A land surveying and mapping data intelligent analysis and management system

Abstract

The present invention relates to the technical field of land surveying and mapping data analysis, and more specifically, to a land surveying and mapping data intelligent analysis and management system, which is used to solve the problem that the prior art cannot provide accurate and comprehensive land use characteristics, cannot reflect the dynamic evolution process of land use characteristics, and is not conducive to the analysis, planning and management of land use; the present invention integrates multi-dimensional data such as terrain, land use, environment and socio-economics through a feature extraction and fusion module, can provide comprehensive land use characteristics, ensure the integrity and accuracy of the analysis results, can dynamically capture the changing trends of surface slope, population density, rainfall and ambient temperature, reflect the dynamic evolution process of land use characteristics, and can be used for land use analysis, planning and management by generating a comprehensive land use feature vector, so as to provide a scientific basis for decision-making.

Description

Technical Field

[0001] The present invention relates to the technical field of land surveying and mapping data analysis, and more specifically, to a land surveying and mapping data intelligent analysis and management system. Background Art

[0002] Land is an important foundation in modern social and economic activities and a key factor in determining the composition of social and economic structures. The accuracy of land surveying and mapping directly affects the scientific nature of land development. However, in the existing technology, there are many deficiencies in the analysis of land surveying and mapping data, such as low analysis accuracy, lack of targeted rectification, and reduced rectification efficiency.

[0003] The patent application with reference publication number CN117314105A discloses a land surveying and mapping data intelligent analysis and management system, including an aerial photography module, the output end of the aerial photography module is electrically connected to the input end of the picture transmission module, and the output end of the picture transmission module is electrically connected to the input end of the picture receiving module. In the present invention, by setting a terrain planning management module, a land model construction module will process a large number of aerial photos received by the picture receiving module, and construct a land model according to the content of the pictures, so as to facilitate land division management. The special terrain marking module marks the special terrain in the land model, and the special terrain includes hillsides, ditches, ponds and other terrains. The system is used to intelligently and reasonably allocate according to the family time situation and the land surveying situation, so that each family can get a reasonable land planting area, avoiding the waste of land resources and the shortage of family arable land. However, the above-mentioned reference patent integrates terrain analysis, family information statistics and intelligent area allocation, ensures fair and effective division of land resources based on aerial photos and family conditions, and pays special attention to special terrains and difficult families. However, it cannot provide accurate and comprehensive land use characteristics, cannot reflect the dynamic evolution process of land use characteristics, is not conducive to the analysis, planning and management of land use, cannot accurately and comprehensively assess the geological disaster risks of target plots, cannot provide a scientific basis for geological disaster warning and prevention, and cannot accurately predict future land use changes, and cannot provide a scientific basis for land resource management and planning.

[0004] To this end, we propose an intelligent analysis and management system for land surveying and mapping data to address the above issues. Summary of the invention

[0005] The purpose of the present invention is to provide an intelligent analysis and management system for land surveying and mapping data, which solves the problems that the prior art cannot provide accurate and comprehensive land use characteristics, cannot reflect the dynamic evolution process of land use characteristics, is not conducive to the analysis, planning and management of land use, cannot accurately and comprehensively assess the geological disaster risks of target plots, cannot provide a scientific basis for geological disaster warning and prevention, and cannot accurately predict future land use changes, and cannot provide a scientific basis for land resource management and planning.

[0006] The purpose of the present invention is achieved through the following technical solutions: A land surveying and mapping data intelligent analysis and management system, including a data acquisition preprocessing module, a feature extraction and fusion module, a geological disaster monitoring module, a land use prediction module and a decision support module; The data collection and preprocessing module is used to collect the land surveying and mapping data in the target plot in real time and perform preprocessing operations on the collected land surveying and mapping data; The feature extraction and fusion module is used to extract land use feature data from the preprocessed land surveying and mapping data, fuse the extracted land use feature data, and generate a comprehensive land use feature vector; The geological disaster monitoring module is used to monitor the geological disaster risk assessment parameters in the target plot in real time and monitor and assess the geological disaster risk of the target plot; The land use prediction module is used to collect historical land surveying and mapping data, build a land use change prediction model, and predict the land use change of the target plot through the model; The decision support module is used to generate the optimal decision plan based on the geological hazard risk assessment results and land use change prediction results of the target plot.

[0007] As a preferred embodiment of the present invention, the specific process of the feature extraction and fusion module extracting land use feature data from land surveying and mapping data and fusing the extracted land use feature data is as follows: Acquire pre-processed land surveying and mapping data, the land surveying and mapping data include terrain signal parameters, land use parameters, environmental signal parameters and socio-economic signal parameters, the terrain signal parameters include surface elevation signals, surface slope signals and surface displacement signals, the land use parameters include land use types and vegetation coverage areas, the environmental signal parameters include ambient temperature signals, ambient humidity signals and rainfall signals, the socio-economic signal parameters include population density signals and gross domestic product signals, extract land use characteristic data from the pre-processed land surveying and mapping data, the land use characteristic data include land use types, surface slope change rate, population density change rate, vegetation coverage rate, rainfall change rate and ambient temperature change rate; The specific steps for extracting land use types are as follows: Land use types are classified according to their purpose, namely agricultural land, forest land, construction land, water area, unused land and special land. The land use types are numbered in sequence: agricultural land is numbered L1, forest land is numbered L2, construction land is numbered L3, water area is numbered L4, unused land is numbered L5 and special land is numbered L6.

