Intelligent analysis and management method and system for land surveying and mapping data

Abstract

The invention relates to the technical field of data mining, in particular to an intelligent analysis and management method and system for land surveying and mapping data. The method comprises the following steps: acquiring land surveying and mapping data, and performing surveying and mapping error correction to obtain land surveying and mapping enhanced data; performing surveying and mapping land space modeling on the land surveying and mapping enhancement data to obtain a land space data model, and performing surveying and mapping land topographic region classification to obtain a surveying and mapping plain space model and a surveying and mapping mountain space model; performing plain soil nutrition trend analysis on the surveying and mapping plain space model to obtain surveying and mapping plain soil nutrition trend data; carrying out mountain soil nutrition trend analysis on the surveying and mapping mountain space model to obtain surveying and mapping mountain soil nutrition trend data, and carrying out plain soil nutrition erosion factor evaluation to obtain plain soil nutrition erosion factors; and according to the plain soil nutrition erosion factors, carrying out land nutrition downflow strategy analysis to obtain a land nutrition downflow strategy. The precision of land surveying and mapping data can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data mining, and particularly to an intelligent analysis and management method and system for land surveying and mapping data. Background Art

[0002] With the continuous advancement of the global urbanization process and the increasing complexity of land use, the acquisition and management of land surveying and mapping data have become key links in land resource management and urban planning. Traditional land surveying and mapping methods mainly rely on manual data collection and ground measurement. Although these methods meet the requirements to a certain extent, with the development of technology, they gradually expose deficiencies such as low efficiency, lagging data update, and complex management. Especially in large-scale land surveying and mapping projects, the limitations of traditional methods become more obvious. For example, in the data processing and analysis stage, it is difficult to efficiently integrate and analyze massive data, thus affecting the accuracy and timeliness of the data. With the rapid development of information technology, especially the application of artificial intelligence, big data, and cloud computing technologies, the intelligent analysis and management of land surveying and mapping data have gradually become an important way to solve traditional problems. Modern surveying and mapping technologies such as remote sensing technology, lidar, and unmanned aerial vehicle aerial photography can provide high-resolution and high-precision land surveying and mapping data. However, the data formats and standards of different surveying and mapping technologies and data sources are inconsistent, resulting in great difficulties in data integration and fusion and making it difficult to conduct comprehensive analysis. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide an intelligent analysis and management method and system for land surveying and mapping data to solve at least one of the above technical problems.

[0004] To achieve the above object, an intelligent analysis and management method for land surveying and mapping data includes the following steps:

[0005] Step S1: Obtain land surveying and mapping data, and perform standardized processing on the longitude and latitude of the land surveying and mapping data to obtain longitude and latitude standardized surveying and mapping data; perform surveying and mapping error correction on the longitude and latitude standardized surveying and mapping data to obtain enhanced land surveying and mapping data;

[0006] Step S2: Perform surveying and mapping land space modeling on the enhanced land surveying and mapping data to obtain a land space data model; perform surveying and mapping land terrain area classification on the land space data model to obtain a surveying and mapping plain space model and a surveying and mapping mountain space model;

[0007] Step S3: Extract land geological features from the land surveying and mapping data to obtain land geological data, and perform plain soil nutrient trend analysis on the surveying and mapping plain space model according to the land geological data to obtain surveying and mapping plain soil nutrient trend data;

[0008] Step S4: Analyze the mountain soil nutrient trend of the surveyed mountain space model based on the land geological data to obtain the surveyed mountain soil nutrient trend data, and evaluate the plain soil nutrient erosion factors for the surveyed mountain soil nutrient trend data based on the surveyed plain soil nutrient trend data to obtain the plain soil nutrient erosion factors;

[0009] Step S5: Divide the surveyed plain space model according to the plain soil nutrient erosion factors to obtain the land nutrient loss area model, and analyze the land nutrient downflow strategy for the land nutrient loss area model to obtain the land nutrient downflow strategy.

[0010] The present invention utilizes modern technologies such as remote sensing technology, lidar, and unmanned aerial vehicle (UAV) aerial photography to efficiently obtain high-resolution and high-precision land surveying data. These data provide detailed geographical information and enhance the basic data support for land resource management and urban planning. Standardized processing can ensure data consistency, enabling data from different sources to be compared and integrated under the same coordinate system, improving data comparability and accuracy, and laying a foundation for subsequent data processing and analysis. Correcting surveying errors helps improve data accuracy, reduces the impact of errors on data analysis results, enhances data reliability, makes subsequent analysis results more accurate, and reduces decision-making risks caused by data errors. Constructing a land spatial data model helps better understand the spatial distribution and characteristics of land. The model can be used to analyze various spatial attributes of land, such as terrain and landform, providing a scientific basis for land use planning and resource management. Conducting spatial classification of land into plains and mountains can divide land into different spatial models, facilitating targeted analysis of land with different topographic characteristics. The classification results provide a basis for formulating specific land use plans and management measures, such as different soil management strategies for plains and mountains. Extracting the geological characteristics of land helps understand the geological composition, soil type, and its suitability of the land. These characteristics have important reference value for aspects such as land use planning, agricultural production, and environmental protection. Analyzing the nutrient trends of plain soil can reveal the changes in soil fertility, provide targeted soil management suggestions for agricultural production, help optimize fertilization strategies, improve the efficiency of agricultural production, and prevent soil degradation. Analyzing the nutrient trends of mountain soil can understand the changes in mountain soil fertility and help formulate corresponding land management and protection measures. This analysis is particularly important for mountain agriculture and ecological environmental protection. Evaluating the nutrient erosion factors of plain soil helps understand the risk of soil erosion and its impact on soil nutrients. This evaluation provides data support for formulating measures to prevent soil erosion, such as vegetation restoration and soil and water conservation projects. According to the analysis results of soil nutrient erosion factors, dividing the land into areas of nutrient loss can help identify areas with severe soil nutrient loss, providing a basis for key treatment. Analyzing land nutrient reduction strategies can propose specific treatment plans and measures to reduce soil nutrient loss. Through effective strategies, it is possible to improve the productive capacity of the land, improve soil quality, and protect the ecological environment. In summary, the combination of these steps not only improves the accuracy and reliability of land surveying data but also provides strong support for the management and planning of land resources through advanced data analysis techniques, promoting the achievement of the goal of sustainable development.

[0011] Optionally, step S1 is specifically as follows:

[0012] Step S11: Obtain land surveying and mapping data, and perform standardized processing of the surveying and mapping longitude and latitude on the land surveying and mapping data to obtain standardized surveying and mapping data of longitude and latitude;

[0013] Step S12: Extract surveying and mapping camera images and surveying and mapping remote sensing images from the standardized surveying and mapping data of longitude and latitude to obtain a set of surveying and mapping camera images and a set of surveying and mapping remote sensing images;

[0014] Step S13: Perform image registration on the set of surveying and mapping camera images and the set of surveying and mapping remote sensing images to obtain a set of registered surveying and mapping images, and calculate the registration accuracy error for the set of registered surveying and mapping images to obtain registration accuracy error data;

[0015] Step S14: Calculate the pixel value error of images with the same longitude and latitude based on the set of registered surveying and mapping images to obtain pixel value error data of images;

[0016] Step S15: Correct the surveying and mapping images of the set of registered surveying and mapping images according to the pixel value error data of images and the registration accuracy error data to obtain a set of corrected surveying and mapping error images;

[0017] Step S16: Perform data enhancement processing on the set of corrected surveying and mapping error images to obtain a set of enhanced land surveying and mapping images, and replace the surveying and mapping images of the standardized surveying and mapping data of longitude and latitude according to the set of enhanced land surveying and mapping images to obtain enhanced land surveying and mapping data.

[0018] Through standardization processing, the present invention can ensure that the surveying and mapping data collected from different sources or at different times have a unified longitude and latitude format, thereby improving the consistency and compatibility of the data. The standardized longitude and latitude data can be more easily docked and integrated with other data sources, simplifying the subsequent data analysis and processing process. By extracting surveying and mapping camera images and remote sensing images, information about the land can be obtained from different perspectives, enhancing the comprehensiveness and accuracy of the data. The camera images and remote sensing images provide different types of data, which helps to comprehensively understand the land features and their changes. Image registration can align different images to ensure the consistency of image data in the same geographical area, facilitating subsequent analysis and applications. The registration accuracy error data can help evaluate the accuracy of registration, thereby determining whether further adjustment and optimization of the registration algorithm are required to ensure high-quality data. Pixel value error calculation can reveal the differences between different images at the same geographical location, helping to identify data inconsistencies or errors. By analyzing the pixel value errors, the data processing method or correction strategy can be adjusted to improve the accuracy of the final data. Error correction can correct systematic and random errors in the images, thereby improving the accuracy and reliability of the images. The corrected image data can better support subsequent analysis and decision-making, reducing the uncertainty introduced by errors. Data enhancement processing can improve the quality and details of the images, making the images clearer and more reliable. The enhanced image set can provide higher resolution and richer information, making subsequent analysis and applications more accurate. Through image replacement, the original surveying and mapping data can be updated with higher-quality enhanced data, improving the practicality and timeliness of the data.

[0019] Optionally, step S15 is specifically as follows:

[0020] Step S151: Perform pixel value error distribution statistics on the image pixel value error data to obtain image pixel value error distribution data;

[0021] Step S152: Perform pixel value statistics on the error distribution regions according to the image pixel value error distribution data to obtain error distribution region pixel value data;

[0022] Step S153: Perform mean square adjustment of the error pixel values on the registered surveying and mapping image set according to the error distribution region pixel value data to obtain a pixel-adjusted image set;

[0023] Step S154: Extract image terrain features from the registration accuracy error data to obtain image terrain error data, and estimate terrain geometric error correction parameters according to the image terrain error data to obtain a terrain geometric error correction parameter set;

[0024] Step S155: Perform geometric terrain correction on the pixel-adjusted image set according to the terrain geometric error correction parameter set to obtain a surveying and mapping error correction image set.

