A Geographic Information Analysis Method Based on Multi-source Data Fusion
By adjusting the anomaly detection threshold and optimizing the data structure, analyzing the density and spatial correlation strength of geographic units, combined with historical planning cases, the problem of insufficient abnormal data screening and feature consistency comparison in traditional methods is solved, and multi-source geospatial data is improved Accuracy of analysis and decision support capabilities.
Patent Information
- Application Number
- CN202411060428.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-05
- Publication Date
- 2024-11-01
- Estimated Expiration
- 2044-08-05
AI Technical Summary
The traditional multi-source geospatial data fusion method lacks effective anomaly data screening and feature consistency comparison, resulting in a large amount of error information in the data, affecting the accuracy of analysis, failing to fully reflect the importance and characteristics of the data source, and limiting the decision-making. Scientific and efficient.
By adjusting the anomaly detection threshold of the data, marking and eliminating the abnormal data, extracting features, optimizing the data structure, analyzing the density estimates and spatial correlation intensity of geographic units, performing risk area classification and evaluation, and combining historical planning cases to evaluate the impact of the current planning scheme. .
It improves data quality and analysis accuracy, enhances the identification accuracy of risk areas, provides data-driven urban planning prediction tools, and improves the comprehensiveness and accuracy of decision support.
Smart Images

Figure CN118568190B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of geographic information analysis, and in particular to a geographic information analysis method of multi-source data fusion. Background Art
[0002] The field of geographic information analysis technology involves the collection, storage, and analysis of geographic data to support decision making and problem solving. This field uses tools such as geographic information systems and combines multidisciplinary knowledge such as cartography, geography, and computer science to manage and analyze spatial data. In geographic information analysis, the types of data are wide-ranging, including but not limited to topography, climate, demographics, and economic activity data. Technical applications cover many aspects such as urban planning, environmental monitoring, resource management, and disaster response. Through these technologies, geographic data can be transformed into useful information to help decision makers understand spatial patterns and associations, thereby making more effective decisions.
[0003] Among them, the geographic information analysis method of multi-source data fusion is a technology that integrates and analyzes geographic data from different sources and types. Its purpose is to synthesize multi-source data, enhance the amount of data information and the accuracy of analysis, so that users of geographic information systems can obtain more in-depth and comprehensive insights. The scope of application includes enhancing decision support for urban planning, optimizing natural resource management, improving emergency response efficiency, and improving environmental monitoring. The core of this method is to effectively process and analyze diverse and large-scale geospatial data to support complex geospatial problem solutions.
[0004] When processing multi-source geospatial data, traditional analysis methods lack effective abnormal data screening and feature consistency comparison, resulting in a large amount of erroneous information contained in the data set, affecting the accuracy of the final analysis. Traditional methods fail to fully realize the dynamic adjustment of geospatial data source weights, so that the importance and characteristics of multiple data sources are not fully reflected, limiting the application effect of data and the scientific nature of decision-making. In terms of geospatial pattern recognition and risk area classification, traditional methods fail to accurately identify and mark high-risk areas and lack effective risk assessment mechanisms, making urban planning face challenges in dealing with complex and dynamic environments, hindering users of geographic information systems from obtaining in-depth and comprehensive insights when making decisions, and reducing the efficiency and effectiveness of decision-making. Summary of the invention
[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a geographic information analysis method of multi-source data fusion.
[0006] In order to achieve the above object, the present invention adopts the following technical solution: a geographic information analysis method of multi-source data fusion, comprising the following steps:
[0007] S1: Based on historical multi-source geospatial data, adjust the data anomaly detection threshold, perform anomaly screening on the current multi-source geospatial data, mark and remove abnormal data, and perform feature extraction on each data source to obtain the basic screening data set;
[0008] S2: Based on the basic screening data set, time dependency analysis is performed on multi-source geospatial data, and weights of differentiated geospatial data sources are adjusted according to the importance and characteristics of the data, the data structure is optimized, and an optimized data set is obtained;
[0009] S3: Based on the optimized data set, analyze the density estimation value and spatial correlation strength of the geographic unit, perform geographic spatial pattern recognition, and classify the risk areas according to the preset threshold, mark the high-risk areas, and obtain the risk assessment analysis results;
[0010] S4: Based on the risk assessment analysis results, obtain historical planning cases in the urban planning database, evaluate the impact of differentiated historical planning schemes on high-risk areas, analyze the impact of current planning schemes on high-risk areas, and generate urban planning effect prediction information.