[0008] As a preferred embodiment of the present invention, the specific steps of extracting the surface slope change rate are as follows: The surface slope signal S(t) is sampled and the instantaneous change of the surface slope is calculated using the differential formula: ; Where ∆S(t) represents the rate of change of the surface slope at time point t, S(t) represents the surface slope at time point t, S(t-1) represents the surface slope at time point t-1, and ∆t represents the sampling time interval; The specific steps for extracting the population density change rate are as follows: The population density signal D(t) is sampled and the instantaneous change of population density is calculated using the differential formula: ; Where ∆D(t) represents the rate of change of population density at time point t, D(t) represents the population density at time point t, and D(t-1) represents the population density at time point t-1; The specific steps for extracting vegetation coverage are as follows: Obtain the total area AD of the target plot and the vegetation coverage area AV of the target plot, and calculate the vegetation coverage rate CV of the target plot using the following formula: .

[0009] As a preferred embodiment of the present invention, the specific steps of extracting the rainfall change rate are as follows: The rainfall signal R(t) is sampled and the instantaneous change of rainfall is calculated using the differential formula: ; Where ∆R(t) represents the rate of change of rainfall at time point t, R(t) represents the rainfall at time point t, and R(t-1) represents the rainfall at time point t-1; The specific steps for extracting the ambient temperature change rate are as follows: The ambient temperature signal T(t) is sampled and the instantaneous change of the ambient temperature is calculated using the differential formula: ; Where ∆T(t) represents the rate of change of ambient temperature at time point t, T(t) represents the ambient temperature at time point t, and T(t-1) represents the ambient temperature at time point t-1; The extracted land use characteristic data, such as land use type, surface slope change rate, population density change rate, vegetation coverage rate, rainfall change rate and ambient temperature change rate, are integrated to generate a land use comprehensive characteristic vector TLT, which is expressed by the following expression: TLT=[Ln,ΔS(t),ΔD(t),CV,ΔR(t),ΔT(t)].

[0010] As a preferred embodiment of the present invention, the specific process of the geological disaster monitoring module monitoring and evaluating the geological disaster risk of the target plot is as follows: Obtaining geological disaster risk assessment parameters within the target plot, including surface elevation, surface slope, rainfall, and vegetation coverage, generating a monitoring cycle, and dividing the monitoring cycle into multiple monitoring periods; Obtain the surface elevation anomaly ratio value of the target plot in multiple monitoring periods. The surface elevation anomaly ratio value represents the ratio of the area enclosed by the line segment of the surface elevation value characteristic curve located above the preset surface elevation value characteristic curve and the preset surface elevation value characteristic curve to the area enclosed by the surface elevation value characteristic curve and the X-axis. In this way, a set A of surface elevation anomaly ratio values ​​is constructed, and then the maximum subset and the minimum subset in the set A are obtained, and the average value of the difference between the maximum subset and the minimum subset in the set A is recorded as the surface elevation anomaly risk value DGF; The surface slope anomaly multiplier value of the target plot in multiple monitoring periods is obtained. The surface slope anomaly multiplier value represents the ratio of the area enclosed by the line segment where the surface slope value characteristic curve is located above the preset surface slope value characteristic curve and the preset surface slope value characteristic curve, and then to the area enclosed by the surface slope value characteristic curve and the X-axis. In this way, a set B of surface slope anomaly multiplier values ​​is constructed, and then the maximum subset and the minimum subset in set B are obtained, and the mean of the difference between the maximum subset and the minimum subset in set B is recorded as the surface slope anomaly risk value DPF.

[0011] As a preferred embodiment of the present invention, the rainfall anomaly multiple value of the target plot in multiple monitoring periods is obtained, and the rainfall anomaly multiple value represents the ratio between the area enclosed by the line segment of the rainfall value characteristic curve located above the preset rainfall value characteristic curve and the preset rainfall value characteristic curve, and then to the area enclosed by the rainfall value characteristic curve and the X-axis, so as to construct a set C of rainfall anomaly multiple values, and then obtain the mean of the difference between the maximum subset and the minimum subset in the set C, which is recorded as the rainfall anomaly risk value JYF; The vegetation coverage anomaly multiple values ​​of the target plot in multiple monitoring periods are obtained. The vegetation coverage anomaly multiple values ​​represent the ratio of the area enclosed by the line segment of the vegetation coverage value characteristic curve located above the preset vegetation coverage value characteristic curve and the preset vegetation coverage value characteristic curve, and then to the area enclosed by the vegetation coverage value characteristic curve and the X-axis. In this way, a set D of vegetation coverage anomaly multiple values ​​is constructed, and then the mean of the difference between the maximum subset and the minimum subset in the set D is obtained and recorded as the vegetation coverage anomaly risk value ZFF.

