A rural digital governance control method and system based on cloud platform sharing

Abstract

The present invention discloses a method and system for rural digital governance control based on cloud platform sharing, which relates to the technical field of rural digital governance, including: determining the control area information and geographic location information to build a wireless sensor network to collect real-time data, storing and updating the pre-processed real-time multi-dimensional data in a dynamic data pool, and storing historical data in a static data pool; dividing the control area based on multiple types of data to obtain control sub-area information, dividing the historical data accordingly and integrating the predicted sub-data, building an impact index prediction stacking model, inputting real-time multi-dimensional data to obtain a dynamic impact index, and determining the decision execution parameters accordingly to formulate a governance plan. The method and system have significant advantages, realizing multi-source data fusion and collaborative analysis, overcoming the problem of traditional data dispersion; building a prediction model to provide dynamic decision support, improving the previous situation of lagging and inaccurate decision-making; optimizing the spatial layout of data collection, and solving the problem of blind layout.

Description

Technical Field

[0001] The present invention relates to the technical field of rural digital governance, and specifically to a rural digital governance control method and system based on cloud platform sharing. Background Art

[0002] With the rapid development of information technology, rural digital governance has become an important way to promote rural revitalization. The rural digital governance control method and system based on cloud platform sharing has improved the intelligence, precision and efficiency of rural governance by integrating data resources and management platforms. This system can realize digital supervision in rural infrastructure, social management, agricultural production and other fields, promote information circulation and resource sharing, and optimize government decision-making and services. Through the advantages of the cloud platform, it breaks the geographical restrictions, provides real-time and comprehensive governance support for villages, promotes rural economic development, improves people's livelihood, and enhances governance capabilities, which has important social and economic significance.

[0003] The existing rural digital governance control methods and systems based on cloud platform sharing have data integration and collaborative analysis. Although there is data processing, the various types of data are independent of each other. For example, agricultural and environmental data are not effectively combined, and the relationship between rural system elements cannot be fully analyzed, resulting in insufficient basis for comprehensive decision-making. In terms of dynamic decision-making support, it relies on experience or simple statistics and lacks accurate prediction models. It is difficult to respond quickly and accurately to complex changes in rural areas. Therefore, it is necessary to provide a rural digital governance control method and system based on cloud platform sharing to solve the above-mentioned problems. Summary of the invention

[0004] In order to solve the above technical problems, a rural digital governance and control method and system based on cloud platform sharing is provided. This technical solution solves the problem that in the existing technology proposed in the above background technology, in terms of data integration and collaborative analysis, although there is data processing, various types of data are independent of each other. For example, agricultural and environmental data are not effectively combined, and the relationship between rural system elements cannot be fully analyzed, resulting in insufficient basis for comprehensive decision-making. In terms of dynamic decision-making support, it relies on experience or simple statistics and lacks accurate prediction models, making it difficult to respond quickly and accurately to complex changes in rural areas.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A rural digital governance and control method based on cloud platform sharing, including:

[0007] Determine the control area information, obtain the rural geographical location information, and build a wireless sensor network based on the rural geographical location information;

[0008] Using a wireless sensor network to collect real-time data, and preprocessing the real-time data to obtain real-time multi-dimensional data, wherein the real-time multi-dimensional data includes real-time agricultural data, real-time environmental data, and real-time infrastructure data;

[0009] Build a dynamic data pool and a static data pool, store real-time multidimensional data in the dynamic data pool, and update the dynamic data pool in real time. The static data pool contains historical environmental data, historical agricultural data, and historical infrastructure data, including:

[0010] Classifying the real-time multi-dimensional data into real-time agricultural sub-information, real-time environmental sub-information and real-time infrastructure sub-information;

[0011] Constructing an agricultural production status impact prediction coordinate system based on initial farmland distribution information, initial river distribution information, and initial residential area distribution information, wherein the agricultural production status impact prediction coordinate system is used to predict an agricultural production status impact index;

[0012] Determine the minimum impact index matrix based on the agricultural production status impact prediction coordinate system, wireless sensor network and real-time environmental sub-information;

[0013] Obtaining the real-time agricultural sub-information coordinates or real-time infrastructure sub-information coordinates corresponding to the real-time agricultural sub-information or real-time infrastructure sub-information in the agricultural production status impact prediction coordinate system;

[0014] In the agricultural production status impact prediction coordinate system, the real-time agricultural sub-information coordinates, the real-time infrastructure sub-information coordinates and the corresponding wireless sensor coordinates are respectively connected to obtain the real-time agricultural production monitoring impact line segment and the real-time infrastructure monitoring impact line segment, and determine the corresponding agricultural production monitoring impact index and the real-time infrastructure monitoring impact index;

[0015] Obtaining a dynamic matrix impact coefficient corresponding to an agricultural production monitoring impact index or a real-time infrastructure monitoring impact index;

[0016] The product of the dynamic matrix impact coefficient and the minimum impact index matrix is ​​used as the minimum monitoring impact dynamic index corresponding to the agricultural production monitoring impact index or the real-time infrastructure monitoring impact index;

[0017] The real-time agricultural sub-information or real-time infrastructure sub-information whose agricultural production monitoring impact index or real-time infrastructure monitoring impact index is less than or equal to the minimum monitoring impact dynamic index is stored in the same position in the dynamic data pool;

[0018] The real-time environment sub-information is stored in the same location of the dynamic data pool;

[0019] Divide the control sub-region information; divide the historical environmental data, historical agricultural data and historical infrastructure data in turn according to the control sub-region information, and integrate the divided data to obtain the prediction sub-data;

[0020] Based on the prediction sub-data, an impact index prediction stacking model is constructed, and then the real-time multi-dimensional data of the dynamic data pool is processed, and the processed real-time multi-dimensional data is sequentially input into the impact index prediction stacking model to obtain the dynamic impact index output by the impact index prediction stacking model;

[0021] Determine the decision execution parameters corresponding to the control sub-area based on the impact index prediction stacking model, control sub-area information and dynamic impact index;

[0022] By deciding execution parameters, a governance plan is formulated to complete the control of the control sub-areas.

[0023] In an optional embodiment, determining the control area information, acquiring the rural geographical location information, and constructing a wireless sensor network through the rural geographical location information specifically includes:

[0024] Determine the control target, and define the corresponding control area based on the control target to obtain the control area scope information;

[0025] According to the control area information and rural geographical location information, obtain initial air quality information, initial water quality information and initial rural ecological area information;

[0026] Determine the initial farmland distribution information, initial river distribution information and initial residential area distribution information through the rural geographical location information and initial rural ecological area information;

[0027] Based on the initial farmland distribution information, the initial agricultural production status information is obtained, and the initial agricultural production quality index is determined;

[0028] Constructing an agricultural production status impact prediction coordinate system based on initial farmland distribution information, initial river distribution information, and initial residential area distribution information, wherein the agricultural production status impact prediction coordinate system is used to predict an agricultural production status impact index;

[0029] The absolute value of the difference between the initial agricultural production quality index and the agricultural production status impact index is used as the dynamic index of agricultural production quality;

[0030] Based on the dynamic index of agricultural production quality, the initial farmland distribution information, initial river distribution information and initial residential area distribution information are evaluated to obtain the sensor influence coefficient of each coordinate point in the prediction coordinate system of agricultural production status;

[0031] Based on the sensor influence coefficient of each coordinate point in the prediction coordinate system affected by agricultural production conditions, a wireless sensor network is constructed.

[0032] In an optional embodiment, the construction of a dynamic data pool and a static data pool, storing real-time multidimensional data in the dynamic data pool, and updating the dynamic data pool in real time specifically includes:

[0033] Build a dynamic data pool based on NoSQL database;

[0034] Extracting timestamp information from the real-time multidimensional data, and dividing the real-time multidimensional data based on the timestamp information to obtain real-time multidimensional sub-data;

[0035] Based on real-time multi-dimensional sub-data, obtain real-time monitoring sub-information;

[0036] Classifying the real-time monitoring sub-information according to the real-time agricultural data, the real-time environmental data and the real-time infrastructure data to obtain the real-time agricultural sub-information, the real-time environmental sub-information and the real-time infrastructure sub-information;

[0037] Obtaining the position of the real-time agricultural sub-information or real-time infrastructure sub-information collected by the same wireless sensor in the agricultural production status impact prediction coordinate system, and obtaining the real-time agricultural sub-information coordinates or the real-time infrastructure sub-information coordinates;

[0038] Determine the real-time agricultural sub-information coordinates and the corresponding wireless sensor coordinates, and connect the real-time agricultural sub-information coordinates and the corresponding wireless sensor coordinates in the agricultural production status impact prediction coordinate system to obtain the real-time agricultural production monitoring impact line segment;

[0039] Determine the real-time infrastructure sub-information coordinates and the corresponding wireless sensor coordinates, and connect the real-time infrastructure sub-information coordinates and the corresponding wireless sensor coordinates in the agricultural production status impact prediction coordinate system to obtain the real-time infrastructure monitoring impact line segment;

[0040] The real-time agricultural production monitoring impact line segment and the real-time infrastructure monitoring impact line segment are used as the agricultural production monitoring impact index and the real-time infrastructure monitoring impact index respectively;

[0041] Based on the wireless sensor network, wireless sensor quality information corresponding to the agricultural production monitoring impact index or the real-time infrastructure monitoring impact index is obtained;

[0042] Obtaining a dynamic matrix impact coefficient corresponding to an agricultural production monitoring impact index or a real-time infrastructure monitoring impact index;

[0043] The product of the dynamic matrix impact coefficient and the minimum impact index matrix is ​​used as the minimum monitoring impact dynamic index corresponding to the agricultural production monitoring impact index or the real-time infrastructure monitoring impact index;

[0044] The real-time agricultural sub-information or real-time infrastructure sub-information whose agricultural production monitoring impact index or real-time infrastructure monitoring impact index is less than or equal to the minimum monitoring impact dynamic index is stored in the same position in the dynamic data pool;

[0045] The real-time environment sub-information is stored in the same position of the dynamic data pool, and the real-time environment sub-information is sorted based on the timestamp information;

[0046] Based on the wireless sensor network, a preset impact range is set, and the coordinates of the real-time agricultural sub-information, the real-time infrastructure sub-information and the real-time environmental sub-information in the agricultural production status impact prediction coordinate system are determined;

[0047] Linking the real-time agricultural sub-information, real-time infrastructure sub-information, and real-time environmental sub-information whose coordinates are all within the preset influence range, and obtaining link information;

[0048] Encrypting the link information to obtain encrypted information, and storing the encrypted information and the link information in a static data pool;

[0049] A data extraction time threshold for the static data pool is set, and based on timestamp information, real-time agricultural data, real-time environmental data, and real-time infrastructure data that meet the data extraction time threshold for the static data pool are stored in the static data pool.

