An AI-based surveying and mapping data processing system

Abstract

The present invention relates to the field of surveying and mapping data technology, and specifically to an AI-based surveying and mapping data processing system, the system comprising a data source weight allocation module, a data fusion module, a real-time terrain monitoring module, and a geographic anomaly analysis module. The present invention, by introducing the timeliness and accuracy evaluation of different data sources in the data source weight allocation, can allocate weights to multi-source data, so that data from different sources can be appropriately adjusted according to their reliability when synthesized, avoiding data redundancy, optimizing the impact of high-quality data, monitoring environmental changes in real time according to the terrain change rate, accurately evaluating the abnormal degree of changes according to the update frequency and terrain type, and identifying potential terrain data problems. By analyzing abnormal terrain changes and combining the impact evaluation on human activity areas, the urgency of abnormal changes can be effectively judged, providing timely and effective support for decision-making.

Description

Technical Field

[0001] The present invention relates to the field of surveying and mapping data technology, and in particular to an AI-based surveying and mapping data processing system. Background Art

[0002] The field of surveying and mapping data technology involves the collection, processing, analysis and display of geographic information. The core technologies in this field include map making, satellite remote sensing, geographic information systems, global positioning systems and photogrammetry. Surveying and mapping technology not only supports the precise measurement of topography and landforms, but also analyzes and predicts the distribution of natural resources, environmental changes and urban development. With the development of technology, surveying and mapping data processing is becoming more and more automated and intelligent. Modern surveying and mapping technology can provide real-time data support through sensors and data processing algorithms, and is widely used in many important fields such as planning, disaster management and national defense.

[0003] Among them, the surveying and mapping data processing system is a system specially designed for efficient organization, analysis and interpretation of surveying and mapping data. The system can process geographic and spatial data collected from various sources, clean, match and integrate the data through algorithms, and generate surveying and mapping data that can be used for a variety of applications. Applications include urban planning, environmental monitoring, traffic flow analysis, and disaster response and management, providing strong data support for decision makers.

[0004] Traditional processing systems directly merge data from different sources, failing to assign reasonable weights to aspects such as time differences and source accuracy, resulting in redundancy or errors in the data fusion process, reducing the reliability and accuracy of the final result. Terrain change monitoring in traditional systems relies on static models and manually set thresholds, which respond slowly to real-time changes and fail to capture abnormal environmental changes in a timely manner. For example, failure to detect and warn of earthquakes or floods in certain areas in a timely manner will cause significant social and economic losses. In addition, traditional systems cannot effectively determine the relationship between abnormal terrain changes and human activities, resulting in delayed emergency responses and inaccurate 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 surveying and mapping data processing system based on AI.

[0006] In order to achieve the above-mentioned purpose, the present invention adopts the following technical solution: an AI-based surveying and mapping data processing system, the system comprising:

[0007] The data source weight allocation module uses AI to collect multi-source mapping data based on the target mapping area. The multi-source mapping data includes satellite data, drone data, and ground measurement data. The real-time score of the differentiated data source is evaluated according to the update frequency and timeliness of the multi-source data. The weight of the differentiated data source is evaluated in combination with the precision and accuracy of the differentiated data source to obtain the data source weight evaluation result.

[0008] The data fusion module synchronizes the timestamp and spatial position of the data based on the data source weight evaluation result, and calculates the comprehensive value of the differentiated data points according to the data source weight to obtain multi-source data fusion information;

[0009] The real-time terrain monitoring module evaluates the terrain change rate of the differentiated locations based on the multi-source data fusion information and the fused terrain data in combination with the corresponding update timestamps, evaluates the abnormal degree of terrain change in combination with the terrain type, identifies abnormal terrain changes, and obtains abnormal terrain change identification results;

[0010] Based on the abnormal terrain change identification results, the geographic anomaly analysis module analyzes the distance between the abnormal terrain change and the human activity area, evaluates the impact of the abnormal terrain change on human activities, and evaluates the urgency of the abnormal terrain change in combination with the area of ​​the abnormal terrain, and generates an abnormal geographic event identification result.

