Intelligent Analysis Method and System for Land Resource Information Data Based on Cloud Computing

Abstract

The present invention relates to the field of data processing, and specifically to an intelligent analysis method and system for land resource information data based on cloud computing. The method includes: dividing the land into multiple regions, constructing a data set for each region; the data set includes three soil data items: soil nutrient, pH value, and vegetation coverage rate; obtaining the local Moran's index of each soil data item within each region, calculating the spatial heterogeneity index of each region, and taking the reciprocal of the product of the local Moran's index of the soil data and the spatial heterogeneity index as the correlation anomaly degree of the corresponding soil data; marking the regions where the correlation anomaly degree of the soil data is greater than a preset anomaly threshold as abnormal regions, and formulating treatment measures for the abnormal regions. By calculating and analyzing the local Moran's index, spatial heterogeneity index, and correlation anomaly degree of the soil data, the present invention can accurately identify abnormal regions and formulate targeted treatment measures.

Description

Technical Field

[0001] The present invention relates to the field of data processing. More specifically, the present invention relates to an intelligent analysis method and system for land resource information data based on cloud computing. Background Art

[0002] Soil, as an important part of the earth's land surface, is not only the material basis for agricultural development and urbanization, but also a key factor in maintaining ecological balance and promoting sustainable development. Through in-depth soil data analysis, we can comprehensively understand key indicators such as soil nutrient status, pH value, and organic matter content, which are of great significance for guiding agricultural production, optimizing land use patterns, and protecting the ecological environment.

[0003] The prior art, such as the patent application document with the publication number CN118735714A, discloses a soil improvement data analysis method and system. The soil improvement data analysis method includes: regularly or continuously sampling soil moisture and salinity in a sample plot, recording them as soil data, based on this data, studying soil moisture content and salinity content, establishing a database, analyzing the spatio-temporal distribution and variation characteristics before and after improvement, and drawing a spatial distribution map, combining with the change of groundwater depth, analyzing the soil improvement situation, obtaining adaptation information, and managing abnormal soil according to the analysis results and optimizing the improvement plan.

[0004] The above soil improvement data analysis method evaluates the effect of soil improvement by analyzing and visualizing the spatial distribution of soil data, and adjusts the management strategy accordingly. However, it does not consider the differences in soil properties at different spatial positions, resulting in significant differences in soil property values in some areas compared to the surrounding areas during analysis. These abnormal values may not be real abnormalities, thus making the soil property analysis results inaccurate. Summary of the Invention

[0005] To solve the technical problem of inaccurate soil property analysis results, the present invention provides solutions in the following aspects.

[0006] In the first aspect, an intelligent analysis method for land resource information data based on cloud computing includes:

[0007] Dividing the land into multiple regions, constructing a data set for each region; the data set includes three soil data items: soil nutrients, pH value, and vegetation coverage rate;

[0008] Obtaining the local Moran index of each soil data item in each region, calculating the spatial heterogeneity index of each region, and taking the reciprocal of the product of the local Moran index of the soil data and the spatial heterogeneity index as the correlation abnormality degree of the corresponding soil data;

[0009] Mark the area where the correlation anomaly degree of soil data is greater than the preset anomaly threshold as the anomaly area, and formulate treatment measures for the anomaly area;

[0010] The spatial heterogeneity index satisfies the following relationship:

[0011] ; where, is the spatial heterogeneity index of the th area, is the number of items of soil data collected, is the weight of the th item of soil data in all areas, is the neighborhood difference degree of the th item of soil data in the th area, is the mean value of the neighborhood difference degrees of all items of soil data in the th area.

[0012] By analyzing the spatial distribution characteristics of soil data, calculating the corresponding local Moran index and spatial heterogeneity index, the present invention comprehensively considers the similarity of soil properties in adjacent areas and the spatial differences of soil properties, which helps to more accurately understand the spatial distribution law of soil properties, thereby improving the accuracy of the analysis results.