[0025] By statistically analyzing the distribution of image pixel value errors, the present invention can comprehensively understand the overall situation of the errors, providing basic data for subsequent error analysis and correction. The statistics of the pixel values in the error distribution area help to determine the areas where the errors mainly concentrate, so that precision improvement can be targeted, enhancing the effectiveness of the correction effect. Adjusting the mean square of the error pixel values for the registered mapping image set can significantly reduce the image errors, improving the overall registration accuracy of the images and making the final images more accurate. Extracting the topographic features of the images and estimating the geometric error correction parameters can more precisely identify and correct the errors caused by the topographic features, enhancing the accuracy of the topographic modeling. Using the topographic geometric error correction parameters to perform geometric topographic correction on the images can eliminate the errors caused by topographic changes, ultimately obtaining a more accurate mapping image set and effectively improving the mapping quality of the images.

[0026] Optionally, step S2 is specifically as follows:

[0027] Step S21: Extract the land remote sensing images from the enhanced land surveying data to obtain the land remote sensing images;

[0028] Step S22: Perform stereo vision high-level information matching based on the land remote sensing images to obtain the land elevation data, and construct a land elevation model for the surveyed area based on the land elevation data;

[0029] Step S23: Calculate the land spatial grid resolution according to the land elevation model of the surveyed area to obtain the land spatial grid resolution data, and perform elevation point grid conversion on the land elevation model of the surveyed area according to the land spatial grid resolution data to obtain the land spatial grid model;

[0030] Step S24: Integrate the surveyed surface features according to the enhanced land surveying data to obtain the surveyed land surface feature data, and fill the land surface features of the land spatial grid model according to the surveyed land surface feature data to obtain the land spatial data model;

[0031] Step S25: Classify the surveyed land topographic areas of the land spatial data model to obtain the surveyed plain spatial model and the surveyed mountain spatial model.

[0032] The extraction of land remote sensing images in the present invention can obtain high-resolution surface information, providing detailed visual data for subsequent analysis and enhancing the accuracy and integrity of the data. Obtaining land elevation data through high-level information matching of stereo vision helps to construct an accurate elevation model, providing a solid foundation for terrain analysis and surveying. Calculating the spatial grid resolution of the land and performing elevation point grid conversion can transform the elevation data into a grid model, facilitating spatial analysis and modeling at different resolutions. Integrating surface feature data and filling the land spatial grid model can enrich the information of the model, improve the description accuracy of land surface features, and optimize the practical application of the land spatial data model. Classifying the terrain regions of the land spatial data model can divide the terrain information into types such as plains and mountains, providing more targeted spatial data support for land use planning and environmental management.

[0033] Optionally, step S24 is specifically as follows:

[0034] Step S241: Extract spectral features from the enhanced land survey data to obtain the spectral data of the surveyed area;

[0035] Step S242: Classify the band reflectance features of the spectral data of the surveyed area to obtain the regional blue band reflectance data and the regional green band reflectance data;

[0036] Step S243: Divide the water body area of the surveyed area based on the regional blue band reflectance data of the spectral data of the surveyed area to obtain the water body data of the surveyed area;

[0037] Step S244: Divide the vegetation area of the surveyed area based on the regional green band reflectance data of the spectral data of the surveyed area to obtain the vegetation data of the surveyed area;

[0038] Step S245: Classify the reflectance of the regional green band reflectance data to obtain the high green band reflectance area data and the low green band reflectance area data;

[0039] Step S246: Cluster the vegetation data of the surveyed area with high green band reflectance based on the high green band reflectance area data to obtain the mountain data of the surveyed area; cluster the vegetation data of the surveyed area with low green band reflectance based on the low green band reflectance area data to obtain the plain data of the surveyed area;

[0040] Step S247: Perform spatial integration of the water body data of the surveyed area, the plain data of the surveyed area, and the mountain data of the surveyed area to obtain the surface feature data of the surveyed land;

[0041] Step S248: Fill the land surface feature of the land spatial grid model according to the surveyed land surface feature data, so as to obtain the land spatial data model.

[0042] The spectral feature extraction of the present invention can obtain the spectral data of the surveyed area and provide detailed spectral information of the surface substances. Such data can be used to distinguish different surface features and enhance the accuracy of land surveying. The band reflectance feature classification helps to decompose the spectral data into reflectance data of different bands. By obtaining the reflectance data of the blue band and the green band in the area, different ground object types such as water bodies and vegetation in the area can be analyzed and identified more accurately. Using the reflectance data of the blue band in the area to divide the water body area can accurately identify the location and scope of the water body in the surveyed area. This step is of great significance for water body monitoring and management. Dividing the vegetation area according to the reflectance data of the green band helps to identify and extract the vegetation coverage in the surveyed area. The reflectance of the green band is usually related to the health status and density of vegetation, so it can effectively distinguish different types of vegetation areas. The reflectance classification can divide the reflectance data of the green band into high green band reflectance areas and low green band reflectance areas. High reflectance usually indicates healthy vegetation or certain specific surface features, while low reflectance may indicate different types of surface cover or degraded vegetation. Clustering the vegetation data according to the data of the high green band reflectance area can distinguish the areas with lush vegetation (such as mountains), while the data of the low green band reflectance area can identify the areas with sparse vegetation (such as plains). This classification helps to divide the surveyed area into terrain types such as mountains and plains in detail and improve the accuracy of terrain classification. Integrating the water body data, plain data and mountain data in the regional surface feature space can combine different surface feature data and provide more comprehensive surface feature information. This process integrates all the key surface data in the area and forms a detailed land surface feature data set. Filling the features of the land spatial grid model according to the surveyed land surface feature data can enrich the information of the grid model and reflect the true surface features of the land. This filling process makes the land spatial data model more authentic and accurate and provides a reliable basis for subsequent analysis and application.

[0043] Optionally, step S3 is specifically as follows:

[0044] Step S31: Extract the land geological features from the land survey data to obtain the land geological data;

[0045] Step S32: Extract the soil element content features from the land geological data to obtain the soil element content data, and perform inverse distance weighted spatial interpolation on the soil element content data to obtain the continuous spatial soil content data;

[0046] Step S33: Integrate the continuous spatial soil content data and the surveyed plain spatial model to obtain the surveyed plain spatial element content model;

[0047] Step S34: Conduct a regression analysis on the soil element content based on the surveyed plain spatial element content model to obtain the plain soil element content trend data;

[0048] Step S35: Obtain the soil nutrient element rules, and perform plain soil nutrient trend integration on the plain soil element content trend data according to the soil nutrient element rules to obtain the surveyed plain soil nutrient trend data.

[0049] The extraction of land geological features in the present invention helps to deeply understand the basic geological conditions of the land and lays a foundation for subsequent soil analysis. By extracting the soil element content and performing inverse distance weighted spatial interpolation, continuous soil element distribution data can be obtained, which provides detailed information for accurately evaluating the soil quality. Integrating the continuous soil element data and the surveyed plain spatial model to form the plain spatial element content model enables a more comprehensive understanding of the spatial distribution of the soil. Conducting a regression analysis on the soil element content helps to identify the change trend of the soil element content, thus providing a scientific basis for land management and improvement. Integrating the trend data according to the soil nutrient element rules can identify the change trend of the soil nutrient status and provide data support for optimizing soil management and enhancing agricultural productivity.

[0050] Optionally, step S4 is specifically as follows:

[0051] Step S41: Extract the mountain geological features from the land geological data according to the surveyed mountain spatial model to obtain the mountain geological data;

[0052] Step S42: Extract the mountain rock element content features and the mountain soil element content features from the mountain geological data to obtain the mountain rock element content data and the mountain soil element content data;

[0053] Step S43: Perform stratified Kriging interpolation on the mountain rock element content data and the mountain soil element content data to obtain the stratified spatial mountain element content data;

[0054] Step S44: Integrate the stratified spatial mountain element content data and the surveyed mountain spatial model to obtain the surveyed mountain spatial element content model;

[0055] Step S45: Conduct a regression analysis on the soil element content based on the surveyed mountain spatial element content model to obtain the mountain soil element content trend data;

[0056] Step S46: Integrate the mountain soil element content trend data according to the soil nutrient element rules to obtain the surveyed mountain soil nutrient trend data;

[0057] Step S47: Evaluate the plain soil nutrient erosion factors for the surveyed mountain soil nutrient trend data to obtain the plain soil nutrient erosion factors.

[0058] Through the extraction of mountain geological characteristics from land geological data based on the surveyed mountain spatial model, detailed mountain geological data can be obtained. This step helps to identify the geological structure, stratigraphic distribution, and geological types in mountainous areas, providing basic data for subsequent soil and mineral analysis. This is conducive to understanding the geological background of mountainous areas and supporting subsequent data analysis and interpretation. By extracting the elemental content characteristics in mountain rocks and soils, the elemental content data of mountain rocks and the elemental content data of mountain soils can be obtained respectively. This process provides the distribution information of key elements in rocks and soils within mountainous areas, providing detailed basic data for understanding the mineral resources and soil quality in mountainous areas. This helps to evaluate the resource potential of the land and the fertility and suitability of the soil. By performing stratified Kriging interpolation on the elemental content data of mountain rocks and the elemental content data of mountain soils, stratified spatial mountain elemental content data can be generated. This interpolation method provides a smoother and more accurate spatial distribution map of elemental content by considering spatial variability, and is suitable for processing complex terrain and soil data. This helps to more accurately understand the spatial distribution and variation of elements within mountainous areas. By integrating the stratified spatial mountain elemental content data with the surveyed mountain spatial model, a surveyed mountain spatial elemental content model can be obtained. This step combines spatial data with a geological model to form a comprehensive mountain spatial elemental distribution model, which is conducive to in-depth understanding of the distribution patterns and concentration distributions of elements in mountain soils and rocks. By performing regression analysis on the soil elemental content based on the surveyed mountain spatial elemental content model, the trend data of mountain soil elemental content can be obtained. This analysis can reveal the change trends of soil elemental content over time or space, thus providing a scientific basis for land management and soil improvement, and helping to predict future soil quality changes and formulate corresponding management measures. According to the rules of soil nutrient elements, by integrating the trend data of mountain soil elemental content, the surveyed mountain soil nutrient trend data can be obtained. This process converts the change trend of soil elemental content into the change trend of nutrient status, helping to identify nutrient deficiencies or surpluses in mountain soils, and thus providing data support for agricultural and environmental management. By evaluating the plain soil nutrient erosion factor for the mountain soil nutrient trend data based on the surveyed plain soil nutrient trend data, this step compares the mountain soil nutrient trend with the plain soil nutrient trend to evaluate the erosion factor of soil nutrients, thereby understanding the potential impact of mountain soils on plain soils. This helps to assess the risk of soil erosion, formulate protection measures, and mitigate the impact of soil erosion on plain agriculture and the ecosystem.