[0011] The present invention is improved in that the method for evaluating the real-time scoring of the differentiated data sources is:

[0012] Based on the target mapping area, AI is used to collect multi-source mapping data, including satellite data, drone data, and ground measurement data;

[0013] Based on the multi-source surveying and mapping data, extract the data acquisition timestamp, analyze the difference between the current time and the data acquisition time, and obtain time difference data;

[0014] Based on the time difference data, combined with the update frequency of the data source, the formula is:

[0015] ;

[0016] Calculate the standardized real-time score of each data source to obtain the data source real-time evaluation result;

[0017] in, is the time decay constant, is the time difference, is the adjustment factor, is the data update frequency, and are the preset minimum and maximum values ​​for the real-time score, is the base of natural logarithms, Standardized real-time scoring.

[0018] The present invention is improved in that the step of obtaining the data source weight evaluation result is:

[0019] Based on the real-time evaluation results of the data sources, the data precision and accuracy parameters corresponding to each data source are extracted to obtain weight association information;

[0020] Based on the weight association information, through the formula:

[0021] ;

[0022] Calculate the weight of each data source and obtain the data source weight evaluation result;

[0023] in, is the precision parameter of the data type, is the accuracy parameter of the data type, To standardize the real-time scoring, , and is the adjustment factor, The weight of the data source.

[0024] The present invention is improved in that the step of acquiring the multi-source data fusion information is:

[0025] Based on the data source weight evaluation result, the time and space position of the data are synchronized, the consistency of the data points in time and space is verified, and data synchronization information is obtained;

[0026] Based on the data synchronization information, by formula:

[0027] ;

[0028] Calculate the fused terrain data value to obtain multi-source data fusion information;

[0029] in, For the The weight of the data source, For the The terrain data value of the data source, is the fused terrain data value, is the number of data sources.

[0030] The present invention is improved in that the method for evaluating the rate of terrain change at a differentiated location is:

[0031] Based on the multi-source data fusion information, terrain data of the target location at the differentiated timestamps are collected, and the corresponding time difference is extracted to obtain terrain change related data;

[0032] Based on the terrain change associated data, through the formula;

[0033] ;

[0034] Calculate the terrain change rate and obtain terrain change information;

[0035] in, and Respectively represent the fused terrain data values ​​of the target location at two time points, is the time difference between two time points, is the rate of terrain change.

[0036] The present invention is improved in that the steps of obtaining the abnormal terrain change identification result are:

[0037] Based on the terrain change information, extracting type data of differentiated locations through a geographic information system to obtain location type information;

[0038] Based on the location type information, by the formula:

[0039] ;

[0040] Calculate the degree of abnormality;

[0041] in, is the terrain change rate, is the average rate of change, is the weight coefficient of the difference, is the terrain type influencing factor, is the adjustment factor, is the translation coefficient, for the degree of abnormality;

[0042] Based on the abnormality degree, the abnormality degree is compared with a preset abnormality threshold, and the terrain change with an abnormality degree higher than the preset abnormality threshold is marked as abnormal, so as to obtain an abnormal terrain change identification result.

[0043] The present invention is improved in that the method for evaluating the impact of abnormal terrain changes on human activities is:

[0044] Based on the abnormal terrain change identification result, extract the central geographic coordinates of the abnormal terrain change area and the human activity area to obtain geographic coordinate information;

[0045] Based on the geographic coordinate information, the formula is:

[0046] ;

[0047] Calculate the distance between the area of ​​abnormal terrain change and the area of ​​human activity;

[0048] in, is the distance between the area of ​​abnormal terrain changes and the area of ​​human activities, is the center coordinate of the abnormal terrain change area, is the center coordinate of the human activity area;

[0049] Based on the distance between the abnormal terrain change area and the human activity area, the formula is:

[0050] ;

[0051] Calculate the impact score of abnormal terrain changes on human activities, evaluate the impact of abnormal terrain changes on human activities, and obtain abnormal impact assessment information;

[0052] in, Indicates the impact score of abnormal terrain changes on human activities, For abnormal degree, is the distance between the area of ​​abnormal terrain changes and the area of ​​human activities, is the influence weight coefficient.