[0050] In an optional embodiment, based on the rural geographical location information, real-time agricultural data, real-time environmental data and real-time infrastructure data, the control area is divided into regions to obtain control sub-region information, specifically including:

[0051] Based on the geographical location information of the village, determine the longitude and latitude coordinate information of the village, topographic information and village layout information;

[0052] Through real-time agricultural data, obtain real-time crop type information, real-time planting area information, real-time growth stage information, real-time soil fertility information and real-time pest and disease information;

[0053] Determine real-time air quality information, real-time water quality information, real-time meteorological condition information and real-time ecological status information based on real-time environmental data;

[0054] Based on real-time infrastructure data, obtain real-time traffic road condition information, real-time water conservancy facility operation information, real-time energy supply status information and real-time communication facility information;

[0055] Obtaining a first division coefficient through real-time crop type information, real-time planting area information, real-time growth stage information, real-time soil fertility information, and real-time pest and disease information;

[0056] Determine the real-time air quality information, real-time water quality information, real-time meteorological condition information and real-time ecological condition information through the real-time environmental data to obtain the second division coefficient;

[0057] Obtaining a third division coefficient through real-time traffic road condition information, real-time water conservancy facility operation information, real-time energy supply status information and real-time communication facility information;

[0058] Based on the first division coefficient, the second division coefficient and the third division coefficient, obtaining a control area division index;

[0059] According to the control area division index, the control area is divided into regions to obtain the control sub-region information.

[0060] In an optional embodiment, the historical environmental data, historical agricultural data and historical infrastructure data are sequentially divided according to the control sub-area information, and the divided data are integrated to obtain prediction sub-data, specifically including:

[0061] Based on the rural geographical location information, determine the geographical location information of the control sub-region information;

[0062] According to the geographical location information of the control sub-region information, historical environmental data, historical agricultural data and historical infrastructure data are mapped to each control sub-region information;

[0063] The historical environmental data, historical agricultural data and historical infrastructure data corresponding to each control sub-area are divided to obtain a subset of historical environmental data, a subset of historical agricultural data and a subset of historical infrastructure data corresponding to each control sub-area;

[0064] A data integration framework is constructed using a historical environmental data subset, a historical agricultural data subset, and a historical infrastructure data subset, wherein the data integration framework includes historical time dimension information, historical data type information, and control sub-area number information;

[0065] Based on the data integration framework, historical data type information is associated and integrated according to historical time dimension information and control sub-area number information to obtain historical integrated data, and the association information between historical time dimension information, historical data type information and control sub-area number information is determined;

[0066] The historical integrated data is preprocessed and the prediction feature information is extracted to obtain the prediction sub-data.

[0067] In an optional embodiment, the influence index prediction stacking model is constructed based on the prediction sub-data, and then the real-time multi-dimensional data of the dynamic data pool is processed, and the processed real-time multi-dimensional data is sequentially input into the influence index prediction stacking model to obtain the dynamic influence index output by the influence index prediction stacking model, specifically including:

[0068] Based on the correlation information between the historical time dimension information, the historical data type information and the control sub-area number information, obtain the first historical impact index of the historical environmental data on the historical agricultural data, the second historical impact index of the historical environmental data on the historical infrastructure data, the first historical joint impact index of the historical agricultural data on the historical environmental data and the historical infrastructure data, and the second historical joint impact index of the historical infrastructure data on the historical environmental data and the agricultural data;

[0069] Based on the prediction sub-data, obtain the proportion of historical environmental data, historical agricultural data and historical infrastructure data in the corresponding control sub-area;

[0070] Obtain the first impact index prediction model, the second impact index prediction model and the third impact index prediction model through the proportion of historical environmental data, the proportion of historical agricultural data, the proportion of historical infrastructure data, the first historical impact index, the second historical impact index, the first historical joint impact index and the second historical joint impact index;

[0071] The first impact index prediction model, the second impact index prediction model and the third impact index prediction model are connected in series to obtain an impact index prediction stacking model;

[0072] Obtain the real-time multi-dimensional data of the dynamic data pool in turn, and based on the prediction sub-data, obtain the proportion of real-time environmental data, real-time agricultural data, and real-time infrastructure data corresponding to the control sub-area;

[0073] The proportion of real-time environmental data, the proportion of real-time agricultural data and the proportion of real-time infrastructure data are input into the impact index prediction stacking model to obtain the dynamic impact index output by the impact index prediction stacking model.

[0074] In an optional embodiment, determining the decision execution parameter corresponding to the control sub-area according to the impact index prediction stacking model, the control sub-area information and the dynamic impact index specifically includes:

[0075] Based on the control sub-area information, determine the control sub-area number information;

[0076] According to the control sub-area number information, collect the real-time environmental data proportion, real-time agricultural data proportion and real-time infrastructure data proportion corresponding to the control sub-area number, input them into the impact index prediction stacking model, and obtain the corresponding real-time dynamic impact index;

[0077] Obtain the average value of the dynamic impact index and the instant dynamic impact index to obtain the standard impact index;

[0078] According to the standard impact index, the decision execution parameters corresponding to the control sub-area are determined, and the decision execution parameters include agricultural production decision parameters, environmental management decision parameters, infrastructure operation and maintenance decision parameters and comprehensive management decision parameters.

[0079] Furthermore, a rural digital governance control system based on cloud platform sharing is proposed, which is used to implement any of the above control methods, including:

[0080] Data collection and transmission module, which is used to build a wireless sensor network and deploy sensors according to the geographical characteristics of the village, collect various real-time data, process and transmit data at the same time, and can connect to external data sources to obtain supplementary data and ensure data access security;

[0081] Data processing and storage module, which is used to pre-process the collected real-time data, clean abnormal values ​​and standardize them, filter and store real-time data according to rules, manage static data pools, store historical data and integrate some real-time data according to thresholds, integrate data, and associate historical data types, time and control area information;

[0082] A regional division and model building module, which is used to divide the control area based on rural geographical location information, real-time agricultural data, real-time environmental data and real-time infrastructure data, obtain control sub-area information, calculate multiple historical impact indexes based on historical data association information, and build an impact index prediction stacking model for predicting dynamic impact indexes;

[0083] A decision support and control execution module, which is used to determine the standard impact index based on the real-time data of the control sub-area and the impact index prediction stacking model, and then determine the decision execution parameters;

[0084] The user interaction and visualization module is used to visualize various data and analysis results and provide user interaction functions.

[0085] In an optional embodiment, the data processing and storage module includes:

[0086] A data preprocessing unit, the data preprocessing unit is used to clean the real-time data collected by the sensor network unit;

[0087] A dynamic data pool management unit, the dynamic data pool management unit is used to build and manage a dynamic data pool based on a NoSQL database, divide the real-time multidimensional data according to the timestamp information, obtain the real-time multidimensional sub-data, and further classify it into real-time agricultural sub-information, real-time environmental sub-information and real-time infrastructure sub-information, and according to the agricultural production monitoring impact index, the real-time infrastructure monitoring impact index and the minimum monitoring impact dynamic index, screen and store the real-time data that meets the requirements to the corresponding position in the dynamic data pool, and sort the real-time environmental sub-information based on the timestamp;

[0088] A static data pool management unit, which is responsible for storing historical environmental data, historical agricultural data and historical infrastructure data, storing encrypted link information in the static data pool, and storing real-time data that meets the conditions in the static data pool regularly according to a set static data pool data extraction time threshold;

[0089] A data integration unit, wherein the data integration unit is used to associate and integrate historical data type information according to historical time dimension information and control sub-area number information based on a data integration framework, and to determine association information between the historical time dimension information, historical data type information and control sub-area number information.

[0090] In an optional embodiment, the region division and model building module includes:

[0091] A regional division unit, the regional division unit is used to determine the rural latitude and longitude coordinate information, topographic information and village layout information based on the rural geographical location information, and calculate the first division coefficient, the second division coefficient and the third division coefficient in combination with the real-time agricultural data, the real-time environmental data and the real-time infrastructure data, so as to obtain the control area division index, accurately divide the control area, obtain the control sub-area information, and assign a unique number to each control sub-area;

[0092] An impact index prediction model construction unit is used to calculate the first historical impact index of historical environmental data on historical agricultural data, the second historical impact index of historical environmental data on historical infrastructure data, the first historical joint impact index of historical agricultural data on historical environmental data and historical infrastructure data, and the second historical joint impact index of historical infrastructure data on historical environmental data and agricultural data based on the correlation information between historical time dimension information, historical data type information and control sub-area number information; according to the predicted sub-data, the proportion of historical environmental data, the proportion of historical agricultural data and the proportion of historical infrastructure data in the corresponding control sub-area are obtained, and a first impact index prediction model, a second impact index prediction model and a third impact index prediction model are constructed; and the first impact index prediction model, the second impact index prediction model and the third impact index prediction model are concatenated into an impact index prediction stacking model.

