spatiotemporal evolution data of elements such as land use, ecological space, urban layout, and infrastructure. Then, spatiotemporal sequence analysis algorithms, such as time series trend analysis, spatial autocorrelation analysis, and hotspot analysis, are used to explore the evolution patterns of land and space elements in the time dimension, their distribution characteristics in the spatial dimension, and their correlation relationships.

[0044] Simultaneously, mature change detection algorithms, such as remote sensing image interpolation, change vector analysis, and machine learning change detection, are employed to accurately identify dynamic changes in the structure, layout, and function of land spatial elements. This includes key information such as change area, change type, change intensity, and change time. The change information is then quantified to generate quantitative change indicators, such as change area, change rate, and change contribution rate. Finally, the identified and quantified dynamic change information is standardized and output.

[0045] This provides data support for subsequent modules.

[0046] The simulation and deduction module is connected to the spatiotemporal change perception module and the knowledge base management module. It receives dynamic change information and, based on the rules and models in the planning knowledge graph, conducts multi-scenario simulations and deductions of the future development trend of national land space.

[0047] It should be noted that, firstly, the system receives dynamic change information of land and space elements output by the spatiotemporal change perception module to clarify the current status quo, trend of change, and potential factors of change in land and space development. Then, it calls the planning knowledge graph stored in the knowledge base management module, including diagnostic rules, constraints, evaluation index models, and historical case knowledge. Combined with constraints such as regional resource and environmental carrying capacity and suitability for land and space development, a multi-scenario simulation and deduction model is constructed.

[0048] The simulation model can set multiple future development scenarios, such as baseline, optimized, and constrained scenarios. Through system dynamics, spatial simulation, and machine learning, it simulates and extrapolates the development trends of national land space over a certain period, focusing on predicting spatial layout, land use structure, ecological environment quality, and the achievement of planning objectives. After the simulation is completed, it outputs the results for each scenario, including trend prediction reports, spatial evolution maps, and indicator achievement predictions, providing a scientific basis for planning implementation decisions and helping to optimize the planning implementation path.

[0049] The implementation effect evaluation module is connected to the data collection module, the spatiotemporal change perception module, and the simulation and deduction module, respectively. It compares the dynamic change information and simulation and deduction results with the preset planning objectives. Based on the evaluation index model in the knowledge base management module, it calculates the compliance, achievement rate and comprehensive benefit index of the planning implementation.

[0050] It should be noted that, firstly, the data collection module acquires pre-set planning target data, obtains dynamic change information of land and space elements from the spatiotemporal change perception module, and obtains simulation results of future development trends from the simulation and deduction module. Then, the dynamic change information and simulation results are compared with the pre-set planning targets from multiple dimensions to clarify the deviations from the targets during the planning implementation process, including the direction, degree, and scope of deviation. Based on this, the evaluation index model in the knowledge base management module is invoked, combined with pre-set evaluation standards and index weights, and calculation methods such as weighted summation, fuzzy comprehensive evaluation, and analytic hierarchy process (AHP) are used to accurately calculate the core evaluation indicators of planning implementation, including planning implementation compliance, planning target achievement rate, and comprehensive benefit index. After the evaluation is completed, a standardized implementation effect evaluation report is generated, clearly presenting the effectiveness of planning implementation, existing deviations, and potential problems.

[0051] The intelligent diagnostic module is connected to the implementation effect evaluation module, the knowledge base management module, and the spatiotemporal change perception module, respectively. Based on the evaluation results of the planning implementation, it combines dynamic change information and planning knowledge graph to perform correlation analysis and reasoning, automatically identify key issues, conflicts and risks in the planning implementation, and generate an intelligent diagnostic report containing causal analysis and optimization suggestions.

[0052] It should be noted that, firstly, based on the evaluation results output by the implementation effect evaluation module, and combined with the land space dynamic change information provided by the spatiotemporal change perception module, the deviations from the goals, abnormal changes in the areas and elements are identified. Then, the planning knowledge graph in the knowledge base management module is called, and through intelligent algorithms such as correlation analysis and logical reasoning, the evaluation deviations, dynamic changes and diagnostic rules, constraints and historical cases are deeply matched to automatically identify key issues, spatial conflicts and potential risks in the implementation of the plan.