[0053] The present invention is improved in that the steps of obtaining the abnormal geographical event identification result are:

[0054] Based on the abnormal impact assessment information, the area of ​​the abnormal terrain change region is extracted through a geographic information system to obtain abnormal area data;

[0055] Based on the abnormal area data, the formula:

[0056] ;

[0057] Calculate the degree of urgency and obtain the results of abnormal geographic event identification;

[0058] in, and is the adjustment coefficient, is the area of ​​abnormal terrain change region, is the area threshold, Score the impact of abnormal terrain changes on human activities, For urgency.

[0059] Compared with the prior art, the advantages and positive effects of the present invention are:

[0060] In the present invention, by introducing the timeliness and accuracy evaluation of different data sources in the data source weight distribution, it is possible to distribute weights for multi-source data, so that when data from different sources are synthesized, they can be appropriately adjusted according to their reliability, avoiding data redundancy, optimizing the impact of high-quality data, monitoring environmental changes in real time according to the terrain change rate, accurately evaluating the abnormal degree of changes according to the update frequency and terrain type, and identifying potential terrain data problems. By analyzing abnormal terrain changes and combining them with the impact evaluation on human activity areas, the urgency of abnormal changes can be effectively judged, providing timely and effective support for decision-making, and avoiding the problems of data asymmetry and poor timeliness in traditional surveying and mapping methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 is a system flow chart of the present invention;

[0062] Figure 2 A flow chart for evaluating the real-time scoring of differentiated data sources for the present invention;

[0063] Figure 3 A flowchart of obtaining a data source weight evaluation result for the present invention;

[0064] Figure 4 A flowchart of the present invention for obtaining multi-source data fusion information;

[0065] Figure 5 A flow chart for evaluating the rate of terrain change at differentiated locations for the present invention;

[0066] Figure 6 A flow chart of obtaining abnormal terrain change identification results for the present invention;

[0067] Figure 7 A flow chart for evaluating the impact of abnormal terrain changes on human activities for the present invention;

[0068] Figure 8 The present invention is a flow chart for obtaining abnormal geographic event identification results. DETAILED DESCRIPTION

[0069] 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.

[0070] 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", etc., indicating positions or positional relationships, are 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 "multiple" is two or more, unless otherwise clearly and specifically defined.

[0071] See also Figure 1 The present invention provides a technical solution: a surveying and mapping data processing system based on AI, the system comprising:

[0072] The data source weight allocation module uses AI to collect multi-source mapping data based on the target mapping area. The multi-source mapping data includes satellite data, drone data, and ground measurement data. The real-time score of the differentiated data source is evaluated according to the update frequency and timeliness of the multi-source data. The weight of the differentiated data source is evaluated in combination with the precision and accuracy of the differentiated data source to obtain the data source weight evaluation result.

[0073] The data fusion module synchronizes the timestamp and spatial position of the data based on the data source weight evaluation results, and calculates the comprehensive value of the differentiated data points according to the data source weight to obtain multi-source data fusion information;

[0074] The real-time terrain monitoring module is based on multi-source data fusion information. According to the fused terrain data combined with the corresponding update timestamp, it evaluates the terrain change rate of differentiated locations, combines the terrain type, evaluates the abnormal degree of terrain change, identifies abnormal terrain changes, and obtains abnormal terrain change identification results;

[0075] Based on the abnormal terrain change identification results, the geographic anomaly analysis module analyzes the distance between the abnormal terrain change and the human activity area, evaluates the impact of the abnormal terrain change on human activities, and evaluates the urgency of the abnormal terrain change based on the area of ​​the abnormal terrain, generating abnormal geographic event identification results.

[0076] The data source weight assessment results include the scoring criteria, data update frequency and weight value of the data source. The multi-source data fusion information includes the weighted average results of timestamp aligned data, spatial label unified data and data sources. The abnormal terrain change identification results include the terrain change rate, terrain change trend and key change area identification results. The abnormal geographic event identification results include a list of abnormal locations, potential environmental impact assessment and urgency rating.