[0093] Compared with the prior art, the present invention has the following beneficial effects:

[0094] This solution proposes a rural digital governance control method and system based on cloud platform sharing. By building a multi-source data integration framework that includes rural geographic location information, real-time agricultural data, real-time environmental data, and real-time infrastructure data, and linking historical data for deep fusion analysis, it achieves collaborative interaction between different types of data, breaks the limitations of the independence of various types of data, comprehensively analyzes the relationship between various elements in the rural system, improves the adequacy of comprehensive decision-making basis, and provides more scientific and comprehensive decision-making support for rural governance.

[0095] This solution proposes a rural digital governance control method and system based on cloud platform sharing. With the help of the impact index prediction stacking model built based on the prediction sub-data, the dynamic impact index is dynamically output according to the changes in real-time multi-dimensional data, and then the corresponding decision execution parameters are determined, realizing the rapid and accurate connection from data to decision-making, changing the previous situation of relying on experience or simple statistics and lacking accurate prediction models, improving the ability to respond quickly and accurately to complex changes in rural areas, and ensuring that rural governance decisions can be in line with actual dynamic development;

[0096] This solution proposes a rural digital governance control method and system based on cloud platform sharing. It uses the agricultural production status to reasonably determine the sensor influence coefficient to build a wireless sensor network, optimizes the sensor layout according to the actual situation of the village, avoids blind deployment, improves the effectiveness and pertinence of the collected data, and makes the acquired data more reflective of the key conditions of the village, facilitating subsequent precise governance analysis.

[0097] This solution proposes a rural digital governance control method and system based on cloud platform sharing. By building dynamic data pools and static data pools to collaboratively manage data and encrypting some key information, it achieves a balance between efficient real-time data utilization and updating and complete traceability of historical data. At the same time, it ensures data security, improves the overall efficiency and security of data management, and meets the complex data management needs in rural digital governance. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] Figure 1 This is a flow chart of a rural digital governance and control method based on cloud platform sharing proposed by the present invention;

[0099] Figure 2 A flowchart of building a wireless sensor network in the present invention;

[0100] Figure 3 This is a flow chart of the division of control sub-areas in the present invention;

[0101] Figure 4 This is a system framework diagram of a rural digital governance and control system based on cloud platform sharing proposed in the present invention. DETAILED DESCRIPTION

[0102] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0103] Reference Figure 1 - Figure 4 As shown, a rural digital governance and control method based on cloud platform sharing includes:

[0104] Determine the control area information, obtain the rural geographical location information, and build a wireless sensor network based on the rural geographical location information;

[0105] Use wireless sensor networks to collect real-time data and perform data preprocessing on the real-time data to obtain real-time multi-dimensional data, which includes real-time agricultural data, real-time environmental data and real-time infrastructure data;

[0106] Build dynamic data pools and static data pools, store real-time multidimensional data in the dynamic data pool, and update the dynamic data pool in real time. The static data pool contains historical environmental data, historical agricultural data, and historical infrastructure data, including:

[0107] Classifying the real-time multi-dimensional data into real-time agricultural sub-information, real-time environmental sub-information and real-time infrastructure sub-information;

[0108] Constructing an agricultural production status impact prediction coordinate system based on initial farmland distribution information, initial river distribution information, and initial residential area distribution information, wherein the agricultural production status impact prediction coordinate system is used to predict an agricultural production status impact index;

[0109] Determine the minimum impact index matrix based on the agricultural production status impact prediction coordinate system, wireless sensor network and real-time environmental sub-information;

[0110] Obtaining the real-time agricultural sub-information coordinates or real-time infrastructure sub-information coordinates corresponding to the real-time agricultural sub-information or real-time infrastructure sub-information in the agricultural production status impact prediction coordinate system;

[0111] In the agricultural production status impact prediction coordinate system, the real-time agricultural sub-information coordinates, the real-time infrastructure sub-information coordinates and the corresponding wireless sensor coordinates are respectively connected to obtain the real-time agricultural production monitoring impact line segment and the real-time infrastructure monitoring impact line segment, and determine the corresponding agricultural production monitoring impact index and the real-time infrastructure monitoring impact index;

[0112] Obtaining a dynamic matrix impact coefficient corresponding to an agricultural production monitoring impact index or a real-time infrastructure monitoring impact index;

[0113] The product of the dynamic matrix impact coefficient and the minimum impact index matrix is ​​used as the minimum monitoring impact dynamic index corresponding to the agricultural production monitoring impact index or the real-time infrastructure monitoring impact index;

[0114] The real-time agricultural sub-information or real-time infrastructure sub-information whose agricultural production monitoring impact index or real-time infrastructure monitoring impact index is less than or equal to the minimum monitoring impact dynamic index is stored in the same position in the dynamic data pool;

[0115] The real-time environment sub-information is stored in the same location of the dynamic data pool;

[0116] Divide the control sub-region information; divide the historical environmental data, historical agricultural data and historical infrastructure data in turn according to the control sub-region information, and integrate the divided data to obtain the prediction sub-data;

[0117] Based on the prediction sub-data, an impact index prediction stacking model is constructed, and then the real-time multi-dimensional data of the dynamic data pool is processed, and the processed real-time multi-dimensional data is sequentially input into the impact index prediction stacking model to obtain the dynamic impact index output by the impact index prediction stacking model;

[0118] Determine the decision execution parameters corresponding to the control sub-area based on the impact index prediction stacking model, control sub-area information and dynamic impact index;

[0119] By deciding execution parameters, a governance plan is formulated to complete the control of the control sub-areas.

[0120] Furthermore, the control area information is determined, the rural geographical location information is obtained, and a wireless sensor network is constructed based on the rural geographical location information, including:

[0121] Determine the control target, and define the corresponding control area based on the control target to obtain the control area scope information;

[0122] According to the control area information and rural geographical location information, obtain initial air quality information, initial water quality information and initial rural ecological area information;

[0123] Determine the initial farmland distribution information, initial river distribution information and initial residential area distribution information through the rural geographical location information and initial rural ecological area information;

[0124] Based on the initial farmland distribution information, the initial agricultural production status information is obtained, and the initial agricultural production quality index is determined;

[0125] According to the initial farmland distribution information, the initial river distribution information and the initial residential area distribution information, a prediction coordinate system of the impact of agricultural production conditions is constructed, and the prediction coordinate system of the impact of agricultural production conditions is used to predict the impact index of agricultural production conditions;

[0126] The absolute value of the difference between the initial agricultural production quality index and the agricultural production status impact index is used as the dynamic index of agricultural production quality;

[0127] Based on the dynamic index of agricultural production quality, the initial farmland distribution information, initial river distribution information and initial residential area distribution information are evaluated to obtain the sensor influence coefficient of each coordinate point in the prediction coordinate system of agricultural production status;

[0128] Based on the sensor influence coefficient of each coordinate point in the prediction coordinate system affected by agricultural production conditions, a wireless sensor network is constructed.

[0129] Specifically, the scope of the control area is determined based on the control objectives, and initial information such as various environments and regional distributions is obtained to build a coordinate system for predicting the impact of agricultural production conditions. The sensor influence coefficient of each coordinate point is calculated through relevant indexes to build a network. The control area scope information is a description of the scope of the specific control area defined based on the control objectives, such as geographical boundaries, covered areas, etc. It clarifies the spatial scope of control and is used to limit the spatial scope of all subsequent data collection, analysis, and implementation of control measures. It is the basic scope definition of the entire control method and system operation. The initial air quality information, initial water quality information, and initial rural ecological area information are descriptions of the geographical location distribution of the initial farmland, rivers, and residential areas in the rural area, such as farmland. The specific location of the plots, the routes of the rivers, the range of residential settlements, etc. are used to assist in constructing a coordinate system for predicting the impact of agricultural production conditions, determine the locations of sensors, analyze the relationships between different functional areas within the region, and provide basic geographic references for subsequent regional divisions and data associations. The initial agricultural production status information is the initial record of agricultural production conditions. Basic conditions such as crop types, planting areas, and yields are summarized as agricultural production status information. The initial agricultural production quality index is a quantitative indicator that comprehensively measures the quality level of agricultural production in the initial stage. It may involve a comprehensive assessment of multiple factors such as yield and quality of agricultural products. It is used for subsequent comparative analysis of production changes and for the calculation of related indicators such as the agricultural production quality dynamic index.

[0130] Among them, the calculation formula of the initial agricultural production quality index is:

[0131]

[0132] In the formula, represents the initial agricultural production quality index, is the initial total output, is the total initial planting area, is the average quality score of the initial agricultural products (which can be quantified by quality testing, etc.), It is The standardized value of the factors that affect the quality of agricultural production (such as the initial value of soil fertility, etc.) is the number of influencing factors. , and They are all weight coefficients of the corresponding factors (the sum is 1).

[0133] It can be understood that the prediction coordinate system of the impact of agricultural production conditions is a spatial coordinate system for predicting the impact of agricultural production conditions based on the information related to the geographical distribution of rural areas. It can intuitively reflect the differences in the impact of different location areas on agricultural production, provide a reference framework for determining the sensor impact coefficient of each location point, so as to reasonably deploy sensors, and also assist in analyzing the spatial distribution characteristics of agricultural production in the region affected by different factors. The prediction coordinate system of the impact of agricultural production conditions is constructed based on the geographical spatial location of the village. For example, first determine the coordinate axis of the coordinate system, establish a two-dimensional coordinate system based on the geographical orientation of the village (such as east-west, north-south, etc.), or add other agricultural production-related factors such as soil fertility as the third-dimensional coordinate axis as needed; then divide the coordinate area, and divide the rural area into multiple small areas according to a certain spatial scale (such as dividing the grid area according to a fixed area); then analyze the various factors affecting agricultural production in each small area (such as the distance from the water source, soil type, etc.), quantify these factors and comprehensively consider and determine the weight of each small area in terms of agricultural production, so as to construct a complete coordinate system.

[0134] The dynamic index of agricultural production quality reflects the changes in agricultural production quality over time or other factors. The degree of dynamic change is measured by the absolute value of the difference between the initial agricultural production quality index and the agricultural production status impact index. It is used to evaluate the fluctuation of agricultural production quality, and further provide a basis for judging the demand for sensor deployment in different regions (i.e., sensor impact coefficient).

