Land consolidation intelligent monitoring method and system fusing space planning and multi-source perception

Abstract

The present application relates to the technical field of data processing and decision support, and particularly relates to a land consolidation intelligent monitoring method and system fusing spatial planning and multi-source perception. The method comprises the following steps: S1: acquiring land consolidation demand data and land monitoring demand data, and dividing the land consolidation demand data into first land consolidation data and second land consolidation data; S2: respectively calculating the correlation degree and lag degree between the first land consolidation demand data, and correcting the land monitoring demand data; S3: acquiring the land monitoring demand data of the second land consolidation demand data, determining the core monitoring demand, and correcting the land monitoring demand data. The present application divides the land consolidation demand into two categories of ownership dislocation and attribute gap, dynamically adjusts the monitoring frequency, extracts the core demand through clustering, and corrects in reverse, fuses multi-source data to generate an optimized monitoring scheme, forms a closed loop feedback, and improves the monitoring adaptation accuracy and intelligent level.

Description

Technical Field

[0001] This invention relates to the field of data processing and decision support technology, and in particular to a smart monitoring method and system for land consolidation that integrates spatial planning and multi-source sensing. Background Technology

[0002] Spatial planning, as the legal basis for land use control and resource allocation, achieves spatial control objectives through land use master plan layers, permanent basic farmland protection area layers, and ecological protection red line layers. Multi-source sensing technology utilizes satellite remote sensing imagery data, UAV lidar point cloud data, and real-time monitoring data from IoT sensors to construct a comprehensive data acquisition system covering the sky and ground. Land consolidation monitoring aims to provide data support for land consolidation projects by identifying land use changes and land quality status. Existing intelligent monitoring methods for land consolidation based on spatial planning and multi-source sensing have achieved significant results in application scenarios such as monitoring illegal occupation of construction land and identifying abandoned farmland by overlaying and comparing planning layers with remote sensing images, greatly improving the automation level and coverage of land supervision.

[0003] However, existing methods still have significant shortcomings in identifying land consolidation needs and dynamically optimizing monitoring schemes. Traditional monitoring strategies often employ uniform monitoring indicators and fixed monitoring frequencies, making it difficult to distinguish consolidation needs driven by different sources, resulting in a structural mismatch between monitoring data and consolidation needs. For consolidation areas involving planning control requirements and ownership status, existing methods lack the ability to analyze the correlation between spatial distribution characteristics and temporal trends. For consolidation areas involving land physical status, the massive monitoring needs lack priority identification and dynamic adjustment mechanisms, making it difficult to achieve accurate adaptation of monitoring schemes. There is a lack of closed-loop feedback paths between monitoring results and spatial planning data; the access to multi-source sensing data remains at the one-way collection level, making it impossible to dynamically optimize planning layers and monitoring strategies based on monitoring analysis results.

[0004] Therefore, there is an urgent need to study a smart monitoring method for land consolidation that integrates spatial planning and multi-source sensing. By establishing a dynamic adaptation mechanism between consolidation needs and monitoring schemes, the intelligent level of land consolidation monitoring can be improved and planning data can be iteratively optimized. Summary of the Invention

[0005] To overcome the drawbacks of heterogeneous data sources and low coupling with demand, this invention provides a smart monitoring method and system for land consolidation that integrates spatial planning and multi-source sensing.

[0006] The technical implementation scheme of the present invention: a smart monitoring method for land consolidation that integrates spatial planning and multi-source sensing, comprising the following steps: S1: Obtain land consolidation demand data and land monitoring demand data, and divide the land consolidation demand data into first land consolidation data and second land consolidation data; S2: Calculate the correlation and lag between the first land consolidation demand data and correct the land monitoring demand data respectively; S3: After obtaining the land monitoring requirement data for the second land consolidation requirement and determining the core monitoring requirements, revise the land monitoring requirement data; S4: Update spatial planning data based on the revised land monitoring demand data, and generate a comprehensive monitoring scheme by integrating multi-source sensing data.

[0007] Preferably, the step of acquiring land consolidation demand data and land monitoring demand data, and dividing the land consolidation demand data into first land consolidation data and second land consolidation data, includes: If the land consolidation demand data involves a mismatch between the legal status and the actual status of land at the planning ownership level, then the land consolidation demand data will be classified as the first land consolidation data. If the land consolidation demand data involves the gap between the physical attributes of the land itself and its ideal state, then the land consolidation demand data will be classified as the second type of land consolidation data.

[0008] Preferably, the step of calculating the correlation and lag between the first land consolidation demand data and correcting the land monitoring demand data includes: Based on the time sequence, two adjacent first land consolidation data points are selected, and the degree of correlation of structural misalignment between the two data points is calculated; Based on spatial location, select two spatially adjacent first land consolidation data points and calculate the degree of lag in the process misalignment between the two data points; The degree of correlation is obtained by calculating the similarity of the spatial distribution patterns of the structural misalignment features of the two first land consolidation data; The degree of lag is obtained by calculating the absolute value of the timestamp difference between two first land consolidation data; The structural misalignment refers to the systematic deviation between the legal status and the actual status of land in the spatial dimension; The process misalignment refers to the lag in updating the legal status and actual status of land in the time dimension; Land monitoring demand data is obtained based on the degree of correlation and lag in the first land consolidation demand data and then corrected.