[0077] See also Figure 2 ,The method to evaluate the real-time score of the differentiated data sources is:

[0078] Based on the target mapping area, AI is used to collect multi-source mapping data, including satellite data, drone data, and ground measurement data;

[0079] Based on multi-source surveying and mapping data, extract the data acquisition timestamp, analyze the difference between the current time and the data acquisition time, and obtain the time difference data;

[0080] Based on the time difference data and the update frequency of the data source, the formula is:

[0081] ;

[0082] Calculate the standardized real-time score of each data source to obtain the data source real-time evaluation result;

[0083] in, is the time decay constant, is the time difference, is the adjustment factor, is the data update frequency, and are the preset minimum and maximum values ​​for the real-time score, is the base of natural logarithms, Standardized real-time scoring.

[0084] formula:

[0085] ; Parameter meaning and acquisition method:

[0086] Time decay constant : The parameter is used to adjust the influence of time difference on real-time score. Usually, This is obtained through experiments or historical data analysis to ensure that the impact of time difference on the score is consistent with the actual application scenario.

[0087] Time difference : It is the difference between the current time and the data collection time, usually obtained through the system timestamp, and is calculated by subtracting the data collection time from the current time point.

[0088] Adjustment factor : The coefficient is used to adjust the weight of data update frequency in the score. Its value is determined based on actual application requirements or through an optimization algorithm to reflect the actual impact of different update frequencies on real-time performance.

[0089] Data update frequency : Indicates the number of updates of the data source per unit time. It is obtained through the update log recorded by the data management system or directly queried through the data interface.

[0090] The preset minimum value of the real-time score and maximum value : The values ​​are set according to specific application requirements and historical data to standardize the real-time score to a reasonable range. These two values ​​are usually determined through statistical analysis or expert experience.

[0091] Calculation example:

[0092] Set the following parameters: current time is December 5, 2023, data collection time is December 1, 2023, time decay constant , a smaller value means that the time delay has less impact, and the update frequency Times / month means 4 updates per month, update frequency adjustment factor , usually between 0.01 and 0.1, adjusted according to actual needs, the minimum score and maximum score , which is a common rating range.

[0093] Calculate time difference :

[0094] ;

[0095] Calculating real-time scores :

[0096] ;

[0097] Real-time scoring of calculation results The score is 0.87032, which means that the real-time performance of the data source is rated as high based on the current parameter settings and data update status. The score reflects the comprehensive impact of the update frequency of the data source and the time of the most recent data collection on its timeliness, and is a useful indicator for real-time evaluation.

[0098] See also Figure 3 , the steps to obtain the data source weight evaluation results are:

[0099] Based on the real-time evaluation results of data sources, the data precision and accuracy parameters corresponding to each data source are extracted to obtain weight association information;

[0100] Based on the weight association information, through the formula:

[0101] ;

[0102] Calculate the weight of each data source and obtain the data source weight evaluation result;

[0103] in, is the precision parameter of the data type, is the accuracy parameter of the data type, To standardize the real-time scoring, , and is the adjustment factor, The weight of the data source.

[0104] formula:

[0105] ;

[0106] The meaning and acquisition method of parameters:

[0107] The precision parameter of the data type : Indicates the measurement precision and small error range of the data, which can be expressed by the accuracy level. For example, there are 10 accuracy levels in total. Level 10 accuracy is within 1 meter, and level 1 accuracy is within 10 meters. The higher the accuracy level, the smaller the error range.

[0108] Data type accuracy parameter : Indicates how well the data agrees with the true value. Usually this is derived by comparing the validation data to a known benchmark or landmark, and is expressed as a percentage.

[0109] Standardized real-time scoring : Calculated by the previous steps.

[0110] Adjustment factor , and : The coefficient is used to adjust the influence of each parameter in the weight calculation. For example, The influence of adjustment accuracy, The impact of adjustment accuracy, Adjust the impact of the real-time score. The coefficient is usually set based on the specific needs of the application or optimized through historical data analysis.

[0111] Calculation example:

[0112] Set the following parameters: Accuracy .accuracy ( ), indicating the degree of agreement with the actual landmark. Generally, the accuracy of satellite data is high, reaching more than 90%. Standardized real-time scoring ,coefficient , , .

