Land resource management information platform based on cloud computing

Abstract

The invention provides a land resource management information platform based on cloud computing, and relates to the technical field of data processing, and the method comprises the steps: an obtaining module, which initializes a current solution into a group of land resource information collection schemes; on the basis of the current solution, generating a new land resource information acquisition scheme through random disturbance; calculating an objective function value for the new land resource information acquisition scheme through an objective function; whether a new solution is accepted or not is judged by using a Metropolis criterion, and after the new solution is accepted, the current solution is updated into the new solution; reducing the current temperature according to a preset temperature reduction rate, simulating cooling in the annealing process until a preset number of iterations is reached so as to obtain an optimal solution, and determining a final land resource information acquisition scheme according to the optimal solution; and collecting land resource information according to the final land resource information collection scheme. According to the invention, the information acquisition efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a land resource management information platform based on cloud computing. Background Art

[0002] In the existing land resource management information platform, some data processing still has some defects. First, some traditional data processing methods rely on centralized servers, which leads to the server's computing power and storage space becoming bottlenecks when processing large amounts of high-dimensional land resource information, seriously affecting the efficiency and accuracy of data processing.

[0003] Secondly, some existing platforms lack intelligent and optimized means of data collection. Some traditional land resource information collection methods are based on manual or simple automated scripts, which is not only inefficient but also difficult to ensure the comprehensiveness and accuracy of the data. Especially in the face of complex and changing land resource environments, the limitations of this method are more obvious. Summary of the invention

[0004] The technical problem to be solved by the present invention is to provide a land resource management information platform based on cloud computing, which can find the optimal solution among many possible land resource information collection schemes, thereby ensuring that the collected land resource information is more comprehensive and accurate, and improving the efficiency of information collection.

[0005] In order to solve the above technical problems, the technical solution of the present invention is as follows: In the first aspect, a land resource management information platform based on cloud computing includes: The acquisition module is used to set the initial temperature, the end temperature and the temperature drop rate; define the objective function of land resource information collection; initialize the current solution as a set of land resource information collection plans; generate a new land resource information collection plan through random perturbations based on the current solution; calculate the objective function value of the new land resource information collection plan through the objective function; use the Metropolis criterion to determine whether to accept the new solution, and when the new solution is accepted, update the current solution to the new solution; reduce the current temperature according to the predetermined temperature drop rate, simulate the cooling during the annealing process, until the preset number of iterations is reached to obtain the optimal solution, and determine the final land resource information collection plan based on the optimal solution; collect land resource information according to the final land resource information collection plan; Cloud computing platform, used to store, process and analyze land resource information to obtain analysis results; A construction module is used to construct a three-dimensional space model based on the analysis results; The query module is used to view the status of land resources in real time based on the three-dimensional space model.

[0006] Furthermore, the objective function The calculation formula is: ; in, Indicates the area covered by each collection point; Indicates the total number of collection points; Indicates the collection point The decision variable of whether to be selected takes the value of 1 or 0, where 1 means that the corresponding collection point is selected for the collection of land resource information, and 0 means that the corresponding collection point is not selected for the collection; Indicates the maximum sensitivity value of the sensor; represents the adjustment factor; Representative collection point Distance to the reference point; represents an exponential decay function; Index variable representing the acquisition point; and Represents the weight coefficient.

[0007] Furthermore, the land resource information is stored, processed and analyzed to obtain analysis results, including: According to the characteristics of land resource information, the land resource information is binary-coded; A certain number of individuals are randomly generated as the initial population, each of which represents a storage, processing and analysis scheme; According to the goal of land resource information management, a fitness function is defined to evaluate the quality of each individual; For each individual in the initial population, the fitness function is used to calculate its fitness value; according to the fitness value, the corresponding individual is selected from the current population as a candidate for reproduction; Randomly pair the selected individuals and exchange some genes between the selected individuals with a certain crossover probability to generate new offspring individuals; randomly change the newly generated offspring individuals with a certain mutation probability, and the new individuals generated by crossover and mutation operations together with some individuals in the parent generation form a new population, and continue to iterate and evolve until the preset number of iterations is reached. After the iteration is completed, the corresponding individual is selected from the last generation population as the final solution; Based on the final solution, the final land resource information storage, processing and analysis plan is obtained; According to the final land resource information storage, processing and analysis plan, the land resource information is stored, processed and analyzed to obtain the analysis results.