[0012] As a preferred embodiment of the present invention, the surface elevation anomaly risk value DGF, the surface slope anomaly risk value DPF, the rainfall anomaly risk value JYF and the vegetation coverage anomaly risk value ZFF are obtained, and the geological disaster risk assessment coefficient DZP is calculated by the following formula: ; Wherein d1, d2, d3 and d4 are all preset proportional factor coefficients, d4>d3>d2>d1>0, the geological disaster risk assessment coefficient DZP is compared with the preset first geological disaster risk assessment coefficient threshold and the preset second geological disaster risk assessment coefficient threshold, and the preset first geological disaster risk assessment coefficient threshold is less than the preset second geological disaster risk assessment coefficient threshold; If DZP is less than the preset first geological disaster risk assessment coefficient threshold, it indicates that the target plot is very unlikely to have a geological disaster and is in a low-risk state; If DZP is greater than or equal to the preset first geological disaster risk assessment coefficient threshold and DZP is less than the preset second geological disaster risk assessment coefficient threshold, it indicates that the target plot has a certain risk of geological disasters and is in a medium risk state; If DZP is greater than or equal to the preset second geological hazard risk assessment coefficient threshold, it indicates that the target plot has serious geological hazard risks and is in a high-risk state.

[0013] As a preferred embodiment of the present invention, the specific process of the land use prediction module constructing a land use change prediction model and predicting the land use change of the target plot through the model is as follows: Acquire historical land surveying and mapping data, generate a collection cycle, divide the collection cycle into multiple collection periods, perform preprocessing operations on the historical land surveying and mapping data, extract land use feature data from the historical land surveying and mapping data in multiple collection periods, fuse the extracted land use feature data, and generate multiple sets of land use comprehensive feature vectors TLT; The generated land use comprehensive feature vector TLT is used as the input of the machine learning model, and the land use change matrix in the future corresponding to each set of land use comprehensive feature vector TLT is used as the output of the machine learning model. The land use change matrix in the future is used as the prediction target, and minimizing the sum of prediction errors of training data is used as the training target. The machine learning model is trained until the sum of prediction errors converges and the training is stopped to obtain the land use change prediction model.

[0014] As a preferred embodiment of the present invention, the land use change prediction model is expressed as follows: ; Among them, TLJ represents the land use change matrix at a certain time in the future, β1, β2, β3, β4 and β5 are all regression coefficients, η is the random error term, u is the label vector, and the output of u is 0 or 1, 0 means that the land use type has not changed, 1 means that the land use type has changed, and Ln represents the land use type at a certain time in the future; Real-time land surveying and mapping data is obtained, converted into the corresponding land use comprehensive feature vector TLT and input into the land use change prediction model. The real-time land use change matrix TLJ for a certain period of time in the future is obtained through the land use change prediction model.

[0015] As a preferred implementation of the present invention, the specific process of the decision support module generating the optimal decision solution is as follows: Obtain the geological hazard risk assessment results and land use change prediction results of the target plot. The geological hazard risk assessment result is the risk status of the target plot, and the land use change prediction result is whether the land use type of the target plot will change after a certain period of time in the future and the land use type of the target plot after a certain period of time in the future, and generate an optimal decision-making plan that comprehensively considers geological hazard risks and land use changes.