[0135] Among them, the dynamic index of agricultural production quality needs to first calculate the agricultural production status impact index (obtained by comprehensively analyzing various factors affecting agricultural production in the region, quantifying and assigning values ​​according to certain rules and weighted summing them up, such as considering the comprehensive impact of factors such as soil, climate, and infrastructure on agricultural production), and then use the absolute value of the difference between the initial agricultural production quality index and the agricultural production status impact index. The result is the dynamic index of agricultural production quality.

[0136] The agricultural production status impact index starts with the initial distribution information of farmland, rivers, and residential areas in the countryside, and sorts out various factors that affect agricultural production, such as the distance between farmland and rivers affects irrigation, the distance from residential areas involves labor, and the type of soil, the water volume and quality of rivers, and the labor supply in residential areas. Then, for the distance between farmland and rivers and residential areas, the intervals are divided according to the distance, and different intervals are assigned values ​​according to the degree of favorable impact on agricultural production. For soil types, they are classified and assigned values ​​according to characteristics such as fertility, and high fertility is assigned high values. For river water volume, it is divided according to different periods, and different values ​​are assigned for different periods; water quality is classified and assigned values ​​according to standards. For the potential supply of labor in residential areas, it is classified and assigned values ​​according to population structure, employment and other conditions, and high values ​​are assigned to sufficient labor. Then, the method of analyzing historical data is used to clarify the importance of each influencing factor in the calculation of the entire agricultural production status impact index, that is, the weight. Finally, the quantified value of each factor is multiplied by the corresponding weight, and then these products are added together to obtain the agricultural production status impact index, which comprehensively reflects the degree of influence of various factors on agricultural production.

[0137] The sensor influence coefficient is a coefficient corresponding to each coordinate point in the prediction coordinate system of agricultural production status. It is used to characterize the importance of deploying sensors at this location or the degree of correlation between this location and agricultural production. It is used to guide the construction of wireless sensor networks. The density of sensors in different areas is determined according to the size of the coefficient to ensure that sensors can focus on collecting data reflecting areas with greater impact on agricultural production, thereby improving the pertinence and effectiveness of data collection. The sensor influence coefficient needs to comprehensively consider the dynamic index of agricultural production quality at the coordinate point, as well as surrounding environmental factors (such as the distance relationship with infrastructure such as rivers and roads, the surrounding ecological environment, etc.), the impact of infrastructure related to agricultural production (such as proximity to irrigation facilities, agricultural product storage facilities, etc.), and other factors. These factors are quantified (converted into comparable values ​​according to the actual distance, the importance of the facilities, etc.), and then the corresponding weights are assigned according to the importance of each factor. Finally, the weighted sum is used to obtain the sensor influence coefficient.

[0138] Furthermore, a dynamic data pool and a static data pool are constructed, and real-time multidimensional data is stored in the dynamic data pool, and the dynamic data pool is updated in real time, including:

[0139] Build a dynamic data pool based on NoSQL database;

[0140] Extracting timestamp information from the real-time multidimensional data, and dividing the real-time multidimensional data based on the timestamp information to obtain real-time multidimensional sub-data;

[0141] Based on real-time multi-dimensional sub-data, obtain real-time monitoring sub-information;

[0142] Classifying the real-time monitoring sub-information according to the real-time agricultural data, the real-time environmental data and the real-time infrastructure data to obtain the real-time agricultural sub-information, the real-time environmental sub-information and the real-time infrastructure sub-information;

[0143] Determine the minimum impact index matrix based on the agricultural production status impact prediction coordinate system, wireless sensor network and real-time environmental sub-information;

[0144] Obtaining the position of the real-time agricultural sub-information or real-time infrastructure sub-information collected by the same wireless sensor in the agricultural production status impact prediction coordinate system, and obtaining the real-time agricultural sub-information coordinates or the real-time infrastructure sub-information coordinates;

[0145] Determine the real-time agricultural sub-information coordinates and the corresponding wireless sensor coordinates, and connect the real-time agricultural sub-information coordinates and the corresponding wireless sensor coordinates in the agricultural production status impact prediction coordinate system to obtain the real-time agricultural production monitoring impact line segment;

[0146] Determine the real-time infrastructure sub-information coordinates and the corresponding wireless sensor coordinates, and connect the real-time infrastructure sub-information coordinates and the corresponding wireless sensor coordinates in the agricultural production status impact prediction coordinate system to obtain the real-time infrastructure monitoring impact line segment;

[0147] The real-time agricultural production monitoring impact line segment and the real-time infrastructure monitoring impact line segment are used as the agricultural production monitoring impact index and the real-time infrastructure monitoring impact index respectively;

[0148] Based on the wireless sensor network, wireless sensor quality information corresponding to the agricultural production monitoring impact index or the real-time infrastructure monitoring impact index is obtained;

[0149] Obtaining a dynamic matrix impact coefficient corresponding to an agricultural production monitoring impact index or a real-time infrastructure monitoring impact index;

[0150] The product of the dynamic matrix impact coefficient and the minimum impact index matrix is ​​used as the minimum monitoring impact dynamic index corresponding to the agricultural production monitoring impact index or the real-time infrastructure monitoring impact index;

[0151] The real-time agricultural sub-information or real-time infrastructure sub-information whose agricultural production monitoring impact index or real-time infrastructure monitoring impact index is less than or equal to the minimum monitoring impact dynamic index is stored in the same position in the dynamic data pool;

[0152] The real-time environment sub-information is stored in the same position of the dynamic data pool, and the real-time environment sub-information is sorted based on the timestamp information;

[0153] Based on the wireless sensor network, a preset impact range is set, and the coordinates of the real-time agricultural sub-information, the real-time infrastructure sub-information and the real-time environmental sub-information in the agricultural production status impact prediction coordinate system are determined;

[0154] Linking the real-time agricultural sub-information, real-time infrastructure sub-information, and real-time environmental sub-information whose coordinates are all within the preset influence range, and obtaining link information;

[0155] Encrypting the link information to obtain encrypted information, and storing the encrypted information and the link information in a static data pool;

[0156] A data extraction time threshold for the static data pool is set, and based on timestamp information, real-time agricultural data, real-time environmental data, and real-time infrastructure data that meet the data extraction time threshold for the static data pool are stored in the static data pool.

[0157] Specifically, a dynamic data pool is built based on the NoSQL database to classify, filter, and store real-time data according to rules such as timestamps; the static data pool stores historical data and integrates some real-time data according to thresholds, and encrypts the relevant link information. Real-time multi-dimensional data is a data set that reflects the current actual status of various aspects of the village collected in real time through the wireless sensor network. Data is recorded from three dimensions: agricultural production, environmental conditions, and infrastructure operation. It is used to reflect the current actual situation of the village in real time, and serves as a real-time data basis for subsequent regional division, impact index calculation, decision-making, etc., to ensure that control measures can be adjusted and optimized in time according to the actual dynamic changes in the village. Timestamp information is the identification information that marks the specific time when real-time multi-dimensional data is generated, and accurately records the time or time period when the data is generated. It is convenient to manage, divide, query, and compare and analyze data in chronological order, and is a key time reference basis for realizing real-time updates of dynamic data pools, data tracing, and analyzing data change trends. Real-time multidimensional sub-data, real-time agricultural sub-information, real-time environmental sub-information, and real-time infrastructure sub-information are data categories obtained by further subdividing real-time multidimensional data based on timestamp information. They correspond to data subsets in different fields such as agriculture, environment, and infrastructure, respectively, and refine the classification management of real-time data. It is convenient for subsequent special processing, analysis, and storage operations for different types of data according to their respective characteristics and needs. For example, according to different rules, the data can be filtered and stored in the corresponding position of the dynamic data pool, which is convenient for accurate management and efficient use of data.

[0158] The minimum impact index matrix is ​​a data structure in the form of a matrix that reflects the minimum impact of each location point in the entire rural system, which is constructed by comprehensively considering the impact of agricultural production conditions on the prediction coordinate system, wireless sensor networks, and real-time environmental sub-information. It presents the basic impact status of different locations. As one of the important reference standards for subsequent judgment of whether the real-time agricultural sub-information and real-time infrastructure sub-information meet the conditions for storage in the dynamic data pool, it ensures that the data stored in the dynamic data pool has a certain relevance and validity. When calculating the minimum impact index matrix, first analyze and determine the various factors that affect each location point (such as the impact of air quality and water quality in environmental factors on different regions, the impact of sensor network coverage on data collected at each location, etc.), quantify the impact of each factor at each location point (converted into quantifiable values ​​based on actual measurement data, distance relationship with relevant facilities, etc.), then determine the weight according to the importance of each factor, and finally multiply the quantified value of each factor by the corresponding weight and accumulate it to form the corresponding minimum impact index matrix element value for each location point. The element values ​​of many location points constitute the minimum impact index matrix.

[0159] It can be understood that the real-time agricultural production monitoring influence line segment and the real-time infrastructure monitoring influence line segment are the line segments formed by connecting the real-time agricultural sub-information coordinates with the corresponding wireless sensor coordinates, and the real-time infrastructure sub-information coordinates with the corresponding wireless sensor coordinates. The relevant quantitative attributes of the line segment (such as length, etc.) are used as the corresponding influence index, reflecting the degree of association and mutual influence between the data collection point and the corresponding information source point. It is used to measure the mutual influence relationship between the real-time agricultural sub-information and the real-time infrastructure sub-information and the sensor in spatial position, and then participate in the calculation process of subsequent indicators such as the minimum monitoring impact dynamic index, and assist the dynamic data pool in data screening and storage decisions. When calculating the corresponding influence index of the three, the real-time agricultural sub-information coordinates, the real-time infrastructure sub-information coordinates and the corresponding wireless sensor coordinates are first determined (the coordinate values ​​are obtained through the installation location record of the sensor and the location identifier corresponding to the data collection), and then the spatial distance calculation formula (such as the distance formula between two points in a two-dimensional plane, etc.) is used to calculate the length of the line segment connecting the corresponding coordinate points, and the length or the quantified value after further combining other factors (such as the importance of the data in the area, etc.) based on the length is used as the corresponding influence index.