[0008] Further, according to the final land resource information storage, processing and analysis plan, the land resource information is stored, processed and analyzed to obtain analysis results, including: Classify the land resource information to obtain classification results; Extract the average, maximum and minimum values ​​of soil moisture and temperature from the classification results; Construct an analysis model based on the average, maximum, and minimum values ​​of soil moisture and temperature; Using historical data to train the analysis model to obtain a trained analysis model; Use the trained analysis model to analyze the current land resource information to obtain analysis results.

[0009] Furthermore, the land resource information is classified to obtain classification results, including: Determine the number of categories K into which the land resource information should be divided, and randomly select K data points as the initial clustering centers; For each point in the data set, the distance to each cluster center is calculated and assigned to the corresponding cluster center. The average value of each cluster is recalculated and the average value is set as the new cluster center until the preset number of iterations is reached to obtain the classification result.

[0010] Furthermore, the fitness function The calculation formula is: ; in, , and represents the weight coefficient; Indicates the amount of data processed; Indicates the time required for processing; represents the coefficient; Indicates the required storage space; Indicates the data redundancy rate; Indicates the data compression ratio; Indicates the number of correct results produced; Indicates the total number of results produced; Represents the error rate.

[0011] Furthermore, land resource information includes soil moisture, temperature, weather, topography and geographical location.

[0012] In a second aspect, a land resource management information method based on cloud computing is applied to the platform, comprising: Set the initial temperature, end temperature and temperature drop rate; define the objective function of land resource information collection; initialize the current solution as a set of land resource information collection plans; generate a new land resource information collection plan through random perturbations based on the current solution; calculate the objective function value of the new land resource information collection plan through the objective function; use the Metropolis criterion to determine whether to accept the new solution, and when the new solution is accepted, update the current solution to the new solution; reduce the current temperature according to the predetermined temperature drop rate, simulate the cooling during the annealing process, until the preset number of iterations is reached to obtain the optimal solution, and determine the final land resource information collection plan based on the optimal solution; collect land resource information according to the final land resource information collection plan; Store, process and analyze land resource information to obtain analysis results; According to the analysis results, a three-dimensional space model is constructed; Based on the three-dimensional spatial model, view the status of land resources in real time.

[0013] According to a third aspect, a computing device includes: one or more processors; 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.

[0014] 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.

[0015] The above scheme of the present invention includes at least the following beneficial effects.

[0016] By introducing the simulated annealing algorithm, the present invention can find the optimal solution among many possible land resource information collection schemes, thereby ensuring that the collected land resource information is more comprehensive and accurate, and improving the efficiency of information collection.

[0017] Based on the architecture of cloud computing platform, the present invention realizes efficient storage, processing and analysis of land resource information. Cloud computing platform has powerful computing power and almost unlimited storage space, which can easily handle large-scale, high-dimensional land resource data and ensure the timeliness and accuracy of data processing.

[0018] Based on the analysis results of the cloud computing platform, the construction module can accurately construct a three-dimensional spatial model of land resources and intuitively display the spatial distribution and status of land resources.

[0019] Through the query module, users can view the status of land resources in real time and obtain a multi-angle, dynamic data interaction experience. This intuitive and convenient data display method greatly improves user work efficiency and reduces the difficulty of data understanding. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 It is a flow chart of a land resource management information platform based on cloud computing provided by an embodiment of the present invention.

[0021] Figure 2 It is a schematic diagram of a geographic information surveying and mapping intelligent planning system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0022] 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.

[0023] like Figure 1 As shown, the embodiment of the present invention proposes a land resource management information platform based on cloud computing, including: The acquisition module is used to set the initial temperature, the end temperature and the temperature drop rate; define the objective function of land resource information collection; initialize the current solution as a set of land resource information collection plans; generate a new land resource information collection plan through random perturbations based on the current solution; calculate the objective function value of the new land resource information collection plan through the objective function; use the Metropolis criterion to determine whether to accept the new solution, and when the new solution is accepted, update the current solution to the new solution; reduce the current temperature according to the predetermined temperature drop rate, simulate the cooling during the annealing process, until the preset number of iterations is reached to obtain the optimal solution, and determine the final land resource information collection plan based on the optimal solution; collect land resource information according to the final land resource information collection plan, and the land resource information includes soil moisture, temperature, weather, terrain and geographical location; Cloud computing platform, used to store, process and analyze land resource information to obtain analysis results; A construction module is used to construct a three-dimensional space model based on the analysis results; The query module is used to view the status of land resources in real time based on the three-dimensional space model.