[0009] Preferably, the step of obtaining and correcting the land monitoring demand data based on the degree of correlation and lag in the first land consolidation demand data includes: The first monitoring adjustment frequency is determined based on the degree of correlation. The first monitoring adjustment frequency is negatively correlated with the degree of correlation. The lower the degree of correlation, the higher the first monitoring adjustment frequency. The second monitoring adjustment frequency is determined based on the degree of lag. The second monitoring adjustment frequency is positively correlated with the degree of lag; the higher the degree of lag, the higher the second monitoring adjustment frequency. The first effect value is obtained by multiplying the first monitoring adjustment frequency with the degree of correlation. The second effect value is obtained by multiplying the second monitoring adjustment frequency with the degree of lag. Compare the first effect value and the second effect value, select the monitoring adjustment frequency corresponding to the largest value as the final monitoring adjustment frequency, and correct the land monitoring demand data based on the final monitoring adjustment frequency; The corrected land monitoring demand data is obtained and defined as the first land monitoring demand data. The first land monitoring demand data is obtained by calculating and correcting the first land consolidation demand data based on the correlation degree and lag degree.

[0010] Preferably, the step of obtaining the second land consolidation demand data and then correcting the land monitoring demand data after determining the core monitoring needs includes: Extract the feature vector for each land monitoring requirement data, the feature vector containing the monitoring indicator type, monitoring area location and monitoring time frequency; Based on the feature vectors, the land monitoring demand data of the second land consolidation demand data are clustered to obtain N monitoring demand categories; The land monitoring demand data closest to the cluster center in each monitoring demand category is selected as the core monitoring demand for that category.

[0011] Preferably, selecting the land monitoring demand data closest to the cluster center in each monitoring demand category as the core monitoring demand for that category includes: The first land monitoring demand data is associated and matched with each core monitoring demand based on spatial proximity and monitoring indicator similarity; For core monitoring needs that have correlation and matching, the monitoring frequency of the core monitoring needs is adjusted based on the monitoring adjustment frequency of the first land monitoring needs data; For core monitoring needs that do not have a correlation match, maintain the original monitoring frequency for the core monitoring needs; Based on the adjusted core monitoring requirements, all land monitoring requirement data of the second land consolidation requirement data were back-reasoned and corrected.

[0012] Preferably, the step of back-correcting all land monitoring requirement data of the second land consolidation requirement data based on the adjusted core monitoring requirements includes: The revised land monitoring demand data is defined as the second land monitoring demand data. The reverse correction refers to allocating the monitoring frequency adjustment amount of the core monitoring needs to other land monitoring needs data belonging to the same monitoring needs category as the core monitoring needs, according to distance weight.

[0013] Preferably, the step of updating spatial planning data based on the corrected land monitoring demand data and generating a comprehensive monitoring scheme by integrating multi-source sensing data includes: Obtain the revised first land monitoring demand data and the revised second land monitoring demand data; Acquire initial spatial planning data, which includes a land use master plan layer, a permanent basic farmland protection area layer, an ecological protection red line layer, and an urban development boundary layer; Based on the revised first land monitoring demand data, identify misaligned areas at the planning ownership level, and based on the revised second land monitoring demand data, identify areas with quality gaps at the physical attribute level. Spatial overlay analysis is performed on the identified misalignment areas and quality gap areas to generate spatial planning adjustment suggestions; The initial spatial planning data is updated based on the spatial planning adjustment recommendations to obtain the updated spatial planning data. Acquire multi-source sensing data; Based on the updated spatial planning data and the revised land monitoring requirements data, a comprehensive monitoring plan is generated, which includes the monitoring area, monitoring indicators, monitoring frequency and matching relationship with multi-source sensing data sources. Monitoring is carried out in accordance with the comprehensive monitoring plan, and multi-source sensing data is accessed and analyzed in real time. The analysis results are fed back to the steps of obtaining land consolidation demand data and land monitoring demand data for iterative optimization.

[0014] Preferably, acquiring multi-source sensing data includes: The multi-source sensing data includes satellite remote sensing image data, UAV lidar point cloud data, UAV hyperspectral image data, and real-time monitoring data from IoT sensors.

[0015] Preferably, the land consolidation intelligent monitoring system based on integrated spatial planning and multi-source sensing includes: The land consolidation demand segmentation module is used to acquire land consolidation demand data and land monitoring demand data, and divides them into first land consolidation data and second land consolidation data according to planning ownership and physical attributes. The first data association lag correction module is used to calculate the association degree and lag degree of the first land consolidation data, and correct the first type of land monitoring demand data based on this. The second data clustering core correction module is used to cluster the monitoring data of the second land consolidation needs to determine the core monitoring needs, adjust the core monitoring frequency using the corrected first monitoring needs, and back-correct all monitoring data of the second category. The spatial planning multi-source fusion module is used to update spatial planning data based on the revised monitoring requirements, integrate multi-source sensing data to generate a comprehensive monitoring scheme, and provide iterative feedback.