[0059] Optionally, step S47 is specifically as follows:

[0060] Step S471: Align the surveyed plain soil nutrient trend data and the surveyed mountain soil nutrient trend data in terms of time and space to obtain the surveyed area soil nutrient trend data;

[0061] Step S472: Conduct principal component analysis of soil nutrients based on the soil nutrient trend data of the surveyed area to obtain soil nutrient principal component data;

[0062] Step S473: Construct a soil erosion model based on the land spatial data model and the soil nutrient principal component data to obtain a soil erosion model;

[0063] Step S474: Calculate the soil nutrient erosion factors for the soil nutrient trend data of the surveyed plain and the soil nutrient trend data of the surveyed mountain respectively according to the soil erosion model to obtain the soil nutrient erosion factor of the surveyed plain area and the soil nutrient erosion factor of the surveyed mountain area;

[0064] Step S475: Quantify the correlation of the plain soil nutrient erosion factor with the soil nutrient erosion factor of the surveyed mountain area according to the soil nutrient erosion factor of the surveyed plain area to obtain the plain soil nutrient erosion factor.

[0065] By performing spatio-temporal alignment on the surveyed plain and mountain soil nutrient trend data, the present invention can ensure the consistency of data in terms of time and space for two different geographical regions. This is a prerequisite for reliable comparison and analysis. After spatio-temporal alignment, a comprehensive and integrated analysis of the soil nutrient trends in the entire surveyed area can be carried out, revealing the changing laws and trends of regional soil nutrients. It ensures the integrity and coherence of soil nutrient data, providing accurate basic data support for subsequent analysis. Through principal component analysis, multiple soil nutrient indicators can be synthesized into a few principal components, thereby simplifying the data structure and reducing the complexity of analysis. Principal component analysis helps to extract the most important soil nutrient components and reveals which factors have the greatest impact on the soil nutrient status. By identifying and quantifying key soil nutrient components, it provides data support for formulating soil management and improvement strategies. The constructed soil erosion model can predict the possibility and degree of soil erosion under different conditions, helping to identify high-risk areas. Based on the results of model analysis, targeted soil protection and restoration measures can be formulated to reduce the negative impact of soil erosion on the environment. Optimize land resource management, reduce the impact of soil erosion on agricultural production and the ecological environment, and thus improve land use efficiency. Calculate the erosion factors for the plain and mountain respectively, which can accurately evaluate the soil nutrient erosion under different terrain conditions. Revealing the differences in soil nutrient erosion factors between the plain and mountain regions helps to understand the impact of different terrain conditions on soil erosion. According to the erosion factor data of different regions, soil protection measures can be adjusted to implement more precise management strategies. Quantifying the correlation between the plain soil nutrient erosion factors and the mountain erosion factors helps to understand the erosion mechanism under different soil types and terrain conditions. Verifying the accuracy of the model through correlation analysis ensures the effectiveness and reliability of the soil erosion model. The quantified correlation data can provide a basis for improving soil management policies, thereby more effectively controlling and reducing soil erosion.

[0066] Optionally, step S5 is specifically as follows:

[0067] Step S51: Conduct statistical analysis of erosion factors based on the plain soil nutrient erosion factors, so as to obtain high-correlation soil nutrient erosion factors and low-correlation soil nutrient erosion factors;

[0068] Step S52: Extract the distribution characteristics of plain element contents according to the surveyed plain spatial element content model, so as to obtain the plain soil element content distribution data;

[0069] Step S53: Conduct factor spatial association based on the high-correlation soil nutrient erosion factors and the plain soil element content distribution data to obtain the data of areas where soil nutrients are easily lost; conduct factor spatial association based on the low-correlation soil nutrient erosion factors and the plain soil element content distribution data to obtain the data of areas where soil nutrients are difficult to lose;

[0070] Step S54: Perform spatial association area division on the surveyed plain spatial model and the surveyed mountain spatial model to obtain an intersection area spatial model and a non-intersection area spatial model;

[0071] Step S55: Perform intersection area spatial division on the intersection area spatial model according to the soil nutrient easily eroded area data to obtain an easily soil nutrient eroded area model; perform intersection area spatial division on the non-intersection area spatial model according to the soil nutrient hardly eroded area data to obtain a hardly soil nutrient eroded area model;

[0072] Step S57: Perform spatial merging on the easily soil nutrient eroded area model and the hardly soil nutrient eroded area model to obtain a soil nutrient eroded area model;

[0073] Step S57: Analyze the soil nutrient flow reduction strategy for the soil nutrient eroded area model to obtain a soil nutrient flow reduction strategy.

[0074] By statistically analyzing the correlation of soil nutrient erosion factors, the present invention can clarify which factors have a significant impact on soil erosion and which have a smaller impact, so as to more accurately identify the key influencing factors. Using the spatial element content model to extract the soil element distribution characteristics helps to obtain detailed soil element distribution data and lay a foundation for further analysis. Determining the easily eroded and hardly eroded soil nutrient areas through factor spatial association can help formulate targeted soil protection measures. Performing spatial area division to clarify the intersection and non-intersection areas helps to optimize the applicability of the model under different terrain conditions. Further refining the easily eroded and hardly eroded area models through spatial division improves the prediction accuracy. Spatially merging different area models and comprehensively considering the characteristics of each area provide a comprehensive soil nutrient eroded area model. Analyzing the flow reduction strategy based on the final model helps to formulate scientific and reasonable soil protection and improvement plans, thereby realizing effective land management.

[0075] Optionally, this specification provides an intelligent analysis and management system for land surveying data, which is used to execute an intelligent analysis and management method for land surveying data as described above. The intelligent analysis and management system for land surveying data includes:

[0076] A surveying error correction module, which is used to obtain land surveying data, perform surveying longitude and latitude standardization processing on the land surveying data to obtain longitude and latitude standardized surveying data; perform surveying error correction on the longitude and latitude standardized surveying data to obtain enhanced land surveying data;

[0077] The land surveying and mapping spatial modeling module is used to perform land surveying and mapping spatial modeling on the enhanced land surveying and mapping data to obtain a land spatial data model; classify the land terrain areas of the land spatial data model to obtain a surveyed plain spatial model and a surveyed mountain spatial model;

[0078] The plain soil nutrient trend analysis module is used to extract land geological characteristics from the land surveying and mapping data to obtain land geological data, and perform plain soil nutrient trend analysis on the surveyed plain spatial model based on the land geological data to obtain surveyed plain soil nutrient trend data;

[0079] The mountain soil nutrient trend analysis module is used to perform mountain soil nutrient trend analysis on the surveyed mountain spatial model based on the land geological data to obtain surveyed mountain soil nutrient trend data, and evaluate the plain soil nutrient erosion factors on the surveyed mountain soil nutrient trend data based on the surveyed plain soil nutrient trend data to obtain plain soil nutrient erosion factors;

[0080] The land nutrient loss area division module is used to divide the land nutrient loss areas of the surveyed plain spatial model based on the plain soil nutrient erosion factors to obtain a land nutrient loss area model, and perform land nutrient downflow strategy analysis on the land nutrient loss area model to obtain a land nutrient downflow strategy.

[0081] The intelligent analysis and management system for land surveying and mapping data of the present invention can implement any intelligent analysis and management method for land surveying and mapping data of the present invention, and is used as a medium for coordinating the operations and signal transmissions between each module to complete the intelligent analysis and management method for land surveying and mapping data. The internal modules of the system cooperate with each other, thereby improving the accuracy and reliability of land surveying and mapping data. BRIEF DESCRIPTION OF THE DRAWINGS

[0082] Other features, objects, and advantages of the present invention will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0083] Figure 1 It is a schematic flowchart of the steps of the intelligent analysis and management method for land surveying and mapping data of the present invention;

[0084] Figure 2 It is a detailed schematic flowchart of step S1 in the present invention;

[0085] Figure 3 It is a detailed schematic flowchart of step S2 in the present invention;

[0086] The realization, functional characteristics, and advantages of the object of the present invention will be further described with reference to the accompanying drawings in conjunction with embodiments. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0087] The technical method of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative efforts belong to the scope of protection of the present invention.

[0088] In addition, the accompanying drawings are only schematic diagrams of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings represent the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0089] It should be understood that although terms such as "first" and "second" may be used here to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit can be called the second unit, and similarly the second unit can be called the first unit. The term "and / or" used here includes any and all combinations of one or more of the listed associated items.

[0090] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides an intelligent analysis and management method for land surveying and mapping data, and the method includes the following steps:

[0091] Step S1: Obtain land surveying and mapping data, perform standardized processing on the longitude and latitude of the land surveying and mapping data to obtain longitude and latitude standardized surveying and mapping data; perform surveying error correction on the longitude and latitude standardized surveying and mapping data to obtain enhanced land surveying and mapping data;

[0092] In this embodiment, land surveying and mapping data including data such as GPS coordinates, land remote sensing data, land geological data, and ground control points are collected. Software is used to perform standardized processing on these data to ensure that all data is represented in a unified coordinate system. Then, an error correction algorithm (such as the least squares method) is applied to correct the standardized data to reduce surveying errors. The finally obtained enhanced land surveying and mapping data can display more accurate geographical information, such as a corrected topographic map.