[0024] In the embodiment of the present invention, through the simulated annealing algorithm introduced in the acquisition module, the platform can efficiently search and determine the optimal land resource information collection scheme. This scheme not only takes into account multiple factors (such as soil moisture, temperature, weather, terrain and geographical location), but also ensures the comprehensiveness and accuracy of the collected information through iterative optimization. The cloud computing platform provides powerful computing and storage capabilities, so that large-scale, multi-dimensional land resource information can be processed and analyzed in a timely and effective manner. This not only improves the efficiency of data processing, but also ensures the security and reliability of data. The construction module can construct a high-precision three-dimensional space model based on the analysis results of the cloud computing platform; through the query module, users can easily view the status of land resources in real time according to the three-dimensional space model, and obtain intuitive data display and interactive experience. This greatly improves the work efficiency of users and also enhances the readability and comprehensibility of data.

[0025] In another preferred embodiment of the present invention, the temperature value at the start of the simulated annealing algorithm is set to a relatively high value to ensure that the algorithm has sufficient probability to accept a poor solution in the early stage of the search, thereby avoiding falling into a local optimum. The temperature value at the stop is set to a positive number close to zero. When the temperature drops to this value, the algorithm considers that it is close enough to the global optimal solution and stops searching. Controlling the speed of temperature drop affects the convergence speed and search quality of the algorithm. Define the objective function of land resource information collection; initialize the current solution as a set of land resource information collection schemes, specifically including: The current solution represents a specific land resource information collection plan, including the location and number of collection points, etc. The initial solution can be randomly generated.

[0026] Based on the current solution, a new land resource information collection plan is generated through random perturbations, including: Random perturbation makes small random modifications to the current solution to generate a new acquisition plan. This modification can be to increase or decrease the acquisition points, adjust the location of the acquisition points, etc.

[0027] The objective function is used to calculate the objective function value of the new land resource information collection plan, including: Use the previously defined objective function to evaluate the quality of the newly generated acquisition plan and obtain a specific value (i.e., the objective function value). Use the Metropolis criterion to determine whether to accept the new solution, including: According to the difference in the objective function value between the new solution and the current solution and the current temperature, decide whether to accept the new solution as the current solution. If the new solution is better, it is accepted unconditionally; if the new solution is worse, it is accepted with a certain probability, which is related to the temperature and the difference in the objective function value. When the new solution is accepted, update the current solution to the new solution: If the new solution is accepted according to the Metropolis criterion, the current solution is updated to the new solution for the next round of iterative search. The current temperature is reduced according to the predetermined temperature reduction rate, including: The cooling step in the simulated annealing process reduces the current temperature value according to the preset temperature drop rate. As the temperature decreases, the probability of the algorithm accepting a poor solution gradually decreases, and the search process gradually tends to find a better solution. Until the preset number of iterations is reached to obtain the optimal solution, where the number of iterations controls the number of executions. After the preset number of iterations is reached, the algorithm stops searching and considers the current solution (or the historical optimal solution) as the optimal solution to the problem. The optimal solution obtained by the search is used as the final land resource information collection plan, which is considered to be the optimal under the evaluation criteria defined by the objective function. According to the final collection plan, the actual land resource information collection work is carried out, including the acquisition of information such as soil moisture, temperature, weather, terrain and geographical location.

[0028] In a preferred embodiment of the present invention, the objective function The calculation formula is: ; in, Indicates the area covered by each collection point; Indicates the total number of collection points; Indicates the collection point The decision variable of whether to be selected takes the value of 1 or 0, where 1 means that the corresponding collection point is selected for the collection of land resource information, and 0 means that the corresponding collection point is not selected for the collection; Indicates the maximum sensitivity value of the sensor; represents the adjustment factor; Representative collection point Distance to the reference point; represents an exponential decay function; Index variable representing the acquisition point; and Represents the weight coefficient.

