A database construction management method for multi-source data

Abstract

This invention relates to the field of database construction technology, specifically disclosing a database construction and management method for multi-source data. The method includes the following steps: S1: acquiring and preprocessing multi-source data; S2: establishing an agricultural and rural spatiotemporal database; S3: establishing a first construction management analysis model; S4: establishing a second construction management analysis model; S5: evaluating the construction management quality; and S6: establishing a construction management in-depth analysis model. This invention acquires and preprocesses multi-source data to construct a spatiotemporal database, and evaluates the construction management quality by establishing a first and a second construction management analysis model. This invention achieves the integration and unified management of multi-source agricultural and rural data, significantly improving data quality and application value, providing comprehensive and accurate data support for agricultural analysis, and helping to improve agricultural production efficiency, reduce production risks, and promote sustainable agricultural development.

Description

Technical Field

[0001] This invention relates to the field of database construction technology, and in particular to a database construction and management method for multi-source data. Background Technology

[0002] With the advancement of agricultural modernization, agricultural and rural data analysis and decision-making are increasingly reliant on multi-source data. However, multi-source data is characterized by its dispersed origins, heterogeneous formats, and complex spatiotemporal attributes. Constructing an efficient and reliable database management system to achieve unified data integration, quality assessment, and in-depth application has become a key challenge in unlocking the value of agricultural data.

[0003] Traditional database construction and management methods often employ a single data source and independent storage model. Satellite remote sensing data is converted into formats using specialized software and then stored in a file system; meteorological data relies on local databases for structured storage; agricultural operational data is scattered across different departmental systems and managed in isolation using relational databases. While this method can manage data to some extent, it has many limitations.

[0004] First, traditional database construction and management methods lack effective spatiotemporal processing tools, failing to systematically integrate the spatial attributes, temporal characteristics, and business features of data. This severs the correlation between data, making it difficult to form a complete agricultural data system and providing comprehensive and accurate data support for agricultural analysis. Second, in terms of database construction and management quality assessment, traditional methods lack systematic evaluation tools, relying solely on subjective human judgment. This makes it difficult to comprehensively and accurately assess the quality of database construction and management, and cannot provide a reliable basis for continuous database improvement. Furthermore, traditional methods lack depth in data application, often limited to simple queries and storage. They lack in-depth analysis of the intrinsic relationship between meteorological data and crop growth data, and cannot generate practically guiding crop growth environment management plans based on data relationships. This makes it difficult to transform data into a basis for agricultural production decisions, greatly limiting the application value of agricultural data. Summary of the Invention

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a database construction and management method for multi-source data to solve the problems mentioned in the background art.

[0006] To achieve the above objectives, the present invention provides the following technical solution: a database construction and management method for multi-source data, comprising the following steps:

[0007] S1: Acquire and preprocess multi-source data: Acquire multi-source agricultural and rural data in real time, preprocess the multi-source data, and generate preprocessed multi-source data. The multi-source data includes satellite remote sensing data, meteorological data, and agricultural business data.

[0008] S2: Establish a spatiotemporal database for agriculture and rural areas: Based on preprocessed multi-source data, a spatiotemporal database for agriculture and rural areas is established using spatiotemporal processing algorithms;

[0009] S3: Establish the first construction management analysis model: obtain the spatial coverage, cloud cover impact rate and geometric correction accuracy of satellite remote sensing data, and evaluate the first construction management status of the spatiotemporal database construction by establishing the first construction management analysis model;

[0010] S4: Establish a second construction management analysis model: Obtain the yield prediction deviation rate, product price volatility rate, and product inventory turnover rate of agricultural business data, and evaluate the second construction management status of the spatiotemporal database construction by establishing a second construction management analysis model;

[0011] S5: Evaluate the quality of construction management: Based on the first construction management analysis model and the second construction management analysis model, evaluate the quality of construction management of the spatiotemporal database, output the construction management quality evaluation results and issue early warnings;

[0012] S6: Establish a deep analysis model for management: By establishing a deep analysis model for management, establish the influence relationship function between meteorological data and crop growth data, generate a crop growth environment management plan, and send the crop growth environment management plan to agricultural managers.

[0013] Preferably, the specific execution method for acquiring and preprocessing multi-source data is as follows:

[0014] A multi-source data acquisition channel is established, connecting to satellite remote sensing data sources, meteorological data sources, and agricultural operational data sources respectively, to acquire multi-source agricultural and rural data in real time. The multi-source data is then preprocessed, specifically by using standardized processing tools to extract the required multi-source data from the original data sources, performing preprocessing operations on the required multi-source data, including data cleaning, format conversion, and missing value handling, merging the preprocessed multi-source data, and uniformly converting the merged multi-source data into a standardized format.