[0093] Step S2: Perform land spatial modeling on the enhanced land surveying data to obtain a land spatial data model; perform land terrain area classification on the land spatial data model to obtain a surveyed plain spatial model and a surveyed mountain spatial model;

[0094] In this embodiment, using the enhanced land surveying data, apply spatial modeling techniques (such as GIS modeling tools) to generate a land spatial data model. Perform terrain area classification on this model, using classification algorithms (such as K-means or decision trees), to divide the area into plains and mountains, and finally obtain a surveyed plain spatial model and a surveyed mountain spatial model.

[0095] Step S3: Extract land geological features from the land surveying data to obtain land geological data, and perform plain soil nutrient trend analysis on the surveyed plain spatial model according to the land geological data to obtain surveyed plain soil nutrient trend data;

[0096] In this embodiment, extract geological feature information from the land surveying data, such as soil type and rock composition. Based on this information, perform soil nutrient trend analysis on the plain spatial model, using soil test data and statistical methods (such as regression analysis), to obtain surveyed plain soil nutrient trend data, showing the nutrient level of the soil and its change trend.

[0097] Step S4: Perform mountain soil nutrient trend analysis on the surveyed mountain spatial model according to the land geological data to obtain surveyed mountain soil nutrient trend data, and perform plain soil nutrient erosion factor assessment on the surveyed mountain soil nutrient trend data according to the surveyed plain soil nutrient trend data to obtain plain soil nutrient erosion factors;

[0098] In this embodiment, perform a similar soil nutrient trend analysis on the mountain spatial model, using soil sample data and analysis tools (such as geostatistical methods), to generate surveyed mountain soil nutrient trend data. Then, combine the surveyed plain soil nutrient trend data to evaluate the impact of erosion factors on plain soil, using erosion models (such as hydrological models) to calculate erosion factors.

[0099] Step S5: Divide the surveyed plain spatial model according to the plain soil nutrient erosion factors to obtain a land nutrient loss area model, and perform land nutrient downflow strategy analysis on the land nutrient loss area model to obtain a land nutrient downflow strategy.

[0100] In this embodiment, according to the evaluated plain soil nutrient erosion factors, the land nutrient loss areas are divided, and a spatial analysis tool (such as buffer analysis) is used to determine the affected areas. For these areas, land nutrient flow reduction strategies are analyzed, flow reduction technologies (such as vegetation cover or soil improvement) are applied, and specific strategies are proposed and optimized to reduce soil nutrient loss.

[0101] Optionally, step S1 is specifically as follows:

[0102] Step S11: Obtain land surveying and mapping data, and perform standardized processing of the surveying and mapping longitude and latitude of the land surveying and mapping data, so as to obtain standardized surveying and mapping data of longitude and latitude;

[0103] In this embodiment, land surveying and mapping data is obtained from local surveying and mapping agencies, drone photography or satellites, including data such as the boundaries of plots, topographic features, terrain remote sensing, and the locations of buildings. These data come from GPS measurements, traditional topographic surveying, or lidar scanning. Using geographic information system (GIS) software, the longitude and latitude coordinates in the surveying and mapping data are converted into a standardized coordinate system, such as the Universal Transverse Mercator (UTM) coordinate system, to ensure the unity and accuracy of the data. For example, import the surveying and mapping data file (such as CSV, Shapefile, or GeoJSON format), select the target coordinate system (such as WGS84 or NAD83) in the GIS software, and use a coordinate conversion tool, such as the gdaltransform function in the GDAL library, to perform the conversion operation to ensure that all data uses the same coordinate reference system. Save the converted data in a standard format, such as a GeoTIFF file, for subsequent processing.

[0104] Step S12: Extract surveying and mapping camera images and surveying and mapping remote sensing images from the standardized surveying and mapping data of longitude and latitude, so as to obtain a set of surveying and mapping camera images and a set of surveying and mapping remote sensing images;

[0105] In this embodiment, surveying and mapping camera images are extracted from the high-resolution images taken by drones. Use image processing software (such as Agisoft Metashape) to crop and stitch the images to generate a complete set of camera images. Extract relevant images from satellite remote sensing data. Use remote sensing data processing software (such as ERDAS IMAGINE) to crop the satellite images to obtain a set of remote sensing images of a specific area. Save the extracted images in TIFF or JPEG format to generate a set of surveying and mapping camera images and a set of surveying and mapping remote sensing images respectively.

[0106] Step S13: Perform image registration on the set of surveying and mapping camera images and the set of surveying and mapping remote sensing images to obtain a set of registered surveying and mapping images, and calculate the registration accuracy error of the set of registered surveying and mapping images to obtain registration accuracy error data;

[0107] In this embodiment, an image registration algorithm (such as SIFT or SURF) is used to register the mapping camera image set with the mapping remote sensing image set. A registration tool (such as cv2.findHomography in the OpenCV library) is applied to find the transformation matrix between the images. The registration accuracy error between the registered image and the original image is calculated. A registration accuracy evaluation tool (such as RMSE or MSE) is used to quantify the error and generate registration accuracy error data. The error data is saved in a report for use in subsequent correction steps.

[0108] Step S14: Calculate the pixel value error of images with the same longitude and latitude based on the registered mapping image set, so as to obtain image pixel value error data;

[0109] In this embodiment, the pixel values of the registered images are compared. Some calibration points are selected, and the pixel value differences of these points in the registered images are calculated. Statistical methods (such as root mean square error, RMSE) are used to calculate the error of the image pixel values and generate image pixel value error data. The calculation results are organized in a table form and saved as a data file for subsequent processing.

[0110] Step S15: Perform mapping image error correction on the registered mapping image set according to the image pixel value error data and the registration accuracy error data, so as to obtain a mapping error correction image set;

[0111] In this embodiment, according to the pixel value error data and the registration accuracy error data, an error correction algorithm (such as an image correction method based on statistical learning) is used to correct the registered image. An image correction tool in image processing software (such as MATLAB) is applied to adjust the pixel values of the image. The error of the corrected image is recalculated to ensure that the error is within an acceptable range. A corrected image set is generated and saved as a high-quality image file (such as GeoTIFF format) for subsequent analysis.

[0112] Step S16: Perform data enhancement processing on the mapping error correction image set to obtain a land mapping enhanced image set, and replace the mapping images in the longitude and latitude standardized mapping data according to the land mapping enhanced image set to obtain land mapping enhanced data.

[0113] In this embodiment, data augmentation techniques (such as rotation, scaling, cropping, brightness adjustment) are applied to the corrected image set to generate an augmented image set. An image processing tool (such as ImageDataGenerator in TensorFlow) is used for augmentation. According to the results of the augmented image set, the original images in the longitude and latitude normalized mapping data are replaced. Ensure that the augmented images are consistent with the coordinates in the normalized mapping data. The augmented image data and the updated longitude and latitude normalized mapping data are saved as a new data set for further analysis and use.

[0114] Optionally, step S15 is specifically as follows:

[0115] Step S151: Perform pixel value error distribution statistics on the image pixel value error data to obtain image pixel value error distribution data;

[0116] In this embodiment, the image is divided into several grid regions, and the pixel value errors within each grid are calculated. By statistically analyzing the error values of each pixel and plotting an error histogram, the distribution data of the pixel value errors is obtained. Taking a satellite image as an example, assume there is an original captured image and a registered remote sensing image. Calculate the error value of each pixel point (actual pixel value minus ideal pixel value), and then perform statistical analysis on these error values. By constructing an error histogram and an error distribution curve, we can determine the distribution characteristics of the errors, such as the mean, standard deviation of the errors, and the skewed distribution of the errors. These statistical data will be used for subsequent error region identification and adjustment.

[0117] Step S152: Perform pixel value statistics for the error distribution regions based on the image pixel value error distribution data to obtain error distribution region pixel value data;

[0118] In this embodiment, using the obtained error distribution data, regions with significant error distributions are identified. The pixel values within these regions are statistically analyzed to obtain the average error value and standard deviation within each region. For example, in the error distribution diagram, select the regions where the error values exceed a certain threshold, and statistically analyze the pixel error data within these regions for subsequent adjustment and correction. Assume that the error distribution shows that most errors are concentrated in certain regions of the image. An error threshold can be set to divide these regions. For example, if the error distribution curve shows that the pixels with errors exceeding 5% are concentrated in the upper half of the image, we can mark these regions as "high error regions". Statistically analyze the pixel values within these regions and calculate the average pixel value, error range, etc. of the error regions. These statistical results will help us understand the characteristics of the error concentration areas and provide data support for the next error correction.

[0119] Step S153: Perform mean square adjustment of the error pixel values on the registered mapping image set according to the pixel value data of the error distribution region, so as to obtain a pixel-adjusted image set;

[0120] In this embodiment, based on the obtained regional pixel value data, mean square adjustment is performed on the image. The least mean square error algorithm (such as the least squares method) is used to adjust the image pixel values to reduce the error. The adjustment process may include spatial transformation or color correction of the image to correct the error. For example, geometric transformation and color correction are applied to a set of remote sensing images to align them with the actual ground data, so as to obtain a pixel-adjusted image set. Specifically, the minimum mean square error (MMSE) algorithm can be used to correct these pixels. The adjustment process includes comparing the original image pixel values with the adjusted pixel values, calculating the sum of squared errors, and minimizing this error. After mean square error adjustment, a new pixel-adjusted image set is obtained, and these images minimize the error below a specified threshold, improving the overall quality of the images.

