A Multi-Scale Monitoring Method and System for the Implementation of Territorial Spatial Planning
By combining the PROV model with deep learning, a multi-scale monitoring system for the implementation of territorial spatial planning was constructed, which solved the problems of data management and reliability assessment, and realized intelligent monitoring and early warning of territorial spatial planning.
Patent Information
- Application Number
- CN202310046007.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-01-30
- Publication Date
- 2026-11-17
- Estimated Expiration
- 2043-01-30
AI Technical Summary
The existing monitoring mechanism for the implementation of national spatial planning is not yet perfect, resulting in problems such as disorder in spatial governance and development disorder. The management of multi-source heterogeneous data relies on manual memory or document records, and lacks a data traceability and knowledge reliability assessment mechanism.
A monitoring metadata model is constructed using the PROV model. Combined with the monitoring indicator system for the implementation of territorial spatial planning, the vertical land management business of SuperMap is integrated with the horizontal geographic unit connectivity. A knowledge extraction method based on a deep learning model is designed to establish a multi-scale territorial spatial planning implementation monitoring network model, and scenario triggers are set for automatic updates and early warnings.
It enables reliability assessment of monitoring data for the implementation of territorial spatial planning, improves the scientific nature and accuracy of monitoring results, assists business personnel in accurately controlling the progress of planning implementation, and achieves early warning and timely adjustment.
Smart Images

Figure CN116050139B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of land and space planning technology, specifically to a multi-scale land and space planning implementation monitoring method and system. Background Technology
[0002] Supervision of the implementation of territorial spatial planning is a crucial means for the government to understand the impact of spatial policies and achieve strategic goals. It serves as an important basis for supervising and inspecting the implementation of territorial spatial planning and for dynamically adjusting and improving territorial spatial planning. Monitoring, evaluation, and early warning of territorial spatial planning implementation are the main components of this supervision. The aim is to construct monitoring, evaluation, and early warning indicators and models for important control lines and key areas, enabling dynamic monitoring, regular evaluation, and timely early warning of territorial spatial planning implementation. Currently, the territorial spatial planning implementation monitoring mechanism is not yet perfect, and problems such as disordered spatial governance and unregulated territorial spatial development still exist. There is an urgent need to sort out the monitoring elements of territorial spatial planning implementation at different spatial scales and, using technologies such as knowledge graphs, to achieve dynamic updating and maintenance of planning implementation monitoring knowledge based on the construction of semantic and spatiotemporal relationships between data. Furthermore, a particular entity involved in the monitoring of territorial spatial planning implementation often has a multi-source, heterogeneous set of data facts. This data is obtained by relevant business departments at different time points using appropriate processing methods. Currently, data source management relies solely on manual memory or document records. In the context of "smart territorial planning," there is an urgent need to utilize next-generation information technologies to achieve data traceability and knowledge reliability assessment mechanisms. Summary of the Invention
[0003] In view of the limitations of the existing methods described above, the purpose of this invention is to propose a multi-scale land spatial planning implementation monitoring method and system to solve one or more technical problems existing in the prior art, and at least provide a beneficial option or create conditions.
[0004] To achieve the above objectives, according to one aspect of the present invention, a multi-scale land spatial planning implementation monitoring method is provided, the method comprising the following steps:
[0005] S1: Systematically sort out the land and space planning data resources needed for planning implementation monitoring, construct a monitoring metadata model based on the PROV model, and form a data reliability evaluation mechanism;
[0006] S2: Combine the aforementioned reliability evaluation mechanism with the monitoring indicator system for the implementation of territorial spatial planning, and perform external information correlation on the monitoring indicator system for the implementation of territorial spatial planning;
[0007] S3: A land parcel-scale national spatial planning implementation monitoring network model that integrates the vertical land management business of SuperMap and the horizontal geographic unit connectivity.
[0008] S4: Based on the monitoring network model for the implementation of territorial spatial planning and the aforementioned reliability evaluation mechanism, design a knowledge extraction method based on a deep learning model;
[0009] S5: Implement a monitoring and early warning mechanism based on the established city / county and plot-scale territorial spatial planning implementation monitoring network model.
[0010] Furthermore, in step S1, the specific steps are as follows:
[0011] S11: Based on the PROV model, design, plan, implement, and monitor data traceability paradigm, including seven concepts: entity, activity, generation and utilization, agency and responsibility, derivation and revision, plan, and time, used to represent information such as data producer, production time, production method, and other derived data.
[0012] S12: Extract metadata information of various types of data involved in the monitoring of the implementation of territorial spatial planning, integrate and summarize them into three parts: vector data, raster data, and text data. Combined with the data traceability paradigm for planning implementation monitoring established in S11, establish a metadata model for planning implementation monitoring that takes into account traceability information.
[0013] S13: Based on the analysis of the quality evaluation index set included in the ISO / IEC 25024 data quality model, and combined with the planning implementation monitoring metadata model established in S12, factor analysis is used to screen and analyze the correlation of indicators that take into account the planning implementation monitoring scenario. Three indicators affecting the reliability evaluation of planning implementation monitoring data are obtained: the data production responsible unit, the data acquisition and processing technology method, and the data timeliness. The TAE model is used to evaluate the reliability of planning implementation monitoring data.
[0014] Preferably, an entity is the basic unit of data storage, including both text documents and spatial data files. An activity refers to various operations on the data, including modification and supplementation of text, and analysis and computation of spatial data. Generation and utilization connect entities and activities; they can be described as activities utilizing entities or entities being generated by activities, pointing to the source and from the future to the past. Agency and responsibility are generally acted upon by organizations and can act on entities or activities, representing entity agents or activity subjects, respectively. Derivation and revision are used to build associations between entities with the same source; for example, a new data is generated after an editing activity, and the new data is a derived version of the original data. Planning is used to expand the semantic relationship from activity to agent; for example, it can represent the start time of an activity and the specifications followed. Time describes when an entity is generated and utilized, and when an activity begins and ends.
[0015] Preferably, the spatial module records the spatial characteristics of geospatial entities, such as coverage, accuracy, spatial reference system, and projected coordinate system, serving as an important identifier of the knowledge domain for planning implementation monitoring. For example, administrative division data is the foundation for various spatial data analyses, and the natural resources business database contains multiple different versions. Understanding the differences in spatial characteristics between these versions is fundamental to the correct use of administrative division data.