[0113] Calculate the weight of the data source as follows:

[0114] ;

[0115] In the calculation example, the weight The score is 2.2311, which combines the precision, accuracy and real-time impact of the data. A score higher than 1 indicates that the data source is of high quality under given parameters. The score can be used to compare with the weights of other data sources to determine which data sources are more suitable for specific applications.

[0116] See also Figure 4 ,The steps to obtain multi-source data fusion information are:

[0117] Based on the data source weight evaluation results, synchronize the time and space location of the data, verify the consistency of the data points in time and space, and obtain data synchronization information;

[0118] Based on data synchronization information, through the formula:

[0119] ;

[0120] Calculate the fused terrain data value to obtain multi-source data fusion information;

[0121] in, For the The weight of the data source, For the The terrain data value of the data source, is the fused terrain data value, is the number of data sources.

[0122] formula:

[0123] ;

[0124] The meaning and acquisition method of parameters:

[0125] : No. The weight of each data source is calculated in the previous step.

[0126] : No. The terrain data values ​​from a data source are raw data directly obtained through measuring equipment.

[0127] : The number of data sources, such as satellite data, drone data, and ground measurement data.

[0128] Calculation example:

[0129] There are three data sources, each with its own terrain height data value. and weight As follows: Data source 1: rice, ; Data source 2: rice, ; Data source 3: rice, .

[0130] Calculate the fused terrain data value:

[0131] ;

[0132] The obtained fused terrain height is 101.1 meters. This result is obtained by combining the terrain heights and corresponding weights of various data sources through weighted averaging, ensuring that the contribution of data sources is considered according to their importance and reliability. This result can be used in terrain analysis or map creation to provide consistent and accurate terrain height information.

[0133] See also Figure 5 , the method to evaluate the rate of terrain change at differentiated locations is:

[0134] Based on multi-source data fusion information, the terrain data of the target location at the differentiated timestamps are collected, and the corresponding time difference is extracted to obtain the terrain change correlation data;

[0135] Based on the terrain change correlation data, through the formula;

[0136] ;

[0137] Calculate the terrain change rate and obtain terrain change information;

[0138] in, and Respectively represent the fused terrain data values ​​of the target location at two time points, is the time difference between two time points, is the rate of terrain change.

[0139] formula;

[0140] ;

[0141] The meaning and acquisition method of parameters:

[0142] and : The fused terrain data value of the target location at two time points, obtained through the previous steps.

[0143] : The time difference between two time points is and The time interval between.

[0144] Calculation example:

[0145] Set the following parameters: At time 1 (January 2023), the terrain height m. At time 2 (March 2023), terrain height 5 meters. Time difference February.

[0146] Calculating terrain change rate :

[0147] ;

[0148] ;

[0149] ;

[0150] ;

[0151] The result is 3.75, represents the rate of change of terrain. The calculation method particularly emphasizes the sensitivity of the rate of change of terrain when the time difference is short, and is more suitable for monitoring rapidly changing terrain.

[0152] See also Figure 6 , the steps to obtain the abnormal terrain change identification results are:

[0153] Based on the terrain change information, the type data of differentiated locations are extracted through the geographic information system to obtain location type information;

[0154] Based on the location type information, through the formula:

[0155] ;

[0156] Calculate the degree of abnormality;

[0157] in, is the terrain change rate, is the average rate of change, is the weight coefficient of the difference, is the terrain type influencing factor, is the adjustment factor, is the translation coefficient, for the degree of abnormality;

[0158] Based on the degree of abnormality, the abnormality is compared with the preset abnormality threshold, and the terrain changes with abnormality levels higher than the preset abnormality threshold are marked as abnormal, thereby obtaining abnormal terrain change identification results.

[0159] formula:

[0160] ;

[0161] The meaning and acquisition method of parameters:

[0162] : Terrain change rate, calculated by the previous step.

[0163] : Average change rate, historical average terrain change rate, represents the average value of terrain change rate in historical time, usually calculated based on measurement data in the past few years.