[0053] Meanwhile, based on historical cases and diagnostic rules in the knowledge graph, in-depth causal analysis is conducted on the identified problems, conflicts and risks to clarify their root causes, including policy factors, technical factors, management factors, market factors, etc. Combining the causal analysis results, an intelligent diagnostic report is generated that includes a problem overview, causal analysis, targeted optimization suggestions and implementation paths. The optimization suggestions can be specific to regions, elements and control measures, providing intelligent decision support for the adjustment and optimization of planning implementation, and promoting the improvement of the quality and efficiency of territorial spatial planning implementation.

[0054] In one embodiment of this application, the data collection module includes: a data interface unit that interfaces with data sources such as land surveys, remote sensing monitoring, real-time sensing, government approvals, and statistical yearbooks; and a data fusion unit that performs spatiotemporal registration, format conversion, and semantic mapping on multi-source heterogeneous data to form a spatiotemporal database with a unified spatiotemporal benchmark.

[0055] It should be noted that the data interface unit connects to multiple data sources, including land surveys, remote sensing monitoring, real-time sensing, government approvals, and statistical yearbooks. Among them, land survey data includes vector data such as annual land change surveys and land survey results; remote sensing monitoring data includes multi-resolution and multi-time series data such as high-resolution satellite imagery and UAV aerial imagery; real-time sensing data comes from various IoT monitoring devices such as soil moisture, water quality, and air quality monitoring equipment; government approval data involves electronic archives for the entire process of land use pre-approval, planning permits, and construction project approvals; and statistical yearbook data covers macro-statistical indicators such as population, economy, land use, and ecological environment.

[0056] The data fusion unit employs data fusion technology to first perform spatiotemporal registration on various types of data, unifying data from different coordinate systems and time scales under the same spatiotemporal reference. Then, it converts data in different formats such as vector, raster, text, and tables into a unified format compatible with the system through format conversion. Finally, it establishes the relationship between different data sources through semantic mapping, resolving ambiguities in terminology and data conflicts, ultimately forming a spatiotemporal database with standardized structure, spatiotemporal uniformity, and semantic consistency.

[0057] In one embodiment of this application, the knowledge base management module includes: a rule extraction unit, which automatically extracts diagnostic rules and constraints from planning text, technical specifications, and a case library; and a knowledge update unit, which updates the rule weights and case library in the planning knowledge graph based on dynamic change information and evaluation results.

[0058] It should be noted that the rule extraction unit, relying on intelligent algorithms such as natural language processing and machine learning, automatically extracts various rules and constraints required for planning implementation diagnosis from various planning documents such as the overall land space plan, detailed plans, and special plans; technical specifications such as land use classification standards, planning preparation technical guidelines, and ecological protection red line control requirements; and case libraries such as past planning implementation cases, violation handling cases, and optimization and adjustment cases. Among them, the diagnostic rules cover land use control, plot ratio restrictions, spatial layout requirements, and ecological protection bottom lines, while the constraints include quantitative indicator constraints, spatial boundary constraints, and time-series progress constraints. At the same time, the extracted rules are classified, organized, and validated to form a standardized rule system and integrated into the planning knowledge graph.

[0059] The knowledge update unit establishes a dynamic update mechanism to capture dynamic changes in the planning implementation process in real time, including actual changes in land use, policy adjustments, updates to technical specifications, and changes in the external environment. At the same time, it combines the evaluation results output by the implementation effect evaluation module to dynamically adjust the rule weights in the planning knowledge graph, supplement, improve, and iteratively optimize the case library, eliminate outdated rules and cases, and add content that meets the current planning requirements, ensuring the timeliness, accuracy, and applicability of the knowledge base, and providing reliable knowledge support for modules such as intelligent diagnosis and simulation.

[0060] In one embodiment of this application, the spatiotemporal change perception module employs a spatiotemporal sequence analysis method including: change vector analysis based on multi-period remote sensing images and land use transfer matrix calculation; and change detection algorithms including semantic segmentation change detection based on deep learning and object-oriented post-classification comparison method.