[0016] The content module records the category to which the data belongs, serving as the primary means of linking knowledge points in planning implementation monitoring. Referring to the "Technical Specification for the Information System for the Supervision of the Implementation of the 'One Map' of Territorial Spatial Planning (GB / T39972-2021)," planning implementation monitoring data is divided into four major categories and thirteen subcategories: basic status quo, planning outcomes, planning implementation, and planning supervision. Basic status quo includes basic geographic information data, geological data, natural resource survey and monitoring data, natural resource management data, and natural and historical cultural protection data; planning outcomes include overall planning data, detailed planning data, and special planning data; planning implementation includes land use control data, ecological status and major ecological restoration project information data; and planning supervision includes planning implementation monitoring, evaluation, and early warning data, resource and environmental carrying capacity monitoring and early warning data, and data automatically and mandatorily recorded throughout the planning process.
[0017] The data tracing module records information about the entire process from data generation to acquisition, serving as a crucial measure of the timeliness and reliability of knowledge in planning implementation monitoring. Based on the data tracing paradigm for planning implementation monitoring, this module comprises seven elements: entity, activity, generation and utilization, agency and responsibility, derivation and revision, plan, and time.
[0018] Furthermore, in step S2, a monitoring indicator system for the implementation of territorial spatial planning at the city and county scale is constructed. This system organizes indicators in a knowledge-based manner across four dimensions: basic territorial spatial conditions, the implementation process of territorial spatial planning, implementation results, and implementation effects, as well as three levels: scenarios, themes, and indicators. External information is linked to the territorial spatial planning implementation monitoring indicator system, including three types: data facts, model methods, and related scenarios, forming three types of relationships. The data facts refer to multi-source heterogeneous data such as current status, planning, and management used to support indicator calculations. The model methods refer to the calculation models and strategies relied upon in the process of producing indicator values based on data. The related scenarios include third-party information such as policies, regulations, and engineering projects upon which territorial spatial planning is based. The three relationships include indicator item-data fact-model method relationship, indicator item-related scenario relationship, and data fact-related scenario relationship. The indicator item-data fact-model method relationship and the data fact-related scenario relationship are used to support data extraction and data updating, while the indicator item-related scenario relationship is used to assist in providing decision-making solutions.
[0019] Preferably, the model method refers to the computational model and strategy relied upon in the process of producing indicator values from raw data. It is an important factor affecting the efficiency of knowledge updates in monitoring and evaluation. The associated scenarios include third-party information such as policies and regulations, engineering projects, etc., on which the land and space planning is based, which are used to provide scientific decision support for problems found in the process of monitoring the implementation of the plan.
[0020] This invention demonstrates the semantic association between the above three types of information and the indicator system, defining the resulting paired or grouped relationships in the following three forms:
[0021] The relationship between indicator items, model methods, and data facts represents the dependency between indicator items and specific facts / data, as well as the methods and approaches used to derive indicators from data. This relationship is a crucial support for measuring the reliability of knowledge. The relationship between the indicator system and model methods, as well as between model methods and data facts, is many-to-many, forming a simple network structure.
[0022] The relationship between indicator items and related scenarios indicates the collinear relationship between indicator items and third-party scenarios. Policy and regulation adjustments and the implementation of engineering projects will lead to changes in indicator items. In order to promote positive changes in indicators, it is necessary to meet policy and regulation requirements while relying on the implementation of engineering projects to provide support for the formulation of decision-making plans based on the monitoring results of planning implementation.
[0023] Data fact-related context relationship: This relationship represents the shared links between specific facts and data corresponding to an engineering project. Collecting the data facts contained in the engineering project is beneficial for real-time monitoring of the planning and implementation progress.
[0024] Furthermore, in step S3, the specific steps are as follows:
[0025] S31: From the perspective of land management operations, the planning implementation monitoring scenarios of micro-plots are sorted out, and the information of five business statuses, including planning, pre-approval and site selection, approval, reserve, and supply, as well as the element information of each status and their relationships, are structured and modeled.
[0026] S32: A spatiotemporal monitoring network model for micro-plots based on hypergraphs is proposed. The hypergraph G = (V, E) is used to construct a set of five stages of state information and spatiotemporal context relationships. The vertex set V = *S, C4+, where S represents the five stages of land management, namely planning, preliminary review and site selection, approval, reserve, and supply. C4 represents the information of the items corresponding to the stage. The hyperedge set E = *R(S, S), R(S, C4), R(C4, C4)+ represents the relationship between stage states, the relationship between stage states and item information, and the relationship between item information, respectively. The hyperedges R(S, S) and R(C4, C4) are the basis for monitoring the sequential and topological relationships between land management states, and the hyperedge R(S, C4) is the basis for monitoring the correlation between land management states.
[0027] Furthermore, in step S4, the specific steps are as follows:
[0028] S41: Taking into account the data update frequency and reliability score, set scenario triggers for multi-source knowledge in the land and space planning implementation monitoring database. When the data monitoring engine finds new data in the database and meets the data update conditions, the planning implementation monitoring knowledge is automatically updated. Data update is a necessary condition for triggering knowledge update. When the data monitoring engine finds new data in the database, it triggers automatic knowledge update if the reliability level is not reduced; otherwise, the knowledge is not updated.
[0029] S42: At the meso-level (city / county) level, knowledge primarily relies on geospatial vector data and remote sensing data. Knowledge is acquired through understanding the relationships between indicators, data facts, and model methods, as well as the relationships between data facts and related scenarios. For the geospatial vector data, a set of automatic knowledge generation rules integrating data facts and model methods needs to be developed under indicator-driven principles. For the remote sensing data, an indicator knowledge extraction method based on deep learning and raster statistics is used. At the micro-level (plot) level, land management knowledge relies on geospatial vector data, remote sensing data, and text data. The knowledge extraction methods for geospatial vector data and remote sensing data are similar to those for the meso-level. For text data, while considering land use stage status information, a micro-plot spatiotemporal monitoring scenario network model with character set embedding and fusion hypergraph is used for knowledge extraction.
[0030] The corpus is labeled, and land management information is pre-trained using a pre-trained model to obtain dynamic word vectors based on context, thereby enhancing the semantic representation ability of land management information. Then, vector feature information is extracted using a BiLSTM model to obtain the scores of characters on each label. The results of the BiLSTM model are corrected using a CRF model to finally obtain the labels corresponding to the characters. The micro-plot spatiotemporal monitoring scenario network model fused with hypergraph is trained in multiple epochs, and the output results of each epoch are compared, with the best result being taken as the final result.