[0029] In the embodiment of the present invention, by introducing the weight coefficient and , the objective function can flexibly balance the influence of different factors. This design allows the acquisition plan to be adjusted according to actual needs, such as paying more attention to the coverage area or the trade-off between sensor sensitivity and distance. The first term in the function The coverage area of ​​each collection point is taken into account. By maximizing this term, it can be ensured that the selected collection points can effectively cover a wider range of land resources, thereby improving the efficiency and comprehensiveness of information collection. The second term in the function The maximum sensitivity of the sensor and the distance between the acquisition point and the reference point are comprehensively considered. , which can reasonably evaluate the attenuation of sensor sensitivity as the distance increases, so that when selecting collection points, the location with moderate distance and high sensor sensitivity is given priority. By abstracting complex practical problems into a mathematical function, it is more convenient to use optimization algorithms (such as simulated annealing algorithm) to solve the optimal collection plan. This mathematical method not only improves the efficiency and accuracy of decision-making, but also makes the adjustment and optimization of the plan more intuitive and controllable. By optimizing the objective function, it can be ensured that the selected collection points not only meet the information collection needs, but also achieve efficient use of resources (such as manpower, material resources, time, etc.).

[0030] In a preferred embodiment of the present invention, the land resource information is stored, processed and analyzed to obtain analysis results, including: According to the characteristics of land resource information, the land resource information is binary coded, including: collecting soil samples in the target area and recording basic information such as location, color, texture (sand, clay, loam), etc.; sending the collected soil samples to be classified and identified, and determining the specific types of soil, such as red soil, brown soil, black soil, etc., according to the domestic standard soil classification system (such as the Chinese soil occurrence classification system); analyzing the physical properties (such as particle composition, bulk density, porosity) and chemical properties (such as organic matter content, pH value, nutrient content) of different types of soil; using geographic information system (GIS) technology, combining soil type data with spatial location, and drawing soil type distribution maps, which helps to understand the variability and distribution of soil types in space; selecting representative locations in the target area, and using soil moisture meters or similar instruments for on-site measurements. Record soil moisture data at different depths and time points. Using satellite remote sensing technology, obtain soil moisture information over a large range with high temporal and spatial resolution. This method has the advantages of wide coverage, short cycle, and low cost, and is suitable for macro monitoring and trend analysis. Statistical analysis and visualization of the collected soil moisture data are performed to reveal the temporal and spatial variation of soil moisture and its relationship with environmental factors such as meteorology and hydrology. Based on the soil moisture data and in combination with relevant drought indicators (such as relative soil moisture), the drought severity and distribution in the target area are assessed. Through the digital elevation model (DEM) or other terrain data sources, terrain information such as elevation, slope, and slope aspect of the target area is obtained, and the terrain is divided into different types, such as plains, hills, and mountains, based on parameters such as elevation and slope; Quantify each attribute. For example, classify soil types into several categories and assign a unique binary code to each category. Connect the binary codes of all attributes in series to form a long binary string, which represents a specific land resource information sample.

[0031] A certain number of individuals are randomly generated as the initial population. Each individual represents a storage, processing and analysis scheme, which specifically includes: determining the population size (i.e., the number of individuals), using a random number generator to generate a random binary string for each individual. The length of the string is consistent with the land resource information encoding length determined above, ensuring that the generated binary string conforms to the valid range of the land resource information.

[0032] According to the goal of land resource information management, a fitness function is defined to evaluate the quality of each individual; For each individual in the initial population, the fitness function is used to calculate its fitness value; according to the fitness value, the corresponding individual is selected from the current population as a candidate for reproduction, specifically including: traversing each individual in the initial population; for each individual, passing its code as an input parameter to the fitness function; the fitness function calculates the corresponding fitness value according to the code of the individual and returns the value, and associates the calculated fitness value with the corresponding individual, for example, it can be stored in a data structure for subsequent use; according to the calculated fitness value, the individuals in the initial population are sorted, usually from high to low, so that excellent individuals can be more easily identified; individuals with higher fitness values ​​are selected as candidates for reproduction. Different selection strategies can be adopted here, such as roulette selection, tournament selection, etc. For example, the probability of each individual being selected is determined according to the proportion of its fitness value in the sum of the overall fitness values. Individuals with high fitness values ​​have a high probability of being selected; ensuring that the selected candidate individuals are diverse and avoiding premature convergence to the local optimal solution can be achieved by introducing a certain degree of randomness in the selection process, for example, using a selection method with random perturbations.