[0016] Beneficial Effects: This invention categorizes land consolidation needs into two types: misaligned planning ownership and discrepancies in physical attributes, enabling precise identification of different driving sources. For planning ownership-related needs, the monitoring frequency is dynamically adjusted by calculating the degree of temporal correlation and spatial lag, overcoming the problem of insufficient analysis of the correlation between spatial distribution and temporal changes. For physical attribute-related needs, core monitoring needs are extracted through clustering and then corrected to similar tasks, solving the problem of missing priorities among massive needs. Based on the corrected monitoring needs, the spatial planning layer is updated, multi-source sensing data is integrated to generate a comprehensive monitoring scheme, and iterative optimization is performed, forming a closed-loop feedback mechanism. This invention significantly improves the dynamic adaptation accuracy of monitoring schemes and consolidation needs, enhancing the intelligence level of land consolidation monitoring and the iterative optimization capability of planning data. Attached Figure Description

[0017] Figure 1 This is a flowchart of the intelligent monitoring method for land consolidation that integrates spatial planning and multi-source sensing, as described in this invention. Figure 2 This is a structural diagram of the intelligent monitoring system for land consolidation that integrates spatial planning and multi-source sensing, as presented in this invention. Detailed Implementation

[0018] The present invention will be further described below with reference to specific embodiments. The illustrative embodiments and descriptions herein are used to explain the present invention, but are not intended to limit the present invention.

[0019] Example 1: A smart monitoring method for land consolidation integrating spatial planning and multi-source sensing, such as... Figure 1 As shown, it includes the following steps: S1: Obtain land consolidation demand data and land monitoring demand data, and divide the land consolidation demand data into first land consolidation data and second land consolidation data, including: If the land consolidation demand data involves a mismatch between the legal status and the actual status of land at the planning ownership level, then the land consolidation demand data will be classified as the first land consolidation data. If the land consolidation demand data involves the gap between the physical attributes of the land itself and its ideal state, then the land consolidation demand data will be classified as the second type of land consolidation data.

[0020] It should be noted that land consolidation demand data and land monitoring demand data are obtained by collecting national land survey results, planning approval documents, and lists of grassroots consolidation projects. An example of the former is a map of the proposed consolidation area, and an example of the latter is a soil sampling and monitoring task. Planning ownership refers to the planned use and ownership boundaries. The legal status of land refers to planning and ownership data, while the actual status refers to the actual use of the land surface. Misalignment issues, such as basic farmland being used for fishponds, require adjustments to ownership and planning implementation, and are therefore classified as the first type of land consolidation data. Physical attributes refer to the natural conditions of soil and topography. The quality of the land itself is a measured indicator, while the ideal state is the target standard. Discrepancies, such as organic matter content below the standard value, require engineering improvements and are therefore classified as the second type of land consolidation data. An example of the first type of land consolidation data is the need for homestead reclamation, and an example of the second type is the need for soil fertility improvement. This step, by distinguishing between these two types of needs, overcomes the shortcomings of heterogeneous data sources and low demand coupling in the background technology, enabling subsequent monitoring to develop differentiated strategies for different problems and improving the matching accuracy between monitoring and demand.

[0021] S2: Calculate the correlation and lag between the first land consolidation demand data and correct the land monitoring demand data, including: Based on the time sequence, two adjacent first land consolidation data points are selected, and the degree of correlation of structural misalignment between the two data points is calculated; Based on spatial location, select two spatially adjacent first land consolidation data points and calculate the degree of lag in the process misalignment between the two data points; The degree of correlation is obtained by calculating the similarity of the spatial distribution patterns of the structural misalignment features of the two first land consolidation data; Specifically, the structural misalignment features are constructed as a three-dimensional feature vector containing misalignment type encoding, misalignment area proportion, and spatial distribution density. The structural misalignment feature vectors of the two first land consolidation datasets are denoted as follows: and The spatial distribution pattern similarity is calculated using cosine similarity: ,in For vector dot product, The vector magnitude. Similarity. The value ranges from [0,1], and the larger the value, the more similar the spatial misalignment patterns are.

[0022] The degree of lag is obtained by calculating the absolute value of the timestamp difference between two first land consolidation data; The timestamp is a standard date format for data collection or updating, such as YYYY-MM-DD. Lag degree. The unit is days. If there are irregular periods in the data collection, the absolute value of the time difference between two consecutive valid data points will be used.

[0023] The structural misalignment refers to the systematic deviation between the legal status and the actual status of land in the spatial dimension; The process misalignment refers to the lag in updating the legal status and actual status of land in the time dimension; Land monitoring demand data is obtained based on the degree of correlation and lag in the first land consolidation demand data and then corrected.