[0031] Preferably, the knowledge at the meso-level (city / county) mainly relies on geospatial vector data and remote sensing data. For geospatial vector data, a set of knowledge automatic generation rules that integrate data facts and model methods needs to be developed under the guidance of indicators. Taking the extraction of cultivated land area index values from land use status vector data patches as an example, the GDAL library is used to automate the extraction of land use status vector patches by attribute and spatial statistical calculations. For remote sensing data, an indicator knowledge extraction method based on deep learning and raster statistics is adopted. Taking the extraction of cultivated land data based on remote sensing imagery as an example, the trained deep learning model is used to interpret remote sensing images to obtain land cover classification data, and the GDAL library is used to extract and statistically analyze cultivated land information.
[0032] Furthermore, in step S5, for the meso-level planning implementation monitoring and early warning, by analyzing the monitoring objectives and key points of each process in the entire life cycle, a city and county-level territorial spatial planning implementation monitoring and early warning mechanism is constructed that takes into account indicator values, indicator changes, and indicator rankings. At the same time, auxiliary decision-making can be carried out based on data facts and related scenario relationships. The planning implementation monitoring data at the plot level is mainly organized based on the micro-spatiotemporal monitoring scenario network model, and an instance network for planning implementation monitoring is formed based on data extraction. The focus of monitoring is the semantic sequence relationship, spatial topological relationship, and correlation between stage states and corresponding information in the instance network.
[0033] Preferably, monitoring the basic planning conditions aims to understand the resource endowment and socio-economic conditions of the land space. It serves as the basis for the implementation of the plan up to the completion of this round of surveys and monitoring, and for the continued implementation of the plan thereafter. This is mainly achieved by ranking indicator values to identify the relative advantages and limitations of regional development, thereby verifying the scientific validity of the planning objectives and formulating reasonable phased plans. Monitoring the planning implementation process aims to strengthen the control and utilization of land space. Firstly, by combining planning information, current status information, and historical operational information, an indicator threshold model for the implementation process is established. By monitoring changes in indicators, timely warnings are issued and operations are optimized, thus mitigating disorderly development to some extent. Taking the remaining construction land space indicator as an example, the upper limit of the remaining construction land space is obtained by deducting the existing construction land and unused approved land from the planned construction land. Combined with the planning target year, an average annual increase in construction land reference value is obtained. An early warning is issued when the change in the remaining construction land space indicator exceeds the average annual increase in construction land reference value.
[0034] Monitoring the implementation results of the plan is used to review the achievement of various binding and control indicators at the survey and monitoring time points. Specifically, it involves calculating the difference between the indicator values at the survey and monitoring points and the planning target values. Based on the positive or negative characteristics of the indicators and the sign of the calculation result, the completion status of the indicators is determined. Early warnings are issued for indicators that have not been completed, making them key areas for further planning implementation. Let the indicator value obtained at the survey and monitoring point be Iobtain, and the planning target value be Itarget. Then the planning implementation result Sresult is...
[0035] S result =I obtain -I target
[0036] For positive indicators, Sresult > 0 indicates that the indicator has been completed, and |Sresult| represents the amount by which the indicator has exceeded expectations; Sresult < 0 indicates that the indicator has not yet been completed, and |Sresult| represents the amount by which the indicator needs to be completed. Negative indicators are the opposite.
[0037] Monitoring the implementation effect of the plan is used to evaluate different areas such as social livability, people's well-being, economic development, ecological environment, and scientific and technological exchange and cooperation at the survey and monitoring time points, so as to indirectly reflect the effect of the territorial spatial planning and its implementation. It mainly shows the status of regional socio-economic environment through the ranking of indicator values and issues early warnings to cities and counties with poor rankings.
[0038] A multi-scale territorial spatial planning implementation monitoring system that takes reliability into account, characterized in that the system includes: a data traceability management module, a planning implementation monitoring knowledge base, an automatic knowledge update module, and a planning implementation monitoring early warning module, wherein the data traceability management module, the planning implementation monitoring knowledge base, the automatic knowledge update module, and the planning implementation monitoring early warning module can implement any one of the steps in the multi-scale territorial spatial planning implementation monitoring method described above.
[0039] The functions of each part in the system are as follows:
[0040] The data traceability management module and the data management module are used to uniformly manage the metadata of data from different sources, such as surveys, management, and monitoring, contained in the territorial spatial planning implementation monitoring database, and to support data traceability and reliability assessment operations.
[0041] The planning implementation monitoring knowledge base is used to store the knowledge resources extracted based on the above steps, including meso-level knowledge such as indicator systems, data facts, model methods and related scenarios at the city and county levels, as well as micro-level knowledge such as land management business at the plot level.
[0042] The knowledge automatic update module is used to trigger knowledge update scenarios based on preset conditions, so as to realize the automatic extraction and updating of monitoring knowledge;
[0043] The planning implementation monitoring and early warning module is used for dynamic monitoring and timely early warning based on the knowledge in the planning implementation monitoring knowledge base.
[0044] The beneficial effects of this invention are as follows:
[0045] 1. Based on the PROV model, the data involved in the planning implementation monitoring were reorganized, a data traceability paradigm for planning implementation monitoring was established, and the reliability assessment of implementation monitoring knowledge was realized, which is conducive to improving the scientificity and accuracy of implementation monitoring results;
[0046] 2. From the perspective of the entire life cycle of planning implementation monitoring, structured modeling of planning implementation monitoring indicators is carried out, linking data facts, model methods, and relevant contexts such as policies, regulations, and engineering projects to form a networked model of planning implementation monitoring at the meso level, which assists business personnel in conducting correlation analysis of planning implementation monitoring results;
[0047] 3. From the perspective of land management business, this paper systematically sorts out the land management business scenarios, proposes a network architecture that integrates hypergraph, and establishes a micro-level networked model for planning implementation monitoring, which helps business personnel to accurately control the progress of planning implementation;
[0048] 4. Based on a comprehensive consideration of data update frequency and reliability score, a scenario trigger for planning implementation monitoring was set up. A combination of rule and deep learning method was used to automatically extract knowledge at both the meso and micro levels, thereby automating the acquisition of knowledge for planning implementation monitoring and enabling timely early warning to a certain extent.