[0011] The present invention is improved in that the method for marking and removing abnormal data is:
[0012] S111: Based on historical multi-source geospatial data, calculate the statistical characteristics of each data source, the statistical characteristics include mean value and standard deviation;
[0013] S112: Based on the statistical features, by formula:
[0014] ;
[0015] Calculate the adjusted anomaly detection threshold ,in, Represents the average value of the data source, Represents the standard deviation of the data source, is the weight factor, Indicates the historical anomaly rate of the data source, is the total number of data points, is the normalization factor, is the adjusted anomaly detection threshold;
[0016] S113: Based on the adjusted abnormality detection threshold , perform anomaly screening on the current multi-source geospatial data, and set the anomaly detection threshold that exceeds the whole The data points are marked as abnormal and removed.
[0017] The present invention is improved in that the step of obtaining the basic screening data set is:
[0018] S121: Based on multi-source geospatial data, feature extraction is performed on each data source, and the extracted features include spectral index of satellite images, temperature gradient of meteorological data, speed and density index of traffic flow data, and data feature information is obtained;
[0019] S122: Based on the data feature information, by formula:
[0020] ;
[0021] Calculating the consistency score ,in, is the weight factor of the data source, is the spectral index of the satellite image, is the temperature gradient of the meteorological data, Speed and density indicators for traffic flow data;
[0022] S123: Based on the consistency score , the consistency score Compare with the preset consistency threshold. If the consistency score, If the consistency is higher than the preset threshold, the data will be compiled into the data set to obtain the basic screening data set.
[0023] The present invention is improved in that the method for analyzing the time dependency of multi-source geographic spatial data is:
[0024] S211: extracting time series data of multi-source geospatial data based on the basic screening data set;
[0025] S212: Based on the time series data, by formula:
[0026] ;
[0027] Calculate the correlation coefficient ,in, Respectively at time From the data source and The data value obtained, The data sources are and The average value of Is the data source and The standard deviation of is the total number of time points in the observation period;
[0028] S213: Based on the correlation coefficient ,according to The size of the value is used to evaluate the time dependency between data sources.
[0029] The present invention is improved in that the step of obtaining the optimized data set is:
[0030] S221: Based on the multi-source geospatial data, obtain a basic weight of each geospatial data source;
[0031] S222: Based on the basic weight and correlation coefficient , through the formula:
[0032] ;
[0033] Calculate the adjusted weights ,in, Is the data source The basic weight of For data source and The time-dependent correlation coefficient between is the adjustment coefficient, For data source The characteristic index of For data source Adjusted weights;
[0034] S223: Based on the adjusted weight , weights adjusted based on differentiated data sources The size of the value, adjust the differentiated data source The proportion and acquisition frequency of are optimized to obtain the optimized data set.
[0035] The present invention is improved in that the steps of obtaining the risk assessment analysis results are:
[0036] S311: Based on the optimized data set, by formula:
[0037] ;
[0038] Calculate density estimates for geographic cells ,in, Represents a geographic unit The density estimate of is the number of data points within a geographic unit, It is a data point To geographic unit The distance from the center, is the spatial diffusion parameter, is the base of natural logarithms.
[0039] S312: Based on the optimized data set, the spatial relationship between each geographic unit and the adjacent units is analyzed, and the formula is:
[0040] ;
[0041] By calculating the spatial correlation strength ,in, It is a geographical unit The spatial correlation strength of express The set of neighboring units, is the spatial weight, It is a geographical unit and The attribute similarity between
[0042] S313: Based on the density estimation value of the geographic unit and spatial correlation strength , through the formula:
[0043] ;
[0044] Calculating risk scores , the risk score The risk level of each unit is determined by comparing it with the preset risk threshold, and the geographical units above the preset threshold are classified and marked as high-risk areas to obtain the risk assessment analysis results, among which: It is a geographical unit The risk score of is the weight coefficient.
[0045] The present invention is improved in that the method for evaluating the impact of differentiated historical planning schemes on high-risk areas is:
[0046] S411: Based on the risk assessment analysis results, extract historical planning cases for high-risk areas from the urban planning database, including planning measures, implementation time and geographical scope involved;
[0047] S412: Based on the historical planning case, by formula:
[0048] ;
[0049] Calculating impact scores for historical plans , and according to The value of the value is used to evaluate the impact of historical planning schemes on high-risk areas. represents the impact score of the historical plan, is the total number of historical planning cases, It is The weight coefficient of each planning case, It is The execution effectiveness parameters of the planning cases, It is The conditional variables for each planning case, It is Risk indicators for each planning case, is the adjustment factor.
