Intelligent analysis and decision-making system for surveying and mapping geographic information data

Abstract

The invention discloses an intelligent analysis and decision-making system for surveying and mapping geographic information data, belongs to the technical field of intelligent analysis and decision-making systems, and aims to clean and preprocess acquired data, standardize the data and enhance the standardized data through a confidence judgment optimization module. Performing multi-source data fusion on the enhanced data through a multi-source data fusion module, fusing the model, fusing logistic regression and a support vector machine model, and evaluating and monitoring the fused model; and outputting the optimized confidence to a comprehensive evaluation module. The confidence values of the point, line, surface and volume data can be accurately output. Therefore, a quantitative basis is provided for judging the reliability of the data, the high-confidence data shows that the model has high accuracy and credibility for judging the classification or position of the data, and the technical problem that the precision of an analysis structure is poor due to the prominent data island phenomenon is solved.

Description

Technical Field

[0001] The present invention relates to an intelligent analysis and decision-making system, in particular to an intelligent analysis and decision-making system for surveying and mapping geographic information data, and belongs to the technical field of intelligent analysis and decision-making systems. Background Art

[0002] In the prior art, when collecting data, UAV images, remote sensing, and LiDAR are used to collect geographic information data and transmit them to the data collection module. Although there are many types and methods of collecting data, the data island phenomenon is prominent, resulting in poor accuracy of the analysis structure. One of the specific problems is that in the process of defining the general feature classes of points, lines, surfaces, and volumes, and extending the attribute fields of feature categories, confidence, and data sources, the confidence is used to judge the reliability or accuracy of the points, lines, surfaces, and volumes. However, because the data used to calculate the confidence itself is biased, noisy, or incomplete, even if the confidence calculation method is correct, the confidence obtained cannot accurately reflect the actual situation of the points, lines, surfaces, and volumes. Different machine learning models or algorithms calculate different confidence levels, and the models themselves have overfitting and underfitting problems, which affect the reliability of confidence levels. In complex geographical environments or scenarios where multiple factors interact, a single confidence index cannot fully and accurately reflect all situations of points, lines, surfaces, and volumes. Therefore, an intelligent analysis and decision-making system for surveying and mapping geographic information data is designed to solve the above problems. Summary of the invention

[0003] The main purpose of the present invention is to provide a surveying and mapping geographic information data intelligent analysis and decision-making system.

[0004] The purpose of the present invention can be achieved by adopting the following technical solutions: An intelligent analysis and decision-making system for surveying and mapping geographic information data includes a data acquisition module for collecting data on geographic information that needs to be surveyed and mapped; Data preprocessing module, used to clean the collected data; The feature extraction module is used to extract points, lines, surfaces, volumes, extended attribute fields, feature categories, confidence levels, and data sources from the data processed by the data preprocessing module; Model training module, used to train various machine learning models on the extracted feature data; It also includes a confidence judgment optimization module, which is used to judge and optimize the confidence of the point, line, surface, and volume data extracted by the feature extraction module and the data trained by the model training module, and output the optimized confidence value of each data object; The reliability judgment optimization module includes a multi-source data fusion module; The multi-source data fusion module fuses the coordinate transformation formula with the affine transformation formula, processes the data extracted by the feature extraction module through the fused formula, and then inputs it into the model training module; The comprehensive evaluation module combines confidence judgment results, domain knowledge and rules, and multi-indicator comprehensive evaluation to conduct a comprehensive evaluation and analysis of the data.

[0005] Preferably, the judgment method of the confidence judgment optimization module specifically includes the following steps: S11: Cleaning and preprocessing the acquired data; S12: Standardize the data; S13: Perform data enhancement processing on the standardized data; S14: performing multi-source data fusion on the data enhanced in S13 through a multi-source data fusion module; S15: Fusion of models, fusion of logistic regression and support vector machine models; S16: Evaluate and monitor the fused model; S17: Output the optimized confidence level to the comprehensive evaluation module.

[0006] Preferably, in S11, the outlier detection is mainly cleaned, specifically using 3 The principle is to process point, line, surface and volume data using the following formula to standardize the data: ; in, is the standardized value; is the original value; is the mean; is the standard deviation.