[0121] Step S154: Extract image terrain features from the registration accuracy error data to obtain image terrain error data, and estimate terrain geometric error correction parameters according to the image terrain error data to obtain a set of terrain geometric error correction parameters;

[0122] In this embodiment, terrain features (such as elevation, slope, etc.) are extracted from the adjusted image, and image terrain error data is obtained through feature extraction algorithms (such as edge detection, texture analysis). Using these data, regression analysis or optimization algorithms are used to estimate terrain geometric error correction parameters. For example, by analyzing the error distribution in the elevation image, methods such as control point registration are used to estimate and correct terrain geometric error parameters to correct the terrain error of the image.

[0123] Step S155: Perform geometric terrain correction on the pixel-adjusted image set according to the set of terrain geometric error correction parameters to obtain a mapping error correction image set.

[0124] In this embodiment, according to the estimated terrain geometric error correction parameters, geometric correction is performed on the pixel-adjusted image set. The correction parameters are applied to correct the images through transformation algorithms (such as affine transformation, projective transformation) to obtain the final mapping error correction image set. For example, the terrain features in the remote sensing image are aligned with the actual terrain data, and the terrain-related errors are eliminated through the geometric correction algorithm, thereby generating an accurate mapping image set. Assume that the correction parameter set contains information such as rotation angle, scaling factor, translation amount, etc., and these parameters are used to correct the geometric shape of the images. In specific implementation, geometric transformation algorithms (such as affine transformation, projective transformation, etc.) can be used to apply these correction parameters to the pixel-adjusted image set for geometric correction of the images. As a result, a corrected mapping error correction image set is obtained. These images have high accuracy in terrain geometric features, the errors are significantly reduced, and the image quality is improved.

[0125] Optionally, step S2 is specifically as follows:

[0126] Step S21: Extract the land remote sensing image from the land surveying and mapping enhanced data to obtain the land remote sensing image;

[0127] In this embodiment, by processing the land surveying and mapping enhanced data, the image processing technology of high-resolution satellite remote sensing images can be used to extract the land remote sensing images. For example, using image segmentation algorithms such as K-means clustering or the U-Net architecture in deep learning models can effectively distinguish surface features and backgrounds, thereby extracting clear land remote sensing images. These images will lay a foundation for the subsequent extraction and analysis of high-level information.

[0128] Step S22: Perform stereo vision high-level information matching based on the land remote sensing image to obtain land elevation data, and construct a land elevation model for the surveying and mapping area based on the land elevation data;

[0129] In this embodiment, based on the extracted land remote sensing image, through stereo vision techniques such as binocular stereo vision or multi-view stereo vision, high-level information matching is performed. Algorithms such as disparity calculation and stereo matching techniques can be applied to extract elevation data from images of multiple perspectives. Then, this data is used to construct a detailed land elevation model for the surveying and mapping area. For example, a triangular irregular network (TIN) model or a grid elevation model is used to represent the elevation information of the land.

[0130] Step S23: Calculate the land spatial grid resolution according to the land elevation model of the surveying and mapping area to obtain land spatial grid resolution data, and perform elevation point grid conversion on the land elevation model of the surveying and mapping area according to the land spatial grid resolution data to obtain the land spatial grid model;

[0131] In this embodiment, according to the elevation model, the raster resolution of the land space is calculated. This can be accomplished through spatial analysis tools in a Geographic Information System (GIS). For example, a raster analysis tool is used to determine an appropriate spatial resolution. This also includes converting elevation data into raster format, which can be achieved through interpolation algorithms such as Kriging interpolation, thereby generating a land space raster model.

[0132] Step S24: Integrate the surveyed surface features based on the enhanced land survey data to obtain surveyed land surface feature data, and fill the land surface features of the land space raster model according to the surveyed land surface feature data, thereby obtaining a land space data model;

[0133] In this embodiment, surface feature integration is performed based on the enhanced land survey data. For example, optical remote sensing images are combined with Light Detection and Ranging (LiDAR) data through data fusion technology to extract detailed surface feature information. Then, these feature data are applied to the land space raster model for feature filling. Spatial interpolation and image synthesis methods can be used to embed the extracted surface feature information into the raster model, thereby forming a comprehensive land space data model.

[0134] Step S25: Classify the surveyed land terrain regions of the land space data model to obtain a surveyed plain space model and a surveyed mountain space model.

[0135] In this embodiment, terrain region classification is performed on the land space data model. For example, classification algorithms such as Support Vector Machine (SVM) or Random Forest are used to classify terrain features and identify plain and mountain regions. The classification results will generate a surveyed plain space model and a surveyed mountain space model. This process may include extracting features from terrain data and performing pattern recognition and region segmentation to ensure accurate terrain region classification. It can also perform spatial model division according to the terrain regions already marked on the surveyed surface features.

[0136] Optionally, step S24 is specifically:

[0137] Step S241: Extract spectral features from the enhanced land survey data to obtain spectral data of the surveyed area;

[0138] In this embodiment, using high - resolution remote sensing images (for example, images from Landsat 8 or Sentinel - 2), first process the images through radiometric correction and atmospheric correction to reduce the influence of the atmosphere and the sensor. Then, use spectral feature extraction algorithms such as Principal Component Analysis (PCA) or spectral index calculation (such as NDVI) to extract the spectral features of each band. After spectral feature extraction, a spectral dataset reflecting land cover types and status will be obtained, including data of blue, green, red, and near - infrared bands.

[0139] Step S242: Classify the spectral data of the surveyed area according to the band reflectance characteristics, so as to obtain the regional blue-band reflectance data and the regional green-band reflectance data;

[0140] In this embodiment, in the extracted spectral data, apply a band reflectance classification algorithm, such as K-means clustering or support vector machine (SVM) classification, to classify the blue band (usually in the range of 450 - 495 nm) and the green band (usually in the range of 500 - 550 nm). Through these algorithms, the data is divided into different categories, and finally the classification results of the regional blue-band reflectance data (such as blue water bodies, bare land, etc.) and the regional green-band reflectance data (such as forests, grasslands, etc.) are obtained.

[0141] Step S243: Divide the spectral data of the surveyed area according to the regional blue-band reflectance data to obtain the water body data of the surveyed area;

[0142] In this embodiment, using the blue-band reflectance data, apply threshold segmentation technology (such as Otsu threshold method) or a trained classification model (such as a random forest classifier) to divide the water body area of the surveyed area. By setting an appropriate blue-band reflectance threshold (usually the reflectance of water bodies is relatively high), the water body area can be identified. The result is a mask data marking the water body area, and all water bodies in the surveyed area are extracted.

[0143] Step S244: Divide the spectral data of the surveyed area according to the regional green-band reflectance data to obtain the vegetation data of the surveyed area;

[0144] In this embodiment, use the green-band reflectance data, apply spectral threshold segmentation (such as based on vegetation index threshold) or supervised classification algorithm (such as decision tree classifier) to identify the vegetation in the area. According to the high green-band reflectance characteristics of the vegetation, set an appropriate threshold to extract the vegetation area from other areas. The final vegetation data obtained includes different types of vegetation areas such as forests and grasslands.

[0145] Step S245: Classify the regional green-band reflectance data to obtain the high green-band reflectance area data and the low green-band reflectance area data;

[0146] In this embodiment, a classification algorithm (such as clustering analysis or threshold segmentation) is applied to classify the green-band reflectance data. A reflectance threshold is set to divide the data into a high green-band reflectance area (such as a dense forest) and a low green-band reflectance area (such as sparse vegetation or bare soil). For example, by setting a green-band reflectance threshold (such as 0.3), the area with a reflectance higher than this threshold is marked as a high green-band area, and the area with a reflectance lower than this threshold is marked as a low green-band area.

[0147] Step S246: Cluster the vegetation data in the survey area into a high green-band reflectance vegetation area based on the data of the high green-band reflectance area to obtain the mountain data in the survey area; cluster the vegetation data in the survey area into a low green-band reflectance vegetation area based on the data of the low green-band reflectance area to obtain the plain data in the survey area.

[0148] In this embodiment, a spatial clustering algorithm (such as K-means clustering or hierarchical clustering) is applied to the data of the high green-band reflectance area to identify areas with dense vegetation, which usually correspond to mountainous or hilly areas. The obtained clustering results are used to label the mountain data. A similar clustering algorithm is used for the data of the low green-band reflectance area to identify areas with sparse vegetation, which usually correspond to plain areas. Through these clustering results, the mountain and plain data of the survey area can be obtained.

[0149] Step S247: Perform spatial integration of the water body data, plain data, and mountain data in the survey area to obtain the land surface feature data of the surveyed land.

[0150] In this embodiment, the obtained water body data, plain data, and mountain data are spatially integrated. Using geographic information system (GIS) tools, they are spatially aligned according to the land surface feature data, and various regional data are merged into a unified land surface feature data model. Through overlay analysis, spatial clipping, and data fusion, the feature information of various regions is integrated into a comprehensive land surface feature dataset, representing the land surface features of the entire surveyed area.

[0151] Step S248: Fill the land surface features of the land spatial raster model according to the land surface feature data of the surveyed land to obtain the land spatial data model.

[0152] In this embodiment, based on the generated land surface feature data, a land spatial raster model is constructed. Using rasterization technology, the land surface feature data is mapped onto the raster grid, and filled according to the features of each raster cell (such as water body, mountain, plain, etc.). Spatial interpolation methods (such as Kriging interpolation) are applied to fill the vacant areas and generate a complete land spatial data model. The final model contains detailed spatial distribution information of various land surface features for further land analysis and management.

[0153] Optionally, step S3 is specifically as follows:

[0154] Step S31: Extract the land geological features from the land surveying and mapping data to obtain land geological data;

[0155] In this embodiment, high-resolution land surveying and mapping data (such as remote sensing images or ground surveying data) is used, and geological feature extraction algorithms (such as principal component analysis, support vector machine classification, etc.) are adopted to analyze the geological features of the land. Specifically, assuming that remote sensing images are used, image classification can be performed through image processing software (such as ENVI or ERDAS) to identify different geological units, such as sandy soil, clay, gravel layer, etc. Then, the distribution information of each geological unit is extracted from the land surveying and mapping data by using geological feature extraction tools (such as geological analysis tools in ArcGIS). Finally, the extracted data is integrated to form a database containing land geological features, and these data will serve as the basis for subsequent steps.