[0016] Compared with the prior art, the advantages of the present invention are: (1) In the present invention, the feature extraction and fusion module integrates multi-dimensional data such as terrain, land use, environment and socio-economics, and can provide comprehensive land use characteristics, ensure the integrity and accuracy of the analysis results, dynamically capture the changing trends of surface slope, population density, rainfall and ambient temperature, and reflect the dynamic evolution of land use characteristics. By generating a comprehensive land use feature vector, it can be used for land use analysis, planning and management, providing a scientific basis for decision-making; (2) In the present invention, the geological disaster monitoring module integrates multi-dimensional parameters such as surface elevation, surface slope, rainfall and vegetation coverage to comprehensively evaluate the geological disaster risk of the target plot. By dividing the monitoring period and calculating the abnormal multiple value of each parameter, the changing trend of the geological disaster risk is dynamically captured to ensure the real-time and accuracy of the evaluation. By constructing an abnormal risk value set and calculating the geological disaster risk assessment coefficient, the risk classification is performed in combination with the preset threshold, providing a scientific basis for geological disaster warning and prevention; (3) In the present invention, the land use prediction module can quickly process a large amount of historical land surveying and mapping data, and conduct training based on these data, so as to more accurately predict future land use changes. It can acquire and process the latest land surveying and mapping data in real time, provide timely prediction results, support dynamic decision-making, have high flexibility, can be adjusted and optimized according to different regions and needs, adapt to various application scenarios, and provide a scientific basis for land resource management and planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a system block diagram of Embodiment 1 of the present invention; Figure 2 This is a system block diagram of Embodiment 2 of the present invention; Figure 3 This is a logical flow diagram of the first embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will combine the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all the embodiments. All other embodiments obtained by ordinary technicians in this field without creative work based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0019] Embodiment 1: Figure 1 and Figure 3 As shown, the land surveying and mapping data intelligent analysis and management system proposed by the present invention includes a data acquisition preprocessing module, a feature extraction and fusion module, a geological disaster monitoring module, a land use prediction module and a decision support module; A data collection and preprocessing module is used to collect land surveying and mapping data in the target plot in real time and perform preprocessing operations on the collected land surveying and mapping data. The preprocessing operations include but are not limited to data cleaning, filtering and normalization. The data collection preprocessing module significantly improves the quality and analysis efficiency of land surveying and mapping data through operations such as data cleaning, filtering and normalization; cleaning removes erroneous and incomplete records, improving the accuracy and consistency of data; filtering reduces noise interference, enhances feature recognition and improves data visual effects; normalization unifies the data range of different dimensions, accelerates algorithm convergence and avoids numerical bias; these preprocessing steps jointly ensure the high quality of data and provide a solid foundation for accurate land planning, resource management and environmental protection decisions.

[0020] The feature extraction and fusion module is used to extract land use feature data from the preprocessed land surveying and mapping data, fuse the extracted land use feature data, and generate a comprehensive land use feature vector; The specific process of the feature extraction and fusion module extracting land use feature data from land surveying and mapping data and fusing the extracted land use feature data is as follows: Acquire pre-processed land surveying and mapping data, the land surveying and mapping data include terrain signal parameters, land use parameters, environmental signal parameters and socio-economic signal parameters, the terrain signal parameters include surface elevation signals, surface slope signals and surface displacement signals, the land use parameters include land use types and vegetation coverage areas, the environmental signal parameters include ambient temperature signals, ambient humidity signals and rainfall signals, the socio-economic signal parameters include population density signals and gross domestic product signals, extract land use characteristic data from the pre-processed land surveying and mapping data, the land use characteristic data include land use types, surface slope change rate, population density change rate, vegetation coverage rate, rainfall change rate and ambient temperature change rate; The specific steps for extracting land use types are as follows: The land use types are classified according to the purpose of the land, namely agricultural land, forest land, construction land, water area, unused land and special land. The land use types are numbered in sequence, with agricultural land numbered as L1, forest land numbered as L2, construction land numbered as L3, water area numbered as L4, unused land numbered as L5, and special land numbered as L6; The specific steps for extracting the surface slope change rate are as follows: The surface slope signal S(t) is sampled and the instantaneous change of the surface slope is calculated using the differential formula: ; Where ∆S(t) represents the rate of change of the surface slope at time point t, S(t) represents the surface slope at time point t, S(t-1) represents the surface slope at time point t-1, and ∆t represents the sampling time interval; The specific steps for extracting the population density change rate are as follows: The population density signal D(t) is sampled and the instantaneous change of population density is calculated using the differential formula: ; Where ∆D(t) represents the rate of change of population density at time point t, D(t) represents the population density at time point t, and D(t-1) represents the population density at time point t-1; The specific steps for extracting vegetation coverage are as follows: Obtain the total area AD of the target plot and the vegetation coverage area AV of the target plot, and calculate the vegetation coverage rate CV of the target plot using the following formula: ; The specific steps for extracting the rainfall change rate are as follows: The rainfall signal R(t) is sampled and the instantaneous change of rainfall is calculated using the differential formula: ; Where ∆R(t) represents the rate of change of rainfall at time point t, R(t) represents the rainfall at time point t, and R(t-1) represents the rainfall at time point t-1; The specific steps for extracting the ambient temperature change rate are as follows: The ambient temperature signal T(t) is sampled and the instantaneous change of the ambient temperature is calculated using the differential formula: ; Where ∆T(t) represents the rate of change of ambient temperature at time point t, T(t) represents the ambient temperature at time point t, and T(t-1) represents the ambient temperature at time point t-1; The extracted land use characteristic data, such as land use type, surface slope change rate, population density change rate, vegetation coverage rate, rainfall change rate and ambient temperature change rate, are integrated to generate a land use comprehensive characteristic vector TLT, which is expressed by the following expression: TLT=[Ln,ΔS(t),ΔD(t),CV,ΔR(t),ΔT(t)]; Through the feature extraction and fusion module, multi-dimensional data such as terrain, land use, environment and socio-economy are integrated to provide comprehensive land use characteristics, ensure the integrity and accuracy of the analysis results, dynamically capture the changing trends of surface slope, population density, rainfall and ambient temperature, and reflect the dynamic evolution of land use characteristics. By generating a comprehensive land use feature vector, it can be used for land use analysis, planning and management, providing a scientific basis for decision-making.