[0050] The present invention is improved in that the method for predicting information on the effect of urban planning is:
[0051] S421: Impact score based on the historical plan , obtain the characteristics and expected goals of the current planning scheme, including planning area, target population and infrastructure factors, and obtain the current planning scheme information;
[0052] S422: Based on the current planning scheme information, the formula:
[0053] ;
[0054] Calculate the current planning impact score , and score based on current planning impact The value is used to analyze the impact of the current planning scheme on high-risk areas and generate urban planning effect prediction information, among which: is the current planning impact score, is the impact score of the historical plan, is the adjustment coefficient, Represents the change in the conditional variables of the current plan relative to the historical cases, Indicates the change in risk indicators of the current plan relative to the historical case, Represents the change in population density of the current plan relative to the historical case.
[0055] Compared with the prior art, the advantages and positive effects of the present invention are:
[0056] In the present invention, by adjusting the data anomaly detection threshold and performing anomaly screening, marking and removing abnormal data, the quality and availability of the data are optimized, providing a high-quality basic data set for subsequent analysis, and by adjusting the weights of different geospatial data sources and optimizing the data structure, the data is made more accurate and effective. By analyzing the density estimates and spatial correlation strengths of geographic units, geospatial pattern recognition is performed, and the accuracy of identifying risk areas is improved. By comprehensively considering historical planning cases, a data-driven prediction tool is provided for urban planning, which enhances the comprehensiveness and accuracy of decision support and effectively improves the effect of urban planning. BRIEF DESCRIPTION OF THE DRAWINGS
[0057] Figure 1 is a flow chart of the method of the present invention;
[0058] Figure 2 A flow chart for marking and removing abnormal data in the present invention;
[0059] Figure 3 A flow chart for obtaining a basic screening data set for the present invention;
[0060] Figure 4 A flow chart of the present invention for analyzing time dependency of multi-source geospatial data;
[0061] Figure 5 A flow chart for obtaining an optimized data set for the present invention;
[0062] Figure 6 A flow chart for obtaining risk assessment analysis results for the present invention;
[0063] Figure 7 A flow chart for evaluating the impact of differentiated historical planning options on high-risk areas for the present invention;
[0064] Figure 8 The present invention is a flow chart for obtaining urban planning effect prediction information. DETAILED DESCRIPTION
[0065] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.
[0066] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.
[0067] See also Figure 1 The present invention provides a technical solution: a geographic information analysis method for multi-source data fusion, comprising the following steps:
[0068] S1: Based on historical multi-source geospatial data, including satellite images, meteorological data, and traffic flow data, the anomaly detection threshold of the data is adjusted, the anomaly screening of the current multi-source geospatial data is performed, the abnormal data is marked and removed, and the feature extraction of each data source is performed to obtain the basic screening data set;
[0069] S2: Based on the basic screening data set, the time dependency relationship of multi-source geospatial data is analyzed, and the weights of differentiated geospatial data sources are adjusted according to the importance and characteristics of the data, the data structure is optimized, and the optimized data set is obtained;
[0070] S3: Based on the optimized data set, the density estimation value and spatial correlation strength of the geographic unit are analyzed to perform geospatial pattern recognition, and the risk area is classified according to the preset threshold, and the high-risk area is marked to obtain the risk assessment analysis results;
[0071] S4: Based on the results of risk assessment analysis, obtain historical planning cases in the urban planning database, evaluate the impact of differentiated historical planning schemes on high-risk areas, analyze the impact of current planning schemes on high-risk areas, and generate urban planning effect prediction information.
[0072] The basic screening data set includes data integrity identification, data source type identification and outlier marking; the optimization data set includes time series dependency analysis results and data source weight distribution information; the risk assessment analysis results include marked high-risk geographic areas and risk levels of differentiated areas; and the urban planning effect prediction information includes the impact prediction value of differentiated planning schemes and the credibility information of the prediction results.
[0073] See also Figure 2 , the method to mark and remove abnormal data is:
[0074] S111: Based on historical multi-source geospatial data, calculate the statistical characteristics of each data source, the statistical characteristics include mean value and standard deviation;
[0075] S112: Based on statistical characteristics, through the formula:
[0076] ;
[0077] Calculate the adjusted anomaly detection threshold ,in, Represents the average value of the data source, Represents the standard deviation of the data source, is the weight factor, Indicates the historical anomaly rate of the data source, is the total number of data points, is the normalization factor, is the adjusted anomaly detection threshold;
[0078] S113: Based on the adjusted anomaly detection threshold , perform anomaly screening on the current multi-source geospatial data, and set the anomaly detection threshold that exceeds the whole The data points are marked as abnormal and removed.