[0061] It should be noted that, based on the change vector analysis of multi-period remote sensing images, by comparing remote sensing images from different time periods, vector information such as image spectral features and texture features is extracted, and vector difference values ​​are calculated. This allows for the identification of change areas, change types, and change intensities within the national land space, effectively capturing the dynamic changes of various land uses such as cultivated land, construction land, and ecological land. The land use transfer matrix calculation, by quantifying the number, direction, and proportion of conversions between land use types in different periods, clearly presents the evolutionary patterns of land use types, such as the conversion of cultivated land to construction land and the conversion of forest land to cultivated land.

[0062] The change detection algorithms used mainly fall into two categories. One category is the semantic segmentation change detection algorithm based on deep learning, which performs semantic segmentation on multiple remote sensing images and achieves accurate identification of changed areas by comparing the segmentation results. It has the advantages of high recognition accuracy, high degree of automation, and the ability to capture subtle changes, and is suitable for detecting fine changes such as illegal land use and vegetation degradation.

[0063] Another type is the object-oriented classification and comparison method. It first segments the single-period remote sensing image, dividing the image into objects with the same spectral and textural features. Then, it classifies the objects from different periods and identifies the changed areas by comparing the classification results. It is suitable for detecting large-area land use changes with clear boundaries, such as the expansion of industrial parks and the contiguous changes of farmland.

[0064] In one embodiment of this application, the simulation and deduction module includes: a scenario setting unit, which sets multiple sets of simulation scenarios under different development strategies, policy interventions or external environmental parameters; and a deduction engine unit, which, based on cellular automata, multi-agent models or land use change simulation models, and combined with spatial constraint rules in the planning knowledge graph, deduces the evolution trend of the national land spatial pattern under different scenarios.

[0065] It should be noted that the scenario setting unit, in combination with the goals of territorial spatial planning, regional development needs and various influencing factors, sets up multiple different simulation scenarios, covering different development strategies, different policy interventions and different external environmental parameters. Each scenario has clearly defined specific parameter settings and constraints to ensure the scientific, reasonable and comprehensive nature of the scenario setting.

[0066] The simulation engine unit, as the core of the simulation, uses cellular automata, multi-agent models, or land use change simulation models (such as CLUE-S and CA-Markov models) to accurately predict the evolution trend of the national land spatial pattern under different scenarios. Specifically, it combines the spatial distribution changes of land use types, urban spatial expansion trends, ecological spatial evolution patterns, and supply and demand balance changes of various types of land. The simulation results are presented in the form of data, charts, etc.

[0067] In one embodiment of this application, in the implementation effect evaluation module: the compliance index reflects the spatial consistency ratio between the actual space use and the planned space use; the achievement rate index is used to measure the phase completion ratio of each planning sub-project objective; and the comprehensive benefit index is calculated by a weighted aggregation function of economic benefits, social benefits, and ecological benefits.

[0068] It should be noted that the compliance index is specifically calculated as the proportion of the area of ​​land whose actual use is consistent with the planned use to the total area of ​​land within the planning scope. This index focuses on measuring the compliance of the planning implementation and can effectively identify problems such as illegal land use and inconsistent use, such as whether the actual use of construction land is consistent with the planned use, and whether cultivated land is protected as required by the plan.

[0069] The achievement rate indicator is used to measure the percentage of completion of each planning sub-project objective at each stage. The planning sub-project objectives cover various quantitative targets such as cultivated land area, construction land scale, ecological green space area, and supporting public service facilities. The achievement rate is calculated as the ratio of the current stage target completion amount to the total planning target amount. It can clearly reflect the progress of each target, identify targets that are lagging behind, and analyze the reasons.

[0070] The comprehensive benefit index is used to comprehensively evaluate the overall benefits of the plan's implementation. It is calculated by weighted aggregation functions of economic, social, and ecological benefits. Economic benefit indicators include land use efficiency, industrial output value increase, and land transfer revenue. Social benefit indicators include improvement in the quality of the living environment, the degree of improvement in public service facilities, and the number of job opportunities. Ecological benefit indicators include vegetation coverage, water quality compliance rate, and ecosystem service value. The weighted aggregation function allocates reasonable weights to the three benefits according to the regional development positioning and planning focus. The resulting comprehensive benefit index can intuitively reflect the overall impact of the plan's implementation on the regional economy, society, and ecology.