[0156] Step S32: Extract the soil element content features from the land geological data to obtain soil element content data, and perform inverse distance weighted spatial interpolation on the soil element content data to obtain continuous spatial soil content data;

[0157] In this embodiment, the element content (such as nitrogen, phosphorus, potassium, etc.) is measured from soil samples, and chemical analysis methods (such as atomic absorption spectrometry, ion chromatography) are used to obtain the element content data of each sample point. Then, the inverse distance weighted (IDW) interpolation algorithm is used to perform spatial interpolation on these discrete data points to generate continuous spatial soil element content data. The specific operation can be completed in GIS software (such as ArcGIS or QGIS). By inputting the soil element content data and sample point coordinates through the IDW tool and setting the interpolation parameters (such as the distance decay factor), a continuous soil element content distribution map is generated. This will make the soil element content data continuous in space and provide support for subsequent analysis.

[0158] Step S33: Integrate the continuous spatial soil content data and the surveyed plain spatial model to obtain the surveyed plain spatial element content model;

[0159] In this embodiment, the continuous spatial soil element content data is integrated with the plain spatial model. First, a plain spatial model (such as a DEM digital elevation model or a terrain model) needs to be established, which can be constructed through existing geographical data and digital models (such as SRTM data). Then, using spatial analysis tools (such as the spatial analysis toolset of ArcGIS), the soil element content data is overlaid with the plain spatial model for spatial interpolation and integration. Perform a spatial overlay analysis on the soil element content data layer and the plain model layer to ensure that the model coverage ranges are consistent, and generate a mapping plain spatial element content model through geostatistical methods. This model will show the distribution of soil elements in the plain area.

[0160] Step S34: Conduct a regression analysis on the soil element content based on the mapping plain spatial element content model to obtain the plain soil element content trend data;

[0161] In this embodiment, regression analysis is performed using the data of the mapping plain spatial element content model. Assuming the goal is to analyze the spatial distribution trend of a certain soil element (such as phosphorus), regression analysis tools (such as SPSS or the R language) can be used to establish a regression model. This includes selecting an appropriate regression method (such as linear regression, polynomial regression), using the data in the mapping plain spatial element content model as the independent variable, and modeling the element content trend as the dependent variable. Fit the regression model, calculate the regression coefficients and relevant statistics to obtain the spatial trend data of the plain soil element content. These data will show the change trend of the soil element content in the plain area.

[0162] Step S35: Obtain the soil nutrient element rules, and perform plain soil nutrient trend integration on the plain soil element content trend data according to the soil nutrient element rules to obtain the mapping plain soil nutrient trend data.

[0163] In this embodiment, based on the soil nutrient element rules (such as the soil nutrient standards of the International Union of Soil Sciences or the standards of local agricultural departments), the plain soil element content trend data is integrated. First, relevant soil nutrient element standards and rules need to be obtained, and these rules include the appropriate ranges of various nutrient elements in the soil. Then, use data analysis tools (such as Excel or the Pandas library in Python) to conduct a comparative analysis on the plain soil element content trend data, compare the actual data with the standards, and identify the deficiencies or surpluses of the soil nutrient elements. Finally, generate the mapping plain soil nutrient trend data based on these analysis results to show the spatial distribution trend of the soil nutrient elements and the potential improvement needs. This data can be used for agricultural management and soil improvement suggestions.

[0164] Optionally, step S4 is specifically as follows:

[0165] Step S41: Extract the mountain geological features from the surveyed mountain spatial model for the land geological data, so as to obtain the mountain geological data;

[0166] In this embodiment, a high-resolution remote sensing image and ground measurement data are used to construct the mountain spatial model. Geological features such as geological units, fault lines, and rock types are extracted through terrain analysis software. These features determine the geological distribution of each mountain body by analyzing the digital elevation model (DEM) and geological survey data, forming a mountain geological data set. For example, in a certain mountainous area, the main rock types and soil layer thicknesses are identified. It is also possible to extract the mountain geological conditions included in the land geological data according to the spatial features included in the surveyed mountain spatial model.

[0167] Step S42: Extract the mountain rock element content features and mountain soil element content features from the mountain geological data, so as to obtain the mountain rock element content data and the mountain soil element content data;

[0168] In this embodiment, elemental analysis of rock and soil samples is performed on the extracted mountain geological data. The main element contents in the samples, such as silicon, aluminum, iron, etc., are determined using an X-ray fluorescence (XRF) spectrometer. Through chemical analysis, the elemental concentration data of each rock and soil sample are obtained, generating the mountain rock and soil element content data. For example, high contents of calcium and magnesium are found in the soil of a certain area.

[0169] Step S43: Perform stratified Kriging interpolation on the mountain rock element content data and the mountain soil element content data, so as to obtain the stratified spatial mountain element content data;

[0170] In this embodiment, stratified Kriging interpolation is applied to the mountain rock element content data and the soil element content data. The Kriging interpolation algorithm is used to estimate the elemental concentrations at different depths and regions, generating a spatial distribution map. This method can effectively fill the data gaps between sample points, forming the stratified spatial mountain element content data. For example, an elemental distribution map of different depths of a certain mountain body is generated.

[0171] Step S44: Integrate the stratified spatial mountain element content data and the surveyed mountain spatial model for the mountain spatial soil element content, so as to obtain the surveyed mountain spatial element content model;

[0172] In this embodiment, the stratified spatial mountain element content data is integrated with the mountain spatial model. The elemental content data is overlaid onto the mountain spatial model through GIS tools, generating a comprehensive elemental content model. This model can display the elemental distributions at different spatial positions and depths. For example, the elemental concentration data of a certain mountain body is integrated with its geological model to generate a complete elemental distribution map.

[0173] Step S45: Perform a regression analysis on the soil element content based on the surveyed mountain spatial element content model to obtain the trend data of the mountain soil element content;

[0174] In this embodiment, a regression analysis is performed on the integrated mountain spatial element content model. A regression model is used to explore the variation trend of the soil element content with the spatial position, and the trend data of the mountain soil element content is obtained. For example, analyze the distribution change of potassium element at different altitudes to determine its spatial trend of content.

[0175] Step S46: Integrate the trend data of the mountain soil element content according to the soil nutrient element rules to obtain the surveyed mountain soil nutrient trend data;

[0176] In this embodiment, the trend data of the mountain soil element content is integrated according to the soil nutrient element rules. Soil science standards and nutrient demand models are applied to evaluate the nutrient trend of the soil. Comprehensive soil nutrient trend data is obtained, such as the content change trends of calcium, magnesium, and potassium in the soil of a certain area.

[0177] Step S47: Evaluate the plain soil nutrient erosion factor on the surveyed mountain soil nutrient trend data to obtain the plain soil nutrient erosion factor.

[0178] In this embodiment, the surveyed mountain soil nutrient trend data is compared with the plain soil nutrient trend data. Through comparison, the impact of the mountain soil on the plain soil nutrient is evaluated, and the plain soil nutrient erosion factor is calculated. For example, identify the impact of nutrient loss in the mountain soil on the quality of the plain soil to obtain the erosion factor data.

[0179] Optionally, step S47 is specifically:

[0180] Step S471: Align the surveyed plain soil nutrient trend data and the surveyed mountain soil nutrient trend data in terms of time and space to obtain the surveyed area soil nutrient trend data;

[0181] In this embodiment, the plain and mountain soil nutrient trend data are aligned by time and space coordinates. For example, using Geographic Information System (GIS) software, map the soil data at different time points onto a unified spatial grid, and then use time series analysis methods (such as time interpolation) for data integration. This will help accurately depict the soil nutrient trend of the entire surveyed area.

[0182] Step S472: Perform a principal component analysis on the soil nutrient based on the surveyed area soil nutrient trend data to obtain the soil nutrient principal component data;

[0183] In this embodiment, principal component analysis (PCA) is performed on the aligned soil nutrient trend data, and an appropriate number of principal components is selected (for example, the principal components with a cumulative explained variance reaching 80% are retained). Using statistical software (such as the scikit-learn library in R or Python), the data is standardized, and then the principal components are extracted to reduce the data dimension and refine the main soil nutrient component data. For example, several principal components that have the greatest impact on soil quality are extracted from data containing various nutrients such as nitrogen, phosphorus, and potassium.

[0184] Step S473: Based on the land spatial data model and the soil nutrient principal component data, construct a soil erosion model to obtain the soil erosion model.

[0185] In this embodiment, based on the land spatial data model (such as a raster model) and the soil nutrient principal component data, a soil erosion model is constructed. For example, first, the rainfall data of the region is obtained, and then the soil erosion model (such as the RUSLE model) is applied to combine the principal component data with the terrain, land cover, and rainfall data to establish a soil erosion prediction model. This will allow the simulation and prediction of soil erosion in different land areas. It is also possible to use the land spatial data model (such as land use / land cover data) combined with the soil nutrient principal component data to establish a soil erosion model. A geographically weighted regression (GWR) model or other spatial regression models can be used for construction. By inputting the soil nutrient principal components and land use characteristics (such as slope, vegetation cover, etc.), the model is trained to obtain the prediction results of soil erosion. The model parameters can be adjusted according to the characteristics of the actual data to optimize the prediction accuracy.

[0186] Step S474: Calculate the soil nutrient erosion factors for the mapped plain soil nutrient trend data and the mapped mountain soil nutrient trend data respectively according to the soil erosion model, so as to obtain the mapped area plain soil nutrient erosion factor and the mapped area mountain soil nutrient erosion factor.

[0187] In this embodiment, using the soil erosion model, the soil nutrient erosion factors are calculated for the soil nutrient trend data of the plain and the mountain respectively. Specifically, it includes applying the erosion model to the spatial location data of each soil sample to calculate the erosion factor of each sample point. For example, by comparing the nutrient component loss situations under different geomorphic conditions, the corresponding erosion factor values are calculated, so as to obtain the erosion factor data of the plain and mountain areas.