[0015] Preferably, the execution method for establishing the first construction management analysis model is as follows:

[0016] The first feature data of satellite remote sensing data is acquired in real time, and the first feature data includes the spatial coverage, cloud cover impact rate and geometric correction accuracy of the satellite remote sensing data.

[0017] The first step is to obtain the spatial coverage, and the specific method for obtaining it is as follows:

[0018] The agricultural and rural areas were designated as the target monitoring area, which was then divided into m grids. Based on land use type data, an agricultural priority weight Q was assigned to each grid. j This is marked as the agricultural priority weight Q of each grid. j j represents the number of each grid cell, j = 1, 2, 3, ..., m, where m is the total number of grid cells;

[0019] The system acquires satellite remote sensing data from the agricultural and rural spatiotemporal database, extracts satellite remote sensing images from the satellite remote sensing data, identifies the effective data boundaries of the images within the grid using an edge detection algorithm, obtains the effective data area within each grid, and determines that the grid is an effective coverage grid when the proportion of the effective data area within a certain grid is greater than a preset area proportion threshold, and marks the effective area in the effective coverage grid as the effective coverage area.

[0020] Obtain the effective coverage area Ea of each grid j and total area Ta j And combined with the agricultural priority weight Q of each grid j Calculate the spatial coverage Sc of satellite remote sensing data;

[0021] The second step is to obtain the cloud coverage impact rate. The specific method for obtaining the cloud coverage impact rate is as follows: obtain satellite remote sensing images from the satellite remote sensing data, extract the cloud coverage area and total coverage area from each satellite remote sensing image, and calculate the cloud coverage impact rate Ir of the satellite remote sensing data.

[0022] The third step is to read the spatial coverage Sc and cloud coverage impact rate Ir of the satellite remote sensing data, and at the same time obtain the geometric correction accuracy Ca of the satellite remote sensing data. The obtained data is normalized, the first construction management analysis model is established, and the first construction management analysis coefficient is calculated.

[0023] The first construction management status of the spatiotemporal database is evaluated based on the first construction management analysis coefficient. Specifically, the first construction management analysis coefficient is compared with a preset construction management analysis coefficient threshold. If the first construction management analysis coefficient is greater than the preset construction management analysis coefficient threshold, the first construction management status of the spatiotemporal database is judged to be normal. Otherwise, the first construction management status of the spatiotemporal database is judged to be abnormal, and a warning message is sent to the mobile device of the administrator.

[0024] Preferably, the method for obtaining the geometric correction accuracy of satellite remote sensing data is as follows:

[0025] Extract the satellite remote sensing image to be corrected from the satellite remote sensing data. Then, uniformly select n ground control points on the satellite remote sensing image. Extract the true coordinates of the n ground control points from a known reference map. Where i represents the number of each ground control point, i=1, 2, 3, ..., n, and n is the total number of ground control points;

[0026] Using remote sensing image processing software, the n ground control points are located on the satellite remote sensing image to be corrected, and the pixel coordinates of the corresponding ground control points on the satellite remote sensing image are read. ;

[0027] Based on the actual coordinates of ground control points and ground control point pixel coordinates The deviation between the true coordinates of each ground control point and the pixel coordinates of the ground control points is calculated, and the calculated deviation is imported into the geometric correction accuracy formula to calculate the geometric correction accuracy Ca of the satellite remote sensing data.

[0028] Preferably, the execution method for establishing the second construction management analysis model is as follows:

[0029] The second feature data of real-time acquisition of satellite remote sensing data includes output prediction deviation rate, product price volatility rate and product inventory turnover rate.

[0030] The first step is to obtain the yield prediction deviation rate. The specific method is as follows: read the agricultural business data in the agricultural and rural spatiotemporal database, obtain the actual output of agricultural products Op and the predicted output of agricultural products Fp in the agricultural business data, and combine the actual output of products and the predicted output of agricultural products to obtain the yield prediction deviation rate Pdr.

[0031] The second step is to obtain product price volatility. Specifically, this is done by using a weekly sampling period and obtaining the highest price of agricultural products within the current week from the agricultural business data. and lowest price Analyze the price range R of agricultural products; obtain the average price of agricultural products within this week from agricultural business data. And at the same time, obtain the average price of agricultural products for the previous week. Analyze the rate of change in agricultural product prices Furthermore, the product price volatility Ppv is analyzed.

[0032] The third step involves reading the agricultural business data, including the yield prediction deviation rate Pdr, product price volatility rate Ppv, and product inventory turnover rate Itr, and then normalizing them to establish a second construction management analysis model. The second construction management analysis coefficient is then calculated, and the second construction management status of the spatiotemporal database is evaluated based on the second construction management analysis coefficient. Finally, the second construction management evaluation result is output.