[0013] Preferably, the process of obtaining the neighborhood difference degree includes:

[0014] Calculate the mean value of the Euclidean distances between the th area and all other areas, and use all areas with Euclidean distances less than the preset distance threshold from the th area as the neighborhood areas of the th area;

[0015] Calculate the mean value of the numerical differences between all items of soil data in all neighborhood areas of the th area and the th item of soil data in the th area to obtain the neighborhood difference degree of the th item of soil data in the th area. The neighborhood difference degree reflects the difference degree of soil data between the

[0016] th area and its neighborhood areas. This difference degree can reveal the spatial distribution characteristics of soil data, including similarity, difference and change trend, etc.; when the neighborhood difference degree of a certain area is significantly too large or too small, it may mean that there is an abnormal situation in the soil properties of this area, which needs special attention and treatment. th area and its neighborhood areas. This difference degree can reveal the spatial distribution characteristics of soil data, including similarity, difference and change trend, etc.; when the neighborhood difference degree of a certain area is significantly too large or too small, it may mean that there is an abnormal situation in the soil properties of this area, which needs special attention and treatment.

[0017] Preferably, the process of obtaining the anomaly threshold is as follows:

[0018] Calculate the average value and standard deviation of the degree of correlation anomaly of any item of soil data in all regions, and take the sum of the average value and the standard deviation as the anomaly threshold.

[0019] The calculation of the anomaly threshold takes into account the average value and standard deviation of the degree of correlation anomaly, which can reflect the distribution characteristics of soil data in all regions. The average value represents the overall level, while the standard deviation reflects the degree of dispersion of the data. The combination of the two makes the anomaly threshold more in line with the actual situation of the data.

[0020] Preferably, the weights of the th item of soil data in all regions satisfy the following relationship:

[0021] ; where is the weight of the th item of soil data in all regions, is the global Moran's I of the th item of soil data in all regions.

[0022] When analyzing soil data, the weights of each item of soil data will directly affect the accuracy and reliability of the analysis results. By setting reasonable weights, the analysis process can be optimized to make the analysis results more in line with the actual situation. Using the above relationship to set weights can make the soil data with strong spatial autocorrelation obtain greater weights in the analysis, thus improving the accuracy of the analysis results.

[0023] Preferably, the process of obtaining the neighborhood difference degree includes:

[0024] Calculate the average value of the Euclidean distances between the th region and all other regions, and regard all regions whose Euclidean distances from the th region are less than a preset distance threshold as the neighborhood regions of the th region;

[0025] For each neighborhood region, take the product of the average Euclidean distance between the th region and all regions and the reciprocal of the Euclidean distance between the th region and this neighborhood region as the distance weight of this neighborhood region;

[0026] Multiply the numerical difference between the th item of soil data in each neighborhood region and the th item of soil data in the th region by the corresponding distance weight and sum them up, and then divide by the number of neighborhood regions to obtain the th item of soil data in the The neighborhood difference degree of soil data items.

[0027] The neighborhood difference degree is an important indicator for measuring the difference degree of soil data between regions. By calculating the numerical difference between the soil data of each neighborhood area and the soil data within the th area, and considering the distance weight, the spatial heterogeneity of soil data can be reflected. This heterogeneity is an important basis for formulating targeted treatment measures.

[0028] Preferably, the weights of the th soil data items of all the areas satisfy the relational expression:

[0029] ; where is the weight of the th soil data item of all the areas, is the global Moran's I of the th soil data item of all the areas, is a constant.

[0030] Preferably, the degree of correlation anomaly also satisfies the relational expression:

[0031] ; where is the degree of correlation anomaly of the th soil data item within the th area, is the local Moran's I of the th soil data item within the th area, is the spatial heterogeneity index of the th area.

[0032] Preferably, the degree of correlation anomaly also satisfies the relational expression:

[0033] ; where is the degree of correlation anomaly of the th soil data item within the th area, is the local Moran's I of the th soil data item within the th area, is the spatial heterogeneity index of the th area, , are both weights.

[0034] In a second aspect, an intelligent analysis system based on cloud computing land resource information data includes: a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned intelligent analysis method based on cloud computing land resource information data is implemented.