[0021] The geological disaster monitoring module is used to monitor the geological disaster risk assessment parameters in the target plot in real time and monitor and assess the geological disaster risk of the target plot; The specific process of the geological disaster monitoring module to monitor and evaluate the geological disaster risks of the target plot is as follows: Obtaining geological disaster risk assessment parameters within the target plot, including surface elevation, surface slope, rainfall, and vegetation coverage, generating a monitoring cycle, and dividing the monitoring cycle into multiple monitoring periods; Obtain the surface elevation anomaly ratio value of the target plot in multiple monitoring periods. The surface elevation anomaly ratio value represents the ratio of the area enclosed by the line segment of the surface elevation value characteristic curve located above the preset surface elevation value characteristic curve and the preset surface elevation value characteristic curve to the area enclosed by the surface elevation value characteristic curve and the X-axis. In this way, a set A of surface elevation anomaly ratio values ​​is constructed, and then the maximum subset and the minimum subset in the set A are obtained, and the average value of the difference between the maximum subset and the minimum subset in the set A is recorded as the surface elevation anomaly risk value DGF; Obtain the surface slope anomaly multiple value of the target plot in multiple monitoring periods. The surface slope anomaly multiple value represents the ratio of the area enclosed by the line segment of the surface slope value characteristic curve located above the preset surface slope value characteristic curve and the preset surface slope value characteristic curve to the area enclosed by the surface slope value characteristic curve and the X-axis. In this way, a set B of surface slope anomaly multiple values ​​is constructed, and then the maximum subset and the minimum subset in the set B are obtained, and the average value of the difference between the maximum subset and the minimum subset in the set B is recorded as the surface slope anomaly risk value DPF; Obtain the rainfall anomaly multiple value of the target plot in multiple monitoring periods. The rainfall anomaly multiple value represents the ratio of the area enclosed by the line segment of the rainfall value characteristic curve located above the preset rainfall value characteristic curve and the preset rainfall value characteristic curve to the area enclosed by the rainfall value characteristic curve and the X-axis. In this way, a set C of rainfall anomaly multiple values ​​is constructed, and then the mean of the difference between the maximum subset and the minimum subset in the set C is obtained and recorded as the rainfall anomaly risk value JYF; Obtain the abnormal multiple value of vegetation coverage rate of the target plot in multiple monitoring periods. The abnormal multiple value of vegetation coverage rate represents the ratio of the area enclosed by the line segment of the vegetation coverage rate value characteristic curve located above the preset vegetation coverage rate value characteristic curve and the preset vegetation coverage rate value characteristic curve, and then to the area enclosed by the vegetation coverage rate value characteristic curve and the X-axis, so as to construct a set D of abnormal multiple values ​​of vegetation coverage rate, and then obtain the mean of the difference between the maximum subset and the minimum subset in the set D, which is recorded as the abnormal risk value ZFF of vegetation coverage rate; The surface elevation anomaly risk value DGF, surface slope anomaly risk value DPF, rainfall anomaly risk value JYF and vegetation coverage anomaly risk value ZFF are obtained, and the geological disaster risk assessment coefficient DZP is calculated by the following formula: ; Wherein d1, d2, d3 and d4 are all preset proportional factor coefficients, d4>d3>d2>d1>0, the geological disaster risk assessment coefficient DZP is compared with the preset first geological disaster risk assessment coefficient threshold and the preset second geological disaster risk assessment coefficient threshold, and the preset first geological disaster risk assessment coefficient threshold is less than the preset second geological disaster risk assessment coefficient threshold; If DZP is less than the preset first geological disaster risk assessment coefficient threshold, it indicates that the target plot is very unlikely to have a geological disaster and is in a low-risk state; If DZP is greater than or equal to the preset first geological disaster risk assessment coefficient threshold and DZP is less than the preset second geological disaster risk assessment coefficient threshold, it indicates that the target plot has a certain risk of geological disasters and is in a medium risk state; If DZP is greater than or equal to the preset second geological disaster risk assessment coefficient threshold, it indicates that the target plot has serious geological disaster risks and is in a high-risk state; Through the geological disaster monitoring module, multi-dimensional parameters such as surface elevation, surface slope, rainfall and vegetation coverage are integrated to comprehensively evaluate the geological disaster risk of the target plot. By dividing the monitoring period and calculating the abnormal multiple value of each parameter, the changing trend of geological disaster risk is dynamically captured to ensure the real-time and accuracy of the assessment. By constructing an abnormal risk value set and calculating the geological disaster risk assessment coefficient, risk classification is carried out in combination with preset thresholds, providing a scientific basis for geological disaster early warning and prevention.