[0049] 5. Based on the characteristics of the city / county-level and plot-level territorial spatial planning implementation monitoring network, it is important to establish a city / county-level planning implementation monitoring and early warning mechanism that takes into account indicator values, indicator changes, and indicator rankings, as well as a plot-level planning implementation monitoring and early warning mechanism that takes into account the status and information of land management stages. This is an important part of the intelligent construction of territorial spatial planning, which is conducive to accurately locating problems that arise during the implementation of territorial spatial planning and achieving "early warning and early action". Attached Figure Description
[0050] The above and other features of the present invention will become more apparent from the detailed description of the embodiments shown in conjunction with the accompanying drawings. In the accompanying drawings, the same reference numerals denote the same or similar elements. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without any creative effort. In the drawings:
[0051] Figure 1 A schematic diagram of the technical process of a multi-scale land spatial planning implementation monitoring method and system;
[0052] Figure 2 A schematic diagram of a planning implementation monitoring metadata model for a multi-scale territorial spatial planning implementation monitoring method and system;
[0053] Figure 3 A schematic diagram of a city-county scale-based monitoring network model for monitoring the implementation of multi-scale territorial spatial planning.
[0054] Figure 4 A schematic diagram of a land parcel-scale-oriented monitoring network model for monitoring the implementation of multi-scale territorial spatial planning.
[0055] Figure 5 A schematic diagram of a knowledge update scenario trigger for a multi-scale land spatial planning implementation monitoring method and system;
[0056] Figure 6 A schematic diagram of a multi-scale land spatial planning implementation monitoring method and system, and a planning implementation monitoring and early warning mechanism.
[0057] Figure 7 A schematic diagram of a multi-scale land spatial planning implementation monitoring method and a system planning implementation monitoring and early warning mechanism;
[0058] Figure 8 This is a schematic diagram of a multi-scale land spatial planning implementation monitoring method and system, and a planning implementation monitoring and early warning system. Detailed Implementation
[0059] The following will provide a clear and complete description of the concept, specific structure, and technical effects of the present invention in conjunction with the embodiments and accompanying drawings, so as to fully understand the purpose, solution, and effects of the present invention. It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other.
[0060] In the description of this invention, "several" means one or more, "more than" means two or more, "greater than," "less than," and "exceeding" are understood to exclude the stated number, while "above," "below," and "within" are understood to include the stated number. The use of "first" and "second" in the description is merely for distinguishing technical features and should not be construed as indicating or implying relative importance, or implicitly indicating the number of indicated technical features, or implicitly indicating the order of the indicated technical features.
[0061] like Figure 1 and Figure 2As shown, a multi-scale land spatial planning implementation monitoring method is provided, the method including the following steps:
[0062] S1: Systematically sort out the land and space planning data resources needed for planning implementation monitoring, construct a monitoring metadata model based on the PROV model, and form a data reliability evaluation mechanism;
[0063] S2: Combine the aforementioned reliability evaluation mechanism with the monitoring indicator system for the implementation of territorial spatial planning, and perform external information correlation on the monitoring indicator system for the implementation of territorial spatial planning;
[0064] S3: A land parcel-scale national spatial planning implementation monitoring network model that integrates the vertical land management business of SuperMap and the horizontal geographic unit connectivity.
[0065] S4: Based on the monitoring network model for the implementation of territorial spatial planning and the aforementioned reliability evaluation mechanism, design a knowledge extraction method based on a deep learning model;
[0066] S5: Implement a monitoring and early warning mechanism based on the established city / county and plot-scale territorial spatial planning implementation monitoring network model.
[0067] Furthermore, in step S1, the specific steps are as follows:
[0068] S11: Based on the PROV model, design, plan, implement, and monitor data traceability paradigm, including seven concepts: entity, activity, generation and utilization, agency and responsibility, derivation and revision, plan, and time, used to represent information such as data producer, production time, production method, and other derived data.
[0069] S12: Extract metadata information of various types of data involved in the monitoring of the implementation of territorial spatial planning, integrate and summarize them into three parts: vector data, raster data, and text data. Combined with the data traceability paradigm for planning implementation monitoring established in S11, establish a metadata model for planning implementation monitoring that takes into account traceability information.
[0070] S13: Based on the analysis of the quality evaluation index set included in the ISO / IEC 25024 data quality model, and combined with the planning implementation monitoring metadata model established in S12, factor analysis is used to screen and analyze the correlation of indicators that take into account the planning implementation monitoring scenario. Three indicators affecting the reliability evaluation of planning implementation monitoring data are obtained: the data production responsible unit, the data acquisition and processing technology method, and the data timeliness. The TAE model is used to evaluate the reliability of planning implementation monitoring data.
[0071] Preferably, an entity is the basic unit of data storage, including both text documents and spatial data files. An activity refers to various operations on the data, including modification and supplementation of text, and analysis and computation of spatial data. Generation and utilization connect entities and activities; they can be described as activities utilizing entities or entities being generated by activities, pointing to the source and from the future to the past. Agency and responsibility are generally acted upon by organizations and can act on entities or activities, representing entity agents or activity subjects, respectively. Derivation and revision are used to build associations between entities with the same source; for example, a new data is generated after an editing activity, and the new data is a derived version of the original data. Planning is used to expand the semantic relationship from activity to agent; for example, it can represent the start time of an activity and the specifications followed. Time describes when an entity is generated and utilized, and when an activity begins and ends.
[0072] Preferably, the spatial module records the spatial characteristics of geospatial entities, such as coverage, accuracy, spatial reference system, and projected coordinate system, serving as an important identifier of the knowledge domain for planning implementation monitoring. For example, administrative division data is the foundation for various spatial data analyses, and the natural resources business database contains multiple different versions. Understanding the differences in spatial characteristics between these versions is fundamental to the correct use of administrative division data.
[0073] The content module records the category to which the data belongs, serving as the primary means of linking knowledge points in planning implementation monitoring. Referring to the "Technical Specification for the Information System for the Implementation Supervision of the 'One Map' of Territorial Spatial Planning (GB / T39972-2021)," planning implementation monitoring data is divided into four major categories and thirteen subcategories: basic status quo, planning outcomes, planning implementation, and planning supervision. Basic status quo includes basic geographic information data, geological data, natural resource survey and monitoring data, natural resource management data, and natural and historical cultural protection data; planning outcomes include overall planning data, detailed planning data, and special planning data; planning implementation includes land use control data, ecological status and major ecological restoration project information data; and planning supervision includes planning implementation monitoring, evaluation, and early warning data, resource and environmental carrying capacity monitoring and early warning data, and data automatically and mandatorily recorded throughout the planning process.