[0035] The beneficial effects of the present invention are as follows:

[0036] By dividing the analyzed land into regions, considering the spatial distribution characteristics of soil data, calculating the local Moran index and the spatial heterogeneity index, and calculating the degree of correlation anomaly of the data according to the local Moran index and the spatial heterogeneity index, this comprehensive analysis helps to more accurately understand the spatial distribution law of soil properties, thereby improving the accuracy of the analysis results;

[0037] Furthermore, by setting an anomaly threshold, areas with abnormal soil properties can be accurately identified. These areas are often areas with poor soil quality or potential problems and require special attention and treatment. Description of the Drawings

[0038] By referring to the following detailed description with reference to the drawings, the above and other objects, features, and advantages of the exemplary embodiments of the present invention will become readily understood. In the drawings, several embodiments of the present invention are shown in an exemplary rather than restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0039] Figure 1 is a flowchart of the method from step S1 to step S3 in the intelligent analysis method based on cloud computing land resource information data according to an embodiment of the present invention. Detailed Embodiments

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0041] The embodiments of the present invention disclose an intelligent analysis method based on cloud computing land resource information data. Referring to Figure 1 , it includes steps S1 - S3, specifically as follows:

[0042] S1: Divide the land into regions to obtain multiple regions, and construct a data set for each region; the data set includes three soil data items: soil nutrient, pH value, and vegetation coverage rate.

[0043] Based on empirical classification according to the influencing factors of land use (such as output capacity, vegetation coverage rate, artificial coverage rate, etc.), regions with similar differences in land influencing factor data are classified into the same region to reduce data fluctuations and errors, and then the total number of land area classifications is recorded as .

[0044] Data collection is carried out for each region, and the data items to be collected are determined, including but not limited to the output capacity of the land, vegetation coverage rate, artificial coverage rate, soil nutrient content, pH value, altitude, slope, etc. The number of items of the collected data is recorded as (Exemplarily, three soil data items of soil nutrient, pH value and vegetation coverage rate are collected, that is ). Among them, the vegetation coverage rate, artificial coverage rate and output capacity can be statistically analyzed through on-site investigations, satellite remote sensing, etc. The soil nutrient content and pH value can be sampled and averaged within each region, and professional instruments are used for soil analysis. The altitude and slope can be measured using movable meteorological equipment (such as GPS, altimeter, slope meter, etc.).

[0045] Furthermore, the value of the th soil data item collected in each region is denoted as , where represents the region number (1 ≤ ≤ ), represents the data item number (1 ≤ ≤ ).

[0046] S2: Obtain the local Moran's index of each soil data item within each region, calculate the spatial heterogeneity index of each region, and take the reciprocal of the product of the local Moran's index of the soil data and the spatial heterogeneity index as the correlation anomaly degree of the corresponding soil data.

[0047] In the embodiments of the present invention, Moran's index is used to analyze land attributes, so as to identify which regions have significant spatial aggregation or dispersion phenomena. However, due to spatial heterogeneity caused by natural or human factors in some regions, their local Moran's index may show anomalies. Here, "anomaly" does not mean that the data is incorrect or there is a problem, but reflects the uniqueness of the spatial distribution of these regions. If the "anomaly" regions caused by normal spatial heterogeneity and the regions that may truly have problems (such as data errors, abnormal events, etc.) are not distinguished, the normal spatial heterogeneity regions may be misidentified as anomaly regions. Such misidentification will affect the accurate judgment of technicians on land resource information data, and further lead to inappropriate decisions or analysis conclusions.

[0048] First, obtain the centroid corresponding to the contour of each region. Calculate the distance between any two regions based on the Euclidean distance between the centroids of each region. Based on the Euclidean distance, calculate the distance weight value between each pair of regions, which is the reciprocal of the Euclidean distance. The expression is , where is the th region and the th region's distance weight value, is the th region and the th region's Euclidean distance. Furthermore, organize the distance weight values of all pairs of regions into a spatial weight matrix W. Use the spatial weight matrix W and the data values of all regions to calculate the global and local Moran's I. Exemplarily, mark the global Moran's I of the th item of soil data for all regions as , and mark the local Moran's I of the th region's th item of soil data as .