[0164] : The weight coefficient of the difference, which indicates the contribution of the difference to the anomaly recognition result. The coefficient is set according to the actual application scenario, generally through multiple experiments or the experience of field experts.

[0165] : Terrain type influencing factor, which indicates the tolerance and impact of terrain type on the rate of change. Different types of terrain have different adaptability to changes. For example, deserts and mountains have different tolerance to the rate of change. It is preset according to demand.

[0166] : Adjustment coefficient, used to adjust the degree of influence of the logarithmic part of the terrain change rate. By analyzing the actual terrain change data, the impact of logarithmic transformation on the anomaly recognition results is determined.

[0167] : Logarithmic translation coefficient, ensuring the internal logarithm The value after adding the absolute value is always positive to avoid negative values ​​in logarithmic calculations. The coefficient is set by the minimum value of the terrain change rate.

[0168] Calculation example:

[0169] Set the following parameters: Meters / month, indicating the current measured rate of terrain change; Meters / month, indicating the historical average rate of terrain change over a period of time; , the weight coefficient of the difference part; , terrain type influencing factor, assuming desert terrain; , adjustment coefficient for the logarithmic part; , logarithmic shift coefficient; set the abnormal threshold to .

[0170] Calculate the difference between the rate of terrain change and the historical average rate

[0171] calculate : ;

[0172] Calculate the contribution of the difference part: ;

[0173] Compute the logarithmic part: ;

[0174] Multiply the logarithmic part by the adjustment factor and terrain type factors : ;

[0175] Calculating outliers : ;

[0176] The calculated outlier value of terrain change is , which is slightly larger than the set abnormal threshold , so the terrain change is judged to be abnormal.

[0177] See also Figure 7 , the method to assess the impact of abnormal terrain changes on human activities is:

[0178] Based on the abnormal terrain change identification results, the central geographic coordinates of the abnormal terrain change area and the human activity area are extracted to obtain the geographic coordinate information;

[0179] Based on geographic coordinate information, through the formula:

[0180] ;

[0181] Calculate the distance between the area of ​​abnormal terrain change and the area of ​​human activity;

[0182] in, is the distance between the area of ​​abnormal terrain changes and the area of ​​human activities, is the center coordinate of the abnormal terrain change area, is the center coordinate of the human activity area;

[0183] Based on the distance between the abnormal terrain change area and the human activity area, the formula is:

[0184] ;

[0185] Calculate the impact score of abnormal terrain changes on human activities, evaluate the impact of abnormal terrain changes on human activities, and obtain abnormal impact assessment information;

[0186] in, Indicates the impact score of abnormal terrain changes on human activities, For abnormal degree, is the distance between the area of ​​abnormal terrain changes and the area of ​​human activities, is the influence weight coefficient.

[0187] formula:

[0188] ;

[0189] The meaning and acquisition method of parameters:

[0190] : Indicates the distance between the area of ​​abnormal terrain change and the area of ​​human activity. The distance is obtained by calculating the Euclidean distance between the center of the abnormal terrain change and the center of the nearest human activity area, usually in meters or kilometers. The coordinates of the two can be obtained through the Geographic Information System (GIS), and then calculated using the Euclidean formula.

[0191] Calculation method:

[0192] ;

[0193] in, and They are the geographical coordinates of abnormal terrain changes and human activity areas, respectively.

[0194] : The abnormality degree is obtained through the previous steps.

[0195] : Impact weight coefficient, which is used to adjust the weight of the distance between abnormal terrain changes and human activity areas on the impact degree. The coefficient reflects the relative importance of abnormal terrain changes and distance in the impact of human activities. A higher value means that the impact of abnormal terrain changes and distance is greater. The coefficient is usually set through expert evaluation.

[0196] Calculation example:

[0197] Set the following parameters: Coordinates of abnormal terrain changes , the coordinates of the human activity area , abnormality , influence weight coefficient .

[0198] Calculate the distance between abnormal terrain changes and human activity areas , calculated using the Euclidean distance formula:

[0199] ;

[0200] Calculate the impact of abnormal terrain changes on human activities :

[0201] ;

[0202] Determine the impact , indicating that under the current distance between abnormal terrain changes and human activity areas, abnormal degree and weight coefficient, the impact of this terrain change on human activities is small.