[0188] Step S475: Quantify the correlation between the mapped area mountain soil nutrient erosion factor and the mapped area plain soil nutrient erosion factor according to the mapped area plain soil nutrient erosion factor, so as to obtain the plain soil nutrient erosion factor.

[0189] In this embodiment, based on the plain soil nutrient erosion factors, the correlation of the mountain soil nutrient erosion factors is quantified. Using statistical analysis methods (such as correlation analysis or regression analysis), the relationship between the erosion factors in the plain and mountainous regions is analyzed. For example, the correlation coefficient between the mountain soil nutrient erosion factors and the plain erosion factors is calculated to evaluate the degree of association of soil nutrient erosion under different geomorphic conditions. Through these analyses, the regional characteristics of soil erosion and its influencing factors are further understood.

[0190] Optionally, step S5 is specifically as follows:

[0191] Step S51: Conduct statistical analysis of erosion factors based on the plain soil nutrient erosion factors, so as to obtain high-correlation soil nutrient erosion factors and low-correlation soil nutrient erosion factors;

[0192] In this embodiment, statistical analysis methods (such as Pearson correlation coefficient or regression analysis) are used to calculate the correlation between each nutrient factor and soil erosion. For example, the analysis results show that the correlations of nitrogen and phosphorus with the erosion degree are relatively high, while the correlation of potassium is relatively low. Therefore, nitrogen and phosphorus are labeled as high-correlation soil nutrient erosion factors, and potassium is labeled as a low-correlation factor.

[0193] Step S52: Extract the distribution characteristics of plain element contents according to the mapping plain spatial element content model, so as to obtain the plain soil element content distribution data;

[0194] In this embodiment, remote sensing technology and ground measurement data are used to establish an element content distribution model for the plain area. The specific operations include using geographic information system (GIS) software to process remote sensing images and extract the spatial distribution characteristics of elements such as nitrogen, phosphorus, and potassium in the soil. These data are used to generate a spatial distribution map of plain soil element contents through an interpolation algorithm (such as Kriging interpolation).

[0195] Step S53: Conduct factor spatial association based on the high-correlation soil nutrient erosion factors and the plain soil element content distribution data, so as to obtain the data of areas where soil nutrients are easily lost; conduct factor spatial association based on the low-correlation soil nutrient erosion factors and the plain soil element content distribution data, so as to obtain the data of areas where soil nutrients are difficult to lose;

[0196] In this embodiment, the statistical data of the obtained high-correlation (nitrogen, phosphorus) and low-correlation (potassium) factors are subjected to spatial association analysis with the extracted element content distribution data. Using a spatial regression model, the high-concentration areas of nitrogen and phosphorus are intersected with the areas with high soil erosion risk to obtain the areas where soil nutrients are easily lost. Correspondingly, the low-concentration areas of potassium are intersected with the areas with low soil erosion risk to obtain the data of areas where soil nutrients are difficult to lose.

[0197] Step S54: Perform spatial correlation region division on the surveyed plain spatial model and the surveyed mountain spatial model to obtain a handover region spatial model and a non-handover region spatial model;

[0198] In this embodiment, a geographic information system (GIS) is used to analyze the spatial models of the plain and the mountain, and the handover region and the non-handover region of the two models are spatially divided. Specifically, it includes overlaying the boundaries of the plain spatial model and the mountain spatial model, and using spatial analysis tools to identify and mark the handover region (such as the junction of the plain and the mountain) and the non-handover region (such as the pure plain or pure mountain area).

[0199] Step S55: Perform intersection region spatial division on the handover region spatial model according to the data of the regions where soil nutrients are easily lost to obtain a model of the regions where land nutrients are easily lost; perform intersection region spatial division on the non-handover region spatial model according to the data of the regions where soil nutrients are difficult to lose to obtain a model of the regions where land nutrients are difficult to lose;

[0200] In this embodiment, the data of the regions where soil nutrients are easily lost is applied to the handover region spatial model for spatial intersection operation to obtain a model of the regions where land nutrients are easily lost. Specifically, use GIS tools to perform overlay analysis on the easily lost regions and the handover regions to determine the regions with higher risks. Similar operations are performed on the data of the regions where soil nutrients are difficult to lose to generate a model of the regions where land nutrients are difficult to lose.

[0201] Step S56: Perform spatial merging on the model of the regions where land nutrients are easily lost and the model of the regions where land nutrients are difficult to lose to obtain a model of the regions where land nutrients are lost;

[0202] In this embodiment, the model of the regions where land nutrients are easily lost and the model of the regions where land nutrients are difficult to lose are spatially merged to obtain a comprehensive model of the regions where land nutrients are lost. Specifically, it includes overlaying the two models in GIS and using spatial analysis tools to generate a comprehensive model of the final regions where land nutrients are lost to identify the overall nutrient loss risk regions.

[0203] Step S57: Perform analysis on the land nutrient reduction flow strategy for the model of the regions where land nutrients are lost to obtain a land nutrient reduction flow strategy.

[0204] In this embodiment, based on the model of the regions where land nutrients are lost, analysis on the reduction flow strategy is performed on the model regions. A decision support system (DSS) can be used to simulate the effects of different reduction flow strategies (such as vegetation restoration, soil protection measures, improved fertilization strategies) on soil nutrient loss. By simulating and comparing the effects of different strategies, an optimal land nutrient reduction flow strategy is formulated, including specific implementation steps and measures, to reduce the risk of soil nutrient loss.

[0205] Optionally, this specification provides an intelligent analysis and management system for land surveying data, which is used to execute an intelligent analysis and management method for land surveying data as described above. The intelligent analysis and management system for land surveying data includes:

[0206] A surveying error correction module, which is used to obtain land surveying data, perform standardized processing of the longitude and latitude of the land surveying data to obtain longitude and latitude standardized surveying data; perform surveying error correction on the longitude and latitude standardized surveying data to obtain enhanced land surveying data;

[0207] A surveyed land space modeling module, which is used to perform surveyed land space modeling on the enhanced land surveying data to obtain a land space data model; perform surveyed land terrain area classification on the land space data model to obtain a surveyed plain space model and a surveyed mountain space model;

[0208] A plain soil nutrient trend analysis module, which is used to extract land geological characteristics from the land surveying data to obtain land geological data, and perform plain soil nutrient trend analysis on the surveyed plain space model according to the land geological data to obtain surveyed plain soil nutrient trend data;

[0209] A mountain soil nutrient trend analysis module, which is used to perform mountain soil nutrient trend analysis on the surveyed mountain space model according to the land geological data to obtain surveyed mountain soil nutrient trend data, and perform plain soil nutrient erosion factor assessment on the surveyed mountain soil nutrient trend data according to the surveyed plain soil nutrient trend data to obtain plain soil nutrient erosion factors;

[0210] A land nutrient loss area division module, which is used to divide the surveyed plain space model according to the plain soil nutrient erosion factors to obtain a land nutrient loss area model, and perform land nutrient downflow strategy analysis on the land nutrient loss area model to obtain a land nutrient downflow strategy.

[0211] The intelligent analysis and management system for land surveying data of the present invention can implement any intelligent analysis and management method for land surveying data of the present invention. It is a medium for coordinating the operations and signal transmissions between various modules to complete the intelligent analysis and management method for land surveying data. The internal modules of the system cooperate with each other, thereby improving the accuracy and reliability of land surveying data.

[0212] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the application documents are intended to be included in the present invention.

[0213] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. An intelligent analysis and management method for land surveying and mapping data, characterized in that, Including the following steps: Step S1: Obtain land surveying and mapping data, and perform standardized processing on the longitude and latitude of the land surveying and mapping data to obtain longitude and latitude standardized surveying and mapping data; Perform surveying and mapping error correction on the longitude and latitude standardized surveying and mapping data to obtain enhanced land surveying and mapping data; Step S2: Perform land space modeling on the enhanced land surveying and mapping data to obtain a land space data model; perform land terrain area classification on the land space data model to obtain a surveyed plain space model and a surveyed mountain space model; Step S3: Extract land geological features from the land surveying and mapping data to obtain land geological data, and perform analysis on the plain soil nutrient trend of the surveyed plain space model based on the land geological data to obtain surveyed plain soil nutrient trend data; Step S4: Perform analysis on the mountain soil nutrient trend of the surveyed mountain space model based on the land geological data to obtain surveyed mountain soil nutrient trend data, and perform an assessment of the plain soil nutrient erosion factor on the surveyed mountain soil nutrient trend data based on the surveyed plain soil nutrient trend data to obtain the plain soil nutrient erosion factor; Step S5: Divide the surveyed plain space model according to the plain soil nutrient erosion factor to obtain a land nutrient loss area model, and perform analysis on the land nutrient downflow strategy for the land nutrient loss area model to obtain a land nutrient downflow strategy.

2. The intelligent analysis and management method for land surveying and mapping data according to claim 1, wherein Step S1 is specifically as follows: Step S11: Obtain land surveying and mapping data, and perform standardized processing on the longitude and latitude of the land surveying and mapping data to obtain longitude and latitude standardized surveying and mapping data; Step S12: Extract surveying and mapping camera images and surveying and mapping remote sensing images from the longitude and latitude standardized surveying and mapping data to obtain a set of surveying and mapping camera images and a set of surveying and mapping remote sensing images; Step S13: Perform image registration on the set of surveying and mapping camera images and the set of surveying and mapping remote sensing images to obtain a registered set of surveying and mapping images, and calculate the registration accuracy error for the registered set of surveying and mapping images to obtain registration accuracy error data; Step S14: Calculate the pixel value error of images with the same longitude and latitude based on the registered set of surveying and mapping images to obtain pixel value error data of the images; Step S15: Perform surveying and mapping image error correction on the registered set of surveying and mapping images according to the pixel value error data of the images and the registration accuracy error data to obtain a set of surveying and mapping error correction images; Step S16: Perform data enhancement processing on the set of surveying and mapping error correction images to obtain a set of enhanced land surveying and mapping images, and replace the longitude and latitude standardized surveying and mapping data with the set of enhanced land surveying and mapping images to obtain enhanced land surveying and mapping data.