[0007] Preferably, in S13, the following formula is used to enhance the data: , the rotated point The coordinate calculation formula is: ; in, are the center coordinates of the image.

[0008] Preferably, in S14, the seven-parameter Bursa model is integrated and derived with the affine transformation formula to perform multi-source data fusion; First, convert the seven-parameter Bursa model to obtain the spatial coordinates , and then project it onto the plane to get the plane coordinates , and then perform affine transformation on the plane coordinates to obtain the final coordinates .

[0009] Preferably, the conversion to the seven-parameter Bursa model is: ; The space coordinates Transform to plane coordinates by projection ; The specific projection function used is: ; ; Finally, perform an affine transformation: ; The fused formula is: .

[0010] Preferably, before S15 model fusion, it also includes model selection and optimization processing; The gradient descent formula for updating weights using logistic regression is: ; in, It is weights; α is the learning rate; J(w) is the loss function, .

[0011] Preferably, the S15 model fusion specifically includes assuming that there are a logistic regression model LR and a support vector machine model SVM, and for the input x, their prediction probabilities are respectively and , the prediction probability formula after fusion is: ; Preferably, S16 specifically includes evaluating and monitoring the fused model using the following formula: Accuracy ; Among them, TP is a true positive example; TN is a true negative example; FP is a false positive; FN is a false negative example.

[0012] Preferably, S17 specifically includes establishing a comprehensive evaluation level and introducing domain knowledge and rules; According to domain knowledge, river line features should be continuous and have consistent flow directions. If a line feature has breakpoints or inconsistent flow directions, its confidence level should be reduced; Let the original confidence be , if there is a breakpoint, the confidence level is adjusted to ; If the flow direction is inconsistent, the confidence is adjusted to ; A multi-index comprehensive evaluation is adopted, combining surface feature classification with boundary roughness and classification confidence; Assume that the classification confidence of the surface feature is The boundary roughness is R in the range of 0-1. The larger the value, the rougher the boundary. The confidence of the comprehensive evaluation ,in, is the weight .

[0013] Beneficial technical effects of the present invention: The present invention provides an intelligent analysis and decision-making system for surveying and mapping geographic information data. The system uses a confidence judgment optimization module to clean and preprocess the acquired data, standardize the data, enhance the data after standardization, fuse the enhanced data through a multi-source data fusion module, fuse the model, fuse the logistic regression and support vector machine models, evaluate and monitor the fused model, and output the optimized confidence to the comprehensive evaluation module to achieve the construction of machine learning models such as logistic regression. By learning and training the extracted rich features, the confidence values ​​of point, line, surface, and volume data can be accurately output. This provides a quantitative basis for judging the reliability of data. High confidence data indicates that the model has high accuracy and credibility in its classification or position judgment, which reduces the prominent data island phenomenon and the technical problem that the accuracy of the analysis structure is relatively poor. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 A system diagram of a preferred embodiment of a surveying and mapping geographic information data intelligent analysis and decision-making system according to the present invention; Figure 2 The present invention is a flowchart of a credibility judgment optimization module according to a preferred embodiment of a surveying and mapping geographic information data intelligent analysis and decision-making system. DETAILED DESCRIPTION

[0015] In order to make the technical solution of the present invention more clear and specific to those skilled in the art, the present invention is further described in detail below in conjunction with embodiments and drawings, but the implementation manner of the present invention is not limited thereto.

[0016] When conducting intelligent analysis and decision-making on surveying and mapping geographic information data, it is necessary to first collect the geographic information data that needs to be surveyed and mapped; In the prior art, when collecting data, the geographic information data is collected and transmitted to the data collection module by using drone images, remote sensing, and LiDAR. Although there are many types and methods of collecting data, the data island phenomenon is prominent, resulting in poor accuracy of the analysis structure. The present invention reduces the problem of data islands by fusing the data of drone images, remote sensing, and LiDAR. The following operations are performed through the data preprocessing module: Establishing a base layer to unify spatial and temporal benchmarks; Adopts WGS84 geographic coordinate system as the benchmark and supports dynamic conversion to UTM projection; The data collection time is recorded uniformly and multi-temporal data overlay analysis is supported.