[0203] See also Figure 8 ,The steps to obtain the abnormal geographic event identification results are:

[0204] Based on the abnormal impact assessment information, the area of ​​the abnormal terrain change area is extracted through the geographic information system to obtain the abnormal area data;

[0205] Based on the abnormal area data, the formula:

[0206] ;

[0207] Calculate the degree of urgency and obtain the results of abnormal geographic event identification;

[0208] in, and is the adjustment coefficient, is the area of ​​abnormal terrain change region, is the area threshold, Score the impact of abnormal terrain changes on human activities, For urgency.

[0209] formula:

[0210] ;

[0211] The meaning and acquisition method of parameters:

[0212] The area of ​​abnormal terrain changes : Indicates the area of ​​abnormal terrain changes, usually in square meters or square kilometers. The parameter is usually extracted through remote sensing data or GIS technology, using satellite images, drone data or ground measurements to obtain spatial information of abnormal terrain areas and calculate the total area of ​​the changed area.

[0213] Area Threshold : Used to determine the size of the area of ​​abnormal terrain changes. After setting the threshold, it can be compared with the actual area. When the area is larger than this threshold, the impact of the urgency will increase. This threshold is usually set through historical data analysis, geographical characteristics or expert experience.

[0214] Impact of abnormal terrain change areas on human activities : Calculated by the previous steps.

[0215] Adjustment factor and :Two coefficients are used to adjust the weights of area and impact in the calculation of urgency. The specific values ​​are usually determined based on historical data, expert experience or field research, indicating the importance of each factor to the urgency. The size of the coefficient determines the contribution of different factors to the urgency.

[0216] Calculation example:

[0217] Set the following parameters: Abnormal terrain change area , indicating that the area of ​​the abnormal terrain change area is 2 square kilometers, and the area threshold The area threshold is set at 1 square kilometer to determine the size of the changed area and the impact of abnormal terrain changes on human activities. , adjustment coefficient and , both coefficients are 0.5, indicating that the area and impact have equal weights on the urgency.

[0218] Calculating urgency :

[0219] ;

[0220] The urgency level , indicating that the urgency of the abnormal terrain change event is high. The abnormal terrain change event has a high urgency and measures need to be taken as soon as possible to respond.

[0221] 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. An AI-based surveying and mapping data processing system, characterized in that: The system includes a data source weight distribution module, a data fusion module, a real-time terrain monitoring module and a geographic anomaly analysis module; The data source weight allocation module uses AI to collect multi-source mapping data based on the target mapping area. The multi-source mapping data includes satellite data, drone data, and ground measurement data. The real-time score of the differentiated data source is evaluated according to the update frequency and timeliness of the multi-source data. The weight of the differentiated data source is evaluated in combination with the precision and accuracy of the differentiated data source to obtain the data source weight evaluation result. The data fusion module synchronizes the timestamp and spatial position of the data based on the data source weight evaluation result, and calculates the comprehensive value of the differentiated data points according to the data source weight to obtain multi-source data fusion information; The real-time terrain monitoring module evaluates the terrain change rate of the differentiated locations based on the multi-source data fusion information and the fused terrain data in combination with the corresponding update timestamps, evaluates the abnormal degree of terrain change in combination with the terrain type, identifies abnormal terrain changes, and obtains abnormal terrain change identification results; Based on the abnormal terrain change identification results, the geographic anomaly analysis module analyzes the distance between the abnormal terrain change and the human activity area, evaluates the impact of the abnormal terrain change on human activities, and evaluates the urgency of the abnormal terrain change in combination with the area of ​​the abnormal terrain, and generates an abnormal geographic event identification result.

2. The AI-based surveying and mapping data processing system according to claim 1, characterized in that: The method for evaluating the real-time scoring of the differentiated data sources is: Based on the target mapping area, AI is used to collect multi-source mapping data, including satellite data, drone data, and ground measurement data; Based on the multi-source surveying and mapping data, extract the data acquisition timestamp, analyze the difference between the current time and the data acquisition time, and obtain time difference data; Based on the time difference data, combined with the update frequency of the data source, the formula is: ； Calculate the standardized real-time score of each data source to obtain the data source real-time evaluation result; in, is the time decay constant, is the time difference, is the adjustment factor, is the data update frequency, and are the preset minimum and maximum values ​​for the real-time score, is the base of natural logarithms, Standardized real-time scoring.

