A method and system for collecting geographic surveying and mapping information based on big data

Abstract

The present invention provides a geographic surveying and mapping information collection method and system based on big data, which relates to the field of data processing technology. The method comprises: collecting geographic surveying and mapping information, including geological soil information, geological disaster information, and hydrological information; classifying the geographic surveying and mapping information to obtain classification results; predicting the disaster risk levels of different regions according to the classification results to obtain prediction results; optimizing the layout of disaster monitoring points according to the prediction results, using the SWAT model to simulate the hydrological cycle process to predict water level and flow changes; evaluating water quality according to water level and flow changes to obtain evaluation results; optimizing the water resource allocation plan according to the evaluation results to obtain data analysis results. The present invention not only improves the efficiency of data collection, but also ensures the comprehensiveness and accuracy of the data.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for collecting geographic surveying and mapping information based on big data. Background Art

[0002] Some traditional methods of collecting geographic surveying and mapping information are based on manual field surveys and sample analysis. Although this method can provide relatively accurate data, it is somewhat inefficient, has limited coverage, and is difficult to update data in a timely manner.

[0003] Therefore, when faced with massive amounts of geographic surveying and mapping data, some traditional data processing methods require a lot of time and computing resources, resulting in low processing efficiency and possibly failing to meet real-time or near-real-time data processing requirements. Some existing classification algorithms are difficult to accurately classify when faced with complex and changeable geographic surveying and mapping data, which seriously affects subsequent risk prediction and assessment work. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a method and system for collecting geographic surveying and mapping information based on big data, which not only improves the efficiency of data collection, but also ensures the comprehensiveness and accuracy of the data.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows:

[0006] In a first aspect, a method for collecting geographic surveying and mapping information based on big data, the method comprising:

[0007] Collect geographic surveying and mapping information, including geological soil information, geological disaster information, and hydrological information;

[0008] Classify geographic surveying and mapping information to obtain classification results;

[0009] According to the classification results, the disaster risk levels of different regions are predicted to obtain the prediction results;

[0010] According to the prediction results, the layout of disaster monitoring points is optimized, and the SWAT model is used to simulate the hydrological cycle process to predict water level and flow changes;

[0011] Assess water quality based on water level and flow changes to obtain assessment results;

[0012] Based on the evaluation results, the water resource allocation plan is optimized to obtain data analysis results.

[0013] Furthermore, the geographic surveying and mapping information is classified to obtain classification results, including:

[0014] Split geographic mapping information into training and testing sets;

[0015] For each sample in the test set, Calculate the distance between each sample and all samples in the training set, where Representation sample and samples The distance between Represents the dimension of the feature, representing the sample and samples The number of features; Indicates The standard deviation of the feature; and It is a sample and samples In the The value after nonlinear transformation on the features; and Respectively represent samples and samples In the The value of a feature; It means that after nonlinear transformation, the sample and samples In the The squared difference between the transformed values ​​on the features; represents the regularization parameter, and its value is between (0, 1); and Represents an index; Indicates The standard deviation of the features; ; ;

[0016] According to the distance, find the K nearest neighbors of the test sample in the geographic mapping information;

[0017] For each category, create a counter with an initial value of 0; for the K nearest neighbors found for the test sample, check the corresponding labels in turn;

[0018] For each nearest neighbor label, find the corresponding category counter and add 1 to its value, indicating that the category appears once in the K nearest neighbors;

[0019] After traversing all K nearest neighbors, compare the values ​​of each category counter to obtain the category corresponding to the counter value, and set the classification label of the test sample to the majority category;

[0020] The test sample and its assigned classification label are recorded as part of the classification result, and the next test sample is processed until all test samples are classified to obtain the classification result.

[0021] Furthermore, based on the classification results, the disaster risk levels of different regions are predicted to obtain prediction results, including:

[0022] Determine the number and names of disaster risk levels and create a mapping table to map the classification labels to the corresponding disaster risk levels;

[0023] Store the classification results in a list, where each element contains the region's identity and classification label;

[0024] For each area in the classification result, extract its classification label and use the mapping table to find the disaster risk level corresponding to each classification label;

[0025] The disaster risk level assessment results of each area obtained during the traversal process are added to the dataset.

[0026] Furthermore, based on the prediction results, the layout of disaster monitoring points is optimized, and the SWAT model is used to simulate the hydrological cycle process to predict water level and flow changes, including:

[0027] Define an evaluation function for evaluating the pros and cons of monitoring point layout schemes;

[0028] Generate an initial monitoring point layout plan. Based on the initial monitoring point layout plan, randomly generate a new layout plan, use the evaluation function to evaluate the pros and cons of the new plan, and compare it with the current plan;

[0029] Decide whether to accept the new plan according to the Metropolis criterion, and update the current layout plan to the accepted new plan until the preset number of iterations is reached to obtain the final monitoring point layout plan;

[0030] Based on the collected hydrological data and topographic information, a hydrological cycle model of the study area is established;

[0031] Use the hydrological cycle model to run simulations and predict water level and flow changes under different climate conditions and monitoring point layouts to obtain simulation results;

[0032] Analyze simulation results and extract key information, including water level and flow changes at each monitoring point.

[0033] Furthermore, the calculation formula of the evaluation function is:

[0034] ;

[0035] in, Represents the value of the evaluation function; represents the weight coefficient; Indicates The area covered by each monitoring point; represents the exponential coefficient; represents the attenuation coefficient; Indicates The distance from a monitoring point to a specific reference point; Indicates the total number of monitoring points; Indicates The water level value of each monitoring point, the actual water level data collected; It represents the average water level of all monitoring points; represents the weight coefficient; represents the weight coefficient; Indicates the target water level, which indicates the ideal water level value to be monitored; The number indicating the target water level; Indicates The flow value of each monitoring point and the actual flow data collected; It represents the average flow rate of all monitoring points; represents the weight coefficient; represents the weight coefficient; Indicates the target flow rate, which indicates the ideal flow rate value that you want to monitor; Indicates the amount of target traffic; It is an index variable, used to traverse all monitoring points; is an index variable used to traverse the data related to the target water level; Is an index variable used to traverse the data related to the target traffic.