[0017] Establish data layer and use structured description of multi-source data; Through the feature extraction module, the common feature classes of points, lines, surfaces and volumes are defined, and the attribute fields of feature categories, confidence levels and data sources are extended; The model training module is used to train various machine learning models on the extracted feature data.

[0018] In the process of defining the general feature classes of points, lines, surfaces, and volumes, and extending the attribute fields of feature categories, confidence, and data sources, confidence is used to judge the reliability or accuracy of points, lines, surfaces, and volumes. However, because the data used to calculate the confidence itself is biased, noisy, or incomplete, even if the confidence calculation method is correct, the obtained confidence cannot accurately reflect the actual situation of the points, lines, surfaces, and volumes. Different machine learning models or algorithms calculate different confidence levels, and the models themselves have overfitting and underfitting problems, which affect the reliability of confidence levels. In complex geographical environments or scenarios where multiple factors interact, a single confidence index cannot fully and accurately reflect all situations of points, lines, surfaces, and volumes; Therefore, the method for solving the above problem by using the confidence judgment optimization module in the present invention is as follows: First, clean and preprocess the acquired data; Specifically include outlier detection; The coordinates of the point data use 3 Principle formula: For a set of point coordinate data, assume it is a one-dimensional coordinate x, and first calculate the mean: , standard deviation ; The outlier judgment conditions are: or .

[0019] Example 1: Assuming that there is a point with coordinate data x=[1,2,3,4,100], calculate the mean .

[0020] Calculate standard deviation .

[0021] Outlier judgment: 1<22-3×39.01 does not hold, <22-3×39.01 does not hold, 3<22-3×39.01 does not hold, 4<22-3×39.01 does not hold, 100>22+3×39.01 does not hold, and 100 here is obviously an outlier.

[0022] The coordinates of the line data use 3 Principle formula: For a coordinate component x-coordinate or y-coordinate in the line data, suppose it contains n data points, which are Then the mean of the coordinate component is The calculation formula is: first calculate the mean , standard deviation ; The outlier judgment conditions are: or .

[0023] The coordinates of the surface data use 3 Principle formula: Extract the x-coordinate and y-coordinate of all points from the surface data, and record them as and Where n is the number of points in the surface data; Calculate the mean: The mean of the x-coordinates : ; The mean of the y coordinates : ; Calculate the standard deviation: The standard deviation of the x-coordinates ; The standard deviation of the y coordinates ; Outlier judgment: For the x coordinate, if or ,but The corresponding point abnormal point; For the y coordinate, if or ,but The corresponding point is anomaly point.

[0024] The coordinates of the volume data use 3 Principle formula: Extract the x-coordinate, y-coordinate, and z-coordinate of all points from the volume data and record them as , , Where n is the number of points in the surface data; Calculate the mean: The mean of the x-coordinates ; The mean of the y coordinates ; The mean of the z coordinates ; Calculate the standard deviation: ; The standard deviation of the y coordinates ; The standard deviation of the z coordinates ; Outlier judgment: For the x-coordinate, if or ,but The corresponding point abnormal point; For the y coordinate, if or ,but The corresponding point abnormal point; For the z coordinate, if or ,but The corresponding point is anomaly point.

[0025] The data was standardized and the following formula was used: ,in is the standardized value, is the original value, is the mean, is the standard deviation.

[0026] Embodiment 2: For the above x=[1,2,3,4,100]; (Calculated ); .

[0027] Perform data enhancement on the standardized data; , the rotated point The coordinate calculation formula is: ; in, are the center coordinates of the image.

[0028] Perform multi-source data fusion on the enhanced data; The present invention adopts a multi-source data fusion module to integrate and derive the seven-parameter Bursa model and the affine transformation formula: Let's observe first: The seven-parameter Bursa model formula is: ; in, are the transformed coordinates, is the original coordinate, m is the scale change parameter, is the rotation parameter, is the translation parameter.

[0029] The affine transformation formula is: ; in, are the original coordinates, are the transformed coordinates, and a, b, c, d, e, and f are the affine transformation parameters.