3. The AI-based surveying and mapping data processing system according to claim 2, characterized in that: The steps for obtaining the data source weight evaluation result are: Based on the real-time evaluation results of the data sources, the data precision and accuracy parameters corresponding to each data source are extracted to obtain weight association information; Based on the weight association information, through the formula: ； Calculate the weight of each data source and obtain the data source weight evaluation result; in, is the precision parameter of the data type, is the accuracy parameter of the data type, To standardize the real-time scoring, , and is the adjustment factor, The weight of the data source.

4. The AI-based surveying and mapping data processing system according to claim 1, characterized in that: The steps for obtaining the multi-source data fusion information are as follows: Based on the data source weight evaluation result, the time and space position of the data are synchronized, the consistency of the data points in time and space is verified, and data synchronization information is obtained; Based on the data synchronization information, by formula: ； Calculate the fused terrain data value to obtain multi-source data fusion information; in, For the The weight of the data source, For the The terrain data value of the data source, is the fused terrain data value, is the number of data sources.

5. The AI-based surveying and mapping data processing system according to claim 1, characterized in that: The method for evaluating the rate of terrain change at differentiated locations is: Based on the multi-source data fusion information, terrain data of the target location at the differentiated timestamps are collected, and the corresponding time difference is extracted to obtain terrain change related data; Based on the terrain change associated data, through the formula; ； Calculate the terrain change rate and obtain terrain change information; in, and Respectively represent the fused terrain data values ​​of the target location at two time points, is the time difference between two time points, is the rate of terrain change.

6. The AI-based surveying and mapping data processing system according to claim 5, characterized in that: The steps for obtaining the abnormal terrain change identification result are: Based on the terrain change information, extracting type data of differentiated locations through a geographic information system to obtain location type information; Based on the location type information, by the formula: ； Calculate the degree of abnormality; in, is the terrain change rate, is the average rate of change, is the weight coefficient of the difference, is the terrain type influencing factor, is the adjustment factor, is the translation coefficient, for the degree of abnormality; Based on the abnormality degree, the abnormality degree is compared with a preset abnormality threshold, and the terrain change with an abnormality degree higher than the preset abnormality threshold is marked as abnormal, so as to obtain an abnormal terrain change identification result.

7. The AI-based surveying and mapping data processing system according to claim 1, characterized in that: The method for evaluating the impact of abnormal terrain changes on human activities is: Based on the abnormal terrain change identification result, extract the central geographic coordinates of the abnormal terrain change area and the human activity area to obtain geographic coordinate information; Based on the geographic coordinate information, the formula is: ； Calculate the distance between the area of ​​abnormal terrain change and the area of ​​human activity; in, is the distance between the area of ​​abnormal terrain changes and the area of ​​human activities, is the center coordinate of the abnormal terrain change area, is the center coordinate of the human activity area; Based on the distance between the abnormal terrain change area and the human activity area, the formula is: ； Calculate the impact score of abnormal terrain changes on human activities, evaluate the impact of abnormal terrain changes on human activities, and obtain abnormal impact assessment information; in, Indicates the impact score of abnormal terrain changes on human activities, For abnormal degree, is the distance between the area of ​​abnormal terrain changes and the area of ​​human activities, is the influence weight coefficient.

8. The AI-based surveying and mapping data processing system according to claim 7, characterized in that: The steps for obtaining the abnormal geographic event identification result are: Based on the abnormal impact assessment information, the area of ​​the abnormal terrain change region is extracted through a geographic information system to obtain abnormal area data; Based on the abnormal area data, the formula: ； Calculate the degree of urgency and obtain the results of abnormal geographic event identification; in, and is the adjustment coefficient, is the area of ​​abnormal terrain change region, is the area threshold, Score the impact of abnormal terrain changes on human activities, For urgency.

Images