[0160] Wireless sensor quality information reflects the comprehensive quality of wireless sensors in terms of performance, working status, data collection accuracy, etc., including multiple indicators such as sensor accuracy, failure rate, signal transmission stability, etc. Wireless sensor quality information is used to evaluate the reliability of data collected by sensors. In the process of determining the minimum monitoring impact dynamic index in combination with other influencing factors, the impact of sensor quality on data validity is fully considered to ensure the accuracy of analysis and decision-making based on sensor data.

[0161] The dynamic matrix impact coefficient is a dynamically changing coefficient determined after comprehensive consideration of multiple factors (such as sensor quality, sensitivity to environmental changes in the region, etc.), which is used to adjust the impact of the minimum impact index matrix on real-time data screening, so that it can more flexibly and accurately adapt to the complex and changeable actual environment of the rural system. The dynamic matrix impact coefficient is multiplied by the minimum impact index matrix to jointly determine whether the real-time agricultural sub-information and real-time infrastructure sub-information are suitable for storage in the dynamic data pool under different circumstances, ensuring that the data screening and storage mechanism can be dynamically adjusted according to actual conditions, and improving the rationality and effectiveness of data storage. When calculating the dynamic matrix impact coefficient, the various factors that affect the coefficient are first determined (such as sensor quality information, the sensitivity of the region to environmental changes, which can be judged based on the fluctuation of historical environmental data, etc.), and each factor is quantified (the various indicators of sensor quality are converted into a quantitative value, and the sensitivity to environmental changes is quantified according to the fluctuation amplitude, etc.), and then the weight is determined according to the importance of each factor, and finally the weighted sum is obtained to obtain the dynamic matrix impact coefficient.

[0162] The minimum monitoring impact dynamic index is a dynamic threshold indicator derived from the comprehensive dynamic matrix impact coefficient and the minimum impact index matrix. It is used to measure whether real-time agricultural sub-information and real-time infrastructure sub-information can enter the dynamic data pool. Only relevant information below this index meets the storage conditions. The minimum monitoring impact dynamic index realizes the dynamic screening and storage function of the dynamic data pool for real-time data, ensuring that the data stored in the dynamic data pool has high relevance and validity, and can adapt to the real-time changing environmental characteristics of the rural system, making data management more in line with actual needs. The calculated dynamic matrix impact coefficient is multiplied by the corresponding minimum impact index matrix element value, and the corresponding minimum monitoring impact dynamic index value is obtained for each location point or each data information, so as to determine whether the real-time data meets the storage requirements.

[0163] Furthermore, based on the rural geographical location information, real-time agricultural data, real-time environmental data and real-time infrastructure data, the control area is divided into regions to obtain the control sub-region information, including:

[0164] Based on the geographical location information of the village, determine the longitude and latitude coordinate information of the village, topographic information and village layout information;

[0165] Through real-time agricultural data, obtain real-time crop type information, real-time planting area information, real-time growth stage information, real-time soil fertility information and real-time pest and disease information;

[0166] Determine real-time air quality information, real-time water quality information, real-time meteorological condition information and real-time ecological status information based on real-time environmental data;

[0167] Based on real-time infrastructure data, obtain real-time traffic road condition information, real-time water conservancy facility operation information, real-time energy supply status information and real-time communication facility information;

[0168] Obtaining a first division coefficient through real-time crop type information, real-time planting area information, real-time growth stage information, real-time soil fertility information, and real-time pest and disease information;

[0169] Determine the real-time air quality information, real-time water quality information, real-time meteorological condition information and real-time ecological condition information through the real-time environmental data to obtain the second division coefficient;

[0170] Obtaining a third division coefficient through real-time traffic road condition information, real-time water conservancy facility operation information, real-time energy supply status information and real-time communication facility information;

[0171] Based on the first division coefficient, the second division coefficient and the third division coefficient, obtaining a control area division index;

[0172] According to the control area division index, the control area is divided into regions to obtain the control sub-region information.

[0173] Specifically, the first, second and third division coefficients are calculated based on rural geographic information and various real-time data, and then the control area division index is obtained to achieve regional division. The first division coefficient is a quantitative coefficient calculated based on real-time agricultural data (such as crop types, planting areas, growth stages, soil fertility, pests and diseases, etc.), which is used to measure the degree of influence of agricultural factors on the division of control areas. The second division coefficient is a coefficient determined based on real-time environmental data (air quality, water quality, meteorological conditions, ecological conditions, etc.), which reflects the weight of environmental factors in the division of control areas. The third division coefficient is a coefficient calculated based on real-time infrastructure data (traffic roads, water conservancy facilities, energy supply, communication facilities, etc.), which reflects the strength of the influence of infrastructure on the division of control areas. These three coefficients jointly participate in the calculation of the control area division index, providing a quantitative basis for the reasonable division of control sub-areas from three different dimensions of agriculture, environment and infrastructure, so that the regional division can fully consider the actual conditions of all aspects of the village and achieve more scientific and reasonable regional subdivision. When calculating the first division coefficient, the various elements in the real-time agricultural data (such as statistics on the proportion of different crop planting areas, assessment of soil fertility levels, analysis of the degree of pests and diseases, etc.) are first quantified, and then the weights are determined according to the importance of each element in agricultural production and regional division. Finally, the quantified values ​​of each element are multiplied by the corresponding weights and accumulated to obtain the first division coefficient. Similarly, the calculation steps of the second and third division coefficients are similar to those of the first division coefficient.

[0174] Furthermore, according to the information of the control sub-areas, the historical environmental data, historical agricultural data and historical infrastructure data are divided in turn, and the divided data are integrated to obtain the prediction sub-data, which specifically includes:

[0175] Based on the rural geographical location information, determine the geographical location information of the control sub-region information;

[0176] According to the geographical location information of the control sub-region information, historical environmental data, historical agricultural data and historical infrastructure data are mapped to each control sub-region information;

[0177] The historical environmental data, historical agricultural data and historical infrastructure data corresponding to each control sub-area are divided to obtain a subset of historical environmental data, a subset of historical agricultural data and a subset of historical infrastructure data corresponding to each control sub-area;

[0178] A data integration framework is constructed based on the historical environmental data subset, the historical agricultural data subset and the historical infrastructure data subset. The data integration framework includes historical time dimension information, historical data type information and control sub-area number information.

[0179] Based on the data integration framework, historical data type information is associated and integrated according to historical time dimension information and control sub-area number information to obtain historical integrated data, and the association information between historical time dimension information, historical data type information and control sub-area number information is determined;

[0180] The historical integrated data is preprocessed and the prediction feature information is extracted to obtain the prediction sub-data.

[0181] Specifically, using the control sub-region information as a link, historical data is mapped to regions and divided into subsets, and then a framework is built to integrate the data and extract key features, providing basic data support for subsequent model construction, so that subsequent analysis can focus on the level of each control sub-region and be based on historical experience data.

[0182] It is understandable that the geographical location range of each control sub-area is clarified, and then according to this range, the existing historical environmental data (such as air quality, water quality, etc. in different time periods in the past), historical agricultural data (previous crop planting conditions, yields, etc.), and historical infrastructure data (previous traffic road conditions, water conservancy facilities operation conditions, etc.) are classified into the corresponding control sub-areas, thereby forming each control sub-area's corresponding historical environment, agriculture, and infrastructure data subsets. Through such division, the management of historical data is refined, so that subsequent analysis can be carried out for specific areas, more in line with the actual regional differences in rural areas, and the historical development laws of different regions are excavated. For example, a village is divided into three control sub-areas A, B, and C. Various types of data on air quality, soil fertility, road maintenance, etc. recorded in history are sorted into the corresponding subsets of A, B, and C areas.

[0183] Constructing a data integration framework and associating integrated data means creating a data integration framework that includes historical time dimension information (such as specific years, seasons, and other time nodes), historical data type information (distinguishing whether it is environmental, agricultural, or infrastructure data), and control sub-area number information (giving each control sub-area a unique number for identification). Under this framework, different types of historical data are associated according to chronological order and regional numbers. For example, the agricultural production data, environmental data, and infrastructure data of region A in the spring of a certain year are associated, and the relationship between them is comprehensively analyzed to form a holistic historical integrated data. It aims to break the isolation between different types of historical data, establish their internal connections through the framework, and present a more comprehensive and systematic picture of the development of villages in various aspects at different times and in different regions, so as to facilitate the mining of deep data value.

[0184] Data preprocessing and extraction of predictive feature information is to preprocess the integrated historical data, such as cleaning errors and missing values ​​in the data, unifying the data format, and other operations to make the data quality more reliable. On this basis, data analysis methods (such as statistical analysis, machine learning algorithms, etc.) are used to extract key feature information that can reflect future development trends and help subsequent predictions, and finally obtain predictive sub-data. For example, by analyzing the trends of changes in planting areas and the occurrence patterns of pests and diseases in past agricultural production data, they are extracted as part of the predictive sub-data. Improving data quality and mining information with predictive value enables the subsequent constructed models to accurately analyze and predict based on high-quality and targeted data, providing a strong data basis for rural governance decisions.