[0030] The idea of ​​affine transformation is introduced into coordinate transformation, especially in the transformation from geodetic coordinates to plane coordinates. Based on the seven-parameter Bursa model, the affine transformation in the plane is further considered to adapt to more local deformation situations.

[0031] Assume that the seven-parameter Bursa model is transformed first to obtain the spatial coordinates , and then project it onto the plane to get the plane coordinates , and then perform affine transformation on the plane coordinates to obtain the final coordinates .

[0032] Conversion to the seven-parameter Bursa model: ; The space coordinates Transform to plane coordinates by projection Taking Gaussian projection as an example, its formula is relatively complicated, so it is simplified here as the projection function , ; Finally, perform an affine transformation: ; Combining the above steps, we get the fused formula: ; The integrated formula not only takes into account the transformation between geodetic coordinate systems, but also can further adjust the plane coordinates through affine transformation to adapt to local terrain changes or projection deformation, thereby improving the accuracy of coordinate transformation.

[0033] In practical applications, appropriate parameters and projection methods are selected according to specific circumstances, and in some cases the calculation process can be simplified. For example, if only simple translation and scaling are required, the affine transformation parameters can be adjusted without the need for complex seven-parameter calculations.

[0034] Next, we will select and optimize the model; The present invention adopts the gradient descent of logistic regression to update the weight formula: ,in is the jth weight, α is the learning rate, and J(w) is the loss function (logarithmic loss function .

[0035] Example 3: Assume there is only one feature x, y=[1,0]x=[1,2], initial weight w=[0], and learning rate α=0.1.

[0036] calculate .

[0037] Loss Function .

[0038] Computing Gradients , .

[0039] Update weight w=0-0.1×0.25=-0.025.

[0040] Then the model is fused, and the fusion formula of logistic regression and support vector machine model is as follows: Assume that there are logistic regression model LR and support vector machine model SVM. For input x, their prediction probabilities are and , the predicted probability after fusion .

[0041] Example 4: Assume that the prediction probability of the logistic regression model for input x is pLR(x)=0.6, and the prediction probability of the support vector machine model for input x is psvM(x)=0.4. The fused prediction probability .

[0042] The present invention uses a comprehensive evaluation module to evaluate and monitor the fused model using the following formula: Accuracy , where TP is a true positive, TN is a true negative, FP is a false positive, and FN is a false negative.

[0043] Example 5: Assuming TP=80, TN=70, FP=10, FN=20, then .

[0044] Establish a comprehensive evaluation level and introduce domain knowledge and rules; Assuming that according to domain knowledge, river line features should be continuous and have consistent flow directions, if a line feature has breakpoints or inconsistent flow directions, its confidence level is reduced.

[0045] Let the original confidence be , if there is a breakpoint, the confidence level is adjusted to ; If the flow direction is inconsistent, the confidence is adjusted to .

[0046] Example 6: Assuming the original confidence of a river line feature ,The detection found that there was inconsistency in flow direction, and the adjusted confidence level C=0.54.

[0047] A multi-index comprehensive evaluation is further adopted, combining the surface feature classification with boundary roughness and classification confidence; Assume that the classification confidence of the surface feature is , the boundary roughness is R (range 0-1, the larger the value, the rougher the boundary), comprehensive evaluation confidence in is the weight .

[0048] Example 7: Assuming the classification confidence is , boundary roughness R=0.2, weight =0.6, C=0.74.

[0049] Through the above specific formulas, calculation processes and implementation solutions, the limitations of confidence judgment can be solved to a certain extent, and the quality of point, line, surface and volume related data and the accuracy of confidence judgment can be improved.

[0050] The above description is only a further embodiment 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 concepts of the present invention within the scope disclosed by the present invention, which belong to the protection scope of the present invention.