[0024] It should be noted that, at the planning ownership level, the misalignment between the legal status and the actual status of land evolves continuously over time. Therefore, it is necessary to select two adjacent first land consolidation data points in chronological order to capture the dynamic evolution characteristics of this misalignment over time. The degree of correlation between the two data points is calculated, measured by the similarity of the spatial distribution patterns of the structural misalignment features. A high degree of correlation indicates a stable spatial misalignment pattern, while a low degree of correlation reflects a disordered spatial misalignment pattern. Selecting two spatially adjacent first land consolidation data points based on spatial location aims to identify the diffusion characteristics and regional agglomeration effects of the misalignment phenomenon in the spatial dimension. The degree of lag in the procedural misalignment between the two data points is calculated, measured by the absolute value of the timestamp difference. A high degree of lag indicates a serious lag in the update of the legal status, while a low degree of lag indicates timely updates. Structural misalignment manifests as basic farmland being divided by residential land, while procedural misalignment manifests as the database not being updated in a timely manner after planning adjustments. By comprehensively analyzing temporal correlation and spatial lag, this step overcomes the shortcomings of existing methods that are difficult to correlate spatial distribution characteristics with temporal change trends. This enables the monitoring scheme to dynamically and adaptively adjust the monitoring frequency and indicators according to the misalignment, effectively improving the matching accuracy between monitoring data and remediation needs.

[0025] Land monitoring demand data, based on correlation and lag levels, is obtained from the first land consolidation demand data and then corrected, including: The first monitoring adjustment frequency is determined based on the degree of correlation. The first monitoring adjustment frequency is negatively correlated with the degree of correlation. The lower the degree of correlation, the higher the first monitoring adjustment frequency. The second monitoring adjustment frequency is determined based on the degree of lag. The second monitoring adjustment frequency is positively correlated with the degree of lag; the higher the degree of lag, the higher the second monitoring adjustment frequency. The first effect value is obtained by multiplying the first monitoring adjustment frequency with the degree of correlation. The second effect value is obtained by multiplying the second monitoring adjustment frequency with the degree of lag. Compare the first effect value and the second effect value, select the monitoring adjustment frequency corresponding to the largest value as the final monitoring adjustment frequency, and correct the land monitoring demand data based on the final monitoring adjustment frequency; The corrected land monitoring demand data is obtained and defined as the first land monitoring demand data. The first land monitoring demand data is obtained by calculating and correcting the first land consolidation demand data based on the correlation degree and lag degree.

[0026] It should be noted that the degree of spatial misalignment is positively correlated with the urgency of monitoring needs. A low correlation indicates that the misalignment between the legal and actual land status lacks a stable pattern, necessitating increased monitoring frequency to capture sudden changes. Therefore, the first monitoring adjustment frequency is negatively correlated with the correlation. The degree of process lag directly reflects data update delays. A high lag means that existing monitoring cannot reflect real changes in a timely manner, requiring more intensive monitoring to catch up. Therefore, the second monitoring adjustment frequency is positively correlated with the lag. The first effect value is obtained by multiplying the first monitoring adjustment frequency by the correlation, specifically... ,in, The first effect value, Adjust the frequency for primary monitoring. The first effect value, representing the degree of correlation, indicates that a monitoring strategy focusing on spatial misalignment is more effective. The second effect value, obtained by multiplying the second monitoring adjustment frequency by the degree of lag, indicates that a monitoring strategy focusing on time lag is more effective. By comparing the two effect values, the adjustment frequency corresponding to the largest value is selected as the final monitoring frequency. This allows for an optimal trade-off between spatial disorder and time lag based on actual conditions, enabling the monitoring scheme to dynamically adapt to specific misalignment characteristics. This solves the problem of fixed monitoring frequencies and the inability to correlate spatial distribution with temporal trends in existing technologies, thereby improving the coupling between monitoring data and remediation needs.

[0027] It should be noted that, to eliminate the influence of dimensions, the lag degree is normalized by dividing by the maximum probable lag time, resulting in the normalized lag degree. The maximum probable lag time is set to 365 days based on the annual update cycle of the national land survey. The second effect value is correspondingly adjusted to the product of the second monitoring adjustment frequency and the normalized lag degree to ensure that the two effect values ​​are comparable across the same dimensions.

[0028] The first monitoring adjustment frequency is achieved through a linear mapping. Calculation, the second monitoring adjustment frequency is through Calculation. The minimum monitoring frequency is calculated. Once a month, the maximum monitoring frequency. The number of times per month will be taken 10 times, and the specific number will be adjusted according to monitoring capabilities and resources. To maximize the monitoring and adjustment frequency, To minimize the monitoring and adjustment frequency, For the degree of correlation, This represents the normalized lag. Linear mapping functions are chosen because they are computationally simple and have clear physical meaning. When or When the value exceeds the range [0,1], it is treated as a boundary value, i.e., if... <0 means 0, >1 is selected as 1; Similarly, the revised first land monitoring demand data includes monitoring adjustment frequency information at the planning ownership level.