[0079] formula:
[0080] ;
[0081] Parameter details and how to obtain them:
[0082] average value : The average value of a data source, calculated by adding up the values of all the data points and dividing by the total number of data points. This is a basic statistical measure that describes the center of a data set.
[0083] Standard Deviation : Indicates the degree of discreteness of data distribution. The calculation method is to first calculate the difference between each data point and the average value. The square of the difference is then added up and finally divided by the number of data points and the square root is taken.
[0084] Weight Factor : is an empirical value used to adjust the looseness or strictness of the threshold. In practical applications, The value of is usually set based on the frequency of anomalies in historical data.
[0085] Abnormality rate : The anomaly rate of historical data, which is obtained by the proportion of abnormal points in the historical data, and is calculated as the number of data points marked as abnormal in the historical data divided by the total number of data points.
[0086] Total number of data points : The total number of observed data points, directly counted from the dataset.
[0087] Normalization factor : It is a parameter set to adjust the numerical range and can be determined based on the standard deviation or data range of the data set. The selection ensures that the logarithmic part of the formula will not cause calculation deviation due to excessively large or small values.
[0088] Calculation example:
[0089] Assume that in the given data set there is data points, historical anomaly rate (i.e. 5% of the data points are abnormal), choose a commonly used normalization factor , and set the weight factor . Let the mean value of the data be , the standard deviation is .
[0090] According to the formula:
[0091] ;
[0092] calculate:
[0093] ;
[0094] Calculate the weight adjustment part:
[0095] ;
[0096] Calculate the adjusted anomaly detection threshold :
[0097] ;
[0098] The implication of this calculation is that any data point exceeding 113.815 will be considered an anomaly and will be flagged and removed.
[0099] See also Figure 3 , the steps to obtain the basic screening data set are:
[0100] S121: Based on multi-source geospatial data, feature extraction is performed on each data source, and the extracted features include spectral index of satellite images, temperature gradient of meteorological data, speed and density index of traffic flow data, and data feature information is obtained;
[0101] S122: Based on the data feature information, the formula is:
[0102] ;
[0103] Calculating the consistency score ,in, is the weight factor of the data source, is the spectral index of the satellite image, is the temperature gradient of the meteorological data, Speed and density indicators for traffic flow data;
[0104] S123: Based on consistency scoring , the consistency score Compare with the preset consistency threshold. If the consistency score If the consistency is higher than the preset threshold, the data will be compiled into the data set to obtain the basic screening data set.
[0105] formula:
[0106] ;
[0107] Parameter details and how to obtain them:
[0108] : The spectral index of satellite images is usually obtained by analyzing the reflectance of different bands of satellite images. For example, it can be obtained by calculating the ratio of the spectral reflectance of a specific band to the total reflectance.
[0109] : The temperature gradient of meteorological data is calculated from the sequence data provided by the meteorological station, usually by averaging the difference between the highest and lowest temperatures within a certain period of time.
[0110] :The speed and density indicators of traffic flow data can be obtained by calculating the average vehicle speed and vehicle density within a certain period of time through the data collected by the traffic monitoring system.
[0111] : The weight factor is set according to the importance of the data source in the entire analysis, which can be obtained through impact analysis of historical data or expert evaluation.
[0112] Calculation example:
[0113] Assume the following data and weights:
[0114] : Represents the spectral index of the satellite image. This value is assumed to be the ratio of the spectral reflectance obtained from a specific band to the total reflectance.
[0115] : The temperature gradient of the meteorological data, assumed to be the difference between the highest and lowest temperatures in a day.
[0116] : The average speed of traffic flow, in kilometers per hour.
[0117] : The weight reflects the contribution of each data source to the final decision.
[0118] Assume that the consistency threshold is 3: the threshold is set based on the results of past processing in the dataset.
[0119] Using the formula , and calculate:
[0120] ;
[0121] Calculated The value is 2.267, compared With the consistency threshold, due to , indicating that the extracted data features are not sufficiently consistent across satellite imagery, meteorology, and traffic flows to be compiled into the basic screening dataset.