[0036] Furthermore, water quality is evaluated based on changes in water level and flow to obtain evaluation results, including:

[0037] Set multiple water quality indicators, including pH value, dissolved oxygen, and turbidity;

[0038] According to each water quality index, a fuzzy evaluation matrix R is constructed, where the formula of the fuzzy evaluation matrix R is:

[0039] ,in, Indicates The indicator for Evaluation of water quality; Indicates the first indicator for the Evaluation of water quality; Indicates the second indicator for the Evaluation of water quality; Indicates Evaluation of Class 1 water quality using indicators; Indicates Evaluation of Class 2 water quality using 10 indicators; Indicates The indicator for Evaluation of water quality; is the total number of indicators; Indicates the total number of water quality assessment categories;

[0040] Set weights for each indicator ,in, For the Indicators in time The dynamic weight of ;

[0041] in, is the number of past observations; It is The indicator is Observation value of the day; It is Indicators in time Observed value of is an adjustment factor; It is Indicators at the previous time point Observed value of Indicates Evaluation of water quality; Indicates the specific time point used to calculate the moving average; Indicates the total number of water quality indicators; It is The indicator is Observation value of the day;

[0042] pass Calculate the fuzzy comprehensive evaluation results, where It is the fuzzy comprehensive evaluation result, which represents the comprehensive evaluation value of different water quality levels.

[0043] Furthermore, based on the evaluation results, the water resource allocation plan is optimized to obtain data analysis results, including:

[0044] Determine the goals of water resource allocation and define objective functions to quantify the effectiveness of allocation plans;

[0045] Divide the water resource allocation problem into several stages, each stage represents a decision cycle, and determine the state space of each stage;

[0046] According to the dynamic characteristics of water resources, the state transfer equation is established to describe the evolution law of the state from one stage to the next;

[0047] For each stage and each state, calculate the evaluation function value when taking different decisions in this state;

[0048] Using the recursive relationship of dynamic programming, reverse calculation is performed from the last stage to the first stage;

[0049] In each stage, the optimal solution of the current stage is updated according to the solution of the previous stage and the state transfer equation. After completing the calculations of all stages, the solution of the first stage is the global final water resource allocation plan, where the global final water resource allocation plan is the result of data analysis.

[0050] In the second aspect, a geographic surveying and mapping information collection system based on big data includes:

[0051] The acquisition module is used to collect geographic surveying and mapping information, including geological soil information, geological disaster information, and hydrological information;

[0052] A classification module is used to classify geographic surveying and mapping information to obtain classification results;

[0053] The evaluation module is used to predict the disaster risk level of different regions based on the classification results to obtain the prediction results;

[0054] The prediction module is used to optimize the layout of disaster monitoring points according to the prediction results, and use the SWAT model to simulate the hydrological cycle process to predict water level and flow changes; evaluate the water quality according to the water level and flow changes to obtain the evaluation results; and optimize the water resource allocation plan according to the evaluation results to obtain data analysis results.

[0055] According to a third aspect, a computing device includes:

[0056] one or more processors;

[0057] The storage device is used to store one or more programs. When the one or more programs are executed by the one or more processors, the one or more processors implement the method described.

[0058] In a fourth aspect, a computer-readable storage medium stores a program, and when the program is executed by a processor, the method described is implemented.

[0059] The above scheme of the present invention includes at least the following beneficial effects.

[0060] By collecting various types of geographic surveying and mapping information, a complete and multi-dimensional data set can be established; classification processing can help to organize the complex geographic surveying and mapping information and improve the organization of data; through accurate classification, the correlation and difference between different types of data can be more effectively identified; disaster risk prediction based on classified data can achieve scientific division of risk levels in different regions, which helps to improve the efficiency and effectiveness of disaster response; by optimizing the layout of disaster monitoring points, it can ensure that the monitoring network covers high-risk areas and improve the sensitivity and timeliness of monitoring. At the same time, using the SWAT model to simulate the hydrological cycle process can help to more accurately predict water level and flow changes; through the analysis of water level and flow changes, the possible pollution risks of water bodies can be discovered in time; optimizing the water resource allocation plan based on water quality assessment results can ensure the rational allocation and efficient use of water resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a flow chart of a method for collecting geographic surveying and mapping information based on big data provided by an embodiment of the present invention.

[0062] Figure 2 It is a schematic diagram of a geographic surveying and mapping information collection system based on big data provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0064] like Figure 1 As shown, an embodiment of the present invention provides a method for collecting geographic surveying and mapping information based on big data, and the method comprises the following steps:

[0065] Step 11, collecting geographic surveying and mapping information, including geological soil information, geological disaster information, and hydrological information;

[0066] Step 12, classifying the geographic surveying and mapping information to obtain a classification result;

[0067] Step 13, predicting the disaster risk levels of different regions according to the classification results to obtain prediction results;

[0068] Step 14, based on the prediction results, optimize the layout of disaster monitoring points, and use the SWAT model to simulate the hydrological cycle process to predict water level and flow changes;

[0069] Step 15, evaluating the water quality according to the changes in water level and flow rate to obtain an evaluation result;

[0070] Step 16: Optimize the water resource allocation plan based on the evaluation results to obtain data analysis results.