[0029] S3: After acquiring the land monitoring requirement data for the second land consolidation needs and determining the core monitoring needs, revise the land monitoring requirement data, including: Extract the feature vector for each land monitoring requirement data, the feature vector containing the monitoring indicator type, monitoring area location and monitoring time frequency; Based on the feature vectors, the land monitoring demand data of the second land consolidation demand data are clustered to obtain N monitoring demand categories; The land monitoring demand data closest to the cluster center in each monitoring demand category is selected as the core monitoring demand for that category.

[0030] It should be noted that the land monitoring demand data for the second land consolidation demand data is obtained through soil sampling, topographic surveying, and irrigation facility verification tasks at the physical attribute level. Due to the lack of a priority identification mechanism for the massive monitoring demands, precise adjustments are achieved by identifying core monitoring demands. Land monitoring demand refers to the specific monitoring task for a single plot, while core monitoring demands refer to representative tasks within the same category. For example, after clustering organic matter monitoring tasks, the sampling point closest to the cluster center is selected as the core. Feature vectors are extracted for each land monitoring demand data. The monitoring indicator type represents the task category, such as soil organic matter monitoring; the monitoring area location represents the plot coordinates, such as 118 degrees east longitude and 32 degrees north latitude; and the monitoring time frequency represents the monitoring cycle, such as once per quarter. Based on the feature vectors, the K-means clustering algorithm is used to cluster the monitoring demands, grouping similar tasks into the same category. The land monitoring demand data closest to the cluster center is selected as the core monitoring demand, as this data best represents the common characteristics of the category. By reflecting the common needs of similar tasks through core monitoring needs, the shortcomings of lacking priority identification and dynamic adjustment mechanisms for massive monitoring needs are overcome. This allows subsequent corrections to spread from core needs to similar tasks, improving the accuracy of the adaptation between monitoring schemes and physical attribute-level remediation needs.

[0031] The land monitoring demand data closest to the cluster center in each monitoring demand category is selected as the core monitoring demand for that category, including: The first land monitoring demand data is associated and matched with each core monitoring demand based on spatial proximity and monitoring indicator similarity; For core monitoring needs that have correlation and matching, the monitoring frequency of the core monitoring needs is adjusted based on the monitoring adjustment frequency of the first land monitoring needs data; For core monitoring needs that do not have a correlation match, maintain the original monitoring frequency for the core monitoring needs; Based on the adjusted core monitoring requirements, all land monitoring requirement data of the second land consolidation requirement data were back-reasoned and corrected.

[0032] It should be noted that the first land monitoring demand data is matched with each core monitoring demand based on spatial proximity and monitoring indicator similarity. Spatial proximity is quantified using Euclidean distance of latitude and longitude coordinates, while monitoring indicator similarity is quantified using cosine similarity of monitoring type codes. The matching degree is obtained by weighting both. The weighting coefficients for spatial proximity and monitoring indicator similarity are denoted as follows: and ,satisfy The weights are preset based on expert experience, such as... =0.6, =0.4, or learn the optimal weights from historical matching data using a logistic regression model. Unless otherwise specified, equal weights are used by default. = =0.5. Core monitoring needs with a matching degree exceeding the preset threshold are considered to have associated matching. If there is no historical data, the initial threshold is set to 0.7, which is determined based on the balance between matching precision and recall in a small sample pre-test. The adaptive adjustment rule is as follows: the matching degree value of all successful associated matches in the current quarter is calculated once per quarter, and the median is used as the new threshold for the next quarter. If there are fewer than 10 successful matching cases in a quarter, the original threshold is used. Core monitoring needs with associated matching are spatially adjacent to the first land monitoring needs data and have similar monitoring indicators, indicating that there are both planning ownership misalignment and physical attribute discrepancies in the area. Therefore, the monitoring frequency of the core monitoring needs needs should be adjusted according to the monitoring adjustment frequency of the first land monitoring needs data to keep the adjustments of the two monitoring schemes consistent. Core monitoring needs without associated matching indicate that there is no planning ownership misalignment problem in the area, and the original monitoring frequency is maintained to avoid over-monitoring. Based on the adjusted core monitoring requirements, all land monitoring requirement data of the second land consolidation requirement data are retrospectively corrected. The frequency adjustment amount of the core monitoring requirements is distributed to other similar monitoring requirements according to the feature spatial distance weight, so that the correction is diffused from the representative sample to all similar requirements. This step overcomes the shortcomings of existing technologies that lack priority identification and dynamic adjustment mechanisms for massive monitoring requirements, and achieves accurate matching between monitoring schemes and consolidation requirements at the physical attribute level.

[0033] Based on the adjusted core monitoring requirements, all land monitoring requirement data for the second land consolidation requirement data were retroactively revised, including: The revised land monitoring demand data is defined as the second land monitoring demand data. The reverse correction refers to allocating the monitoring frequency adjustment amount of the core monitoring needs to other land monitoring needs data belonging to the same monitoring needs category as the core monitoring needs, according to distance weight.