[0074] The data tracing module records information about the entire process from data generation to acquisition, serving as a crucial measure of the timeliness and reliability of knowledge in planning implementation monitoring. Based on the data tracing paradigm for planning implementation monitoring, this module comprises seven elements: entity, activity, generation and utilization, agency and responsibility, derivation and revision, plan, and time.
[0075] Preferably, the reliability evaluation score of the data can be expressed as:
[0076] S reliability =S T (S A +SE )
[0077] Here, Sreliability represents the data reliability score, SA represents the authority dimension score, SE represents the accuracy dimension score, and ST represents the timeliness dimension score. For the authority dimension (A), the reliability level depends on the level of the institution. The data for planning implementation monitoring primarily consists of data released by the natural resources department, supplemented by data produced by other relevant departments and spatiotemporal big data collected via the internet. For example, for forest land data, there are two types: data obtained by the natural resources department based on land change surveys and statistical survey data from the forestry department. Planning implementation monitoring should prioritize data provided by the natural resources department. For population data, there are census data obtained by the National Bureau of Statistics and population big data information obtained by internet companies through methods such as mobile phone signaling. Planning implementation monitoring should prioritize data provided by the National Bureau of Statistics. Let the reliability scores of data from the natural resources department, other government departments, and internet companies be SA1, SA2, and SA3, respectively, and let the relationship S exist. A3 A2 A1 ;
[0078] For the accuracy dimension (E), the reliability level depends on the technical methods employed. Data acquisition and processing techniques can be categorized into two types: those based on traditional surveys and those based on next-generation information technologies. Taking land use data acquisition as an example, traditional surveying and measurement methods are theoretically rigorous and highly accurate, but the process is complex and the data acquisition cycle is long, making it difficult to meet real-time monitoring needs. Next-generation techniques, represented by remote sensing image interpretation, are based on statistical theory, have a simpler process, and can achieve multi-time-series monitoring, but their accuracy needs further improvement. Let the reliability scores of traditional methods and next-generation information technology methods be SE1 and SE2, respectively, and let the relationship S be... E2 E1 ;
[0079] For the timeliness dimension (T), the reliability level depends on the frequency of updates. Data timeliness is a crucial prerequisite for ensuring the smooth implementation of planning and monitoring. Drawing on international methods for assessing the timeliness of planning implementation monitoring data, and guided by expert experience, the timeliness range of data for different monitoring topics is categorized and graded. For example, the time validity of cultivated land data is divided into three levels, using data release as the starting point: January to February, February to May, and after May. The relationship between the time validity levels ST1, ST2, and ST3 is S... T3 T2 T1 ;
[0080] By using the methods described above, a data organization paradigm for planning implementation monitoring that takes reliability into account can be formed, and on this basis, reliable knowledge for planning implementation monitoring can be developed.
[0081] like Figure 3 As shown, further, in step S2, a monitoring indicator system for the implementation of territorial spatial planning at the city and county scale is constructed. The indicator system organizes the indicators in a knowledge-based manner from four dimensions: basic conditions of territorial spatial planning, implementation process of territorial spatial planning, implementation results and implementation effects, and three levels: scenario, theme and indicator. External information is associated with the monitoring indicator system for the implementation of territorial spatial planning, including three types: data facts, model methods and associated scenarios, forming three types of association relationships. Among them, the data facts refer to the multi-source heterogeneous data such as current status, planning and management used to support the calculation of indicators. The model methods refer to the calculation models and strategies relied upon in the process of producing indicator values based on data. The associated scenarios include third-party information such as policies and regulations, engineering projects and other information on which territorial spatial planning is based. The three relationships are: indicator item-data fact-model method relationship, indicator item-associated scenario relationship, and data fact-associated scenario relationship. Among them, the indicator item-data fact-model method relationship and the data fact-associated scenario relationship are used to support data extraction and data updating, and the indicator item-associated scenario relationship is used to assist in providing decision-making solutions.
[0082] Preferably, the model method refers to the computational model and strategy relied upon in the process of producing indicator values from raw data. It is an important factor affecting the efficiency of knowledge updates in monitoring and evaluation. The associated scenarios include third-party information such as policies and regulations, engineering projects, etc., on which the land and space planning is based, which are used to provide scientific decision support for problems found in the process of monitoring the implementation of the plan.
[0083] This invention demonstrates the semantic association between the above three types of information and the indicator system, defining the resulting paired or grouped relationships in the following three forms:
[0084] The relationship between indicator items, model methods, and data facts represents the dependency between indicator items and specific facts / data, as well as the methods and approaches used to derive indicators from data. This relationship is a crucial support for measuring the reliability of knowledge. The relationship between the indicator system and model methods, as well as between model methods and data facts, is many-to-many, forming a simple network structure.
[0085] The relationship between indicator items and related scenarios indicates the collinear relationship between indicator items and third-party scenarios. Policy and regulation adjustments and the implementation of engineering projects will lead to changes in indicator items. In order to promote positive changes in indicators, it is necessary to meet policy and regulation requirements while relying on the implementation of engineering projects to provide support for the formulation of decision-making plans based on the monitoring results of planning implementation.
[0086] Data fact-related context relationship: This relationship represents the shared links between specific facts and data corresponding to an engineering project. Collecting the data facts contained in the engineering project is beneficial for real-time monitoring of the planning and implementation progress.
[0087] Furthermore, in step S3, the specific steps are as follows:
[0088] S31: From the perspective of land management operations, the planning implementation monitoring scenarios of micro-plots are sorted out, and the information of five business statuses, including planning, pre-approval and site selection, approval, reserve, and supply, as well as the element information of each status and their relationships, are structured and modeled.
[0089] S32: A spatiotemporal monitoring network model for micro-plots based on hypergraphs is proposed. The hypergraph G = (V, E) is used to construct a set of five stages of state information and spatiotemporal context relationships. The vertex set V = *S, C4+, where S represents the five stages of land management, namely planning, preliminary review and site selection, approval, reserve, and supply. C4 represents the information of the items corresponding to the stage. The hyperedge set E = *R(S, S), R(S, C4), R(C4, C4)+ represents the relationship between stage states, the relationship between stage states and item information, and the relationship between item information, respectively. The hyperedges R(S, S) and R(C4, C4) are the basis for monitoring the sequential and topological relationships between land management states, and the hyperedge R(S, C4) is the basis for monitoring the correlation between land management states.