[0071] In an embodiment of the present invention, step 11, by collecting geological soil information, geological disaster information and hydrological information, the method can establish a comprehensive geographic surveying and mapping information database. Step 12, classification processing can make the complex geographic surveying and mapping information more orderly and structured. Through classification, the intrinsic connections and differences between different types of data can be more effectively identified. Step 13, based on the classification results, the method can scientifically predict the disaster risk level in different regions, which helps to timely discover potential high-risk areas. Step 14, by optimizing the layout of disaster monitoring points, the method improves the coverage and effectiveness of monitoring. At the same time, by simulating the hydrological cycle process using the SWAT model, changes in water level and flow can be more accurately predicted. Step 15, based on changes in water level and flow, the method can effectively evaluate water quality, which helps to timely discover water quality problems. Step 16, based on the water quality assessment results, the method can formulate a more reasonable and efficient water resource allocation plan.

[0072] In another preferred embodiment of the present invention, the above step 11, collecting geographic surveying and mapping information, including geological soil information, geological disaster information, and hydrological information, may include:

[0073] Through field exploration, drilling sampling, geophysical exploration and other means, information on stratigraphic structure, rock properties, soil types and their physical and chemical properties is collected; using remote sensing technology, geographic information system (GIS) and other tools, combined with historical disaster data and field observations, information on the types, distribution, frequency and potential impacts of geological disasters is collected; through hydrological site observations, remote sensing monitoring, hydrological model simulation and other means, relevant data on rivers, lakes, reservoirs and other water bodies are systematically collected.

[0074] In a preferred embodiment of the present invention, the above step 12, classifying the geographic surveying and mapping information to obtain the classification result, may include:

[0075] Step 121, splitting the geographic surveying and mapping information into a training set and a test set. The purpose of this step is to divide the data into two parts: one part is used to train the model (training set), and the other part is used to evaluate the performance of the model (test set). The original data will be randomly divided into a training set and a test set, and the ratio can be 70:30 or 80:20.

[0076] Step 122, for each sample in the test set, Calculate the distance between each sample and all samples in the training set, where Representation sample and samples The distance between Represents the dimension of the feature, representing the sample and samples The number of features; Indicates The standard deviation of the feature; and It is a sample and samples In the The value after nonlinear transformation on the features; and Respectively represent samples and samples In the The value of a feature; It means that after nonlinear transformation, the sample and samples In the The squared difference between the transformed values ​​on the features; represents the regularization parameter, and its value is between (0, 1); and Represents an index; Indicates The standard deviation of the features; ; , including:

[0077] For each sample, consider its n features, which are the type of geological soil, the frequency of occurrence of a certain geological disaster, the value of a specific hydrological parameter, etc.; apply nonlinear transformations (such as logarithmic transformations) to process the feature values. In this example, we use Such a transformation helps deal with skewed distribution or nonlinear relationships of features; for each sample in the test set And each sample in the training set , calculate the distance between them , where the weight of each feature is inversely proportional to its standard deviation, which means that features with large variations (large standard deviations) will have relatively small effects in the distance calculation, thus preventing these features from over-dominantly leading the results; in addition, a regularization parameter is introduced , used to balance the differences and similarities between features, The value of is between 0 and 1; after this step, a distance matrix is ​​obtained, which contains the distance between each sample in the test set and all samples in the training set.

[0078] Step 123, based on the distance, find the K nearest neighbors of the test sample in the geographic surveying and mapping information, specifically including:

[0079] Step 124, for each category, create a counter with an initial value of 0; for the K nearest neighbors found for the test sample, check the corresponding labels in turn, specifically including: sorting the distances between the test sample and all samples in the training set calculated in step 122 from small to large, using a sorting algorithm (such as quick sort, merge sort, etc.); from the sorted distance list, select the training samples corresponding to the first K smallest distances. These samples are the K nearest neighbors of the test sample, where K is a pre-set parameter determined according to the size of the data set, and the K nearest neighbors found and their corresponding distance values ​​are stored.

[0080] Step 125, for each nearest neighbor label, find the corresponding category counter and add 1 to its value, indicating that the category appears once in the K nearest neighbors, specifically including: creating a corresponding number of counters according to the number of categories in the data set. Each counter corresponds to a category and is initialized to 0. These counters will be used to count the number of occurrences of each category in the K nearest neighbors; for the K nearest neighbors found in step 123, traverse each nearest neighbor in turn; during the traversal process, check the category label of each nearest neighbor, which is provided together with the training sample and identifies the category to which the sample belongs.

[0081] Step 126, after traversing all K nearest neighbors, compare the values ​​of each category counter to obtain the category corresponding to the counter value, and set the classification label of the test sample to the majority category, specifically including: in the process of traversing the K nearest neighbors and checking their labels, for each nearest neighbor's label, find the category counter corresponding to the label; add 1 to the value of the found category counter, which means that the category appears once again in the K nearest neighbors, and repeat the above process until all K nearest neighbors are traversed. After this step, a set of updated category counters will be obtained, which reflect the frequency of occurrence of each category in the K nearest neighbors.

[0082] Step 127, recording the test sample and its assigned classification label as part of the classification result, and continuing to process the next test sample until all test samples are classified to obtain the classification result, specifically including: creating an empty data structure (such as a list, array or dictionary) for storing the test sample and its corresponding classification label, and this data structure will be used as part of the final classification result; for the test sample currently being processed, determining the classification label of the test sample according to the category counter value obtained in the previous step (such as step 125); selecting the category with the largest counter value as the classification label of the test sample, that is, the majority voting principle; if there are multiple categories with the same and largest counter values, the tie can be broken according to preset rules (such as random selection, considering the next nearest neighbor, etc.) to determine the final classification label; recording the identifier (such as index, number, etc.) of the current test sample and the classification label assigned to it together in the previously initialized classification result data structure, repeating the above process until all test samples are assigned classification labels and recorded, when all test samples are processed, the classification result data structure obtained will contain each test sample and its corresponding classification label.