[0034] It should be noted that the distance weights are calculated based on the Euclidean distance between the core requirement and similar requirements in the feature space, using a Gaussian kernel function. The smaller the distance, the greater the weight. The bandwidth of the Gaussian kernel function is set to the sample standard deviation of the feature distances of similar requirements, or a fixed empirical value of 1.0, to ensure that the weights decay smoothly with distance. (Gaussian kernel function bandwidth...) The formula for calculating the sample standard deviation is: ,in For core needs and the first Euclidean distance in the feature space of similar needs Let this be the mean of these distances. This refers to the quantity of similar demand. If... If the value is less than 5, then a fixed empirical value is used. =1.0. This allocation is based on the similarity of similar needs in terms of monitoring indicator type, regional location, and time frequency. A Gaussian kernel function is used to calculate the weight between each similar need and the core need; the smaller the distance, the greater the weight. Specifically, the frequency adjustment amount refers to the difference between the adjusted monitoring frequency of the core monitoring need and its original monitoring frequency. For each other land monitoring need data belonging to the same monitoring need category as the core need, its obtained monitoring frequency adjustment amount is the frequency adjustment amount of the core monitoring need multiplied by the weight value of that need, and then divided by the sum of the weight values ​​of all other needs in that category. Through back-reasoning correction, the correction is diffused from the representative core need to all similar needs, overcoming the deficiency of lack of dynamic adjustment for massive monitoring needs and improving the accuracy of monitoring scheme adaptation.

[0035] S4: Update spatial planning data based on the revised land monitoring needs data, and generate a comprehensive monitoring scheme by integrating multi-source sensing data, including: Obtain the revised first land monitoring demand data and the revised second land monitoring demand data; Acquire initial spatial planning data, which includes a land use master plan layer, a permanent basic farmland protection area layer, an ecological protection red line layer, and an urban development boundary layer; Based on the revised first land monitoring demand data, identify misaligned areas at the planning ownership level, and based on the revised second land monitoring demand data, identify areas with quality gaps at the physical attribute level. Spatial overlay analysis is performed on the identified misalignment areas and quality gap areas to generate spatial planning adjustment suggestions; The initial spatial planning data is updated based on the spatial planning adjustment recommendations to obtain the updated spatial planning data. Acquire multi-source sensing data; Based on the updated spatial planning data and the revised land monitoring requirements data, a comprehensive monitoring plan is generated, which includes the monitoring area, monitoring indicators, monitoring frequency and matching relationship with multi-source sensing data sources. Monitoring is carried out in accordance with the comprehensive monitoring plan, and multi-source sensing data is accessed and analyzed in real time. The analysis results are fed back to the steps of obtaining land consolidation demand data and land monitoring demand data for iterative optimization.

[0036] The specific iterative optimization process is as follows: After each comprehensive monitoring plan is executed, the newly acquired multi-source sensing data analysis results are compared with historical monitoring data to identify newly emerging areas with misaligned planning ownership or physical attribute quality gaps. These newly identified problem areas and their corresponding monitoring data are then updated in the land consolidation demand database and the land monitoring demand database. Quarterly or annually, based on the project cycle, steps S1 to S4 are re-executed. The updated demand data is used to re-divide, calculate correlation lags, correct monitoring frequencies, and generate new comprehensive monitoring plans, achieving dynamic closed-loop optimization. A complete replacement strategy is adopted when integrating new and old data, meaning new data overwrites old data to ensure that the planning layer and monitoring plan always reflect the latest status.

[0037] It should be noted that the revised first and second land monitoring demand data reflect the revision results at the planning ownership level and physical attribute level, respectively, and form the basis for updating spatial planning and generating monitoring schemes. The initial spatial planning data is obtained from the national land spatial information platform and includes the overall land use planning layer, the permanent basic farmland protection area layer, the ecological protection red line layer, and the urban development boundary layer. These layers constitute the legal basis for spatial use control. Based on the revised first land monitoring demand data, misaligned areas at the planning ownership level are identified, such as unregistered homesteads within the basic farmland area. Based on the revised second land monitoring demand data, areas with quality gaps at the physical attribute level are identified, such as arable land with soil organic matter below the standard value. Spatial overlay analysis is performed on the misaligned areas and quality gap areas. Through GIS spatial intersection and buffer zone analysis, the spatial relationship between the two types of areas is determined. If the misaligned areas and quality gap areas overlap, it is recommended to simultaneously adjust the planning boundary and implement engineering improvements; if the misaligned areas are located within the ecological red line, it is recommended to adjust the red line range or strengthen supervision. The initial spatial planning data is updated based on spatial planning adjustment recommendations, resulting in updated spatial planning data that better reflects the actual land condition and remediation needs. Multi-source sensing data is acquired, including satellite remote sensing imagery, UAV lidar point clouds, UAV hyperspectral imagery, and real-time monitoring data from IoT sensors. Based on the updated spatial planning data and revised land monitoring requirements data, a comprehensive monitoring plan is generated. This plan clearly defines the monitoring area, monitoring indicators, monitoring frequency, and the matching relationship between multi-source sensing data sources. For example, high-frequency satellite monitoring is used for misaligned areas, and UAV hyperspectral sampling is used for areas with quality differences. Monitoring is executed according to the comprehensive monitoring plan, and multi-source sensing data is analyzed in real time. The analysis results are fed back to the steps of acquiring land remediation and land monitoring requirements data for iterative optimization. Specific iterative steps include: comparing new monitoring data with historical data, identifying newly emerging misalignments or gaps, updating the requirements data, and re-dividing and correcting the data to achieve dynamic closed-loop optimization. This step overcomes the deficiency of closed-loop feedback between monitoring results and spatial planning data in existing technologies, shifting multi-source sensing data from unidirectional acquisition to dynamic driving, and improving the coupling between the monitoring plan and remediation needs.