[0122] See also Figure 4 ,The method for temporal dependency analysis of multi-source geospatial data is:
[0123] S211: Extracting time series data of multi-source geospatial data based on basic screening datasets;
[0124] S212: Based on time series data, through the formula:
[0125] ;
[0126] Calculate the correlation coefficient ,in, Respectively at time From the data source and The data value obtained, The data sources are and The average value of Is the data source and The standard deviation of is the total number of time points in the observation period;
[0127] S213: Based on the correlation coefficient ,according to The size of the value is used to evaluate the time dependency between data sources.
[0128] formula:
[0129] ;
[0130] Parameter details and how to obtain them:
[0131] : It is a specific time Data points from the data source and The data sources can be satellite images, meteorological or traffic flow data, and the data are usually collected from the historical records of each source through time series analysis.
[0132] Is the data source and The average value, obtained by averaging the data points during the entire observation period, reflects the average performance of each data source during the observation period.
[0133] This is the data source and The standard deviation measures the fluctuation difference of data from two data sources at the same time point, which is usually obtained by calculating the standard deviation of the difference between all matching time points of the two data sources.
[0134] : The total number of time points in the observation period, directly calculated from the data set, representing the number of observations within a given time frame.
[0135] : It is a threshold used to determine whether there is significant time dependence between two data sources, usually set based on historical data analysis or expert advice.
[0136] Calculation example:
[0137] Assume there are two data sources and , respectively representing the satellite temperature readings of a certain area and the traffic flow data of the area at the corresponding time. Assume the following data and parameters:
[0138] Time Day, data source Data points The value on the 15th day is ,average value , data source Data points The value on the 15th day is Vehicles / hour, average Vehicles / hour, standard deviation .
[0139] Calculate the 15th day and :
[0140] ;
[0141] Calculate the correlation coefficient formula :
[0142] ;
[0143] Assuming that the data change pattern of all days is similar to that of the 15th day, the calculation of the above numerator is:
[0144] ;
[0145] The denominator is assumed to be:
[0146] ;
[0147] but:
[0148] ;
[0149] What you get , due to its small value, it shows that the temporal dependence of the two data sources is not significant.
[0150] See also Figure 5 , the steps to obtain the optimized data set are:
[0151] S221: Based on the multi-source geospatial data, obtain a basic weight of each geospatial data source;
[0152] S222: Based on the basic weights and correlation coefficients , through the formula:
[0153] ;
[0154] Calculate the adjusted weights ,in, Is the data source The basic weight of For data source and The time-dependent correlation coefficient between is the adjustment coefficient, For data source The characteristic index of For data source Adjusted weights;
[0155] S223: Based on the adjusted weight , weights adjusted based on differentiated data sources The size of the value, adjust the differentiated data source The proportion and acquisition frequency of are optimized to obtain the optimized data set.
[0156] formula:
[0157] ;
[0158] Parameter details and how to obtain them:
[0159] Base Weight : Data source The basic weights of the data source are set according to its initial importance and characteristics. Characteristics can be data accuracy, update frequency, coverage, etc. The weights are preset through expert evaluation or historical data analysis.
[0160] Correlation coefficient : Data source and The time-dependent correlation coefficient between is calculated in the previous step.
[0161] Characteristics : Data source Characteristic indicators reflect the specific attributes of the data source, such as data quality, information richness, data update frequency, accuracy or coverage. The indicators are evaluated based on the detailed characteristics of the data source.
[0162] Adjustment coefficient : is the empirical coefficient, used to adjust the correlation coefficient and characteristic indicators The influence in the final weight calculation. The coefficient is adjusted according to the data analysis needs and the expected impact strength.
[0163] Calculation example:
[0164] Assume the following data and parameter settings:
[0165] Data Source The basic weight , with another data source Correlation coefficient , data source Characteristics of the index , adjustment coefficient , .
[0166] Calculating weights :
[0167] ;
[0168] Adjusted weight Indicates that, considering the time dependency with other data sources and its own characteristics, the data source The relative importance increases during the integration process, and such a weight adjustment strategy helps to optimize the construction of feature datasets.
[0169] See also Figure 6 , the steps to obtain the risk assessment analysis results are:
[0170] S311: Based on the optimized data set, by formula:
[0171] ;
[0172] Calculate density estimates for geographic cells ,in, Represents a geographic unit The density estimate of is the number of data points within a geographic unit, It is a data point To geographic unit The distance from the center, is the spatial diffusion parameter, is the base of natural logarithms.