Claims

1. A surveying and mapping geographic information data intelligent analysis and decision-making system, including a data acquisition module, for collecting data on geographic information that needs to be surveyed and mapped; Data preprocessing module, used to clean the collected data; The feature extraction module is used to extract points, lines, surfaces, volumes, extended attribute fields, feature categories, confidence levels, and data sources from the data processed by the data preprocessing module; Model training module, used to train various machine learning models on the extracted feature data; Features: It also includes a confidence judgment optimization module, which is used to judge and optimize the confidence of the point, line, surface, and volume data extracted by the feature extraction module and the data trained by the model training module, and output the optimized confidence value of each data object; The reliability judgment optimization module includes a multi-source data fusion module; The multi-source data fusion module fuses the coordinate transformation formula with the affine transformation formula, processes the data extracted by the feature extraction module through the fused formula, and then inputs it into the model training module; The comprehensive evaluation module combines confidence judgment results, domain knowledge and rules, and multi-indicator comprehensive evaluation to conduct a comprehensive evaluation and analysis of the data.

2. The intelligent analysis and decision-making system for surveying and mapping geographic information data according to claim 1, characterized in that: The determination method of the confidence determination optimization module specifically comprises the following steps: S11: Cleaning and preprocessing the acquired data; S12: Standardize the data; S13: Perform data enhancement processing on the standardized data; S14: performing multi-source data fusion on the data enhanced in S13 through a multi-source data fusion module; S15: Fusion of models, fusion of logistic regression and support vector machine models; S16: Evaluate and monitor the fused model; S17: Output the optimized confidence level to the comprehensive evaluation module.

3. The intelligent analysis and decision-making system for surveying and mapping geographic information data according to claim 2 is characterized by: In S11, the outlier detection is mainly cleaned, specifically using 3 The principle is to process point, line, surface and volume data using the following formula to standardize the data: ;in, is the standardized value; is the original value; is the mean; is the standard deviation.

4. The intelligent analysis and decision-making system for surveying and mapping geographic information data according to claim 2 is characterized by: In S13, the following formula is used to enhance the data. For the points in the image , the rotated point The coordinate calculation formula is: ; in, are the center coordinates of the image.

5. The intelligent analysis and decision-making system for surveying and mapping geographic information data according to claim 2 is characterized by: In S14, the seven-parameter Bursa model is integrated with the affine transformation formula to derive multi-source data fusion; First, convert the seven-parameter Bursa model to obtain the spatial coordinates , and then project it onto the plane to get the plane coordinates , and then perform affine transformation on the plane coordinates to obtain the final coordinates .

6. The intelligent analysis and decision-making system for surveying and mapping geographic information data according to claim 2, characterized in that: Conversion to the seven-parameter Bursa model: ; The spatial coordinates Transform to plane coordinates by projection ; The specific projection function used is: ; ; Finally, perform an affine transformation: ; The fused formula is: .

7. The intelligent analysis and decision-making system for surveying and mapping geographic information data according to claim 2 is characterized by: Before S15 model fusion, it also includes model selection and optimization processing; The gradient descent formula for updating weights using logistic regression is: ; in, It is weights; α is the learning rate; J(w) is the loss function, .

8. The intelligent analysis and decision-making system for surveying and mapping geographic information data according to claim 2 is characterized by: S15 model fusion specifically includes assuming that there are a logistic regression model LR and a support vector machine model SVM. For input x, their prediction probabilities are and , the prediction probability formula after fusion is: .

9. The intelligent analysis and decision-making system for surveying and mapping geographic information data according to claim 2, characterized in that: S16 specifically includes evaluating and monitoring the fused model using the following formula: Accuracy ; Among them, TP is a true positive example; TN is a true negative example; FP is a false positive; FN is a false negative example.

10. The intelligent analysis and decision-making system for surveying and mapping geographic information data according to claim 9, characterized in that: S17 specifically includes establishing a comprehensive evaluation level and introducing domain knowledge and rules; According to domain knowledge, river line features should be continuous and have consistent flow directions. If a line feature has breakpoints or inconsistent flow directions, its confidence level should be reduced; Let the original confidence be , if there is a breakpoint, the confidence level is adjusted to ; If the flow direction is inconsistent, the confidence is adjusted to ; A multi-index comprehensive evaluation is adopted, combining surface feature classification with boundary roughness and classification confidence; Assume that the classification confidence of the surface feature is The boundary roughness is R in the range of 0-1. The larger the value, the rougher the boundary. The confidence of the comprehensive evaluation ,in, is the weight .

Images