[0083] In an embodiment of the present invention, by comprehensively considering multiple feature dimensions and introducing the standard deviation of the features for weighting, the method can more accurately measure the similarity or difference between samples. This precise distance calculation helps to accurately find the K nearest neighbors of the test sample, thereby improving the accuracy of classification. The introduction of the regularization parameter λ can prevent overfitting to a certain extent, making the model more robust to noise data or outliers. This regularization method helps to balance the impact of different features on the classification results and avoid some features dominating the classification results due to excessive or small values. By performing nonlinear transformations (such as logarithmic transformations) on the feature values, the method can process data with nonlinear relationships, thereby capturing more complex feature patterns. This is particularly important for nonlinear relationships that may exist in geographic surveying and mapping information, and helps to improve the generalization ability of the classification model. Accurate classification results provide a reliable data basis for subsequent disaster risk prediction, water resources management and other activities. By ensuring the accuracy of classification, the characteristic differences in different regions can be more effectively identified, thereby formulating more accurate prevention and response strategies.

[0084] In a preferred embodiment of the present invention, the above step 13 predicts the disaster risk levels of different regions according to the classification results to obtain the prediction results, including:

[0085] Step 131, determine the number and names of disaster risk levels, create a mapping table, and map the classification labels to corresponding disaster risk levels, specifically including: determining the number of disaster risk levels according to actual needs or industry standards, for example, dividing them into three levels of "low risk", "medium risk" and "high risk", and assigning a specific name to each level; using a data structure (such as a dictionary, hash table, etc.) to create a mapping table; using the classification label as a key and the corresponding disaster risk level as a value in the mapping table to ensure that each classification label has a unique corresponding disaster risk level.

[0086] Step 132, storing the classification results in a list, each element of which contains the region identifier and classification label, specifically includes: creating an empty list for storing the classification results; for each classification result, creating a tuple or dictionary containing the region identifier and classification label; adding the tuple or dictionary to the list to ensure that the region identifier is unique so that each region can be accurately identified later.

[0087] Step 133, for each area in the classification result, extract its classification label, and use the mapping table to find the disaster risk level corresponding to each classification label, specifically including: using a loop to traverse the list storing the classification results, for each element in the list, extract the classification label, use the extracted classification label as the key, find the corresponding disaster risk level in the mapping table, and after obtaining the disaster risk level, associate it with the area identifier.

[0088] Step 134, adding the disaster risk level assessment results of each area obtained during the traversal process to the data set, specifically including: if the data set does not exist yet, creating a new data set structure, which can be a list, database table or other format suitable for storing structured data; if the data set already exists, ensuring that it has enough space or structure to store the new assessment results; in the process of traversing the classification results, whenever the disaster risk level assessment results of a region are obtained, it is added to the data set, ensuring that the added data contains the region identifier and the corresponding disaster risk level, so that it can be accurately queried and analyzed later; after all the assessment results are added, the data is verified to ensure the accuracy and completeness of the data.

[0089] In an embodiment of the present invention, step 131 is used to determine the number and names of disaster risk levels, and a mapping table is created so that classification labels that may have been relatively abstract or complex can be intuitively mapped to specific disaster risk levels. Step 132 stores the classification results in a list format, with each element containing the identification and classification label of the region, thereby improving the readability and operability of the data. Through step 133, each region can be quickly matched with its corresponding disaster risk level. This rapid assessment capability is particularly important in responding to emergencies, and can quickly provide decision makers with key information so that they can respond in a timely and effective manner. The determined disaster risk level makes the results easier to visualize, whether through map annotation, chart analysis or report form, it can help relevant personnel more intuitively understand the distribution of disaster risks in various regions, which helps to improve the efficiency of information transmission and strengthen communication among stakeholders.

[0090] In a preferred embodiment of the present invention, the above step 14, based on the prediction results, optimizes the layout of disaster monitoring points, and uses the SWAT model to simulate the hydrological cycle process to predict water level and flow changes, including:

[0091] Step 141, defining an evaluation function for evaluating the pros and cons of the monitoring point layout scheme;

[0092] Step 142, generate an initial monitoring point layout plan, randomly generate a new layout plan based on the initial monitoring point layout plan, use the evaluation function to evaluate the pros and cons of the new plan, and compare it with the current plan, specifically including: generate an initial monitoring point layout plan, based on the initial layout plan, generate a new layout plan by randomly adjusting the position or number of monitoring points, use the evaluation function defined in step 141, evaluate the newly generated layout plan to obtain an evaluation score, compare the evaluation score of the new plan with the evaluation score of the current plan, and determine whether the new plan is better.

[0093] Step 143, decide whether to accept the new plan according to the Metropolis criterion, update the current layout plan to the accepted new plan, until the preset number of iterations is reached to obtain the final monitoring point layout plan, specifically including: according to the Metropolis criterion, if the evaluation score of the new plan is higher than the current plan, or meets certain random acceptance conditions (even if the new plan is slightly worse), accept the new plan; if it is decided to accept the new plan, update the current layout plan to the new plan, repeat steps 142 and 143, until the preset number of iterations is reached, to obtain the final monitoring point layout plan.

[0094] Step 144, based on the collected hydrological data and terrain information, establish a hydrological cycle model for the study area, specifically including: for hydrological data, obtain historical records of rainfall, evaporation, river flow, etc.; for terrain information, access the Geographic Information System (GIS) database or use remote sensing technology (such as satellite images) to obtain elevation, slope and soil type data; obtain electronic or paper versions of hydrological data from relevant institutions to ensure the accuracy and completeness of the data; use GIS software or online platforms to download the required terrain information data to ensure that the resolution and coverage of the data meet the research needs; clean and format the collected hydrological data, remove outliers, and unify data units and time scales; pre-process the terrain information, such as coordinate conversion, clipping and splicing, to match it with the hydrological data; study The theoretical basis, functional characteristics and scope of application of the SWAT model ensure that the model is suitable for the simulation of the hydrological cycle in the study area; create a new project file in the SWAT model and set the basic information of the project, such as the project name, location of the study area and simulation time range, and import the sorted hydrological data and terrain information into the SWAT model; define the parameters of the model according to the characteristics of the study area, such as the hydraulic properties of soil types, vegetation coverage, groundwater parameters, etc.; use the watershed division tool of the SWAT model to divide the study area into different watersheds and sub-basins according to the terrain information, and ensure that the division of watersheds and sub-basins is reasonable and can reflect the actual water flow path and catchment area; set the initial conditions of the model according to historical data or actual conditions, such as initial soil moisture content, groundwater level, etc.