[0038] Acquire multi-source sensing data, including: The multi-source sensing data includes satellite remote sensing image data, UAV lidar point cloud data, UAV hyperspectral image data, and real-time monitoring data from IoT sensors.

[0039] Example 2: Based on Example 1, a smart monitoring system for land consolidation that integrates spatial planning and multi-source sensing, such as... Figure 2 As shown, it includes: The land consolidation demand segmentation module is used to acquire land consolidation demand data and land monitoring demand data, and divides them into first land consolidation data and second land consolidation data according to planning ownership and physical attributes. The first data association lag correction module is used to calculate the association degree and lag degree of the first land consolidation data, and correct the first type of land monitoring demand data based on this. The second data clustering core correction module is used to cluster the monitoring data of the second land consolidation needs to determine the core monitoring needs, adjust the core monitoring frequency using the corrected first monitoring needs, and back-correct all monitoring data of the second category. The spatial planning multi-source fusion module is used to update spatial planning data based on the revised monitoring requirements, integrate multi-source sensing data to generate a comprehensive monitoring scheme, and provide iterative feedback.

[0040] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A smart monitoring method for land consolidation that integrates spatial planning and multi-source sensing, characterized by: Includes the following steps: S1: Obtain land consolidation demand data and land monitoring demand data, and divide the land consolidation demand data into first land consolidation data and second land consolidation data; S2: Calculate the correlation and lag between the first land consolidation demand data and correct the land monitoring demand data respectively; S3: After obtaining the land monitoring requirement data for the second land consolidation requirement and determining the core monitoring requirements, revise the land monitoring requirement data; S4: Update spatial planning data based on the revised land monitoring demand data, and generate a comprehensive monitoring scheme by integrating multi-source sensing data.

2. The intelligent monitoring method for land consolidation that integrates spatial planning and multi-source sensing as described in claim 1, characterized in that, The acquisition of land consolidation demand data and land monitoring demand data, and the division of land consolidation demand data into first land consolidation data and second land consolidation data, includes: If the land consolidation demand data involves a mismatch between the legal status and the actual status of land at the planning ownership level, then the land consolidation demand data will be classified as the first land consolidation data. If the land consolidation demand data involves the gap between the physical attributes of the land itself and its ideal state, then the land consolidation demand data will be classified as the second type of land consolidation data.

3. The intelligent monitoring method for land consolidation that integrates spatial planning and multi-source sensing as described in claim 1, characterized in that, The calculation of the correlation and lag between the first land consolidation demand data and the correction of the land monitoring demand data include: Based on the time sequence, two adjacent first land consolidation data points are selected, and the degree of correlation of structural misalignment between the two data points is calculated; Based on spatial location, select two spatially adjacent first land consolidation data points and calculate the degree of lag in the process misalignment between the two data points; The degree of correlation is obtained by calculating the similarity of the spatial distribution patterns of the structural misalignment features of the two first land consolidation data; The degree of lag is obtained by calculating the absolute value of the timestamp difference between two first land consolidation data; The structural misalignment refers to the systematic deviation between the legal status and the actual status of land in the spatial dimension; The process misalignment refers to the lag in updating the legal status and actual status of land in the time dimension; Land monitoring demand data is obtained based on the degree of correlation and lag in the first land consolidation demand data and then corrected.

4. The intelligent monitoring method for land consolidation that integrates spatial planning and multi-source sensing as described in claim 3, is characterized in that... The process of obtaining and correcting land monitoring demand data based on correlation and lag in the first land consolidation demand data includes: The first monitoring adjustment frequency is determined based on the degree of correlation. The first monitoring adjustment frequency is negatively correlated with the degree of correlation. The lower the degree of correlation, the higher the first monitoring adjustment frequency. The second monitoring adjustment frequency is determined based on the degree of lag. The second monitoring adjustment frequency is positively correlated with the degree of lag; the higher the degree of lag, the higher the second monitoring adjustment frequency. The first effect value is obtained by multiplying the first monitoring adjustment frequency with the degree of correlation. The second effect value is obtained by multiplying the second monitoring adjustment frequency with the degree of lag. Compare the first effect value and the second effect value, select the monitoring adjustment frequency corresponding to the largest value as the final monitoring adjustment frequency, and correct the land monitoring demand data based on the final monitoring adjustment frequency; The corrected land monitoring demand data is obtained and defined as the first land monitoring demand data. The first land monitoring demand data is obtained by calculating and correcting the first land consolidation demand data based on the correlation degree and lag degree.