[0049] It should be noted that Moran's I is a prior art, and the specific acquisition steps will not be elaborated in detail.

[0050] Secondly, for each region, calculate the difference between it and all neighboring regions in each item of data.

[0051] Specifically, calculate the mean value of the Euclidean distances between the th region and all other regions. Take all regions whose Euclidean distance from the th region is less than a preset distance threshold (in the embodiment of the present invention, take the mean value of the Euclidean distances between the th region and all other regions as the distance threshold) as the th region's neighboring regions; calculate the mean value of the numerical differences between the th region's all neighboring regions' th item of soil data and the th region's th item of soil data, and obtain the neighborhood difference degree of the th region's th item of soil data.

[0052] Exemplarily, the neighborhood difference degree of the th region's th item of soil data satisfies the relational expression:

[0053]

[0054] In the formula, is the th region's The neighborhood difference degree of the soil data item is the total number of neighborhood regions of the th region, is the th soil data value of the th neighborhood region, is the th soil data value within the th region.

[0055] When the difference between the th region and its neighborhood regions regarding the th soil data item increases, also increases, which means the spatial autocorrelation of this soil data item weakens and the spatial variability strengthens.

[0056] Furthermore, considering that regions closer in distance are more similar to the th region in terms of soil properties, environmental conditions, etc., a distance weight is introduced such that regions closer in distance have a greater impact on the th region.

[0057] Specifically, calculate the average of the Euclidean distances between the th region and all other regions. Consider all regions with Euclidean distances less than a preset distance threshold from the th region as the neighborhood regions of the th region; for each neighborhood region, take the product of the average Euclidean distance between the th region and all regions and the reciprocal of the Euclidean distance between the th region and this neighborhood region as the distance weight of this neighborhood region; multiply the numerical difference between the th soil data item of each neighborhood region and the th soil data item within the th region by the corresponding distance weight and sum them up, then divide by the number of neighborhood regions to obtain the neighborhood difference degree of the th soil data item within the th region.

[0058] Exemplarily, the neighborhood difference degree of the th soil data item within the th region after introducing the distance weight satisfies the relational expression:

[0059]

[0060] In the formula, is the neighborhood difference degree of the th soil data item within the th region, is the The total number of neighborhood regions of a region, is the Euclidean distance between the th region and the th neighborhood region, is the average Euclidean distance between the th region and all regions, is the th soil data value of the th neighborhood region, is the th soil data value within the

[0061] By adjusting the distance weights, the contributions of different neighborhood regions to the central region's degree of difference can be balanced. Although regions with a large distance also have a certain degree of correlation, their influence is relatively small, so their weights are also relatively low. This can avoid the deviation of the overall degree of difference calculation result caused by data anomalies in individual distant regions.

[0062] Then, according to the neighborhood difference degree of each item of data in each region, the spatial heterogeneity index of the region is obtained, that is, the relational expression is satisfied as:

[0063]

[0064] In the formula, is the spatial heterogeneity index of the th region, is the number of items of soil data collected, is the weight of the th item of soil data for all regions, is the th neighborhood difference degree of the th item of soil data within the th region, is the mean value of the neighborhood difference degrees of all items of soil data within the

[0065] Among them, ; in the formula, is the weight of the th item of soil data for all regions, is the global Moran's I of the th item of soil data for all regions.

[0066] represents the th within the The degree of difference between the neighborhood difference degree of a soil data item and the average of the neighborhood difference degrees of all data items. The higher this value, the greater the difference in the neighborhood difference degrees of all data items, that is, the neighborhood difference degrees of all data items are not uniform, which may mean that there are abnormalities or special features in the regional data.