[0095] Step 145, use the hydrological cycle model to perform simulation operations to predict the changes in water level and flow under different climatic conditions and monitoring point layouts to obtain simulation results, specifically including: defining several different climatic condition scenarios based on historical climate data and research needs, such as normal years, drought years, wet years, etc.; for each climatic condition, determining key climate parameters, such as rainfall, temperature, evaporation, wind speed, etc., and ensuring that these parameters remain consistent during the simulation; designing a variety of monitoring point layout scenarios based on the characteristics of the study area and monitoring needs. These scenarios can include different numbers, locations and types of monitoring points (such as rainfall stations, water level stations, flow stations, etc.); for each layout scenario, plan the specific locations of the monitoring points in detail to ensure that they can effectively cover the key hydrological characteristic points of the study area; format the defined climate conditions and monitoring point layout scenario data into input files or parameter settings that the model can accept; load the input conditions, including climate condition data and monitoring point layout information, into the SWAT model or other selected hydrological cycle model, adjust other configuration parameters of the model as needed, such as simulation time step, output frequency, etc., initialize the model to ensure that all components and parameters are in the correct starting state; start the model for simulation and let the model run for a specified time period (such as one hydrological year, multiple hydrological years, etc.) under given climate conditions and monitoring point layout scenarios; monitor the progress and status of the simulation process to ensure that the simulation can proceed smoothly and no errors or anomalies are encountered; after the simulation run is completed, extract the water level and flow data of each monitoring point from the model. These data are usually presented in the form of time series, recording the changes during the entire simulation period; statistical analysis is performed on the extracted water level and flow data, and key indicators such as the average, maximum, minimum, and standard deviation are calculated; time series graphs or change curves of water level and flow are drawn to intuitively display the change trends and characteristics under different climate conditions and monitoring point layout scenarios, compare the simulation results under different scenarios, and analyze the degree and laws of the impact of climate conditions and monitoring point layout on water level and flow changes; organize the extracted and analyzed simulation result data to ensure data integrity and consistency, and convert the data into data formats (such as CSV, Excel, etc.); save the organized simulation result data to a safe storage location, which can be a local computer hard disk, network server, or cloud storage platform.

[0096] Step 146, analyze the simulation results and extract key information, including the changes in water level and flow at each monitoring point, specifically including: check whether there are abnormal values, missing values ​​or duplicate values ​​in the simulation result data, and perform corresponding processing. For example, interpolation methods can be used to fill missing values, or abnormal values ​​can be eliminated according to the data distribution; if the units or formats of the simulation result data are not uniform, data conversion is required so that all data use the same units and formats, and the data is standardized as needed to eliminate the impact of the dimension on the analysis results; calculate the mean, median, standard deviation and other statistical indicators of the water level and flow at each monitoring point to describe the overall distribution of the data, analyze the skewness and peak state of the data, and understand the morphological characteristics of the data distribution; analyze the correlation between water level and flow between different monitoring points, explore the mutual influence relationship between them, and use correlation coefficients (such as Pearson correlation coefficient) to quantify the degree of correlation between monitoring points; use time series analysis methods (such as moving average method) to identify the long-term trend of water level and flow, and detect whether there are periodic changes or seasonal patterns in the data; use chart software (such as Excel, Tableau, Python's matplotlib library, etc.) can be used to draw time series graphs of water level and flow at each monitoring point, clearly showing how the data changes over time, and making box plots, histograms, etc. to present the distribution characteristics of the data in a visual way; if the study area is large or there are multiple monitoring points, GIS software can be used to mark the locations of the monitoring points on the map, and grade and color them according to the water level or flow data, and display the simulation results in the form of spatial distribution maps, and make dynamic maps or time series animations to show the continuous changes of water level and flow in space and time; extract the water level and flow change trends of each monitoring point from the cleaned and sorted data, such as rising, falling or remaining stable, identify and record the peak time of water level and flow, analyze the causes and laws of the peak, and interpret the extracted key information in combination with the actual situation of the study area. For example, rising water levels may mean an increase in rainfall or an increase in upstream water.

[0097] In an embodiment of the present invention, step 141, the evaluation function provides an objective and quantifiable standard for the pros and cons of the monitoring point layout, so that different layout schemes can be compared fairly. The determined evaluation criteria help guide the subsequent layout optimization work and ensure that the improvement direction is correct and effective. Step 142, by randomly generating new schemes, it is possible to explore the possible layout space extensively to avoid falling into the local optimum. By comparing with the current scheme, better layout schemes can be continuously screened out to promote the improvement of the overall layout quality. Step 143, the Metropolis criterion allows the acceptance of poor new schemes under certain conditions, which helps the algorithm to jump out of the local optimum and find a better global solution. Through multiple iterations, the algorithm can gradually converge to a better layout scheme, improving the rationality and effectiveness of the layout. Step 144, the model established based on actual data can more realistically reflect the hydrological cycle process in the study area and improve the accuracy of the simulation. Combined with specific terrain information, the model can conduct refined analysis for specific areas and provide a more accurate basis for decision-making. Step 145, through simulation operation, it is possible to predict the changes in water level and flow under different conditions, provide important information for disaster warning and response, and simulate scenarios under different climate conditions and monitoring point layouts, which helps to comprehensively assess various possible risks and impacts. Step 146, extracting key information from complex simulation results, such as water level and flow changes at each monitoring point, helps to quickly understand the core situation.