[0071] In one embodiment of this application, the intelligent diagnostic module includes: an association analysis unit, which identifies abnormal associations between dynamic change information, evaluation results and planning knowledge graph based on spatiotemporal association rule mining and causal relationship inference; a risk identification unit, which provides graded early warnings for planning implementation risks such as exceeding limits, conflict overlap, and delayed response; and a report generation unit, which uses natural language generation technology to output a diagnostic report containing a problem list, spatial distribution map, causal chain and targeted optimization strategies.

[0072] It should be noted that the correlation analysis unit, relying on spatiotemporal correlation rule mining algorithms and causal relationship inference models, conducts in-depth correlation analysis on the dynamic change information captured by the spatiotemporal change perception module, the evaluation results output by the implementation effect evaluation module, and the rules and constraints in the planning knowledge graph. This identifies abnormal correlations among the three, such as the correlation between illegal growth of construction land in a certain area and imperfect planning constraint rules and lagging evaluation indicators, or the correlation between declining ecological quality in a certain area and land use changes and inadequate policy implementation. Through correlation analysis, the underlying causes of these problems are found.

[0073] The risk identification unit addresses various risks that may arise during the implementation of the plan, including deviations from the plan (such as the scale of construction land exceeding the planning indicators), conflicts and overlaps (such as conflicts in land use scope and land use nature between different plans), and delayed responses (such as planning adjustments lagging behind actual development needs and ecological protection measures lagging behind environmental changes). It establishes risk classification standards, conducts graded early warnings for various risks, and clarifies the priority of handling and response requirements for different levels of risks.

[0074] The report generation unit includes a problem list (clearly defining the problem's location, type, severity, and scope of impact), a spatial distribution map (marking the spatial location and distribution characteristics of problem and risk areas), a causal chain, and targeted optimization strategies.

[0075] In one embodiment of this application, a visualization module is also included, comprising: a spatial visualization unit, which renders and overlays key issues, risk areas and their spatial distribution in the intelligent diagnostic report in the form of thematic maps, heat maps or spatiotemporal animations; and a report push unit, which pushes the structured diagnostic report and visualization results to planning management, supervision and execution and public query terminals according to preset user roles and permissions, and provides interactive query functions based on maps and charts.

[0076] It should be noted that the thematic maps are specially designed to display different types of problems, clearly marking the specific location, scope and type of the problem area; the heat map intuitively presents the concentration of problems and risks, with darker colors indicating a higher concentration of problems and a higher risk level; the spatiotemporal animation dynamically displays the process of land space change, risk evolution trends and planning implementation progress, allowing users to intuitively experience the dynamic changes in land space.

[0077] The report push unit allows planning and management personnel to view complete diagnostic reports and optimization strategies, supervisors to view key issues and risk warnings, and the public to access publicly available diagnostic results and visualizations. It also provides interactive query functions based on maps and charts, allowing users to click on map areas to query specific location details and risk levels, and filter diagnostic data of different types and time periods through charts.

[0078] The present application and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present application. The actual structure is not limited to this. In conclusion, if a person skilled in the art is inspired by this description and designs a similar structure and embodiment without departing from the spirit of the present application, such design should fall within the protection scope of the present application.