[0033] Preferably, the specific method for evaluating the construction management quality is as follows:

[0034] Based on the first construction management analysis model, the first construction management analysis coefficient is obtained. Based on the second construction management analysis model, the second construction management analysis coefficient is obtained. The first construction management analysis coefficient and the second construction management analysis coefficient are combined to obtain the construction management evaluation index. The construction management evaluation index is used to evaluate the construction management quality of the spatiotemporal database, output the construction management quality evaluation result, and issue early warning reminders.

[0035] Preferably, the specific steps for establishing and constructing the deep analysis model for management are as follows:

[0036] S61: Obtain the optimal light intensity for the crop growth stage from the management database corresponding to the crop. and light adaptation range half width This refers to the acceptable range of light exposure for crops; and it involves real-time monitoring of actual light intensity. Based on the deviation between actual light intensity and optimal light intensity, the influence of light intensity on crop growth is analyzed, and the light influence coefficient Kl is obtained.

[0037] S62: Obtain the optimal rainfall for the crop growth stage from the management database corresponding to the crop. and critical rainfall range ,in, Indicates the minimum effective rainfall. This indicates the maximum tolerable rainfall, and the actual rainfall is collected in real time. Based on the deviation between the actual rainfall and the optimal rainfall, the impact of rainfall on crop growth is analyzed, and the rainfall impact coefficient Kr is obtained.

[0038] S63: Obtain the light impact coefficient Kl and rainfall impact coefficient Kr from meteorological data, establish the influence relationship function between them and crop growth data, generate management plans corresponding to the crop growth environment based on the influence relationship function, and send the management plans corresponding to the crop growth environment to agricultural managers.

[0039] As described above, the database construction and management method for multi-source data provided by the present invention has at least the following beneficial effects:

[0040] This invention provides a database construction and management method for multi-source data. It involves acquiring and preprocessing real-time satellite remote sensing data, meteorological data, and agricultural operational data related to agriculture and rural areas. Then, a spatiotemporal processing algorithm is used to construct an agricultural and rural spatiotemporal database from the preprocessed data. Subsequently, a first construction and management analysis model is established to assess the construction and management status of the spatiotemporal database based on spatial coverage, cloud cover impact rate, and geometric correction accuracy. A second construction and management analysis model is established to assess the construction and management status of the spatiotemporal database based on yield prediction deviation rate, product price volatility, and product inventory turnover rate. The construction and management quality of the spatiotemporal database is then comprehensively evaluated based on the two models, and the evaluation results and early warnings are output. Finally, a deep analysis model for construction and management is used to establish the influence relationship function between meteorological data and crop growth data, generate a crop growth environment management plan, and send it to agricultural managers. This invention not only realizes closed-loop management of agricultural multi-source data from collection, storage, evaluation to in-depth application, but also significantly improves the integration efficiency and analysis accuracy of agricultural data. It can assist agricultural managers in making scientific and reasonable production decisions, help reduce costs and increase efficiency in agricultural production, and promote the digital and intelligent development of agriculture. It has broad application value and significant economic benefits in optimizing the allocation of agricultural resources, improving the yield and quality of agricultural products, and early warning and prevention of agricultural disasters. Attached Figure Description

[0041] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0042] Figure 1 This is a flowchart illustrating a database construction and management method for multi-source data according to the present invention. Detailed Implementation

[0043] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] Please see Figure 1 As shown, the present invention provides a database construction and management method for multi-source data, comprising the following steps:

[0045] S1: Acquire and preprocess multi-source data: Acquire multi-source agricultural and rural data in real time, preprocess the multi-source data, and generate preprocessed multi-source data. The multi-source data includes satellite remote sensing data, meteorological data, and agricultural business data.

[0046] In this embodiment, it should be specifically explained that the execution method for acquiring and preprocessing multi-source data is as follows:

[0047] A multi-source data acquisition channel is established, connecting to satellite remote sensing data sources, meteorological data sources, and agricultural operational data sources respectively, to acquire multi-source agricultural and rural data in real time. The multi-source data is then preprocessed, specifically by using standardized processing tools to extract the required multi-source data from the original data sources, performing preprocessing operations on the required multi-source data, including data cleaning, format conversion, and missing value handling, merging the preprocessed multi-source data, and uniformly converting the merged multi-source data into a standardized format.

[0048] The specific content of fusing the preprocessed multi-source data is as follows:

[0049] Establish a unified spatiotemporal reference framework to unify data from different sources into the same spatiotemporal standard;

[0050] Perform data time consistency processing to resample data from different collection frequencies to the same time series;

[0051] Perform spatial consistency processing on the data, resampling spatial data at different resolutions to a uniform resolution;

[0052] Establish a metadata database for multi-source data to record information such as data source, collection time, and processing method;

[0053] Generate a preprocessed multi-source dataset and add data quality labels.