[0098] In a preferred embodiment of the present invention, the calculation formula of the evaluation function is:

[0099] ;

[0100] in, Represents the value of the evaluation function; represents the weight coefficient; Indicates The area covered by each monitoring point; represents the exponential coefficient; represents the attenuation coefficient; Indicates The distance from a monitoring point to a specific reference point; Indicates the total number of monitoring points; Indicates The water level value of each monitoring point, the actual water level data collected; It represents the average water level of all monitoring points; represents the weight coefficient; represents the weight coefficient; Indicates the target water level, which indicates the ideal water level value to be monitored; The number indicating the target water level; Indicates The flow value of each monitoring point and the actual flow data collected; It represents the average flow rate of all monitoring points; represents the weight coefficient; represents the weight coefficient; Indicates the target flow rate, which indicates the ideal flow rate value that you want to monitor; Indicates the amount of target traffic; It is an index variable, used to traverse all monitoring points; is an index variable used to traverse the data related to the target water level; Is an index variable used to traverse the data related to the target traffic.

[0101] In the embodiment of the present invention, the evaluation function takes into account multiple influencing factors, including area, distance, water level and flow, etc., and can comprehensively evaluate the comprehensive performance of the monitoring system, which helps to discover potential problems in the system; by introducing parameters such as exponential coefficient, attenuation coefficient and weight coefficient, the function can more accurately reflect the impact of various factors on the evaluation results, which helps to improve the accuracy and reliability of the evaluation; each parameter in the function can be adjusted according to actual conditions to adapt to different scenarios and needs; by introducing parameters such as target water level and target flow, the function can determine the deviation between the monitoring system and actual needs. This helps to guide the system to move closer to the predetermined goal and improve the pertinence and effectiveness of hydrological monitoring.

[0102] In a preferred embodiment of the present invention, the above step 15, evaluating the water quality according to the water level and flow rate changes to obtain the evaluation result, includes:

[0103] Step 151, setting a plurality of water quality indicators, the water quality indicators including pH value, dissolved oxygen, and turbidity;

[0104] Step 152, construct a fuzzy evaluation matrix R according to each water quality index, wherein the formula of the fuzzy evaluation matrix R is:

[0105] ,in, Indicates The indicator for Evaluation of water quality; Indicates the first indicator for the Evaluation of water quality; Indicates the second indicator for the Evaluation of water quality; Indicates Evaluation of Class 1 water quality using indicators; Indicates Evaluation of Class 2 water quality using 10 indicators; Indicates The indicator for Evaluation of water quality; is the total number of indicators; Indicates the total number of water quality assessment categories;

[0106] Step 153: Set weights for each indicator ,in, For the Indicators in time The dynamic weight of ;

[0107] in, is the number of past observations; It is The indicator is Observation value of the day; It is Indicators in time Observed value of is an adjustment factor; It is Indicators at the previous time point Observed value of Indicates Evaluation of water quality; Indicates the specific time point used to calculate the moving average; Indicates the total number of water quality indicators; It is The indicator is Observation value of the day;

[0108] Step 154, pass Calculate the fuzzy comprehensive evaluation results, where It is the fuzzy comprehensive evaluation result, which represents the comprehensive evaluation value of different water quality levels.

[0109] In an embodiment of the present invention, by considering multiple water quality indicators (such as pH value, dissolved oxygen, turbidity, etc.), the method can comprehensively reflect the overall quality status of the water body. This comprehensive evaluation helps to understand the water quality more accurately. The use of a fuzzy evaluation matrix can handle the uncertainty and ambiguity in water quality assessment. This flexibility makes the assessment results closer to the actual situation and can better cope with complex and changeable water quality environments. By introducing dynamic weights, the method can adjust the weights of different indicators according to the changes at different time points, thereby more accurately reflecting the real-time importance of water quality indicators. This dynamic evaluation helps to detect water quality changes in a timely manner.

[0110] In a preferred embodiment of the present invention, the above step 16, based on the evaluation results, optimizes the water resource allocation plan to obtain data analysis results, including:

[0111] Step 161, determine the goal of water resource allocation, and define an objective function for quantifying the effect of the allocation plan, wherein the calculation formula of the objective function is:

[0112] ;

[0113] in, Represents a small positive number; represents the marginal cost of water allocation; represents the coefficient; represents the expected or ideal water resource allocation; λ represents the weight coefficient; Z represents the objective function value, which represents the total benefit or total efficiency of water resource allocation; Indicates The goal is The benefits under the configuration scheme; Indicated in Select the target The amount of water allocated under each scheme; represents the total target number for water resource allocation; Represents the total number of water resource allocation options; Represents an index, which is used to identify a specific water resource allocation target; Represents an index, which is used to identify a specific water resource allocation plan. The value range is 1 to .

[0114] Step 162, divide the water resource allocation problem into several stages, each stage represents a decision cycle, and determine the state space of each stage, specifically including: according to the characteristics and time scale of the water resource allocation problem, divide the entire allocation process into several independent decision cycles, each cycle is called a "stage". For example, it can be divided by quarter, year or other appropriate time units; for each stage, define key variables that can fully describe the water resource status of the stage, such as available water, demand, storage, etc., all possible combinations of these variables constitute the state space of the stage, and each state is a specific value combination of these variables at a specific time point.