[0067] Indicates the result of normalizing the Moran's I of the th soil data item (the global Moran's I ranges from (-1, 1)). Moran's I is an index to measure the spatial autocorrelation of data. The closer its value is to 1, the stronger the positive correlation; the closer it is to -1, the stronger the negative correlation; and being close to 0 indicates no significant autocorrelation. In the spatial heterogeneity index formula, the smaller the Moran's I of the

[0068] th soil data item, the weaker the autocorrelation of this data item, and the lower the reference degree of the difference of this data item.

[0069] It should be noted that the calculation of

[0070]

[0071] also provides another calculation method, that is, the relational expression is satisfied as: where is the weight of the th soil data item of all regions, is the global Moran's I of the th soil data item of all regions, and

[0072] is a constant. Finally, take the reciprocal of the product of the local Moran's I of the th soil data item and the spatial heterogeneity index of the th region as the correlation abnormality degree of the th soil data item of the

[0073]

[0074] th region. That is, the relational expression is satisfied as: where is the correlation abnormality degree of the th soil data item within the th region, The local Moran's Index of the th soil data within a region, is the spatial heterogeneity index of the th region.

[0075] The above-mentioned correlation anomaly degree provides another calculation formula:

[0076]

[0077] In the formula, is the correlation anomaly degree of the th soil data within the th region, is the local Moran's Index of the th soil data within the th region, is the spatial heterogeneity index of the th region.

[0078] The difference between this formula and the first formula for calculating the correlation anomaly degree is that it uses the absolute value to ensure that even if the local Moran's Index is negative, its contribution to the correlation anomaly degree is positive, thus comprehensively considering the directionality of spatial autocorrelation.

[0079] The above-mentioned correlation anomaly degree also provides another calculation formula:

[0080]

[0081] In the formula, is the correlation anomaly degree of the th soil data within the th region, is the local Moran's Index of the th soil data within the th region, is the spatial heterogeneity index of the th region, , are both weights.

[0082] The difference between this calculation formula and the first formula for calculating the correlation anomaly degree is that it uses the weight coefficients and to balance the contributions of the two indicators, enabling the analysis results to be adjusted according to specific situations. For example, if the local Moran's Index is more important for the correlation of a specific dataset, the value of can be increased; conversely, if the spatial heterogeneity index is more crucial, the value of can be increased.

[0083] Furthermore, the degree of correlation anomaly of all soil data is obtained.

[0084] S3: Mark the area where the degree of correlation anomaly of the soil data is greater than the preset anomaly threshold as an abnormal area, and formulate treatment measures for the abnormal area.

[0085] Based on the degree of correlation anomaly of all soil data calculated in the above step S2, when the soil data in a certain area shows a high degree of correlation anomaly, it means that the spatial autocorrelation between the soil data in this area is low, that is, the correlation between the data is not strong, and there may be problems such as uneven data distribution, mutation or outliers.

[0086] Specifically, calculate the average value and standard deviation of the degree of correlation anomaly of any soil data in all areas, use the sum of the average value and the standard deviation as the anomaly threshold, mark the area where the degree of correlation anomaly of the soil data is greater than the anomaly threshold as an abnormal area, and formulate treatment measures for the abnormal area (such as conducting in-depth analysis of the abnormal area to find out the reasons for the data anomaly, which may be caused by pollution sources, geological conditions or other environmental factors, and technicians can further formulate a repair plan).

[0087] The embodiment of the present invention also discloses an intelligent analysis system for cloud computing-based land resource information data, including a processor and a memory. The memory stores computer program instructions, and when the computer program instructions are executed by the processor, the intelligent analysis method for cloud computing-based land resource information data according to the present invention is implemented.

[0088] The system also includes other components well-known to those skilled in the art such as a communication bus and a communication interface, and their settings and functions are known in the art, so they will not be described in detail here.

[0089] In the present invention, the foregoing memory may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as, for example, a resistive random access memory (RRAM), a dynamic random access memory (DRAM), a static random access memory (SRAM), an enhanced dynamic random access memory (EDRAM), a high-bandwidth memory (HBM), a hybrid memory cube (HMC), etc., or any other medium that can be used to store the required information and can be accessed by an application program, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0090] In the description of this specification, the meanings of "a plurality of" and "several" are at least two, for example, two, three, or more, etc., unless otherwise specifically defined.