[0033] Randomly pair the selected individuals and exchange some genes between the selected individuals with a certain crossover probability to generate new offspring individuals; randomly change the newly generated offspring individuals with a certain mutation probability, and the new individuals generated by crossover and mutation operations together with some individuals in the parent generation form a new population, and continuously iterate and evolve until the preset number of iterations is reached. After the iteration is completed, the corresponding individual is selected from the last generation population as the final solution, and the final land resource information storage, processing and analysis plan is obtained according to the final solution, which specifically includes: Randomly select two individuals as a pair from the set of candidate individuals that have been selected based on fitness, and repeat this process until all candidate individuals are paired or only a single individual that cannot be paired remains (if the total number is odd); determine a crossover probability value (such as 0.7 or 0.8), which indicates the possibility of gene exchange between paired individuals. Perform a crossover operation: For each pair of individuals, generate a random number, and if the random number is less than or equal to the crossover probability, perform the crossover operation: a. Randomly select one or more crossover points (i.e., gene positions).

[0034] b. Exchange the gene fragments of the two individuals at the crossover point to generate two new offspring individuals.

[0035] Randomly change the offspring individuals with a certain mutation probability, including: Determine a smaller mutation probability value (such as 0.01 or 0.001), which represents the possibility of random changes in the genes of the offspring individuals. For each newly generated offspring individual, traverse its gene sequence and generate a random number at each gene position. If the random number is less than or equal to the mutation probability, the gene is mutated, that is, its value is randomly changed (for example, from 0 to 1, or from 1 to 0).

[0036] The new offspring individuals generated by crossover and mutation operations are combined with some individuals with higher fitness in the parent generation (retained according to the elite strategy) to form a new population. The new population is used as the initial population for the next iteration. Each iteration may produce individuals that are more adapted to the land resource information management goals. Before starting the iteration, a preset number of iterations (such as 100 times, 500 times, etc.) is determined as the condition for the termination of the algorithm. When the preset number of iterations is reached, the iteration is stopped, and the individual with the highest fitness is selected from the last generation of the population as the final solution to the problem. The binary code of the final solution is converted back to the corresponding land resource information attributes (such as soil type, moisture, terrain, etc.).

[0037] According to the final land resource information storage, processing and analysis plan, the land resource information is stored, processed and analyzed to obtain the analysis results.

[0038] In the embodiment of the present invention, through binary coding, land resource information can be efficiently converted into a format that can be directly processed by a computer, which is convenient for storage, retrieval and management. This coding method reduces the redundancy of data storage and improves storage efficiency. The genetic algorithm has a global search capability and can find the optimal solution in a wide solution space. This means that no matter what the initial conditions are, the algorithm can find the land resource information storage, processing and analysis scheme with the highest fitness through iterative evolution. The genetic algorithm evaluates the pros and cons of each individual through the fitness function and selects candidates for reproduction of offspring according to the fitness value. This adaptive mechanism enables the algorithm to flexibly adjust the search direction according to different scenarios and needs, and at the same time has strong robustness and can resist a certain degree of noise and interference. Through crossover and mutation operations, the genetic algorithm can generate new offspring individuals, which inherit the excellent genes of the parent generation and may produce new characteristics. This innovation and diversity helps the algorithm to jump out of the local optimal solution and explore a wider solution space. The optimized land resource information storage, processing and analysis scheme can more reasonably allocate and utilize computing resources and reduce unnecessary waste. At the same time, efficient algorithm implementation can shorten processing time and improve analysis efficiency.

[0039] In a preferred embodiment of the present invention, according to the final land resource information storage, processing and analysis scheme, the land resource information is stored, processed and analyzed to obtain analysis results, including: Classify the land resource information to obtain classification results; The average, maximum and minimum values ​​of soil moisture and temperature are extracted from the classification results, specifically including: for each land category, all relevant soil moisture and temperature data are collected; the average, maximum and minimum values ​​of the soil moisture and temperature data of each category are calculated respectively, and the calculated average, maximum and minimum values ​​are stored.