[0115] Step 163, based on the dynamic characteristics of water resources, establish a state transfer equation to describe the evolution of the state from one stage to the next stage, specifically including: studying the dynamic characteristics of water resources, including seasonal changes, supply and demand changes, storage and allocation capacity, etc.; based on these dynamic characteristics, establish a state transfer equation to describe the evolution of the state from one stage to the next stage, the state transfer equation expresses how the state of the next stage depends on the state of the current stage and the decision taken. When applied specifically, it is assumed that in the first The status of the stage is ,in, By key variables such as water availability , demand , Storage The state transfer equation can be written as:

[0116] ;

[0117] in, Indicates the amount of water available for the next stage; Indicates the demand in the next stage; Represents the storage capacity of the next stage; For the Water input in each stage; Indicates the change in demand.

[0118] Step 164, for each stage and each state, calculate the evaluation function value when different decisions are taken in the state, specifically including: for each stage and each state in the stage, calculate the value of the evaluation function under all possible decisions through the above objective function.

[0119] Step 165, using the recursive relationship of dynamic programming, reversely calculate from the last stage to the first stage, specifically including: starting from the last stage, initializing an optimal value for each state of the stage (the maximum or minimum value of the evaluation function in the state); recursively forward stage by stage, for each stage and each state, according to the state transfer equation and the optimal solution of the subsequent stage, update the optimal value of the current state, which involves selecting a decision that can make the evaluation function reach the optimal value under the given current state, and recording this decision and the corresponding optimal value.

[0120] Step 166, in each stage, according to the solution of the previous stage and the state transfer equation, the optimal solution of the current stage is updated. After completing the calculation of all stages, the solution of the first stage is the global final water resource allocation plan, wherein the global final water resource allocation plan is the result of data analysis, specifically including: at the end of each stage, according to the optimal solution of the previous stage and the state transfer equation, the optimal solution of the current stage is updated, including determining the optimal decision to be taken in each state of the current stage; when all stages are calculated, the optimal solution of the first stage (i.e., the initial stage) represents the global final water resource allocation plan, which is based on the optimal decision sequence of each stage in the entire decision-making process, and aims to achieve the predefined water resource allocation goal.

[0121] In an embodiment of the present invention, by determining the goal of water resource allocation and defining an objective function that quantifies the effect of the allocation scheme, the method can ensure that the water resource allocation scheme is consistent with the predetermined goal. This goal-oriented nature helps to improve the pertinence and effectiveness of water resource allocation. The water resource allocation problem is divided into several stages, each of which represents a decision cycle. This stage division helps to simplify complex problems, allowing decision makers to focus on different priorities at different stages, thereby making more reasonable decisions. By establishing a state transition equation to describe the evolution law of the state from one stage to the next, the method can fully consider the dynamic characteristics of water resources. This dynamic adaptability enables the allocation scheme to be adjusted according to actual conditions and better cope with the challenges brought about by changes in water resources. At each stage and each state, the evaluation function value when taking different decisions is calculated, and the effects of various possible solutions can be comprehensively evaluated. This helps decision makers to have a more comprehensive understanding of the pros and cons of various solutions, thereby making more informed choices. Using the recursive relationship of dynamic programming, reverse calculation from the last stage to the first stage can ensure that the global optimal water resource allocation scheme is found. This global optimality helps to improve the overall efficiency and effect of water resource allocation.

[0122] like Figure 2 As shown, an embodiment of the present invention further provides a geographic surveying and mapping information collection system 20 based on big data, comprising:

[0123] The acquisition module 21 is used to acquire geographic surveying and mapping information, including geological soil information, geological disaster information, and hydrological information;

[0124] The classification module 22 is used to classify the geographic surveying and mapping information to obtain a classification result;

[0125] An evaluation module 23 is used to predict the disaster risk levels of different regions according to the classification results to obtain prediction results;

[0126] The prediction module 24 is used to optimize the layout of disaster monitoring points according to the prediction results, use the SWAT model to simulate the hydrological cycle process to predict the changes in water level and flow; evaluate the water quality according to the changes in water level and flow to obtain the evaluation results; and optimize the water resource allocation plan according to the evaluation results to obtain the data analysis results.

[0127] It should be noted that the system is a system corresponding to the above method, and all implementation methods in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0128] The embodiment of the present invention further provides a computing device, comprising: a processor, a memory storing a computer program, wherein when the computer program is executed by the processor, the method described above is executed. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0129] The embodiment of the present invention also provides a computer-readable storage medium storing instructions, which, when executed on a computer, enable the computer to execute the method described above. All implementations in the above method embodiment are applicable to this embodiment and can achieve the same technical effect.

[0130] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A method for collecting geographic surveying and mapping information based on big data, characterized in that: The method comprises: Collect geographic surveying and mapping information, including geological soil information, geological disaster information, and hydrological information; Classify geographic surveying and mapping information to obtain classification results; According to the classification results, the disaster risk levels of different regions are predicted to obtain the prediction results; According to the prediction results, the layout of disaster monitoring points is optimized, and the SWAT model is used to simulate the hydrological cycle process to predict water level and flow changes; Assess water quality based on water level and flow changes to obtain assessment results; Based on the assessment results, optimize the water resource allocation plan to obtain data analysis results; based on the prediction results, optimize the layout of disaster monitoring points, and use the SWAT model to simulate the hydrological cycle process to predict water level and flow changes, including: Define an evaluation function for evaluating the pros and cons of monitoring point layout schemes; Generate an initial monitoring point layout plan. Based on the initial monitoring point layout plan, randomly generate a new layout plan, use the evaluation function to evaluate the pros and cons of the new plan, and compare it with the current plan; Decide whether to accept the new plan according to the Metropolis criterion, and update the current layout plan to the accepted new plan until the preset number of iterations is reached to obtain the final monitoring point layout plan; Based on the collected hydrological data and topographic information, a hydrological cycle model of the study area is established; Use the hydrological cycle model to run simulations and predict water level and flow changes under different climate conditions and monitoring point layouts to obtain simulation results; Analyze simulation results and extract key information, including water level and flow changes at each monitoring point; The calculation formula of the evaluation function is: ； in, Represents the value of the evaluation function; represents the weight coefficient; Indicates The area covered by each monitoring point; represents the exponential coefficient; represents the attenuation coefficient; Indicates The distance from each monitoring point to the reference point; Indicates the total number of monitoring points; Indicates The water level value of each monitoring point, the actual water level data collected; It represents the average water level of all monitoring points; represents the weight coefficient; represents the weight coefficient; Indicates the target water level, which indicates the ideal water level value to be monitored; The number indicating the target water level; Indicates The flow value of each monitoring point and the actual flow data collected; It represents the average flow rate of all monitoring points; represents the weight coefficient; represents the weight coefficient; Indicates the target flow rate, which indicates the ideal flow rate value that you want to monitor; Indicates the amount of target traffic; It is an index variable, used to traverse all monitoring points; is an index variable used to traverse the data related to the target water level; Is an index variable used to traverse the data related to the target traffic.