3. The intelligent analysis and management method for land surveying and mapping data according to claim 2, wherein, Step S15 is specifically as follows: Step S151: Perform statistics on the pixel value error distribution of the pixel value error data of the images to obtain pixel value error distribution data of the images; Step S152: Perform statistics on the pixel values of the error distribution regions according to the pixel value error distribution data of the images to obtain pixel value data of the error distribution regions; Step S153: Perform mean square adjustment of the error pixel values on the registered set of surveying and mapping images according to the pixel value data of the error distribution regions to obtain a set of pixel-adjusted images; Step S154: Extract the image terrain features from the registration accuracy error data to obtain the image terrain error data, and estimate the terrain geometric error correction parameters based on the image terrain error data to obtain the terrain geometric error correction parameter set; Step S155: Perform geometric terrain correction on the pixel adjustment image set according to the terrain geometric error correction parameter set to obtain the mapping error correction image set.

4. The intelligent analysis and management method for land surveying and mapping data according to claim 1, characterized in that, Step S2 is specifically as follows: Step S21: Extract the land remote sensing image from the land surveying and mapping enhanced data to obtain the land remote sensing image; Step S22: Perform stereo vision high-level information matching based on the land remote sensing image to obtain the land elevation data, and construct the land elevation model of the surveying and mapping area based on the land elevation data; Step S23: Calculate the land spatial grid resolution according to the land elevation model of the surveying and mapping area to obtain the land spatial grid resolution data, and perform elevation point grid conversion on the land elevation model of the surveying and mapping area according to the land spatial grid resolution data to obtain the land spatial grid model; Step S24: Integrate the surveying and mapping surface features according to the land surveying and mapping enhanced data to obtain the surveying and mapping land surface feature data, and fill the land surface features of the land spatial grid model according to the surveying and mapping land surface feature data to obtain the land spatial data model; Step S25: Classify the surveying and mapping land terrain areas of the land spatial data model to obtain the surveying and mapping plain spatial model and the surveying and mapping mountain spatial model.

5. The intelligent analysis and management method for land surveying and mapping data according to claim 1, characterized in that Step S24 is specifically as follows: Step S241: Extract the spectral features from the land surveying and mapping enhanced data to obtain the spectral data of the surveying and mapping area; Step S242: Classify the band reflectance features of the spectral data of the surveying and mapping area to obtain the regional blue band reflectance data and the regional green band reflectance data; Step S243: Divide the water body area of the surveying and mapping area according to the regional blue band reflectance data of the spectral data of the surveying and mapping area to obtain the water body data of the surveying and mapping area; Step S244: Divide the vegetation area of the surveying and mapping area according to the regional green band reflectance data of the spectral data of the surveying and mapping area to obtain the vegetation data of the surveying and mapping area; Step S245: Classify the reflectance of the regional green band reflectance data to obtain the high green band reflectance area data and the low green band reflectance area data; Step S246: Cluster the high green band reflectance vegetation areas of the surveying and mapping area vegetation data according to the high green band reflectance area data to obtain the mountain data of the surveying and mapping area; Cluster the low green band reflectance vegetation areas of the surveying and mapping area vegetation data according to the low green band reflectance area data to obtain the plain data of the surveying and mapping area; Step S247: Integrate the regional surface features of the water body data of the surveying and mapping area, the plain data of the surveying and mapping area, and the mountain data of the surveying and mapping area to obtain the surveying and mapping land surface feature data; Step S248: Fill the land surface features of the land spatial grid model according to the surveying and mapping land surface feature data to obtain the land spatial data model.

6. The intelligent analysis and management method for land surveying and mapping data according to claim 1, characterized in that, Step S3 is specifically as follows: Step S31: Extract the land geological features from the land surveying data to obtain the land geological data; Step S32: Extract the soil element content features from the land geological data to obtain the soil element content data, and perform inverse distance weighted spatial interpolation on the soil element content data to obtain the continuous spatial soil content data; Step S33: Integrate the continuous spatial soil content data and the surveyed plain spatial model to obtain the surveyed plain spatial element content model; Step S34: Conduct a regression analysis of the soil element content based on the surveyed plain spatial element content model to obtain the plain soil element content trend data; Step S35: Obtain the soil nutrient element rules, and perform plain soil nutrient trend integration on the plain soil element content trend data according to the soil nutrient element rules to obtain the surveyed plain soil nutrient trend data.

7. The intelligent analysis and management method for land surveying and mapping data according to claim 1, characterized in that Step S4 is specifically as follows: Step S41: Extract the mountain geological features from the land geological data according to the surveyed mountain spatial model to obtain the mountain geological data; Step S42: Extract the mountain rock element content features and the mountain soil element content features from the mountain geological data to obtain the mountain rock element content data and the mountain soil element content data; Step S43: Perform stratified kriging interpolation on the mountain rock element content data and the mountain soil element content data to obtain the stratified spatial mountain element content data; Step S44: Integrate the stratified spatial mountain element content data and the surveyed mountain spatial model to obtain the surveyed mountain spatial element content model; Step S45: Conduct a regression analysis of the soil element content based on the surveyed mountain spatial element content model to obtain the mountain soil element content trend data; Step S46: Perform mountain soil nutrient trend integration on the mountain soil element content trend data according to the soil nutrient element rules to obtain the surveyed mountain soil nutrient trend data; Step S47: Evaluate the plain soil nutrient erosion factor on the surveyed mountain soil nutrient trend data based on the surveyed plain soil nutrient trend data to obtain the plain soil nutrient erosion factor.

8. The intelligent analysis and management method for land surveying and mapping data according to claim 7, characterized in that Step S47 is specifically as follows: Step S471: Align the surveyed plain soil nutrient trend data and the surveyed mountain soil nutrient trend data in time and space to obtain the surveyed area soil nutrient trend data; Step S472: Conduct a principal component analysis of the soil nutrient based on the surveyed area soil nutrient trend data to obtain the soil nutrient principal component data; Step S473: Construct a soil erosion model based on the land spatial data model and the soil nutrient principal component data to obtain the soil erosion model; Step S474: Calculate the soil nutrient erosion factor for the surveyed plain soil nutrient trend data and the surveyed mountain soil nutrient trend data respectively according to the soil erosion model to obtain the surveyed area plain soil nutrient erosion factor and the surveyed area mountain soil nutrient erosion factor; Step S475: Quantify the correlation between the plain soil nutrient erosion factors and the mountain soil nutrient erosion factors in the surveyed area according to the plain soil nutrient erosion factors in the surveyed area, so as to obtain the plain soil nutrient erosion factors.

9. The intelligent analysis and management method for land surveying and mapping data according to claim 1, characterized in that Step S5 specifically includes: Step S51: Conduct statistical analysis of the erosion factors based on the plain soil nutrient erosion factors, so as to obtain the soil nutrient erosion factors with high correlation and the soil nutrient erosion factors with low correlation; Step S52: Extract the distribution characteristics of the plain element content according to the plain space element content model of the surveyed plain, so as to obtain the plain soil element content distribution data; Step S53: Conduct factor spatial association according to the soil nutrient erosion factors with high correlation and the plain soil element content distribution data, so as to obtain the data of the areas where soil nutrients are easily lost; conduct factor spatial association according to the soil nutrient erosion factors with low correlation and the plain soil element content distribution data, so as to obtain the data of the areas where soil nutrients are difficult to lose; Step S54: Divide the spatial association areas of the surveyed plain space model and the surveyed mountain space model, so as to obtain the intersection area space model and the non-intersection area space model; Step S55: Divide the intersection area space of the intersection area space model according to the data of the areas where soil nutrients are easily lost, so as to obtain the model of the areas where land nutrients are easily lost; divide the intersection area space of the non-intersection area space model according to the data of the areas where soil nutrients are difficult to lose, so as to obtain the model of the areas where land nutrients are difficult to lose; Step S56: Merge the model of the areas where land nutrients are easily lost and the model of the areas where land nutrients are difficult to lose spatially, so as to obtain the model of the areas where land nutrients are lost; Step S57: Analyze the land nutrient flow reduction strategy for the model of the areas where land nutrients are lost, so as to obtain the land nutrient flow reduction strategy.

10. An intelligent analysis and management system for land surveying and mapping data, characterized in that, A land survey data intelligent analysis and management system for executing a land survey data intelligent analysis and management method as described in claim 1, the land survey data intelligent analysis and management system includes: A survey error correction module, configured to obtain land survey data, perform standardized processing of the longitude and latitude of the land survey data, so as to obtain longitude and latitude standardized survey data; correct the survey error of the longitude and latitude standardized survey data, so as to obtain enhanced land survey data; A surveyed land space modeling module, configured to perform surveyed land space modeling on the enhanced land survey data, so as to obtain a land space data model; classify the surveyed land terrain areas of the land space data model, so as to obtain a surveyed plain space model and a surveyed mountain space model; A plain soil nutrient trend analysis module, configured to extract land geological characteristics from the land survey data, so as to obtain land geological data, and perform plain soil nutrient trend analysis on the surveyed plain space model according to the land geological data, so as to obtain surveyed plain soil nutrient trend data; The mountain soil nutrition trend analysis module is used to analyze the mountain soil nutrition trend of the surveyed mountain space model based on the land geological data, so as to obtain the surveyed mountain soil nutrition trend data, and evaluate the plain soil nutrition erosion factor for the surveyed mountain soil nutrition trend data based on the surveyed plain soil nutrition trend data, so as to obtain the plain soil nutrition erosion factor; The land nutrition loss area division module is used to divide the surveyed plain space model according to the plain soil nutrition erosion factor to obtain the land nutrition loss area model, and analyze the land nutrition downflow strategy for the land nutrition loss area model to obtain the land nutrition downflow strategy.

Images