[0054] S2: Establish a spatiotemporal database for agriculture and rural areas: Based on preprocessed multi-source data, a spatiotemporal database for agriculture and rural areas is established using spatiotemporal processing algorithms;

[0055] In this embodiment, it should be specifically explained that the execution method for establishing the agricultural and rural spatiotemporal database is as follows:

[0056] The process involves acquiring preprocessed multi-source data, applying spatiotemporal processing algorithms, and establishing a spatiotemporal database for agriculture and rural areas. Specifically, this involves: applying spatiotemporal interpolation algorithms to the preprocessed multi-source data to generate a continuous spatiotemporal data field; employing spatiotemporal clustering algorithms to identify spatiotemporal patterns and regularities in the data; using spatiotemporal variograms to analyze the spatiotemporal autocorrelation and heterogeneity of the data; and finally establishing a spatiotemporal database for agriculture and rural areas.

[0057] It is important to clarify that the spatiotemporal processing algorithm fully considers the correlation and change characteristics of data in the spatiotemporal dimension, integrating and organizing data from different sources according to spatial location and temporal order, thereby achieving spatialized and standardized data management. This spatiotemporal processing approach can provide accurate and efficient spatiotemporal data support for various analyses and applications in the agricultural and rural fields. For example, it can clearly present the changes in crop planting area in a certain region over time and its correlation with meteorological conditions, or track the spatiotemporal distribution of traceability information for livestock products.

[0058] S3: Establish the first construction management analysis model: obtain the spatial coverage, cloud cover impact rate and geometric correction accuracy of satellite remote sensing data, and evaluate the first construction management status of the spatiotemporal database construction by establishing the first construction management analysis model;

[0059] In this embodiment, it should be specifically explained that the execution method for establishing the first construction management analysis model is as follows:

[0060] The first feature data of satellite remote sensing data is acquired in real time, and the first feature data includes the spatial coverage, cloud cover impact rate and geometric correction accuracy of the satellite remote sensing data.

[0061] The first step is to obtain the spatial coverage, and the specific method for obtaining it is as follows:

[0062] The agricultural and rural areas were designated as the target monitoring area, which was then divided into m grids. Based on land use type data, an agricultural priority weight Q was assigned to each grid. j This is marked as the agricultural priority weight Q of each grid. j j represents the number of each grid cell, j = 1, 2, 3, ..., m, where m is the total number of grid cells;

[0063] It should be noted that, in a specific embodiment, the target monitoring area is divided into m grids, which can be divided into grids of size 1km*1km.

[0064] It should be noted that, in a specific embodiment, the land use type data includes cultivated land, gardens, forest land, and construction land. The agricultural priority weight of cultivated land area can be set to 1.0, the agricultural priority weight of garden area can be set to 0.8, the agricultural priority weight of forest area can be set to 0.3, and the agricultural priority weight of construction land area can be set to 0.1.

[0065] The system acquires satellite remote sensing data from the agricultural and rural spatiotemporal database, extracts satellite remote sensing images from the satellite remote sensing data, identifies the effective data boundaries of the images within the grid using an edge detection algorithm, obtains the effective data area within each grid, and determines that the grid is an effective coverage grid when the proportion of the effective data area within a certain grid is greater than a preset area proportion threshold, and marks the effective area in the effective coverage grid as the effective coverage area.

[0066] It should be noted that, in a specific embodiment, the preset area ratio threshold is set to 70%. If the effective data area ratio within a certain grid is 80%, then the grid is determined to be an effective coverage grid.

[0067] Obtain the effective coverage area Ea of each grid j and total area Ta j And combined with the agricultural priority weight Q of each grid j Calculate the spatial coverage Sc of satellite remote sensing data;

[0068] The formula for calculating the spatial coverage of the satellite remote sensing data is as follows: Where Sc represents the spatial coverage of satellite remote sensing data, and Ea j Ta represents the effective coverage area of ​​the j-th grid. j Let Q represent the total area of ​​the j-th grid. j This represents the agricultural priority weight of the j-th grid.

[0069] The second step is to obtain the cloud coverage impact rate. The specific method for obtaining the cloud coverage impact rate is as follows: obtain satellite remote sensing images from the satellite remote sensing data, extract the cloud coverage area and total coverage area from each satellite remote sensing image, and calculate the cloud coverage impact rate Ir of the satellite remote sensing data.

[0070] The formula for calculating the cloud cover impact rate of the satellite remote sensing data is as follows: Where Ir represents the cloud cover impact rate of satellite remote sensing data, This represents the cloud coverage area of ​​the k-th satellite remote sensing image. This represents the total coverage area of ​​the k-th satellite remote sensing image, where k represents the number of each satellite remote sensing image, k = 1, 2, 3, ..., L, and L is the total number of satellite remote sensing images;

[0071] The third step is to read the spatial coverage Sc and cloud coverage impact rate Ir of the satellite remote sensing data, and at the same time obtain the geometric correction accuracy Ca of the satellite remote sensing data. The obtained data is normalized to eliminate the influence of dimensions, and the first construction management analysis model is established to calculate the first construction management analysis coefficient.