[0091] Although this specification has shown and described multiple embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will think of many changes, alterations, and alternative ways without departing from the spirit and scope of the present invention. It should be understood that various alternatives to the embodiments of the present invention described herein may be employed in practicing the present invention.

Claims

1. An intelligent analysis method for land resource information data based on cloud computing, characterized in that, Including: Dividing the land into multiple regions, constructing a data set for each region; the data set includes three soil data items: soil nutrients, pH value, and vegetation coverage rate; Obtaining the local Moran index of each soil data item in each region, calculating the spatial heterogeneity index of each region, and taking the reciprocal of the product of the local Moran index of the soil data and the spatial heterogeneity index as the correlation anomaly degree of the corresponding soil data; or The correlation anomaly degree satisfies the relational expression: ; wherein, is the degree of correlation anomaly of the th item of soil data in the th area, is the local Moran's index of the th item of soil data in the th area, is the spatial heterogeneity index of the th area; or The correlation anomaly degree satisfies the relational expression: ; where, is the degree of correlation anomaly of the th soil data item in the th area, is the local Moran's index of the th soil data item in the th area, is the spatial heterogeneity index of the th area, , are both weights; Marking the regions where the correlation anomaly degree of the soil data is greater than a preset anomaly threshold as abnormal regions, and formulating treatment measures for the abnormal regions; The spatial heterogeneity index satisfies the relational expression: ; where, is the spatial heterogeneity index of the th region, is the number of items for collecting soil data, is the weight of the th item of soil data for all regions, is the neighborhood difference degree of the th item of soil data within the th region, is the mean value of the neighborhood difference degrees of all items of soil data within the th region.

2. The intelligent analysis method based on cloud computing land resource information data according to claim 1, wherein, The process of obtaining the neighborhood difference degree includes: Calculate the mean of the Euclidean distances between the th region and all other regions, and regard all regions whose Euclidean distance from the th region is less than a preset distance threshold as the th region's neighborhood region; Calculate the mean of the numerical differences between the th soil data of all neighborhood regions of the th region and the th soil data within the th region to obtain the neighborhood difference degree of the th soil data within the th region.

3. The intelligent analysis method based on cloud computing land resource information data according to claim 2, wherein, The process of obtaining the anomaly threshold is: Calculating the average value and standard deviation of the correlation anomaly degree of any soil data item in all regions, and taking the sum of the average value and the standard deviation as the anomaly threshold.

4. The intelligent analysis method based on cloud computing land resource information data according to claim 3, characterized in that The weights of the soil data for all the regions described in item satisfy the following relationship: ; In the formula, is the weight of the th soil data for all regions, is the global Moran's index of the th soil data for all regions.

5. The intelligent analysis method based on cloud computing land resource information data according to claim 1, characterized in that The process of obtaining the neighborhood difference degree includes: Calculate the mean of the Euclidean distances between the th region and all other regions, and use all regions whose Euclidean distances from the th region are less than a preset distance threshold as the th region's neighborhood regions; For each neighborhood region, use the product of the average Euclidean distance between the th region and all regions and the reciprocal of the Euclidean distance between the th region and this neighborhood region as the distance weight of this neighborhood region; Multiply the numerical difference between the th soil data of each neighborhood area and the th soil data in the th area by the corresponding distance weight and sum them up, then divide by the number of neighborhood areas to obtain the neighborhood difference degree of the th soil data in the th area.

6. The intelligent analysis method based on cloud computing land resource information data according to claim 1, characterized in that The weights of the soil data for all the regions in item satisfy the following relationship: ; where, is the weight of the -th soil data for all regions, is the global Moran's I of the -th soil data for all regions, is a constant.

7. An intelligent analysis system for land resource information data based on cloud computing, characterized in that, Including: A processor and a memory, the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the intelligent analysis method based on cloud computing land resource information data according to any one of claims 1-6 is implemented.

Images