2. The method for collecting geographic surveying and mapping information based on big data according to claim 1, characterized in that: Classify geographic surveying and mapping information to obtain classification results, including: Split geographic mapping information into training and testing sets; For each sample in the test set, Calculate the distance between each sample and all samples in the training set, where Representation sample and samples The distance between Represents the dimension of the feature, representing the sample and samples The number of features; Indicates The standard deviation of the feature; and It is a sample and samples In the The value after nonlinear transformation on the features; Respectively represent samples and samples In the The value of a feature; It means that after nonlinear transformation, the sample and samples In the The squared difference between the transformed values ​​on the features; represents the regularization parameter, and its value is between (0, 1); and Represents an index; Indicates The standard deviation of the features; ; ; According to the distance, find the K nearest neighbors of the test sample in the geographic mapping information; For each category, create a counter with an initial value of 0; for the K nearest neighbors found for the test sample, check the corresponding labels in turn; For each nearest neighbor label, find the corresponding category counter and add 1 to its value, indicating that the category appears once in the K nearest neighbors; After traversing all K nearest neighbors, compare the values ​​of each category counter to obtain the category corresponding to the counter value, and set the classification label of the test sample to the majority category; The test sample and its assigned classification label are recorded as part of the classification result, and the next test sample is processed until all test samples are classified to obtain the classification result.

3. The method for collecting geographic surveying and mapping information based on big data according to claim 2, characterized in that: According to the classification results, the disaster risk level of different regions is predicted to obtain the prediction results, including: Determine the number and names of disaster risk levels and create a mapping table to map the classification labels to the corresponding disaster risk levels; Store the classification results in a list, where each element contains the region's identity and classification label; For each area in the classification result, extract its classification label and use the mapping table to find the disaster risk level corresponding to each classification label; The disaster risk level assessment results of each area obtained during the traversal process are added to the dataset.

4. The method for collecting geographic surveying and mapping information based on big data according to claim 3 is characterized in that: Water quality is assessed based on changes in water level and flow to obtain assessment results, including: Set multiple water quality indicators, including pH value, dissolved oxygen, and turbidity; According to each water quality index, a fuzzy evaluation matrix R is constructed, where the formula of the fuzzy evaluation matrix R is: ,in, Indicates The indicator for Evaluation of water quality; Indicates the first indicator for the Evaluation of water quality; Indicates the second indicator for the Evaluation of water quality; Indicates Evaluation of Class 1 water quality using indicators; Indicates Evaluation of Class 2 water quality using 10 indicators; Indicates The indicator for Evaluation of water quality; is the total number of indicators; Indicates the total number of water quality assessment categories; Set weights for each indicator ,in, For the Indicators in time The dynamic weight of ; in, is the number of past observations; It is The indicator is Observation value of the day; It is Indicators in time Observed value of is an adjustment factor; It is Indicators at the previous time point Observed value of Indicates Evaluation of water quality; Indicates the specific time point used to calculate the moving average; Indicates the total number of water quality indicators; It is The indicator is Observation value of the day; pass Calculate the fuzzy comprehensive evaluation results, where It is the fuzzy comprehensive evaluation result, which represents the comprehensive evaluation value of different water quality levels.

5. The method for collecting geographic surveying and mapping information based on big data according to claim 4, characterized in that: Based on the assessment results, optimize the water resource allocation plan to obtain data analysis results, including: Determine the goals of water resource allocation and define objective functions to quantify the effectiveness of allocation plans; Divide the water resource allocation problem into several stages, each stage represents a decision cycle, and determine the state space of each stage; According to the dynamic characteristics of water resources, the state transfer equation is established to describe the evolution law of the state from one stage to the next; For each stage and each state, calculate the evaluation function value when taking different decisions in this state; Using the recursive relationship of dynamic programming, reverse calculation is performed from the last stage to the first stage; In each stage, the optimal solution of the current stage is updated according to the solution of the previous stage and the state transfer equation. After completing the calculations of all stages, the solution of the first stage is the global final water resource allocation plan, where the global final water resource allocation plan is the result of data analysis.

6. A geographic surveying and mapping information collection system based on big data, characterized in that: Applied to the method according to any one of claims 1 to 5, comprising: The acquisition module is used to collect geographic surveying and mapping information, including geological soil information, geological disaster information, and hydrological information; A classification module is used to classify geographic surveying and mapping information to obtain classification results; The evaluation module is used to predict the disaster risk level of different regions based on the classification results to obtain the prediction results; The prediction module is used to optimize the layout of disaster monitoring points according to the prediction results, and use the SWAT model to simulate the hydrological cycle process to predict water level and flow changes; evaluate the water quality according to the water level and flow changes to obtain the evaluation results; and optimize the water resource allocation plan according to the evaluation results to obtain data analysis results.

7. A computing device, characterized in that include: one or more processors; A storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the one or more processors implement the method as claimed in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which implements the method according to any one of claims 1 to 5 when executed by a processor.

Images