[0022] The land use prediction module is used to collect historical land surveying and mapping data, build a land use change prediction model, and predict the land use change of the target plot through the model; The specific process of the land use prediction module to construct a land use change prediction model and predict the land use change of the target plot through the model is as follows: Acquire historical land surveying and mapping data, generate a collection cycle, divide the collection cycle into multiple collection periods, perform preprocessing operations on the historical land surveying and mapping data, extract land use feature data from the historical land surveying and mapping data in multiple collection periods, fuse the extracted land use feature data, and generate multiple sets of land use comprehensive feature vectors TLT; The generated land use comprehensive feature vector TLT is used as the input of the machine learning model, and the land use change matrix corresponding to each set of land use comprehensive feature vector TLT in the future is used as the output of the machine learning model. The land use change matrix in the future is used as the prediction target, and the sum of the prediction errors of the training data is minimized as the training target. The machine learning model is trained until the sum of the prediction errors reaches convergence and the training is stopped to obtain a land use change prediction model. The land use change prediction model is expressed as follows: ; Among them, TLJ represents the land use change matrix at a certain time in the future, β1, β2, β3, β4 and β5 are all regression coefficients, η is the random error term, u is the label vector, and the output of u is 0 or 1, 0 means that the land use type has not changed, 1 means that the land use type has changed, and Ln represents the land use type at a certain time in the future; Obtain real-time land surveying and mapping data, convert it into the corresponding land use comprehensive feature vector TLT and input it into the land use change prediction model, and obtain the real-time land use change matrix TLJ for a certain period of time in the future through the land use change prediction model; The land use prediction module can quickly process a large amount of historical land surveying and mapping data, and conduct training based on these data, so as to more accurately predict future land use changes. It can obtain and process the latest land surveying and mapping data in real time, provide timely prediction results, support dynamic decision-making, and has a high degree of flexibility. It can be adjusted and optimized according to different regions and needs, adapt to a variety of application scenarios, and provide a scientific basis for land resource management and planning.

[0023] Embodiment 2: The technical solution of the embodiment of the present invention is different from that of embodiment 1 in that: like Figure 2 As shown, the decision support module is used to generate the optimal decision plan based on the geological disaster risk assessment results and land use change prediction results of the target plot; The specific process of the decision support module generating the optimal decision solution is as follows: Obtain the geological hazard risk assessment results and land use change prediction results of the target plot. The geological hazard risk assessment results are the risk status of the target plot, and the land use change prediction results are whether the land use type of the target plot will change and the land use type of the target plot after a certain period of time in the future. Generate an optimal decision plan that comprehensively considers geological hazard risks and land use changes to ensure the safety and sustainable development of the target plot. The specific contents of the optimal decision plan are: Low-risk plots: Agricultural land: continue to be used for agricultural production, and appropriately increase investment in agricultural infrastructure; Forest land: Strengthen forest protection and management to prevent illegal logging; Construction land: moderate development to ensure building safety; Water areas: protect water resources and prevent pollution; Unused land: reasonably developed or protected according to future planning; Special land use: formulate corresponding protection or development strategies according to specific uses; Medium risk plots: Agricultural land: adjust the planting structure and choose crops with strong disaster resistance; Forest land: Strengthen forest fire prevention and pest and disease control; Construction land: Strengthen the earthquake-resistant design of buildings and conduct regular safety inspections; Water areas: Strengthen the construction of flood control facilities to prevent water pollution; Unused land: restrict development and give priority to ecological restoration; Special land use: Strengthen safety management and formulate emergency plans; High-risk plots: Agricultural land: reduce or stop agricultural production and convert it into ecological land; Forest land: Strengthen forest protection and ecological restoration; Construction land: restrict or prohibit development and conduct geological disaster control; Water areas: Strengthen flood prevention and pollution control, and relocate water bodies when necessary; Unused land: development is prohibited and ecological restoration is carried out; Special land use: strictly restrict development, relocate or close if necessary; The decision support module can comprehensively consider geological hazard risks and land use changes, generate scientific and comprehensive decision-making plans, ensure the safety and sustainable development of the target plots, effectively assess geological hazard risks, optimize land resource allocation, and quickly process and analyze large amounts of data to improve decision-making efficiency. It is highly flexible and can be adjusted and optimized according to different regions and needs, adapt to a variety of application scenarios, and provide a scientific basis for land resource management and planning.

[0024] The above are only preferred specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solutions and improved concepts of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A land surveying and mapping data intelligent analysis and management system, characterized in that: It includes data collection and preprocessing module, feature extraction and fusion module, geological disaster monitoring module, land use prediction module and decision support module; The data collection and preprocessing module is used to collect the land surveying and mapping data in the target plot in real time and perform preprocessing operations on the collected land surveying and mapping data; The feature extraction and fusion module is used to extract land use feature data from the preprocessed land surveying and mapping data, fuse the extracted land use feature data, and generate a comprehensive land use feature vector; The geological disaster monitoring module is used to monitor the geological disaster risk assessment parameters in the target plot in real time and monitor and assess the geological disaster risk of the target plot; The land use prediction module is used to collect historical land surveying and mapping data, build a land use change prediction model, and predict the land use change of the target plot through the model; The decision support module is used to generate the optimal decision plan based on the geological hazard risk assessment results and land use change prediction results of the target plot.