Claims

1. A dynamic tracking and intelligent diagnostic system for the implementation effect of territorial spatial planning, characterized in that: Includes the following modules: The data collection module accesses and integrates multi-source heterogeneous land and space data, which includes at least planning target data, current status monitoring data, and socio-economic statistics data, forming a spatiotemporal database; The knowledge base management module is connected to the data collection module to store and manage diagnostic rules, constraints, evaluation index models and historical case knowledge in the field of land and space planning, forming an updatable planning knowledge graph. The spatiotemporal change perception module is connected to the data collection module. Based on the spatiotemporal database, it identifies and quantifies the dynamic changes in the structure, layout, and function of land space elements through spatiotemporal sequence analysis and change detection algorithms. The simulation and deduction module is connected to the spatiotemporal change perception module and the knowledge base management module, receives the dynamic change information, and performs multi-scenario simulation and deduction of the future development trend of national land space based on the rules and models in the planning knowledge graph. The implementation effect evaluation module is connected to the data collection module, the spatiotemporal change perception module, and the simulation and deduction module, respectively. It compares the dynamic change information and simulation and deduction results with the preset planning objectives, and calculates the compliance, achievement rate, and comprehensive benefit index of the planning implementation based on the evaluation index model in the knowledge base management module. The intelligent diagnostic module is connected to the implementation effect evaluation module, the knowledge base management module, and the spatiotemporal change perception module, respectively. Based on the evaluation results of the planning implementation, it combines the dynamic change information and the planning knowledge graph to perform correlation analysis and reasoning, automatically identify key issues, conflicts, and risks in the planning implementation, and generate an intelligent diagnostic report containing causal analysis and optimization suggestions.

2. The dynamic tracking and intelligent diagnosis system for the implementation effect of territorial spatial planning according to claim 1, characterized in that, The data collection module includes: The data interface unit connects to data sources such as land surveys, remote sensing monitoring, real-time sensing, government approvals, and statistical yearbooks. The data fusion unit performs spatiotemporal registration, format conversion, and semantic mapping on multi-source heterogeneous data to form a spatiotemporal database with a unified spatiotemporal benchmark.

3. The dynamic tracking and intelligent diagnosis system for the implementation effect of territorial spatial planning according to claim 1, characterized in that, The knowledge base management module includes: The rule extraction unit automatically extracts diagnostic rules and constraints from planning texts, technical specifications, and case libraries; The knowledge update unit updates the rule weights and case library in the planning knowledge graph based on dynamic changes and evaluation results.

4. The dynamic tracking and intelligent diagnosis system for the implementation effect of territorial spatial planning according to claim 1, characterized in that, The spatiotemporal change perception module employs spatiotemporal sequence analysis methods including: change vector analysis based on multi-period remote sensing images and land use transfer matrix calculation. The change detection algorithms include semantic segmentation change detection based on deep learning and object-oriented post-classification comparison methods.

5. The dynamic tracking and intelligent diagnosis system for the implementation effect of territorial spatial planning according to claim 1, characterized in that, The simulation module includes: The scenario setting unit allows for the creation of multiple simulated scenarios under different development strategies, policy interventions, or external environmental parameters. The inference engine unit, based on cellular automata, multi-agent models or land use change simulation models, combined with spatial constraint rules in the planning knowledge graph, infers the evolution trend of the national land spatial pattern under different scenarios.

6. The dynamic tracking and intelligent diagnosis system for the implementation effect of territorial spatial planning according to claim 1, characterized in that, In the implementation effect evaluation module: The compliance index reflects the spatial consistency ratio between the actual space use and the planned space use; The achievement rate indicator is used to measure the percentage of each planning sub-project's phase completion. The comprehensive benefit index is calculated by a weighted aggregation function of economic, social, and ecological benefits.

7. The dynamic tracking and intelligent diagnosis system for the implementation effect of territorial spatial planning according to claim 1, characterized in that, The intelligent diagnostic module includes: The association analysis unit, based on spatiotemporal association rule mining and causal relationship inference, identifies abnormal associations between dynamically changing information, evaluation results, and the planning knowledge graph; The risk identification unit provides graded early warnings for planning implementation risks such as exceeding limits, overlapping conflicts, and delayed responses. The report generation unit uses natural language generation technology to output a diagnostic report that includes a list of problems, a spatial distribution map, a chain of causes, and targeted optimization strategies.

8. The dynamic tracking and intelligent diagnosis system for the implementation effect of territorial spatial planning according to claim 1, characterized in that, It also includes a visualization module, including: The spatial visualization unit renders and overlays the key issues, risk areas and their spatial distribution in the intelligent diagnostic report in the form of thematic maps, heat maps or spatiotemporal animations. The report push unit pushes structured diagnostic reports and visualization results to planning management, supervision and execution, and public query terminals according to preset user roles and permissions, and provides interactive query functions based on maps and charts.

Images