[0040] An analysis model is constructed based on the average, maximum, and minimum values ​​of soil moisture and temperature, and the analysis model is trained using historical data to obtain a trained analysis model, including: Analyze land resource information data, especially soil moisture and temperature data. According to business needs and data characteristics, determine the average, maximum, and minimum values ​​of soil moisture and temperature as input features. These statistical values ​​can reflect the basic conditions and extreme conditions of land resources. Extract these statistical values ​​from the original data and organize them into a format suitable for machine learning model processing. According to the nature of the problem and the characteristics of the data, select a suitable clustering model, such as K-means clustering. In the selected clustering model, set the initial parameters. For example, for the K-means algorithm, it is necessary to set the number of clusters K, the number of iterations, the convergence threshold, etc.; use cross-validation methods (such as K-fold cross-validation) to optimize these parameters, and through multiple experiments, find the parameter combination that makes the model perform best; check whether there are missing values, outliers or duplicate values ​​in the historical data, and perform corresponding processing, such as filling missing values, deleting or replacing outliers, removing duplicate records, etc.; in order to eliminate the dimensional differences between different features, standardize the data, such as using the Z-score standardization method to scale the feature values ​​to a distribution with a mean of 0 and a standard deviation of 1; randomly divide the preprocessed historical data into a training set, a validation set (sometimes also a test set), use 70%-80% of the data as the training set, and the remaining data as the validation set and test set; use the training set data to train the selected clustering model. During the training process, the model will try to divide the data into different clusters or categories; optimize the model parameters by minimizing a loss function (such as the sum of squared errors in the K-means algorithm) so that the data points in the same cluster are as similar as possible, while the data points between different clusters are as different as possible. Multiple iterations are required during the training process until the convergence condition is met or the preset number of iterations is reached; use the validation set data to verify the trained clustering model, input the validation set data into the model, and obtain the clustering results; select evaluation indicators (such as silhouette coefficient, Davies-Bouldin Index, etc.) according to business needs to evaluate the clustering effect of the model. These indicators can help judge the compactness and separation of the clustering results; adjust the model parameters or try different clustering algorithms based on the evaluation results to seek better clustering effects.

[0041] Use the trained analysis model to analyze the current land resource information to obtain analysis results, which may include: Collect land resource information data at the current time point to ensure that the data is up to date and covers the area to be analyzed; convert the collected data into the same format as the data used when training the model. This includes alignment of data structures, application of feature engineering, etc. to ensure that the model can correctly read and process the data; check whether there are missing values ​​in the current data and handle them according to the actual situation, such as filling with the mean, median or other interpolation methods; detect outliers in the data through statistical methods or visualization means, and decide whether to remove or replace them according to business logic; load the previously trained analysis model to ensure that all dependencies of the model have been correctly installed and configured; extract features corresponding to the model input from the preprocessed current land resource information data, that is, the average, maximum, minimum, etc. of soil moisture and temperature determined previously; input the extracted features into the trained model for prediction or analysis. For clustering models, this will involve assigning data points to corresponding clusters; visualize the output results of the model, such as scatter plots and heat maps of clustering results, so as to more intuitively understand the distribution and characteristics of land resource information, and analyze and interpret land resource information according to the output results of the model and business needs. For example, identifying specific types of land resource areas, judging the utilization status or change trends of land resources, etc.

[0042] In the embodiment of the present invention, by accurately classifying land resource information, a more detailed and accurate land type division can be obtained, and the automated information storage and processing process reduces manual intervention, improves the speed and accuracy of data processing, and thus improves management efficiency.

[0043] In a preferred embodiment of the present invention, the land resource information is classified to obtain a classification result, including: Determine the number of categories K into which the land resource information should be divided, and randomly select K data points as the initial clustering centers; For each point in the data set, the distance to each cluster center is calculated and assigned to the corresponding cluster center. The average value of each cluster is recalculated and the average value is set as the new cluster center until the preset number of iterations is reached to obtain the classification result.

[0044] In the embodiment of the present invention, by classifying land resource information, the management department can more clearly understand the characteristics and uses of various types of land, so as to formulate more accurate management strategies. This helps to reduce resource waste and improve land use efficiency. The classification results can provide detailed information on the distribution of land resources; by classifying land resources, it is easier to identify ecologically sensitive areas and areas that need special protection.

[0045] When specifically applied, this includes: According to the specific needs of land resource management, determine the number of categories K into which land resource information needs to be divided. This K value may be based on various factors such as land use, soil type, vegetation cover, etc. Based on the analysis and consultation results, a K value is initially set as the input parameter of the clustering algorithm.

[0046] Make sure you have a complete land resource information dataset, and each data point contains relevant features for clustering, such as soil moisture, temperature, etc.; randomly select K data points from the dataset as the initial cluster centers. These cluster centers will be gradually adjusted in subsequent iterations.

[0047] For each point in the data set, the distance between it and each cluster center is calculated. The distance can be calculated using the Euclidean distance. Based on the calculated distance, each data point is assigned to the cluster center with the closest distance, thus forming a preliminary clustering result.