[0090] according to Figure 5 As shown, further, in step S4, the specific steps are as follows:
[0091] S41: Taking into account the data update frequency and reliability score, set scenario triggers for multi-source knowledge in the land and space planning implementation monitoring database. When the data monitoring engine finds new data in the database and meets the data update conditions, the planning implementation monitoring knowledge is automatically updated. Data update is a necessary condition for triggering knowledge update. When the data monitoring engine finds new data in the database, it triggers automatic knowledge update if the reliability level is not reduced; otherwise, the knowledge is not updated.
[0092] S42: At the meso-level (city / county) level, knowledge primarily relies on geospatial vector data and remote sensing data. Knowledge is acquired through understanding the relationships between indicators, data facts, and model methods, as well as the relationships between data facts and related scenarios. For the geospatial vector data, a set of automatic knowledge generation rules integrating data facts and model methods needs to be developed under indicator-driven principles. For the remote sensing data, an indicator knowledge extraction method based on deep learning and raster statistics is used. At the micro-level (plot) level, land management knowledge relies on geospatial vector data, remote sensing data, and text data. The knowledge extraction methods for geospatial vector data and remote sensing data are similar to those for the meso-level. For text data, while considering land use stage status information, a micro-plot spatiotemporal monitoring scenario network model with character set embedding and fusion hypergraph is used for knowledge extraction.
[0093] The corpus is labeled, and land management information is pre-trained using a pre-trained model to obtain dynamic word vectors based on context, thereby enhancing the semantic representation ability of land management information. Then, vector feature information is extracted using a BiLSTM model to obtain the scores of characters on each label. The results of the BiLSTM model are corrected using a CRF model to finally obtain the labels corresponding to the characters. The micro-plot spatiotemporal monitoring scenario network model fused with hypergraph is trained in multiple epochs, and the output results of each epoch are compared, with the best result being taken as the final result.
[0094] Preferably, the knowledge at the meso-level (city / county) mainly relies on geospatial vector data and remote sensing data. For geospatial vector data, a set of knowledge automatic generation rules that integrate data facts and model methods needs to be developed under the guidance of indicators. Taking the extraction of cultivated land area index values from land use status vector data patches as an example, the GDAL library is used to automate the extraction of land use status vector patches by attribute and spatial statistical calculations. For remote sensing data, an indicator knowledge extraction method based on deep learning and raster statistics is adopted. Taking the extraction of cultivated land data based on remote sensing imagery as an example, the trained deep learning model is used to interpret remote sensing images to obtain land cover classification data, and the GDAL library is used to extract and statistically analyze cultivated land information.
[0095] like Figure 6 and Figure 7 As shown, further, in step S5, for the monitoring and early warning of the implementation of planning at the meso-level, a monitoring and early warning mechanism for the implementation of territorial spatial planning at the city and county levels is constructed by analyzing the monitoring objectives and key points of each process in the entire life cycle;
[0096] Monitoring the basic conditions of planning aims to understand the resource endowment and socio-economic conditions of the national land space. It serves as the basis for the implementation of the plan up to the completion of this round of surveys and monitoring, and for the continued implementation of the plan thereafter. It primarily uses the ranking of indicator values to identify the relative advantages and limitations of regional development, thereby verifying the scientific validity of the planning objectives and formulating reasonable phased plans. Monitoring the planning implementation process aims to strengthen the control and utilization of national land space. Firstly, it combines planning information, current status information, and historical operational information to establish an indicator threshold model for the implementation process. By monitoring changes in indicators, it provides timely warnings and optimizes operations, mitigating disorderly development to some extent. Taking the remaining construction land space indicator as an example, the upper limit of the remaining construction land space is obtained by deducting existing construction land and unused approved land from the planned construction land. Combined with the annual target year, a reference value for the average annual increase in construction land is obtained. A warning is issued when the change in the remaining construction land space indicator exceeds the reference value for the average annual increase in construction land.
[0097] Monitoring the implementation results of the plan is used to review the achievement of various binding and control indicators at the survey and monitoring time points. Specifically, it involves calculating the difference between the indicator values at the survey and monitoring points and the planning target values. Based on the positive or negative characteristics of the indicators and the sign of the calculation result, the completion status of the indicators is determined. Early warnings are issued for indicators that have not been completed, making them key areas for further planning implementation. Let the indicator value obtained at the survey and monitoring point be Iobtain, and the planning target value be Itarget. Then the planning implementation result Sresult is...
[0098] S result =I obtain -I target
[0099] For positive indicators, Sresult > 0 indicates that the indicator has been completed, and |Sresult| represents the amount by which the indicator has exceeded expectations; Sresult < 0 indicates that the indicator has not yet been completed, and |Sresult| represents the amount by which the indicator needs to be completed. Negative indicators are the opposite.
[0100] The monitoring of the implementation effect of the plan is used to evaluate different fields such as social livability, people's well-being, economic development, ecological environment, and scientific and technological exchange and cooperation at the time point of the investigation and monitoring, so as to reflect the effect of the territorial spatial planning and its implementation. It mainly shows the status of regional socio-economic environment through the ranking of indicator values and provides early warning for cities and counties with poor rankings.
[0101] like Figure 4 As shown, the planning implementation monitoring data at the plot level is mainly organized based on the micro-spatiotemporal monitoring scenario network model to form an instance network for planning implementation monitoring. The focus of the monitoring is the semantic sequence relationship, spatial topological relationship, and correlation relationship of R(S,C4) in the instance network.
[0102] The semantic sequence of R(S,S) represents the progress of land management operations. Ideally, the planning (S1), preliminary review and site selection (S2), approval (S3), reserve (S4), and supply (S5) stages are carried out sequentially, with five possible sequences: R(S1), R(S1,S2), R(S1,S2,S3), R(S1,S2,S3,S4), and R(S1,S2,S3,S4,S5). When the state relationship of each stage does not satisfy any of the above, an early warning is issued.
[0103] The spatial topological relationship of R(S,S) refers to the relationship between the spatial extents corresponding to each stage of land management operations. Combining the semantic sequence of R(S,S), it can be seen that the spatial topological relationship of each stage satisfies in This represents the spatial range corresponding to the business state Si (i = {1, 2, 3, 4}). When the topological relationship between states in each stage violates the above rules, an early warning is issued.