[0185] Furthermore, based on the prediction sub-data, an impact index prediction stacking model is constructed, and then the real-time multidimensional data of the dynamic data pool is processed, and the processed real-time multidimensional data is sequentially input into the impact index prediction stacking model to obtain the dynamic impact index output by the impact index prediction stacking model, which specifically includes:

[0186] Based on the correlation information between the historical time dimension information, the historical data type information and the control sub-area number information, obtain the first historical impact index of the historical environmental data on the historical agricultural data, the second historical impact index of the historical environmental data on the historical infrastructure data, the first historical joint impact index of the historical agricultural data on the historical environmental data and the historical infrastructure data, and the second historical joint impact index of the historical infrastructure data on the historical environmental data and the agricultural data;

[0187] Based on the prediction sub-data, obtain the proportion of historical environmental data, historical agricultural data and historical infrastructure data in the corresponding control sub-area;

[0188] Obtain the first impact index prediction model, the second impact index prediction model and the third impact index prediction model through the proportion of historical environmental data, the proportion of historical agricultural data, the proportion of historical infrastructure data, the first historical impact index, the second historical impact index, the first historical joint impact index and the second historical joint impact index;

[0189] The first impact index prediction model, the second impact index prediction model and the third impact index prediction model are connected in series to obtain an impact index prediction stacking model;

[0190] Obtain the real-time multi-dimensional data of the dynamic data pool in turn, and based on the prediction sub-data, obtain the proportion of real-time environmental data, real-time agricultural data, and real-time infrastructure data corresponding to the control sub-area;

[0191] The proportion of real-time environmental data, the proportion of real-time agricultural data and the proportion of real-time infrastructure data are input into the impact index prediction stacking model to obtain the dynamic impact index output by the impact index prediction stacking model.

[0192] Specifically, based on the prediction sub-data prepared in advance, we deeply explore the influence relationship between historical data, build multiple sub-models and combine them into a stacking model to achieve quantitative modeling of the complex mutual influence between different data. Then, we combine the real-time data proportion input model, combine historical data with real-time conditions, and output a dynamic impact index to reflect the actual situation of the current rural areas under the influence of various factors, providing a dynamic basis for decision-making.

[0193] It is understandable that the calculation of multiple historical impact indexes is based on the correlation between historical time dimension information, historical data type information and control sub-area number information, and in-depth analysis of the mutual influence relationship between historical data. For example, check how environmental data (such as air quality changes) have affected agricultural data (such as crop yield fluctuations) in different time periods and different control sub-areas in the past, and quantify the first historical impact index of historical environmental data on historical agricultural data; similarly, analyze and calculate several other historical impact indexes of environment on infrastructure, agriculture on environment and infrastructure, and infrastructure on environment and agriculture. For example, through statistical analysis, it is found that when the air quality in a certain area improved in the past, the crop yield increased accordingly, and the corresponding impact index was calculated based on this degree of correlation. Quantifying the interaction relationship between historical data reveals the inherent connection law of various aspects of rural development in the past, provides key parameter basis for building a prediction model, and enables the model to capture the influence logic between data based on historical experience.

[0194] The construction of sub-models and stacking models based on the proportion of data in the control sub-regions is to count the proportion of historical environmental data, historical agricultural data and historical infrastructure data in each control sub-region based on the predicted sub-data. Then, using these data proportions and the various historical impact indexes calculated previously, the first impact index prediction model, the second impact index prediction model and the third impact index prediction model are constructed respectively through appropriate mathematical modeling methods (such as linear regression, machine learning algorithms, etc.). Finally, the three sub-models are connected in series in a certain logical order to form an impact index prediction stacking model. For example, taking factors such as the proportion of historical environmental data as input variables, the model calculates the output predicted impact index, and the combination of multiple models can more comprehensively consider various influencing factors. Based on the historical data characteristics of each control sub-region and the excavated historical impact relationship, a targeted prediction model system is constructed. Through the stacking model, multiple factors are integrated to improve the accuracy and comprehensiveness of the prediction of the mutual influence of different data to adapt to the complex system environment of the countryside.

[0195] The dynamic impact index is obtained by inputting the proportion of real-time data in sequence from the dynamic data pool (real-time agricultural, environmental, and infrastructure data). For each control sub-area, the corresponding proportion of real-time environmental data, real-time agricultural data, and real-time infrastructure data is determined. These real-time data proportions are used as input values ​​and substituted into the already constructed impact index prediction stacking model. After the internal calculation of the model, the dynamic impact index of the control sub-area is finally output, reflecting the actual state of the mutual influence of various elements in the village at the current moment. For example, the proportion of data such as the real-time air quality, crop growth, and traffic road conditions in a certain area is input into the model to obtain the dynamic impact index of the area at this moment. It realizes the combination of real-time data and historical data, and uses the model constructed by historical experience to dynamically evaluate the current rural situation, providing real-time data support and quantitative reference for timely grasping the development trends of the village, discovering potential problems, and subsequent decision-making adjustments.

[0196] Furthermore, according to the impact index prediction stacking model, the control sub-area information and the dynamic impact index, the decision execution parameters corresponding to the control sub-area are determined, including:

[0197] Based on the control sub-area information, determine the control sub-area number information;

[0198] According to the control sub-area number information, collect the real-time environmental data proportion, real-time agricultural data proportion and real-time infrastructure data proportion corresponding to the control sub-area number, input them into the impact index prediction stacking model, and obtain the corresponding real-time dynamic impact index;

[0199] Obtain the average value of the dynamic impact index and the instant dynamic impact index to obtain the standard impact index;

[0200] The standard impact index is calculated by averaging the dynamic impact index (the impact index that reflects the current general situation calculated by the model based on the proportion of real-time data) and the instant dynamic impact index (the latest impact index calculated based on the proportion of the latest collected instant data). For example, if the dynamic impact index is 0.6 and the instant dynamic impact index is 0.7, then the standard impact index is (0.6 + 0.7) / 2 = 0.65.

[0201] According to the standard impact index, the decision execution parameters corresponding to the control sub-area are determined. The decision execution parameters include agricultural production decision parameters, environmental management decision parameters, infrastructure operation and maintenance decision parameters, and comprehensive management decision parameters.

[0202] Based on the calculated standard impact index, combined with the goals, requirements and actual conditions of rural governance in agricultural production, environmental management, infrastructure operation and maintenance, and comprehensive management, specific decision-making execution parameters are analyzed and determined. For example, if the standard impact index shows that agricultural production in a certain region is greatly affected by environmental factors, and the current agricultural production data has a downward trend, then in terms of agricultural production decision parameters, it may be determined to increase agricultural technical support for the region, adjust the planting structure and other specific measures; in terms of environmental management decision parameters, strengthen the control of surrounding pollution sources, etc. By taking the average value, the generality and immediacy of the current rural situation are comprehensively considered, and a more comprehensive impact index that can balance short-term fluctuations and long-term trends is obtained, so that the subsequent decision-making execution parameters determined based on this are more robust and reasonable, avoiding decision-making errors due to the one-sidedness of a single data.

[0203] Specifically, on the basis of the dynamic impact index, the real-time data is introduced and the model is calculated again, and the average value is taken to obtain a more comprehensive and timely standard impact index. Finally, the decision-making execution parameters in various aspects are determined based on this index, and the transformation from data to specific decision-making content is completed, providing clear guidance for the actual operation of rural digital governance and control. The real-time data proportion is collected and input into the model to obtain the real-time dynamic impact index. The number of each control sub-area is determined by the control sub-area information. For each control sub-area corresponding to the number, the current real-time environmental data proportion (such as the current air quality, water quality and other data account for the proportion of overall environmental related indicators), the real-time agricultural data proportion (such as the current crop planting area, yield and other data account for the proportion of agricultural related indicators) and the real-time infrastructure data proportion (such as the current traffic road conditions, water conservancy facilities operation status and other data account for the proportion of infrastructure related indicators) are collected. These real-time data proportions are input into the impact index prediction stacking model, and the real-time dynamic impact index is obtained through model calculation to reflect the latest mutual influence of various factors. For example, the current proportion of various data in area A of a village is checked in real time and input into the model to obtain the real-time dynamic impact index at this moment. Timely capture the latest changes in the current status of the village, use the model to quickly analyze the degree of mutual influence of various factors at the moment, provide the latest data basis for subsequent comprehensive evaluation and decision-making, and ensure that the decision is in line with the current actual situation in the village.

[0204] It can be understood that according to the standard impact index, the decision execution parameters corresponding to the control sub-area are determined, taking the agricultural production decision parameters as an example:

[0205] Determine the type of information on agricultural production decision parameters, including planting structure, irrigation strategies and technical support;

[0206] According to the standard impact index of the control sub-area, determine the agricultural production decision parameters corresponding to the control sub-area. If the standard impact index is greater than or equal to 0.7, the planting structure is adjusted by ±15% to ensure that the arable land quality index is greater than 0.7. The adjustment coefficient algorithm is index volatility × benchmark capacity × 0.83. The drip irrigation ratio of the irrigation strategy is greater than or equal to 40%. The adjustment coefficient algorithm is (1-current carrying capacity) × technical compensation factor. The input support of technical support is increased by 20%, and the annual increase in the contribution rate of science and technology is ensured to be less than 5%. The adjustment coefficient algorithm is hysteresis coefficient × regional gap index × regional gap index;

[0207] Take environmental management decision parameters as an example:

[0208] If the standard impact index of the control sub-area is greater than or equal to 0.85, the control sub-area will be designated as a first-level control area, and production will be suspended and limited by 90%. If the standard impact index is less than 0.85 but greater than or equal to 0.5, the control sub-area will be designated as a second-level control area, and technical transformation will be 50%. If the standard impact index is less than 0.5 but greater than or equal to 0.2, the control sub-area will be designated as a third-level control area, and routine supervision will be carried out;

[0209] Take infrastructure operation and maintenance parameters as an example:

[0210] The infrastructure inspection interval is = min (7 days, 30 × (1-standard impact index) ^ 2);

[0211] Take the comprehensive management decision parameters as an example:

[0212] Obtain the average value of the standard impact index of all control sub-areas. If the average value of the standard impact index of all control sub-areas is greater than or equal to 0.7, establish a multi-objective optimization function: Max Z = α×ecological benefit + β×economic benefit + γ×social benefit Constraints: ∑(resource consumption) ≤ environmental capacity threshold people's livelihood security index ≥ benchmark value×1.1.