2. The land surveying and mapping data intelligent analysis and management system according to claim 1, characterized in that: The specific process of the feature extraction and fusion module extracting land use feature data from land surveying and mapping data and fusing the extracted land use feature data is as follows: Acquire pre-processed land surveying and mapping data, the land surveying and mapping data include terrain signal parameters, land use parameters, environmental signal parameters and socio-economic signal parameters, the terrain signal parameters include surface elevation signals, surface slope signals and surface displacement signals, the land use parameters include land use types and vegetation coverage areas, the environmental signal parameters include ambient temperature signals, ambient humidity signals and rainfall signals, the socio-economic signal parameters include population density signals and gross domestic product signals, extract land use characteristic data from the pre-processed land surveying and mapping data, the land use characteristic data include land use types, surface slope change rate, population density change rate, vegetation coverage rate, rainfall change rate and ambient temperature change rate; The specific steps for extracting land use types are as follows: Land use types are classified according to their purpose, namely agricultural land, forest land, construction land, water area, unused land and special land. The land use types are numbered in sequence: agricultural land is numbered L1, forest land is numbered L2, construction land is numbered L3, water area is numbered L4, unused land is numbered L5 and special land is numbered L6.

3. The land surveying and mapping data intelligent analysis and management system according to claim 2, characterized in that: The specific steps for extracting the surface slope change rate are as follows: The surface slope signal S(t) is sampled and the instantaneous change of the surface slope is calculated using the differential formula: ； Where ∆S(t) represents the rate of change of the surface slope at time point t, S(t) represents the surface slope at time point t, S(t-1) represents the surface slope at time point t-1, and ∆t represents the sampling time interval; The specific steps for extracting the population density change rate are as follows: The population density signal D(t) is sampled and the instantaneous change of population density is calculated using the differential formula: ； Where ∆D(t) represents the rate of change of population density at time point t, D(t) represents the population density at time point t, and D(t-1) represents the population density at time point t-1; The specific steps for extracting vegetation coverage are as follows: Obtain the total area AD of the target plot and the vegetation coverage area AV of the target plot, and calculate the vegetation coverage rate CV of the target plot using the following formula: 。 4. The land surveying and mapping data intelligent analysis and management system according to claim 3, characterized in that: The specific steps for extracting the rainfall change rate are as follows: The rainfall signal R(t) is sampled and the instantaneous change of rainfall is calculated using the differential formula: ； Where ∆R(t) represents the rate of change of rainfall at time point t, R(t) represents the rainfall at time point t, and R(t-1) represents the rainfall at time point t-1; The specific steps for extracting the ambient temperature change rate are as follows: The ambient temperature signal T(t) is sampled and the instantaneous change of the ambient temperature is calculated using the differential formula: ； Where ∆T(t) represents the rate of change of ambient temperature at time point t, T(t) represents the ambient temperature at time point t, and T(t-1) represents the ambient temperature at time point t-1; The extracted land use characteristic data, such as land use type, surface slope change rate, population density change rate, vegetation coverage rate, rainfall change rate and ambient temperature change rate, are integrated to generate a land use comprehensive characteristic vector TLT, which is expressed by the following expression: TLT=[Ln,ΔS(t),ΔD(t),CV,ΔR(t),ΔT(t)].

5. The land surveying and mapping data intelligent analysis and management system according to claim 1, characterized in that: The specific process of the geological disaster monitoring module to monitor and evaluate the geological disaster risk of the target plot is as follows: Obtaining geological disaster risk assessment parameters within the target plot, including surface elevation, surface slope, rainfall, and vegetation coverage, generating a monitoring cycle, and dividing the monitoring cycle into multiple monitoring periods; Obtain the surface elevation anomaly ratio value of the target plot in multiple monitoring periods. The surface elevation anomaly ratio value represents the ratio of the area enclosed by the line segment of the surface elevation value characteristic curve located above the preset surface elevation value characteristic curve and the preset surface elevation value characteristic curve to the area enclosed by the surface elevation value characteristic curve and the X-axis. In this way, a set A of surface elevation anomaly ratio values ​​is constructed, and then the maximum subset and the minimum subset in the set A are obtained, and the average value of the difference between the maximum subset and the minimum subset in the set A is recorded as the surface elevation anomaly risk value DGF; The surface slope anomaly multiplier value of the target plot in multiple monitoring periods is obtained. The surface slope anomaly multiplier value represents the ratio of the area enclosed by the line segment where the surface slope value characteristic curve is located above the preset surface slope value characteristic curve and the preset surface slope value characteristic curve, and then to the area enclosed by the surface slope value characteristic curve and the X-axis. In this way, a set B of surface slope anomaly multiplier values ​​is constructed, and then the maximum subset and the minimum subset in set B are obtained, and the mean of the difference between the maximum subset and the minimum subset in set B is recorded as the surface slope anomaly risk value DPF.