[0173] S312: Based on the optimized data set, the spatial relationship between each geographic unit and the adjacent units is analyzed, and the formula is:
[0174] ;
[0175] By calculating the spatial correlation strength ,in, It is a geographical unit The spatial correlation strength of express The set of neighboring units, is the spatial weight, It is a geographical unit and The attribute similarity between
[0176] S313: Based on the density estimation value of the geographic unit and spatial correlation strength , through the formula:
[0177] ;
[0178] Calculating risk scores , the risk score The risk level of each unit is determined by comparing it with the preset risk threshold, and the geographical units above the preset threshold are classified and marked as high-risk areas to obtain the risk assessment analysis results, among which: It is a geographical unit The risk score of is the weight coefficient.
[0179] formula:
[0180] and and ;
[0181] Parameter details and how to obtain them:
[0182] Geographical unit The density estimate of is calculated by measuring the distribution density of data points in the geographic unit. The specific calculation uses the kernel density estimation method, where Yes To geographic unit The Euclidean distance of the center, is the bandwidth of the kernel function and determines the smoothness. The smaller the value, the closer the density estimation is to the actual point distribution.
[0183] : Indicates geographical unit The strength of spatial association between adjacent units. This is evaluated by calculating the attribute similarity and spatial weight between adjacent units. Spatial weight Reflects geographical units With Neighbors The spatial proximity of It is an attribute-based similarity function.
[0184] : A risk score calculated based on the density estimate and strength of spatial association for a geographic unit. Weight Adjusts the influence of density and spatial association. Weights are usually set based on historical data or expert opinion to ensure the validity and rationality of the scoring system.
[0185] Calculation example:
[0186] Assuming geographic unit The data is as follows:
[0187] Number of data points , assuming that the average distance from all points to the center is ,bandwidth , the average attribute similarity of adjacent units , spatial weight , weight factor , , the preset risk threshold is 4.
[0188] Compute density estimate :
[0189] ;
[0190] Spatial correlation strength Calculation:
[0191] ;
[0192] Risk Scoring Calculation:
[0193] ;
[0194] because Less than the preset risk threshold of 4, geographical unit Not marked as a high-risk area.
[0195] See also Figure 7, the method to evaluate the impact of differentiated historical planning schemes on high-risk areas is:
[0196] S411: Based on the results of risk assessment analysis, extract historical planning cases for high-risk areas from the urban planning database, including planning measures, implementation time and geographical scope involved;
[0197] S412: Based on historical planning cases, through the formula:
[0198] ;
[0199] Calculating impact scores for historical plans , and according to The value of the value is used to evaluate the impact of historical planning schemes on high-risk areas. represents the impact score of the historical plan, is the total number of historical planning cases, It is The weight coefficient of each planning case, It is The execution effectiveness parameters of the planning cases, It is The conditional variables for each planning case, It is Risk indicators for each planning case, is the adjustment factor.
[0200] formula:
[0201] ;
[0202] Parameter details and how to obtain them:
[0203] :Indicates the The importance weight of each historical planning case is usually assigned based on the case’s size, scope of influence, or expected impact, which can be obtained from the success rate of historical planning or expert evaluation.
[0204] :The effectiveness of plan implementation is a quantitative indicator that represents the quality and effectiveness of the implementation of planning measures. This can be achieved by evaluating the actual improvements after the implementation of the plan, such as through changed traffic flow, reduced number of accidents or improved environmental indicators.
[0205] : Represent the condition variables and related risk indicators of the planning case respectively. Including population density, traffic flow, etc. Including accident rate, crime rate, etc. Variables are usually obtained through statistical data in urban data sets or planning databases.
[0206] : is the adjustment coefficient used to balance the conditional variables and risk indicators The weight used in calculating the impact score. The coefficients are set based on historical data analysis or model testing to ensure the accuracy and relevance of the calculation results.
[0207] Calculation example:
[0208] Assumption: Number of historical planning cases ;
[0209] Weight coefficient They are 0.3, 0.4, and 0.3 respectively;
[0210] Effectiveness parameters They are 0.85, 0.75, and 0.9 respectively;
[0211] Condition variables They are 120, 180, 160 respectively;
[0212] Risk Indicators They are 45, 55, and 50 respectively;
[0213] Adjustment factor and ;
[0214] Calculation process:
[0215] ;
[0216] For the first case:
[0217] ;
[0218] For the second case:
[0219] ;
[0220] For the third case:
[0221] ;
[0222] Impact score
[0223] ;
[0224] The calculated average impact score is 28.2125, indicating that the historical planning cases have, on average, a relatively moderate impact on high-risk areas.