[0104] The correlation of R(S,C4) refers to the interrelationship between stage status and event information, where S is the specific manifestation of C4, and C4 is the basic support of S. An early warning is issued when S and C4 cannot correspond effectively or when only one exists. For example, the activation of the pre-approval and site selection (S2) stage status indicates that land use pre-approval and planning site selection have been completed. If the monitoring data does not contain corresponding information for land use pre-approval (C42), an early warning is issued.
[0105] like Figure 8 As shown, a multi-scale territorial spatial planning implementation monitoring system that takes reliability into account is characterized in that the system includes: a data traceability management module, a planning implementation monitoring knowledge base, an automatic knowledge update module, and a planning implementation monitoring early warning module. The data traceability management module, the planning implementation monitoring knowledge base, the automatic knowledge update module, and the planning implementation monitoring early warning module can implement any one of the steps in the multi-scale territorial spatial planning implementation monitoring method described above.
[0106] The functions of each part in the system are as follows:
[0107] The data traceability management module and the data management module are used to uniformly manage the metadata of data from different sources, such as surveys, management, and monitoring, contained in the territorial spatial planning implementation monitoring database, and to support data traceability and reliability assessment operations.
[0108] The planning implementation monitoring knowledge base is used to store the knowledge resources extracted based on the above steps, including meso-level knowledge such as indicator systems, data facts, model methods and related scenarios at the city and county levels, as well as micro-level knowledge such as land management business at the plot level.
[0109] The knowledge automatic update module is used to trigger knowledge update scenarios based on preset conditions, so as to realize the automatic extraction and updating of monitoring knowledge;
[0110] The planning implementation monitoring and early warning module is used for dynamic monitoring and timely early warning based on the knowledge in the planning implementation monitoring knowledge base.
[0111] Although the invention has been described in considerable detail and particularly with regard to several of the described embodiments, it is not intended to limit itself to any of these details or embodiments or any particular embodiment, thereby effectively covering the intended scope of the invention. Furthermore, the invention has been described above with respect to embodiments foreseeable by the inventors in order to provide a useful description, and non-substantial modifications to the invention that have not yet been foreseen may still represent equivalent modifications.
Claims
1. A multi-scale land spatial planning implementation monitoring method, characterized in that, The method includes the following steps: S1: Systematically sort out the land and space planning data resources needed for planning implementation monitoring, construct a monitoring metadata model based on the PROV model, and form a data reliability evaluation mechanism; S2: Combine the aforementioned reliability evaluation mechanism with the monitoring indicator system for the implementation of territorial spatial planning, and perform external information correlation on the monitoring indicator system for the implementation of territorial spatial planning; S3: A monitoring network model for the implementation of national spatial planning at the plot scale that integrates the vertical land management business of SuperMap and the horizontal geographic unit connection. S4: Based on the monitoring network model for the implementation of territorial spatial planning and the aforementioned reliability evaluation mechanism, design a knowledge extraction method based on a deep learning model; S5: Implement a monitoring and early warning mechanism based on the established city / county and plot-scale territorial spatial planning implementation monitoring network model; In step S1, the specific steps are as follows: S11: Based on the PROV model, design, plan and implement a monitoring data traceability paradigm, which includes seven concepts: entity, activity, generation and utilization, agency and responsibility, derivation and revision, plan and time, used to represent the data producer, production time, production method and other derived data information; S12: Extract metadata information of various types of data involved in the monitoring of the implementation of national spatial planning, integrate and summarize them into three parts: vector data, raster data, and text data, and combine them with the data traceability paradigm of planning implementation monitoring established in S11 to establish a metadata model of planning implementation monitoring that takes into account traceability information. S13: Based on the analysis of the quality evaluation index set included in the ISO / IEC 25024 data quality model, and combined with the planning implementation monitoring metadata model established in S12, factor analysis is used to screen and analyze the correlation of indicators that take into account the planning implementation monitoring scenario. Three indicators affecting the reliability evaluation of planning implementation monitoring data are obtained: the data production responsible unit, the data acquisition and processing technology and method, and the data timeliness. The TAE model is used to evaluate the reliability of planning implementation monitoring data. The reliability score of the data can be expressed as: ; Among them, Sreliability represents the reliability score of the data, SA represents the authority dimension score, SE represents the accuracy dimension score, and ST represents the timeliness dimension score. For the authority dimension (A), the reliability level depends on the level of the organization. In step S2, a monitoring indicator system for the implementation of territorial spatial planning at the city and county scale is constructed. The indicator system organizes the indicators in a knowledge-based manner from four dimensions: basic conditions of territorial spatial planning, implementation process of territorial spatial planning, implementation results and implementation effects, and three levels: scenario, theme and indicator. External information is associated with the monitoring indicator system for the implementation of territorial spatial planning, including three types: data facts, model methods and associated scenarios, forming three types of association relationships. Among them, the data facts refer to the multi-source heterogeneous data of current status, planning and management used to support the calculation of indicators. The model methods refer to the calculation models and strategies relied upon in the process of producing indicator values based on data. The associated scenarios include policies and regulations on which territorial spatial planning is based and third-party information of engineering projects. The three relationships are: indicator item-data fact-model method relationship, indicator item-associated scenario relationship, and data fact-associated scenario relationship. Among them, the indicator item-data fact-model method relationship and the data fact-associated scenario relationship are used to support data extraction and data updating, and the indicator item-associated scenario relationship is used to assist in providing decision-making solutions. Model-based methods refer to the computational models and strategies relied upon in the process of producing indicator values from raw data. They are an important factor affecting the efficiency of knowledge updates in monitoring and evaluation. Related scenarios include policies and regulations on which territorial spatial planning is based, and third-party information on engineering projects, which are used to provide scientific decision-making support for problems found in the process of monitoring the implementation of planning. The above three types of information are semantically associated with the indicator system, and the resulting paired or grouped relationships are defined in the following three forms: The relationship between indicator items, model methods, and data facts represents the dependency between indicator items and specific facts and data, as well as the methods and approaches to derive indicators from data. This relationship is an important support for the measurement of knowledge reliability. The relationship between indicator system and model methods, as well as between model methods and data facts, is a many-to-many relationship. The three of them form a simple network structure. The relationship between indicator items and related scenarios indicates the collinear relationship between indicator items and third-party scenarios. Policy and regulation adjustments and the implementation of engineering projects will lead to changes in indicator items. In order to promote positive