6. The land surveying and mapping data intelligent analysis and management system according to claim 5, characterized in that: Obtain the rainfall anomaly multiple value of the target plot in multiple monitoring periods. The rainfall anomaly multiple value represents the ratio of the area enclosed by the line segment of the rainfall value characteristic curve located above the preset rainfall value characteristic curve and the preset rainfall value characteristic curve to the area enclosed by the rainfall value characteristic curve and the X-axis. In this way, a set C of rainfall anomaly multiple values ​​is constructed, and then the mean of the difference between the maximum subset and the minimum subset in the set C is obtained and recorded as the rainfall anomaly risk value JYF; The vegetation coverage anomaly multiple values ​​of the target plot in multiple monitoring periods are obtained. The vegetation coverage anomaly multiple values ​​represent the ratio of the area enclosed by the line segment of the vegetation coverage value characteristic curve located above the preset vegetation coverage value characteristic curve and the preset vegetation coverage value characteristic curve, and then to the area enclosed by the vegetation coverage value characteristic curve and the X-axis. In this way, a set D of vegetation coverage anomaly multiple values ​​is constructed, and then the mean of the difference between the maximum subset and the minimum subset in the set D is obtained and recorded as the vegetation coverage anomaly risk value ZFF.

7. The land surveying and mapping data intelligent analysis and management system according to claim 6, characterized in that: The surface elevation anomaly risk value DGF, surface slope anomaly risk value DPF, rainfall anomaly risk value JYF and vegetation coverage anomaly risk value ZFF are obtained, and the geological disaster risk assessment coefficient DZP is calculated by the following formula: ； Wherein d1, d2, d3 and d4 are all preset proportional factor coefficients, d4>d3>d2>d1>0, the geological disaster risk assessment coefficient DZP is compared with the preset first geological disaster risk assessment coefficient threshold and the preset second geological disaster risk assessment coefficient threshold, and the preset first geological disaster risk assessment coefficient threshold is less than the preset second geological disaster risk assessment coefficient threshold; If DZP is less than the preset first geological disaster risk assessment coefficient threshold, it indicates that the target plot is very unlikely to have a geological disaster and is in a low-risk state; If DZP is greater than or equal to the preset first geological disaster risk assessment coefficient threshold and DZP is less than the preset second geological disaster risk assessment coefficient threshold, it indicates that the target plot has a certain risk of geological disasters and is in a medium risk state; If DZP is greater than or equal to the preset second geological hazard risk assessment coefficient threshold, it indicates that the target plot has serious geological hazard risks and is in a high-risk state.

8. The land surveying and mapping data intelligent analysis and management system according to claim 1, characterized in that: The specific process of the land use prediction module constructing a land use change prediction model and predicting the land use change of the target plot through the model is as follows: Acquire historical land surveying and mapping data, generate a collection cycle, divide the collection cycle into multiple collection periods, perform preprocessing operations on the historical land surveying and mapping data, extract land use feature data from the historical land surveying and mapping data in multiple collection periods, fuse the extracted land use feature data, and generate multiple sets of land use comprehensive feature vectors TLT; The generated land use comprehensive feature vector TLT is used as the input of the machine learning model, and the land use change matrix in the future corresponding to each set of land use comprehensive feature vector TLT is used as the output of the machine learning model. The land use change matrix in the future is used as the prediction target, and minimizing the sum of prediction errors of training data is used as the training target. The machine learning model is trained until the sum of prediction errors converges and the training is stopped to obtain the land use change prediction model.

9. The land surveying and mapping data intelligent analysis and management system according to claim 8, characterized in that: The land use change prediction model is expressed as follows: ； Among them, TLJ represents the land use change matrix at a certain time in the future, β1, β2, β3, β4 and β5 are all regression coefficients, η is the random error term, u is the label vector, and the output of u is 0 or 1, 0 means that the land use type has not changed, 1 means that the land use type has changed, and Ln represents the land use type at a certain time in the future; Real-time land surveying and mapping data is obtained, converted into the corresponding land use comprehensive feature vector TLT and input into the land use change prediction model. The real-time land use change matrix TLJ for a certain period of time in the future is obtained through the land use change prediction model.

10. The land surveying and mapping data intelligent analysis and management system according to claim 1, characterized in that: The specific process of the decision support module generating the optimal decision solution is as follows: Obtain the geological hazard risk assessment results and land use change prediction results of the target plot. The geological hazard risk assessment result is the risk status of the target plot, and the land use change prediction result is whether the land use type of the target plot will change after a certain period of time in the future and the land use type of the target plot after a certain period of time in the future, and generate an optimal decision-making plan that comprehensively considers geological hazard risks and land use changes.

Images