[0048] For each cluster (or cluster), calculate the average value of all data points in it. This average value is calculated based on the features used for clustering (such as soil moisture and temperature); the calculated average value is set as the new center of the cluster. This new center more accurately reflects the distribution of data points in the cluster, and the cluster center is recalculated until the preset number of iterations is met or other stopping conditions are met (such as the change in the cluster center is less than a certain threshold); after multiple iterative optimizations, the algorithm will converge to a stable clustering result. At this point, each data point is assigned to a specific cluster, and the center of each cluster accurately reflects the distribution of data points in the cluster. The final clustering results can be evaluated, such as using indicators such as the silhouette coefficient to measure the quality of the clustering.

[0049] In a preferred embodiment of the present invention, the fitness function The calculation formula is: ; in, , and represents the weight coefficient; Indicates the amount of data processed; Indicates the time required for processing; represents the coefficient; Indicates the required storage space; Indicates the data redundancy rate; Indicates the data compression ratio; Indicates the number of correct results produced; Indicates the total number of results produced; Represents the error rate.

[0050] In this embodiment of the present invention, the fitness function It can combine multiple performance indicators to give a single value to represent the overall performance of the system. This simplifies the process of performance comparison and optimization, making it easier for decision makers to make decisions based on The value of F(P) is used to select the best configuration or strategy. When optimizing system performance, F(P) can be used as an objective function to guide the search direction of optimization algorithms (such as genetic algorithms, particle swarm optimization, etc.). By constantly adjusting system parameters to maximize or minimize By considering the time required for processing , Storage Space and data compression ratio Factors such as Helps improve resource utilization efficiency. For example, when storage space is limited, optimizing This can force the system to choose a more efficient data compression strategy. By considering the number of correct results and error rate , It can guarantee the quality of system output to a certain extent.

[0051] According to the analysis results, a three-dimensional space model is constructed, including: Extract key data from the analysis results, including the location, type, attributes and other information of land resources, and select 3D modeling software, such as ArcGIS, Blender, 3D Max, etc.; use the extracted data to create a basic model of land resources in the 3D modeling software; according to the type of land resources (such as cultivated land, forest land, water area, etc.), give different materials and textures to the model to enhance the realism of the model, and add necessary geographic information and labels, such as place names, altitudes, slopes, etc., to facilitate subsequent queries and analysis.

[0052] Optimize the constructed 3D model, reduce unnecessary details and complexity to improve the rendering speed and performance of the model, and export the optimized model to a common 3D file format, such as OBJ, FBX, etc., to ensure that the model can be viewed and analyzed in different platforms and software.

[0053] Based on the 3D spatial model, the status of land resources can be viewed in real time, including: Select a 3D visualization platform or framework, such as Cesium, Three.js, etc., for real-time rendering and display of 3D space models, configure the server and network environment, and ensure that the platform can run stably and efficiently; import the constructed 3D space model into the visualization platform.

[0054] A land resource management information method based on cloud computing, applied to the platform, includes: Set the initial temperature, end temperature and temperature drop rate; define the objective function of land resource information collection; initialize the current solution as a set of land resource information collection plans; generate a new land resource information collection plan through random perturbations based on the current solution; calculate the objective function value of the new land resource information collection plan through the objective function; use the Metropolis criterion to determine whether to accept the new solution, and when the new solution is accepted, update the current solution to the new solution; reduce the current temperature according to the predetermined temperature drop rate, simulate the cooling during the annealing process, until the preset number of iterations is reached to obtain the optimal solution, and determine the final land resource information collection plan based on the optimal solution; collect land resource information according to the final land resource information collection plan; Store, process and analyze land resource information to obtain analysis results; According to the analysis results, a three-dimensional space model is constructed; Based on the three-dimensional spatial model, view the status of land resources in real time.

[0055] It should be noted that the platform is a platform 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.

[0056] 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.

[0057] 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.

[0058] 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 land resource management information platform based on cloud computing, characterized in that: include: The acquisition module is used to set the initial temperature, the end temperature and the temperature drop rate; Define the objective function of land resource information collection; Initialize the current solution as a set of land resource information collection schemes; generate a new land resource information collection scheme through random perturbations based on the current solution; calculate the objective function value of the new land resource information collection scheme through the objective function; use the Metropolis criterion to determine whether to accept the new solution, and when the new solution is accepted, update the current solution to the new solution; The current temperature is reduced according to the predetermined temperature drop rate, and the temperature drop during the annealing process is simulated until the preset number of iterations is reached to obtain the optimal solution, and the final land resource information collection plan is determined based on the optimal solution; Collect land resource information according to the final land resource information collection plan; Cloud computing platform, used to store, process and analyze land resource information to obtain analysis results; A construction module is used to construct a three-dimensional space model based on the analysis results; The query module is used to view the status of land resources in real time based on the three-dimensional space model.