[0225] See also Figure 8 , the method of urban planning effect prediction information is:
[0226] S421: Impact scoring based on historical planning , obtain the characteristics and expected goals of the current planning scheme, including planning area, target population and infrastructure factors, and obtain the current planning scheme information;
[0227] S422: Based on the current planning scheme information, the formula is:
[0228] ;
[0229] Calculate the current planning impact score , and score based on current planning impact The value is used to analyze the impact of the current planning scheme on high-risk areas and generate urban planning effect prediction information, among which: is the current planning impact score, is the impact score of the historical plan, is the adjustment coefficient, Represents the change in the conditional variables of the current plan relative to the historical cases, Indicates the change in risk indicators of the current plan relative to the historical case, Represents the change in population density of the current plan relative to the historical case.
[0230] formula:
[0231] ;
[0232] Parameter details and how to obtain them:
[0233] : Represents the impact score of the historical plan, calculated in the previous steps.
[0234] : Adjustment coefficients are used to adjust the influence of current planning condition variables, risk indicators and population density changes in the forecast model. These coefficients are set based on regression analysis of historical data or expert evaluation to ensure the accuracy and relevance of the forecast model.
[0235] : The change in the condition variables of the current plan relative to the historical case. Condition variables can include land use type, infrastructure distribution, etc. By comparing the data of these variables in the current plan and the historical case, the change is calculated.
[0236] :The change in risk indicators of the current plan relative to the historical cases. Risk indicators include accident rates, environmental pollution index, etc. By analyzing these indicator data in the current plan and historical cases, the change is calculated.
[0237] : The change in population density of the current plan relative to the historical case. It is obtained by comparing the population density data in the current plan and the historical case, and can usually be obtained from statistical yearbooks or urban planning databases.
[0238] Calculation example:
[0239] Assume the following parameters:
[0240] Historical Planning Impact Scoring ;
[0241] Current planning condition variable change ;
[0242] Current planning risk indicator change ;
[0243] Current planned population density change ;
[0244] Adjustment coefficient ;
[0245] Apply the prediction formula:
[0246] ;
[0247] Calculation results The impact score of the current plan on geospatial data is 29.5207, taking into account changes in condition variables, risk indicators, and population density relative to the historical case. The score provides a quantitative prediction to help decision makers assess the potential impact of the current plan.
[0248] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.
Claims
1. A geographic information analysis method based on multi-source data fusion, characterized in that: The following steps are involved: Based on historical multi-source geospatial data, the anomaly detection threshold of the data is adjusted, the anomaly screening of the current multi-source geospatial data is performed, the abnormal data is marked and removed, and the feature extraction of each data source is performed to obtain the basic screening data set; Based on the basic screening data set, a time dependency analysis is performed on the multi-source geospatial data, and according to the importance and characteristics of the data, the weights of the differentiated geospatial data sources are adjusted to optimize the data structure and obtain an optimized data set; Based on the optimized data set, the density estimation value and spatial correlation strength of the geographic units are analyzed to perform geospatial pattern recognition, and risk areas are classified according to preset thresholds, high-risk areas are marked, and risk assessment analysis results are obtained; Based on the risk assessment analysis results, obtain historical planning cases in the urban planning database, evaluate the impact of differentiated historical planning schemes on high-risk areas, analyze the impact of current planning schemes on high-risk areas, and generate urban planning effect prediction information; The method for predicting the urban planning effect information is as follows: Impact scoring of high-risk areas based on differentiated historical planning schemes The characteristics and expected goals of the current planning scheme, including planning area, target population and infrastructure factors, to obtain information on the current planning scheme; Based on the current planning scheme information, the formula: ; Calculate the current planning impact score , and score based on current planning impact The impact of the current planning scheme on high-risk areas is analyzed based on the size of the value, and urban planning effect prediction information is generated. is the current planning impact score, is the impact score of the historical plan, is the adjustment coefficient, Indicates the change in the conditional variables of the current plan relative to the historical case, Indicates the change in risk indicator of the current plan relative to the historical case, Indicates the change in population density of the current plan relative to the historical case.