[0213] Furthermore, a rural digital governance control system based on cloud platform sharing is proposed, which is used to implement any of the above control methods, including:

[0214] Data collection and transmission module: The data collection and transmission module is used to build a wireless sensor network and deploy sensors according to the geographical characteristics of the village, collect various real-time data, process and transmit data at the same time, and can connect to external data sources to obtain supplementary data and ensure data access security;

[0215] Data processing and storage module: The data processing and storage module is used to pre-process the collected real-time data, clean up abnormal values ​​and standardize them, manage dynamic data pools, filter and store real-time data according to rules, manage static data pools, store historical data and integrate some real-time data according to thresholds, integrate data, and associate historical data types, time and control area information;

[0216] The regional division and model building module is used to determine the rural geographical details and divide the control area based on multiple types of data, obtain the control sub-area information, calculate multiple historical impact indexes based on historical data association information, and build an impact index prediction stacking model to predict the dynamic impact index;

[0217] Decision support and control execution module: The decision support and control execution module is used to determine the standard impact index based on the real-time data and prediction model of the control sub-area, and then determine the decision execution parameters, including agriculture, environment, infrastructure and comprehensive management, etc., and convert the decision parameters into instructions and send them to various execution departments or smart devices to implement control;

[0218] User interaction and visualization module: The user interaction and visualization module is used to visualize various types of data and analysis results, and provide user interaction functions, including login, permission management, data query, screening and customized reports, to meet the needs of different user roles.

[0219] Furthermore, the data processing and storage module includes:

[0220] Data preprocessing unit: The data preprocessing unit is used to clean the real-time data collected by the sensor network unit, remove abnormal values, noise data, etc., such as eliminating obviously erroneous meteorological observation data or abnormal readings caused by sensor failure, and standardize the data to make different types of data comparable, such as unifying soil fertility data to a specific quantitative standard to facilitate subsequent analysis and calculation;

[0221] The dynamic data pool management unit is used to build and manage the dynamic data pool based on the NoSQL database, divide the real-time multidimensional data according to the timestamp information, obtain the real-time multidimensional sub-data, and further classify it into real-time agricultural sub-information, real-time environmental sub-information and real-time infrastructure sub-information. According to the rules of agricultural production monitoring impact index, real-time infrastructure monitoring impact index and minimum monitoring impact dynamic index, the real-time data that meets the requirements is screened and stored in the corresponding position in the dynamic data pool. At the same time, the real-time environmental sub-information is sorted based on the timestamp to quickly retrieve and query the latest environmental data;

[0222] Static data pool management unit: The static data pool management unit is responsible for storing historical environmental data, historical agricultural data and historical infrastructure data, storing the encrypted link information and the original link information in the static data pool, and storing the real-time data that meets the conditions in the static data pool regularly according to the set static data pool data extraction time threshold, so as to realize the organic combination of historical data and real-time data and provide data support for long-term analysis and prediction;

[0223] Data integration unit: The data integration unit is used to associate and integrate historical data type information according to historical time dimension information and control sub-area number information based on the data integration framework. For example, the agricultural data, environmental data and infrastructure data of the same control sub-area in different historical periods are integrated to construct historical integrated data, and determine the association information between historical time dimension information, historical data type information and control sub-area number information, so as to provide a structured data foundation for subsequent analysis and modeling.

[0224] Furthermore, the region division and model building module includes:

[0225] The regional division unit is used to determine the rural latitude and longitude coordinate information, topographic information and village layout information based on the rural geographical location information, and calculate the first division coefficient, the second division coefficient and the third division coefficient in combination with the real-time agricultural data, the real-time environmental data and the real-time infrastructure data, so as to obtain the control area division index, accurately divide the control area, obtain the control sub-area information, and assign a unique number to each control sub-area for easy management and data association;

[0226] The impact index prediction model construction unit is used to calculate the first historical impact index of historical environmental data on historical agricultural data, the second historical impact index of historical environmental data on historical infrastructure data, the first historical joint impact index of historical agricultural data on historical environmental data and historical infrastructure data, and the second historical joint impact index of historical infrastructure data on historical environmental data and agricultural data based on the correlation information between historical time dimension information, historical data type information and control sub-area number information; according to the predicted sub-data, the proportion of historical environmental data, the proportion of historical agricultural data and the proportion of historical infrastructure data in the corresponding control sub-area are obtained; through these proportions and various historical impact indexes, the first impact index prediction model, the second impact index prediction model and the third impact index prediction model are constructed, and they are concatenated into an impact index prediction stacking model to provide core algorithm support for the prediction of dynamic impact index.

[0227] Implementation process: First, determine the control area information and rural geographical location information, build a wireless sensor network to collect real-time data and pre-process it to obtain real-time multi-dimensional data (including agriculture, environment, and infrastructure data). Secondly, build dynamic and static data pools to store real-time and historical corresponding data respectively, and update the dynamic data pool in real time. Then, divide the control area based on multiple types of data to obtain control sub-area information, and then divide and integrate historical data to obtain predicted sub-data. Finally, build an impact index prediction stacking model, input real-time multi-dimensional data to obtain a dynamic impact index, and finally determine the decision execution parameters based on this to formulate a governance plan.

[0228] The above shows and describes the basic principles, main features and implementation process of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may have various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A rural digital governance and control method based on cloud platform sharing, characterized in that: include: Determine the control area information, obtain the rural geographical location information, and build a wireless sensor network based on the rural geographical location information; Using a wireless sensor network to collect real-time data, and preprocessing the real-time data to obtain real-time multi-dimensional data, wherein the real-time multi-dimensional data includes real-time agricultural data, real-time environmental data, and real-time infrastructure data; Build a dynamic data pool and a static data pool, store real-time multidimensional data in the dynamic data pool, and update the dynamic data pool in real time. The static data pool contains historical environmental data, historical agricultural data, and historical infrastructure data, including: Classifying the real-time multi-dimensional data into real-time agricultural sub-information, real-time environmental sub-information and real-time infrastructure sub-information; Constructing an agricultural production status impact prediction coordinate system based on initial farmland distribution information, initial river distribution information, and initial residential area distribution information, wherein the agricultural production status impact prediction coordinate system is used to predict an agricultural production status impact index; Determine the minimum impact index matrix based on the agricultural production status impact prediction coordinate system, wireless sensor network and real-time environmental sub-information; Obtaining the real-time agricultural sub-information coordinates or real-time infrastructure sub-information coordinates corresponding to the real-time agricultural sub-information or real-time infrastructure sub-information in the agricultural production status impact prediction coordinate system; In the agricultural production status impact prediction coordinate system, the real-time agricultural sub-information coordinates, the real-time infrastructure sub-information coordinates and the corresponding wireless sensor coordinates are respectively connected to obtain the real-time agricultural production monitoring impact line segment and the real-time infrastructure monitoring impact line segment, and determine the corresponding agricultural production monitoring impact index and the real-time infrastructure monitoring impact index; Obtaining a dynamic matrix impact coefficient corresponding to an agricultural production monitoring impact index or a real-time infrastructure monitoring impact index; The product of the dynamic matrix impact coefficient and the minimum impact index matrix is ​​used as the minimum monitoring impact dynamic index corresponding to the agricultural production monitoring impact index or the real-time infrastructure monitoring impact index; The real-time agricultural sub-information or real-time infrastructure sub-information whose agricultural production monitoring impact index or real-time infrastructure monitoring impact index is less than or equal to the minimum monitoring impact dynamic index is stored in the same position in the dynamic data pool; The real-time environment sub-information is stored in the same location of the dynamic data pool; Divide the control sub-region information; divide the historical environmental data, historical agricultural data and historical infrastructure data in turn according to the control sub-region information, and integrate the divided data to obtain the prediction sub-data; Based on the prediction sub-data, an impact index prediction stacking model is constructed, and then the real-time multi-dimensional data of the dynamic data pool is processed, and the processed real-time multi-dimensional data is sequentially input into the impact index prediction stacking model to obtain the dynamic impact index output by the impact index prediction stacking model; Determine the decision execution parameters corresponding to the control sub-area based on the impact index prediction stacking model, control sub-area information and dynamic impact index; By deciding execution parameters, a governance plan is formulated to complete the control of the control sub-areas.

2. According to claim 1, a rural digital governance and control method based on cloud platform sharing is characterized in that: The determining of the control area information, obtaining the rural geographical location information, and building a wireless sensor network through the rural geographical location information specifically includes: Determine the control target, and define the corresponding control area based on the control target to obtain the control area scope information; According to the control area information and rural geographical location information, obtain initial air quality information, initial water quality information and initial rural ecological area information; Determine the initial farmland distribution information, initial river distribution information and initial residential area distribution information through the rural geographical location information and initial rural ecological area information; Based on the initial farmland distribution information, the initial agricultural production status information is obtained, and the initial agricultural production quality index is determined; Constructing an agricultural production status impact prediction coordinate system based on initial farmland distribution information, initial river distribution information, and initial residential area distribution information, wherein the agricultural production status impact prediction coordinate system is used to predict an agricultural production status impact index; The absolute value of the difference between the initial agricultural production quality index and the agricultural production status impact index is used as the dynamic index of agricultural production quality; Based on the dynamic index of agricultural production quality, the initial farmland distribution information, initial river distribution information and initial residential area distribution information are evaluated to obtain the sensor influence coefficient of each coordinate point in the prediction coordinate system of agricultural production status; Based on the sensor influence coefficient of each coordinate point in the prediction coordinate system affected by agricultural production conditions, a wireless sensor network is constructed.