changes in indicators, it is necessary to meet policy and regulation requirements while relying on the implementation of engineering projects to provide support for the formulation of decision-making plans based on the monitoring results of planning implementation. Data fact-related context relationship: This relationship represents the shared links between specific facts and data corresponding to an engineering project. Collecting the data facts contained in the engineering project is beneficial for real-time monitoring of the planning and implementation progress. In step S3, the specific steps are as follows: S31: From the perspective of land management operations, the planning implementation monitoring scenarios of micro-plots are sorted out, and the information of five business statuses, namely planning, pre-approval and site selection, approval, reserve and supply, as well as the element information of each status and their relationships, are structured and modeled. S32: Proposes a network model for spatiotemporal monitoring of micro-plots by incorporating hypergraphs, utilizing hypergraphs. Construct a set of five stages of state information and spatiotemporal context relationships, including a vertex set. S represents the five stages of land management, namely planning, preliminary review and site selection, approval, reserve, and supply. C4 represents the information related to each stage. (Super-edge set) These represent the relationships between stage states, the relationships between stage states and event information, and the relationships between event information, respectively. Hyperedges R(S,S) and R(C4,C4) are the basis for monitoring the sequential and topological relationships between land management states, while hyperedge R(S,C4) is the basis for monitoring the correlation relationships between land management states. In step S4, the specific steps are as follows: S41: Taking into account the data update frequency and reliability score, set scenario triggers for multi-source knowledge in the land and space planning implementation monitoring database. When the data monitoring engine finds new data in the database and meets the data update conditions, the planning implementation monitoring knowledge is automatically updated. Data update is a necessary condition for triggering knowledge update. When the data monitoring engine finds new data in the database, it triggers automatic knowledge update if the reliability level is not reduced; otherwise, the knowledge is not updated. S42: At the meso-level (city / county) level, knowledge primarily relies on geospatial vector data and remote sensing data. Knowledge is acquired from the relationships between indicator items, data facts, and model methods, as well as the relationships between data facts and related scenarios. For the geospatial vector data, a set of automatic knowledge generation rules integrating data facts and model methods needs to be developed under indicator-driven principles. For the remote sensing data, an indicator knowledge extraction method based on deep learning and raster statistics is used. At the micro-level (plot) level, land management knowledge relies on geospatial vector data, remote sensing data, and text data. The knowledge extraction methods for geospatial vector data and remote sensing data are similar to those for the meso-level. For text data, while considering land use stage status information, a micro-plot spatiotemporal monitoring scenario network model with character set embedding and fusion hypergraph is used for knowledge extraction. The corpus is labeled, and land management information is pre-trained using a pre-trained model to obtain dynamic word vectors based on context, thereby enhancing the semantic representation ability of land management information. Then, vector feature information is extracted using a BiLSTM model to obtain the scores of characters on each label. The results of the BiLSTM model are corrected using a CRF model to finally obtain the labels corresponding to the characters. The micro-plot spatiotemporal monitoring scenario network model fused with hypergraph is trained in multiple epochs, and the output results of each epoch are compared, with the best result being taken as the final result. In step S5, for the meso-level planning implementation monitoring and early warning, by analyzing the monitoring objectives and key points of each process in the whole life cycle, a city and county-level territorial spatial planning implementation monitoring and early warning mechanism is constructed that takes into account the indicator values, indicator changes, and indicator rankings. At the same time, auxiliary decision-making can be carried out based on the data facts-related scenario relationships. The planning implementation monitoring data at the plot level is mainly organized based on the micro-spatiotemporal monitoring scenario network model, and an instance network for planning implementation monitoring is formed based on data extraction. The focus of monitoring is the semantic sequence relationship, spatial topological relationship, and correlation between the stage states and the corresponding information in the instance network. Monitoring the implementation results of the plan is used to review the achievement of various binding and control indicators at the survey and monitoring time points. Specifically, it involves calculating the difference between the indicator values at the survey and monitoring points and the planning target values. Based on the positive or negative characteristics of the indicators and the sign of the calculation results, the completion status of the indicators is determined. Early warnings are issued for indicators that are not completed, making them key areas for future plan implementation. Let the indicator values obtained at the survey and monitoring points be... The target value of the plan is So what are the results of the implementation of the plan? for ; For positive indicators, >0 indicates that the indicator has been completed. | indicates the amount by which this indicator exceeded expectations; <0 indicates that the indicator has not yet been completed. | indicates the amount of work to be done for this indicator; negative indicators are the opposite. The monitoring of the implementation effect of the plan is used to evaluate different areas such as social livability, people's well-being, economic development, ecological environment, and scientific and technological exchange and cooperation at the time point of the investigation and monitoring, so as to reflect the effect of the territorial spatial planning and its implementation. It mainly shows the status of regional socio-economic environment through the ranking of indicator values and provides early warning for cities and counties with poor rankings. The planning implementation monitoring data at the plot level is mainly organized based on the micro-spatiotemporal monitoring scenario network model to form an instance network for planning implementation monitoring. The focus of the monitoring is the semantic sequence relationship, spatial topological relationship, and correlation relationship of R(S,S) in the instance network. The semantic sequence of R(S,S) represents the progress of land management operations. Ideally, the stages of planning (S1), preliminary review and site selection (S2), approval (S3), reserve (S4), and supply (S5) are carried out sequentially. Five types of sequential relationships are defined. An early warning is issued when the state relationship at each stage does not satisfy any of the above conditions. The spatial topological relationship of R(S,S) refers to the relationship between the spatial extents corresponding to each stage of land management operations. Combining the semantic sequence of R(S,S), it can be seen that the spatial topological relationship of each stage satisfies ,in This represents the spatial range corresponding to the business state Si (i={1,2,3,4}). When the topological relationship between states in each stage violates the above rules, an early warning is issued. The correlation of R(S,C4) refers to the relationship between stage status and event information. S is the specific manifestation of C4, and C4 is the basic support of S. When S and C4 cannot correspond effectively or only one exists, an early warning is issued.
2. A multi-scale land spatial planning implementation monitoring system that takes reliability into account, characterized in that, The system includes: a data traceability management module, a planning implementation monitoring knowledge base, an automatic knowledge update module, and a planning implementation monitoring and early warning module. The data traceability management module, the planning implementation monitoring knowledge base, the automatic knowledge update module, and the planning implementation monitoring and early warning module can implement the steps in any one of the multi-scale territorial spatial planning implementation monitoring methods in claim 1.
Citation Information
Patent Citations
System and method for implementing supervision and evaluation of territorial space planning through one graph
CN110599024A
Land space planning index model management and application method based on knowledge pedigree
CN115099722A