5. The intelligent monitoring method for land consolidation that integrates spatial planning and multi-source sensing as described in claim 1, characterized in that, The process of obtaining land monitoring demand data for the second land consolidation demand and determining core monitoring needs, followed by revising the land monitoring demand data, includes: Extract the feature vector for each land monitoring requirement data, the feature vector containing the monitoring indicator type, monitoring area location and monitoring time frequency; Based on the feature vectors, the land monitoring demand data of the second land consolidation demand data are clustered to obtain N monitoring demand categories; The land monitoring demand data closest to the cluster center in each monitoring demand category is selected as the core monitoring demand for that category.

6. The intelligent monitoring method for land consolidation that integrates spatial planning and multi-source sensing as described in claim 5, is characterized in that... The selection of land monitoring demand data closest to the cluster center in each monitoring demand category as the core monitoring demand for that category includes: The first land monitoring demand data is associated and matched with each core monitoring demand based on spatial proximity and monitoring indicator similarity; For core monitoring needs that have correlation and matching, the monitoring frequency of the core monitoring needs is adjusted based on the monitoring adjustment frequency of the first land monitoring needs data; For core monitoring needs that do not have a correlation match, maintain the original monitoring frequency for the core monitoring needs; Based on the adjusted core monitoring requirements, all land monitoring requirement data of the second land consolidation requirement data were back-reasoned and corrected.

7. The intelligent monitoring method for land consolidation that integrates spatial planning and multi-source sensing as described in claim 6, characterized in that, The process of back-calculating and correcting all land monitoring requirement data for the second land consolidation requirement data based on the adjusted core monitoring requirements includes: The revised land monitoring demand data is defined as the second land monitoring demand data. The reverse correction refers to allocating the monitoring frequency adjustment amount of the core monitoring needs to other land monitoring needs data belonging to the same monitoring needs category as the core monitoring needs, according to distance weight.

8. The intelligent monitoring method for land consolidation that integrates spatial planning and multi-source sensing as described in claim 1, characterized in that, The method of updating spatial planning data based on corrected land monitoring demand data and integrating multi-source sensing data to generate a comprehensive monitoring scheme includes: Obtain the revised first land monitoring demand data and the revised second land monitoring demand data; Acquire initial spatial planning data, which includes a land use master plan layer, a permanent basic farmland protection area layer, an ecological protection red line layer, and an urban development boundary layer; Based on the revised first land monitoring demand data, identify misaligned areas at the planning ownership level, and based on the revised second land monitoring demand data, identify areas with quality gaps at the physical attribute level. Spatial overlay analysis is performed on the identified misalignment areas and quality gap areas to generate spatial planning adjustment suggestions; The initial spatial planning data is updated based on the spatial planning adjustment recommendations to obtain the updated spatial planning data. Acquire multi-source sensing data; Based on the updated spatial planning data and the revised land monitoring requirements data, a comprehensive monitoring plan is generated, which includes the monitoring area, monitoring indicators, monitoring frequency and matching relationship with multi-source sensing data sources. Monitoring is carried out in accordance with the comprehensive monitoring plan, and multi-source sensing data is accessed and analyzed in real time. The analysis results are fed back to the steps of obtaining land consolidation demand data and land monitoring demand data for iterative optimization.

9. The intelligent monitoring method for land consolidation that integrates spatial planning and multi-source sensing as described in claim 8, characterized in that, The acquisition of multi-source sensing data includes: The multi-source sensing data includes satellite remote sensing image data, UAV lidar point cloud data, UAV hyperspectral image data, and real-time monitoring data from IoT sensors.

10. A smart monitoring system for land consolidation integrating spatial planning and multi-source sensing, used to implement the smart monitoring method for land consolidation integrating spatial planning and multi-source sensing as described in any one of claims 1-9, characterized in that, include: The land consolidation demand segmentation module is used to acquire land consolidation demand data and land monitoring demand data, and divides them into first land consolidation data and second land consolidation data according to planning ownership and physical attributes. The first data association lag correction module is used to calculate the association degree and lag degree of the first land consolidation data, and correct the first type of land monitoring demand data based on this. The second data clustering core correction module is used to cluster the monitoring data of the second land consolidation needs to determine the core monitoring needs, adjust the core monitoring frequency using the corrected first monitoring needs, and back-correct all monitoring data of the second category. The spatial planning multi-source fusion module is used to update spatial planning data based on the revised monitoring requirements, integrate multi-source sensing data to generate a comprehensive monitoring scheme, and provide iterative feedback.

Images