2. The cloud computing-based land resource management information platform according to claim 1 is characterized in that: Objective Function The calculation formula is: ； in, Indicates the area covered by each collection point; Indicates the total number of collection points; Indicates the collection point The decision variable of whether to be selected takes the value of 1 or 0, where 1 means that the corresponding collection point is selected for the collection of land resource information, and 0 means that the corresponding collection point is not selected for the collection; Indicates the maximum sensitivity value of the sensor; represents the adjustment factor; Representative collection point Distance to the reference point; represents an exponential decay function; Index variable representing the acquisition point; and Represents the weight coefficient.

3. The cloud computing-based land resource management information platform according to claim 2 is characterized in that: Store, process and analyze land resource information to obtain analysis results, including: According to the characteristics of land resource information, the land resource information is binary-coded; A certain number of individuals are randomly generated as the initial population, each of which represents a storage, processing and analysis scheme; According to the goal of land resource information management, a fitness function is defined to evaluate the quality of each individual; For each individual in the initial population, the fitness function is used to calculate its fitness value; according to the fitness value, the corresponding individual is selected from the current population as a candidate for reproduction; Randomly pair the selected individuals and exchange some genes between the selected individuals with a certain crossover probability to generate new offspring individuals; randomly change the newly generated offspring individuals with a certain mutation probability, and the new individuals generated by crossover and mutation operations together with some individuals in the parent generation form a new population, and continue to iterate and evolve until the preset number of iterations is reached. After the iteration is completed, the corresponding individual is selected from the last generation population as the final solution; Based on the final solution, the final land resource information storage, processing and analysis plan is obtained; According to the final land resource information storage, processing and analysis plan, the land resource information is stored, processed and analyzed to obtain the analysis results.

4. The cloud computing-based land resource management information platform according to claim 3 is characterized in that: According to the final land resource information storage, processing and analysis plan, the land resource information is stored, processed and analyzed to obtain analysis results, including: Classify the land resource information to obtain classification results; Extract the average, maximum and minimum values ​​of soil moisture and temperature from the classification results; Construct an analysis model based on the average, maximum, and minimum values ​​of soil moisture and temperature; Using historical data to train the analysis model to obtain a trained analysis model; Use the trained analysis model to analyze the current land resource information to obtain analysis results.

5. The cloud computing-based land resource management information platform according to claim 4 is characterized in that: Classify the land resource information to obtain classification results, including: Determine the number of categories K into which the land resource information should be divided, and randomly select K data points as the initial clustering centers; For each point in the data set, the distance to each cluster center is calculated and assigned to the corresponding cluster center. The average value of each cluster is recalculated and the average value is set as the new cluster center until the preset number of iterations is reached to obtain the classification result.

6. The cloud computing-based land resource management information platform according to claim 5 is characterized in that: Fitness function The calculation formula is: ； in, , and represents the weight coefficient; Indicates the amount of data processed; Indicates the time required for processing; represents the coefficient; Indicates the required storage space; Indicates the data redundancy rate; Indicates the data compression ratio; Indicates the number of correct results produced; Indicates the total number of results produced; Represents the error rate.

7. The cloud computing-based land resource management information platform according to claim 6 is characterized in that: Land resource information includes soil moisture, temperature, weather, topography and geographical location.

8. A land resource management information method based on cloud computing, characterized in that: Applied to the platform according to any one of claims 1 to 7, comprising: Set the initial temperature, end temperature and temperature drop rate; define the objective function of land resource information collection; initialize the current solution as a set of land resource information collection plans; generate a new land resource information collection plan through random perturbations based on the current solution; calculate the objective function value of the new land resource information collection plan through the objective function; use the Metropolis criterion to determine whether to accept the new solution, and when the new solution is accepted, update the current solution to the new solution; reduce the current temperature according to the predetermined temperature drop rate, simulate the cooling during the annealing process, until the preset number of iterations is reached to obtain the optimal solution, and determine the final land resource information collection plan based on the optimal solution; collect land resource information according to the final land resource information collection plan; Store, process and analyze land resource information to obtain analysis results; According to the analysis results, a three-dimensional space model is constructed; Based on the three-dimensional spatial model, view the status of land resources in real time.

9. 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 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a program, which, when executed by a processor, implements the method according to any one of claims 1 to 7.

Images