[0072] The first construction management status of the spatiotemporal database is evaluated based on the first construction management analysis coefficient. Specifically, the first construction management analysis coefficient is compared with a preset construction management analysis coefficient threshold. If the first construction management analysis coefficient is greater than the preset construction management analysis coefficient threshold, the first construction management status of the spatiotemporal database is judged to be normal. Otherwise, the first construction management status of the spatiotemporal database is judged to be abnormal, and a warning message is sent to the mobile device of the administrator.

[0073] The calculation formula for the first construction management analysis model is as follows:

[0074] Where FMC represents the first construction management analysis coefficient, This represents the minimum spatial coverage. This represents the maximum spatial coverage, and Cad represents the geometric correction accuracy deviation. This indicates the preset maximum allowable deviation in geometric correction accuracy. These represent the weighting coefficients for spatial coverage, cloud cover impact rate, and geometric correction accuracy, respectively. .

[0075] In this embodiment, it should be specifically noted that the larger the spatial coverage Sc, the smaller the cloud coverage influence rate Ir, and the smaller the geometric correction accuracy deviation Cad in the formula, the larger the first construction management analysis coefficient FMC, indicating that the first construction management status of the spatiotemporal database construction is normal.

[0076] It should be noted that, in one specific embodiment, It can be set to 0.4. It can be set to 0.3. The weight can be set to 0.3. Spatial coverage, as a fundamental prerequisite for data usability, directly determines whether the monitoring area can be effectively covered, and should be given the highest relative weight (0.4) to ensure the basic value of the data. Cloud coverage impact rate will interfere with data quality, but in long-term, full-domain ecological monitoring, it can be compensated to some extent by multi-temporal data, so it is given a medium weight (0.3) to balance its impact. Geometric correction accuracy deviation affects the accuracy of data spatial location, which is crucial for routine analysis. However, compared with the fundamental position of spatial coverage, its importance is slightly less, so it is also set to 0.3. The sum of the weights of the three is 1. The balanced allocation highlights the fundamental nature of spatial coverage and takes into account the synergistic impact of cloud interference and geometric accuracy on data quality, so as to achieve a comprehensive and balanced assessment of the database construction and management status, and adapt to the routine monitoring needs without special bias.

[0077] The method for obtaining the geometric correction accuracy deviation is as follows: read the geometric correction accuracy Ca of the satellite remote sensing data, and simultaneously obtain the standard geometric correction accuracy of the satellite remote sensing data from the management database. The geometric correction accuracy deviation (Cad) of satellite remote sensing data is calculated using the following formula: ;

[0078] In this embodiment, it should be specifically explained that the method for obtaining the geometric correction accuracy of satellite remote sensing data is as follows:

[0079] Extract the satellite remote sensing image to be corrected from the satellite remote sensing data. Then, uniformly select n ground control points on the satellite remote sensing image. Extract the true coordinates of the n ground control points from a known reference map. Where i represents the number of each ground control point, i=1, 2, 3, ..., n, and n is the total number of ground control points;

[0080] Using remote sensing image processing software (such as ENVI or ERDAS), locate the n ground control points on the satellite remote sensing image to be corrected, and read the corresponding pixel coordinates of the n ground control points on the satellite remote sensing image. ;

[0081] Based on the actual coordinates of ground control points and ground control point pixel coordinates The deviation between the true coordinates of each ground control point and the pixel coordinates of the ground control points is calculated, and the calculated deviation is imported into the geometric correction accuracy formula to calculate the geometric correction accuracy Ca of the satellite remote sensing data.

[0082] The specific steps for calculating the deviation between the true coordinates of each ground control point and the pixel coordinates of the ground control points are as follows:

[0083] Deviation of x-coordinate of ground control points: ;

[0084] Vertical coordinate deviation of various ground control points: ;

[0085] The formula for calculating the geometric correction accuracy of the satellite remote sensing data is as follows: , where Ca represents the geometric correction accuracy of the satellite remote sensing data.

[0086] It should be noted that, when selecting ground control points, priority should be given to ground features with obvious characteristics and known coordinates (such as road intersections, bridge endpoints, corners of landmark buildings, etc.).

[0087] S4: Establish a second construction management analysis model: Obtain the yield prediction deviation rate, product price volatility rate, and product inventory turnover rate of agricultural business data, and evaluate the second construction management status of the spatiotemporal database construction by establishing a second construction management analysis model;

[0088] In this embodiment, it should be specifically explained that the execution method for establishing the second construction management analysis model is as follows:

[0089] The second feature data of real-time acquisition of satellite remote sensing data includes output prediction deviation rate, product price volatility rate and product inventory turnover rate.