2. The geographic information analysis method of multi-source data fusion according to claim 1 is characterized in that: The method for marking and removing abnormal data is: Based on historical multi-source geospatial data, calculate the statistical characteristics of each data source, including the mean and standard deviation; Based on the statistical characteristics, the formula: ; Calculate the adjusted anomaly detection threshold ,in, Represents the average value of the data source, Represents the standard deviation of the data source, is the weight factor, Indicates the historical anomaly rate of the data source, is the total number of data points, is the normalization factor, is the adjusted anomaly detection threshold; Based on the adjusted anomaly detection threshold , anomaly screening of the current multi-source geospatial data will exceed the adjusted anomaly detection threshold The data points are marked as abnormal and removed.
3. The geographic information analysis method of multi-source data fusion according to claim 2 is characterized in that: The steps for obtaining the basic screening data set are: Based on multi-source geospatial data, feature extraction is performed on each data source. The extracted features include spectral index of satellite images, temperature gradient of meteorological data, speed and density indicators of traffic flow data, and data feature information is obtained. Based on the data feature information, the formula: ; Calculating consistency scores ,in, is the weight factor of the data source, is the spectral index of the satellite image, is the temperature gradient of meteorological data, Speed and density indicators for traffic flow data; Based on the consistency score , the consistency score Compare with the preset consistency threshold, if the consistency score If the consistency is higher than the preset threshold, the data will be compiled into the data set to obtain the basic screening data set.
4. The geographic information analysis method of multi-source data fusion according to claim 1, characterized in that: The method for analyzing the temporal dependency of multi-source geospatial data is as follows: extracting time series data of multi-source geospatial data based on the basic screening data set; Based on the time series data, the formula: ; Calculate the correlation coefficient ,in, Respectively at time From the data source and The data value obtained, The data sources are and The average value of Is the data source and The standard deviation of is obtained by calculating the standard deviation of the difference between all matching time points of the two data sources. is the total number of time points in the observation period; Based on the correlation coefficient ,according to The size of the value is used to evaluate the time dependency between data sources.
5. The geographic information analysis method of multi-source data fusion according to claim 4 is characterized in that: The steps for obtaining the optimized data set are: Based on multi-source geospatial data, obtain the basic weight of each geospatial data source; Based on the basic weights and correlation coefficients , through the formula: ; Calculate the adjusted weights ,in, Is the data source The basic weight of Is the data source and The time-dependent correlation coefficient between is the adjustment coefficient, For data sources The characteristic indicators of For data sources Adjusted weights; Based on the adjusted weights , weights adjusted based on differentiated data sources The size of the value, adjust the differentiated data source The proportion and acquisition frequency of are optimized to obtain the optimized data set.
6. The geographic information analysis method of multi-source data fusion according to claim 1, characterized in that: The steps for obtaining the risk assessment analysis results are: Based on the optimized data set, the formula: ; Calculate density estimates for geographic cells ,in, Represents a geographic unit The density estimate of is the number of data points within a geographic unit, is a data point To geographic unit The distance from the center, is the spatial diffusion parameter, is the base of natural logarithms; Based on the optimized data set, the spatial relationship between each geographic unit and the adjacent units is analyzed and the formula is used: ; By calculating the spatial correlation strength ,in, It is a geographical unit The spatial correlation strength of express The set of neighboring cells, is the spatial weight, It is a geographical unit and The attribute similarity between Density estimates based on the geographic unit and spatial correlation strength , through the formula: ; Calculating risk scores , the risk score Compare with the preset risk threshold to determine the risk level of each unit, classify and mark the geographical units above the preset threshold as high-risk areas, and obtain the risk assessment analysis results, among which, It is a geographical unit The risk score, and is the weight coefficient.
7. The geographic information analysis method of multi-source data fusion according to claim 1, characterized in that: The method for evaluating the impact of differentiated historical planning options on high-risk areas is: Based on the risk assessment analysis results, extract historical planning cases for high-risk areas from the urban planning database, including planned measures, implementation time, and geographical scope involved; Based on the historical planning case, the formula: ; Calculating impact scores for historical plans , and according to The value of the value is used to evaluate the impact of historical planning schemes on high-risk areas, where represents the impact score of historical planning, is the total number of historical planning cases, It is The weight coefficient of each planning case, It is The execution effectiveness parameters of each planning case, It is The conditional variables for each planning case, It is Risk indicators for each planning case, and is the adjustment factor.
Citation Information
Patent Citations
Intelligent city planning system and method based on big data analysis
CN116823578A
Urban surface deformation risk fine identification method combined with multi-source data assistance
CN117975297A
Land resource space optimization configuration method applied to land utilization planning
CN117993572A
KR20190105209A