[0090] The first step is to obtain the yield forecast deviation rate. Specifically, this is done by reading agricultural business data from the agricultural and rural spatiotemporal database, obtaining the actual yield (Op) and predicted yield (Fp) of agricultural products from the agricultural business data, and combining the actual yield and the predicted yield to obtain the yield forecast deviation rate (Pdr). The calculation formula is as follows: ;

[0091] The second step is to obtain product price volatility. Specifically, this is done by using a weekly sampling period and obtaining the highest price of agricultural products within the current week from the agricultural business data. and lowest price The formula for calculating the price range R of agricultural products is as follows: Obtain the average price of agricultural products within this week from agricultural business data. And at the same time, obtain the average price of agricultural products for the previous week. Analyze the rate of change in agricultural product prices The calculation formula is: Furthermore, the product price volatility Ppv is analyzed, and the calculation formula is as follows: ;

[0092] The third step involves reading the agricultural business data, including the yield prediction deviation rate Pdr, product price volatility rate Ppv, and product inventory turnover rate Itr, and then normalizing them to eliminate the influence of dimensions. A second construction management analysis model is then established, and the second construction management analysis coefficient is calculated. Based on the second construction management analysis coefficient, the second construction management status of the spatiotemporal database is evaluated, and the second construction management evaluation result is output.

[0093] The second construction management status of the spatiotemporal database is evaluated based on the second construction management analysis coefficient. Specifically, the second construction management analysis coefficient is compared with a preset construction management analysis coefficient threshold. If the second construction management analysis coefficient is greater than the preset construction management analysis coefficient threshold, the second construction management status of the spatiotemporal database is judged to be normal. Otherwise, the second construction management status of the spatiotemporal database is judged to be abnormal, and an early warning message is sent to the mobile device of the administrator.

[0094] The calculation formula for the second construction management analysis model is as follows:

[0095] Where SMC represents the second construction management analysis coefficient, These represent the preset maximum allowable output forecast deviation rate and the maximum allowable product price volatility, respectively. This indicates the preset standard product inventory turnover rate;

[0096] In this embodiment, it should be specifically noted that the smaller the production prediction deviation rate Pdr, the smaller the product price volatility rate Ppv, and the larger the product inventory turnover rate Itr in the formula, the larger the second construction management analysis coefficient SMC, indicating that the second construction management status of the spatiotemporal database construction is normal.

[0097] S5: Evaluate the quality of construction management: Based on the first construction management analysis model and the second construction management analysis model, evaluate the quality of construction management of the spatiotemporal database, output the construction management quality evaluation results and issue early warnings;

[0098] In this embodiment, it should be specifically explained that the method for evaluating the construction management quality is as follows:

[0099] Based on the first construction management analysis model, the first construction management analysis coefficient is obtained. Based on the second construction management analysis model, the second construction management analysis coefficient is obtained. The first construction management analysis coefficient and the second construction management analysis coefficient are combined to obtain the construction management evaluation index. The construction management evaluation index is used to evaluate the construction management quality of the spatiotemporal database, output the construction management quality evaluation result, and issue early warning reminders.

[0100] The formula for calculating the construction management evaluation index is as follows: Where MEI represents the construction management evaluation index of the spatiotemporal database, FMC represents the first construction management analysis coefficient, and SMC represents the second construction management analysis coefficient. Let represent the weighting factors of the first and second construction management analysis coefficients, respectively. , where e is the natural constant.

[0101] It should be specifically explained that the evaluation of the construction management quality of the spatiotemporal database based on the construction management evaluation index is as follows: the construction management evaluation index is compared with a preset construction management evaluation index threshold. If the construction management evaluation index is greater than the preset construction management evaluation index threshold, the construction management quality of the spatiotemporal database is judged to be qualified; otherwise, the construction management quality of the spatiotemporal database is judged to be unqualified. The unqualified construction management quality is marked as the construction management quality evaluation result, and an early warning message is issued.

[0102] S6: Establish a deep analysis model for management: By establishing a deep analysis model for management, establish the influence relationship function between meteorological data and crop growth data, generate a crop growth environment management plan, and send the crop growth environment management plan to agricultural managers.

[0103] In this embodiment, it should be specifically explained that the execution steps for establishing and constructing the deep analysis model for management are as follows:

[0104] S61: Obtain the optimal light intensity for the crop growth stage from the management database corresponding to the crop. and light adaptation range half width This refers to the acceptable range of light exposure for crops; and it involves real-time monitoring of actual light intensity. Based on the deviation between actual light intensity and optimal light intensity, the influence of light intensity on crop growth is analyzed, and the light influence coefficient Kl is obtained.

[0105] The formula for calculating the illumination influence coefficient Kl is: ,in, Represents an exponential function;

[0106] S62: Obtain the optimal rainfall for the crop growth stage from the management database corresponding to the crop. and critical rainfall range ,in, Indicates the minimum effective rainfall. This indicates the maximum tolerable rainfall, and the actual rainfall is collected in real time. Based on the deviation between the actual rainfall and the optimal rainfall, the impact of rainfall on crop growth is analyzed, and the rainfall impact coefficient Kr is obtained.

[0107] The formula for calculating the rainfall impact coefficient Kr is as follows: The rainfall impact coefficient ranges from 0 to 1, with the value closer to 1 indicating more suitable rainfall conditions.

[0108] S63: Obtain the light impact coefficient Kl and rainfall impact coefficient Kr from meteorological data, establish the influence relationship function between them and crop growth data, generate management plans corresponding to the crop growth environment based on the influence relationship function, and send the management plans corresponding to the crop growth environment to agricultural managers.

[0109] The influence relationship function The formula is: ,in, This indicates the daily increase in actual crop biomass. denoted as , representing the maximum daily increase in crop biomass under ideal weather conditions, and c represents the environmental adaptation constant (c>0), reflecting the crop's tolerance to non-ideal conditions.

[0110] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0111] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A database construction and management method for multi-source data, characterized in that, Includes the following steps: S1: Acquire and preprocess multi-source data: Acquire multi-source agricultural and rural data in real time, preprocess the multi-source data, and generate preprocessed multi-source data. The multi-source data includes satellite remote sensing data, meteorological data, and agricultural business data. S2: Establish a spatiotemporal database for agriculture and rural areas: Based on preprocessed multi-source data, a spatiotemporal database for agriculture and rural areas is established using spatiotemporal processing algorithms; S3: Establish the first construction management analysis model: obtain the spatial coverage, cloud cover impact rate and geometric correction accuracy of satellite remote sensing data, and evaluate the first construction management status of the spatiotemporal database construction by establishing the first construction management analysis model; S4: Establish a second construction management analysis model: Obtain the yield prediction deviation rate, product price volatility rate, and product inventory turnover rate of agricultural business data, and evaluate the second construction management status of the spatiotemporal database construction by establishing a second construction management analysis model; S5: Evaluate the quality of construction management: Based on the first construction management analysis model and the second construction management analysis model, evaluate the quality of construction management of the spatiotemporal database, output the construction management quality evaluation results and issue early warnings; S6: Establish a deep analysis model for management: By establishing a deep analysis model for management, establish the influence relationship function between meteorological data and crop growth data, generate a crop growth environment management plan, and send the crop growth environment management plan to agricultural managers; The specific execution method for establishing the first construction management analysis model is as follows: The first feature data of satellite remote sensing data is acquired in real time, and the first feature data includes the spatial coverage, cloud cover impact rate and geometric correction accuracy of the satellite remote sensing data. The first step is to obtain the spatial coverage, and the specific method for obtaining it is as follows: The agricultural and rural area is determined as the target monitoring area, and the target monitoring area is divided into m grids, and the agricultural priority weight Q of each grid is set in combination with the land use type data j , which is marked as the agricultural priority weight Q of each grid j , j represents the number of each grid, j=1, 2, 3,..., m, and m is the total number of grids The system acquires satellite remote sensing data from the agricultural and rural spatiotemporal database, extracts satellite remote sensing images from the satellite remote sensing data, identifies the effective data boundaries of the images within the grid using an edge detection algorithm, obtains the effective data area within each grid, and determines that the grid is an effective coverage grid when the proportion of the effective data area within a certain grid is greater than a preset area proportion threshold, and marks the effective area in the effective coverage grid as the effective coverage area. Obtain the effective coverage area Ea of each grid j and total area Ta j And combined with the agricultural priority weight Q of each grid j Calculate the spatial coverage Sc of satellite remote sensing data; The second step is to obtain the cloud coverage impact rate. The specific method for obtaining the cloud coverage impact rate is as follows: obtain satellite remote sensing images from the satellite remote sensing data, extract the cloud coverage area and total coverage area from each satellite remote sensing image, and calculate the cloud coverage impact rate Ir of the satellite remote sensing data. The third step is to read the spatial coverage Sc and cloud coverage impact rate Ir of the satellite remote sensing data, and at the same time obtain the geometric correction accuracy Ca of the satellite remote sensing data. The obtained data is normalized, the first construction management analysis model is established, and the first construction management analysis coefficient is calculated. The first construction management status of the spatiotemporal database is evaluated based on the first construction management analysis coefficient. Specifically, the first construction management analysis coefficient is compared with a preset construction management analysis coefficient threshold. If the first construction management analysis coefficient is greater than the preset construction management analysis coefficient threshold, the first construction management status of the spatiotemporal database is judged to be normal. Otherwise, the first construction management status of the spatiotemporal database is judged to be abnormal, and a warning message is sent to the mobile device of the administrator. The specific execution method for establishing the second construction management analysis model is as follows: The second feature data of real-time acquisition of satellite remote sensing data includes output prediction deviation rate, product price volatility rate and product inventory turnover rate. The first step is to obtain the yield prediction deviation rate. The specific method is as follows: read the agricultural business data in the agricultural and rural spatiotemporal database, obtain the actual output of agricultural products Op and the predicted output of agricultural products Fp in the agricultural business data, and combine the actual output of products and the predicted output of agricultural products to obtain the yield prediction deviation rate Pdr. The second step is to obtain product price volatility. Specifically, this is done by using a weekly sampling period and obtaining the highest price of agricultural products within the current week from the agricultural business data. and lowest price Analyze the price range R of agricultural products; obtain the average price of agricultural products within this week from agricultural business data. And at the same time, obtain the average price of agricultural products for the previous week. Analyze the rate of change in agricultural product prices Furthermore, the product price volatility Ppv is analyzed. The third step is to read the yield prediction deviation rate Pdr, product price volatility rate Ppv, and product inventory turnover rate Itr from agricultural business data, and normalize them respectively to establish a second construction management analysis model. The second construction management analysis coefficient is calculated, and the second construction management status of the spatiotemporal database is evaluated based on the second construction management analysis coefficient, and the second construction management evaluation result is output. The specific implementation method for evaluating the construction management quality is as follows: Based on the first construction management analysis model, the first construction management analysis coefficient is obtained. Based on the second construction management analysis model, the second construction management analysis coefficient is obtained. The first construction management analysis coefficient and the second construction management analysis coefficient are combined to obtain the construction management evaluation index. The construction management evaluation index is used to evaluate the construction management quality of the spatiotemporal database, output the construction management quality evaluation result, and issue early warning reminders.

2. The database construction and management method for multi-source data according to claim 1, characterized in that: The specific execution method for acquiring and preprocessing multi-source data is as follows: A multi-source data acquisition channel is established, connecting to satellite remote sensing data sources, meteorological data sources, and agricultural operational data sources respectively, to acquire multi-source agricultural and rural data in real time. The multi-source data is then preprocessed, specifically by using standardized processing tools to extract the required multi-source data from the original data sources, performing preprocessing operations on the required multi-source data, including data cleaning, format conversion, and missing value handling, merging the preprocessed multi-source data, and uniformly converting the merged multi-source data into a standardized format.

3. The database construction and management method for multi-source data according to claim 1, characterized in that: The specific method for obtaining the geometric correction accuracy of satellite remote sensing data is as follows: Extract the satellite remote sensing image to be corrected from the satellite remote sensing data. Then, uniformly select n ground control points on the satellite remote sensing image. Extract the true coordinates of the n ground control points from a known reference map. Where i represents the number of each ground control point, i=1, 2, 3, ..., n, and n is the total number of ground control points; Using remote sensing image processing software, the n ground control points are located on the satellite remote sensing image to be corrected, and the pixel coordinates of the corresponding ground control points on the satellite remote sensing image are read. ; Based on the actual coordinates of ground control points and ground control point pixel coordinates The deviation between the true coordinates of each ground control point and the pixel coordinates of the ground control points is calculated, and the calculated deviation is imported into the geometric correction accuracy formula to calculate the geometric correction accuracy Ca of the satellite remote sensing data.

4. The database construction and management method for multi-source data according to claim 1, characterized in that: The specific steps for establishing and building the deep analysis model for management are as follows: S61: Obtain the optimal light intensity for the crop growth stage from the management database corresponding to the crop. and light adaptation range half width This refers to the acceptable range of light exposure for crops; and it involves real-time monitoring of actual light intensity. Based on the deviation between actual light intensity and optimal light intensity, the influence of light intensity on crop growth is analyzed, and the light influence coefficient Kl is obtained. S62: Obtain the optimal rainfall for the crop growth stage from the management database corresponding to the crop. and critical rainfall range ,in, Indicates the minimum effective rainfall. This indicates the maximum tolerable rainfall, and the actual rainfall is collected in real time. Based on the deviation between the actual rainfall and the optimal rainfall, the impact of rainfall on crop growth is analyzed, and the rainfall impact coefficient Kr is obtained. S63: Obtain the light impact coefficient Kl and rainfall impact coefficient Kr from meteorological data, establish the influence relationship function between them and crop growth data, generate management plans corresponding to the crop growth environment based on the influence relationship function, and send the management plans corresponding to the crop growth environment to agricultural managers.

Images