3. According to claim 2, a rural digital governance and control method based on cloud platform sharing is characterized in that: The construction of the dynamic data pool and the static data pool, storing the real-time multi-dimensional data in the dynamic data pool, and updating the dynamic data pool in real time, specifically includes: Build a dynamic data pool based on NoSQL database; Extracting timestamp information from the real-time multidimensional data, and dividing the real-time multidimensional data based on the timestamp information to obtain real-time multidimensional sub-data; Based on real-time multi-dimensional sub-data, obtain real-time monitoring sub-information; Classifying the real-time monitoring sub-information according to the real-time agricultural data, the real-time environmental data and the real-time infrastructure data to obtain the real-time agricultural sub-information, the real-time environmental sub-information and the real-time infrastructure sub-information; Obtaining the position of the real-time agricultural sub-information or real-time infrastructure sub-information collected by the same wireless sensor in the agricultural production status impact prediction coordinate system, and obtaining the real-time agricultural sub-information coordinates or the real-time infrastructure sub-information coordinates; Determine the real-time agricultural sub-information coordinates and the corresponding wireless sensor coordinates, and connect the real-time agricultural sub-information coordinates and the corresponding wireless sensor coordinates in the agricultural production status impact prediction coordinate system to obtain the real-time agricultural production monitoring impact line segment; Determine the real-time infrastructure sub-information coordinates and the corresponding wireless sensor coordinates, and connect the real-time infrastructure sub-information coordinates and the corresponding wireless sensor coordinates in the agricultural production status impact prediction coordinate system to obtain the real-time infrastructure monitoring impact line segment; The real-time agricultural production monitoring impact line segment and the real-time infrastructure monitoring impact line segment are used as the agricultural production monitoring impact index and the real-time infrastructure monitoring impact index respectively; Based on the wireless sensor network, wireless sensor quality information corresponding to the agricultural production monitoring impact index or the real-time infrastructure monitoring impact index is obtained; Obtaining a dynamic matrix impact coefficient corresponding to an agricultural production monitoring impact index or a real-time infrastructure monitoring impact index; The product of the dynamic matrix impact coefficient and the minimum impact index matrix is ​​used as the minimum monitoring impact dynamic index corresponding to the agricultural production monitoring impact index or the real-time infrastructure monitoring impact index; The real-time agricultural sub-information or real-time infrastructure sub-information whose agricultural production monitoring impact index or real-time infrastructure monitoring impact index is less than or equal to the minimum monitoring impact dynamic index is stored in the same position in the dynamic data pool; The real-time environment sub-information is stored in the same position of the dynamic data pool, and the real-time environment sub-information is sorted based on the timestamp information; Based on the wireless sensor network, a preset impact range is set, and the coordinates of the real-time agricultural sub-information, the real-time infrastructure sub-information and the real-time environmental sub-information in the agricultural production status impact prediction coordinate system are determined; Linking the real-time agricultural sub-information, real-time infrastructure sub-information, and real-time environmental sub-information whose coordinates are all within the preset influence range, and obtaining link information; Encrypting the link information to obtain encrypted information, and storing the encrypted information and the link information in a static data pool; A data extraction time threshold for the static data pool is set, and based on timestamp information, real-time agricultural data, real-time environmental data, and real-time infrastructure data that meet the data extraction time threshold for the static data pool are stored in the static data pool.

4. According to claim 3, a rural digital governance and control method based on cloud platform sharing is characterized in that: Based on the rural geographic location information, real-time agricultural data, real-time environmental data and real-time infrastructure data, the control area is divided into regions to obtain the control sub-region information, including: Based on the geographical location information of the village, determine the longitude and latitude coordinate information of the village, topographic information and village layout information; Through real-time agricultural data, obtain real-time crop type information, real-time planting area information, real-time growth stage information, real-time soil fertility information and real-time pest and disease information; Determine real-time air quality information, real-time water quality information, real-time meteorological condition information and real-time ecological status information based on real-time environmental data; Based on real-time infrastructure data, obtain real-time traffic road condition information, real-time water conservancy facility operation information, real-time energy supply status information and real-time communication facility information; Obtaining a first division coefficient through real-time crop type information, real-time planting area information, real-time growth stage information, real-time soil fertility information, and real-time pest and disease information; Determine the real-time air quality information, real-time water quality information, real-time meteorological condition information and real-time ecological condition information through the real-time environmental data to obtain the second division coefficient; Obtaining a third division coefficient through real-time traffic road condition information, real-time water conservancy facility operation information, real-time energy supply status information and real-time communication facility information; Based on the first division coefficient, the second division coefficient and the third division coefficient, obtaining a control area division index; According to the control area division index, the control area is divided into regions to obtain the control sub-region information.

5. According to claim 4, a rural digital governance and control method based on cloud platform sharing is characterized in that: According to the control sub-area information, the historical environmental data, historical agricultural data and historical infrastructure data are divided in turn, and the divided data are integrated to obtain the prediction sub-data, which specifically includes: Based on the rural geographical location information, determine the geographical location information of the control sub-region information; According to the geographical location information of the control sub-region information, historical environmental data, historical agricultural data and historical infrastructure data are mapped to each control sub-region information; The historical environmental data, historical agricultural data and historical infrastructure data corresponding to each control sub-area are divided to obtain a subset of historical environmental data, a subset of historical agricultural data and a subset of historical infrastructure data corresponding to each control sub-area; A data integration framework is constructed using a historical environmental data subset, a historical agricultural data subset, and a historical infrastructure data subset, wherein the data integration framework includes historical time dimension information, historical data type information, and control sub-area number information; Based on the data integration framework, historical data type information is associated and integrated according to historical time dimension information and control sub-area number information to obtain historical integrated data, and at the same time, the association information between historical time dimension information, historical data type information and control sub-area number information is determined; The historical integrated data is preprocessed and the prediction feature information is extracted to obtain the prediction sub-data.

6. According to claim 5, a rural digital governance and control method based on cloud platform sharing is characterized in that: The method constructs an impact index prediction stacking model based on the prediction sub-data, then processes the real-time multi-dimensional data of the dynamic data pool, and sequentially inputs the processed real-time multi-dimensional data into the impact index prediction stacking model to obtain the dynamic impact index output by the impact index prediction stacking model, specifically including: Based on the correlation information between the historical time dimension information, the historical data type information and the control sub-area number information, obtain the first historical impact index of the historical environmental data on the historical agricultural data, the second historical impact index of the historical environmental data on the historical infrastructure data, the first historical joint impact index of the historical agricultural data on the historical environmental data and the historical infrastructure data, and the second historical joint impact index of the historical infrastructure data on the historical environmental data and the agricultural data; Based on the prediction sub-data, obtain the proportion of historical environmental data, historical agricultural data and historical infrastructure data in the corresponding control sub-area; Obtain the first impact index prediction model, the second impact index prediction model and the third impact index prediction model through the proportion of historical environmental data, the proportion of historical agricultural data, the proportion of historical infrastructure data, the first historical impact index, the second historical impact index, the first historical joint impact index and the second historical joint impact index; The first impact index prediction model, the second impact index prediction model and the third impact index prediction model are connected in series to obtain an impact index prediction stacking model; Obtain the real-time multi-dimensional data of the dynamic data pool in turn, and based on the prediction sub-data, obtain the proportion of real-time environmental data, real-time agricultural data, and real-time infrastructure data corresponding to the control sub-area; The proportion of real-time environmental data, the proportion of real-time agricultural data and the proportion of real-time infrastructure data are input into the impact index prediction stacking model to obtain the dynamic impact index output by the impact index prediction stacking model.

7. A rural digital governance and control method based on cloud platform sharing according to claim 6, characterized in that: The step of determining the decision execution parameters corresponding to the control sub-area according to the impact index prediction stacking model, the control sub-area information and the dynamic impact index specifically includes: Based on the control sub-area information, determine the control sub-area number information; According to the control sub-area number information, collect the real-time environmental data proportion, real-time agricultural data proportion and real-time infrastructure data proportion corresponding to the control sub-area number, input them into the impact index prediction stacking model, and obtain the corresponding real-time dynamic impact index; Obtain the average value of the dynamic impact index and the instant dynamic impact index to obtain the standard impact index; According to the standard impact index, the decision execution parameters corresponding to the control sub-area are determined, and the decision execution parameters include agricultural production decision parameters, environmental management decision parameters, infrastructure operation and maintenance decision parameters and comprehensive management decision parameters.

8. A rural digital governance control system based on cloud platform sharing, used to implement the control method according to any one of claims 1 to 7, characterized in that: include: Data collection and transmission module, which is used to build a wireless sensor network and deploy sensors according to the geographical characteristics of the village, collect various real-time data, process and transmit data at the same time, and can connect to external data sources to obtain supplementary data and ensure data access security; Data processing and storage module, which is used to pre-process the collected real-time data, clean abnormal values ​​and standardize them, filter and store real-time data according to rules, manage static data pools, store historical data and integrate some real-time data according to thresholds, integrate data, and associate historical data types, time and control area information; A regional division and model building module, which is used to divide the control area based on rural geographical location information, real-time agricultural data, real-time environmental data and real-time infrastructure data, obtain control sub-area information, calculate multiple historical impact indexes based on historical data association information, and build an impact index prediction stacking model for predicting dynamic impact indexes; A decision support and control execution module, which is used to determine the standard impact index based on the real-time data of the control sub-area and the impact index prediction stacking model, and then determine the decision execution parameters; The user interaction and visualization module is used to visualize various data and analysis results and provide user interaction functions.

9. According to claim 8, a rural digital governance and control system based on cloud platform sharing is characterized in that: The data processing and storage module includes: A data preprocessing unit, the data preprocessing unit is used to clean the real-time data collected by the sensor network unit; A dynamic data pool management unit, the dynamic data pool management unit is used to build and manage a dynamic data pool based on a NoSQL database, divide the real-time multidimensional data according to the timestamp information, obtain the real-time multidimensional sub-data, and further classify it into real-time agricultural sub-information, real-time environmental sub-information and real-time infrastructure sub-information, and according to the agricultural production monitoring impact index, the real-time infrastructure monitoring impact index and the minimum monitoring impact dynamic index, screen and store the real-time data that meets the requirements to the corresponding position in the dynamic data pool, and sort the real-time environmental sub-information based on the timestamp; A static data pool management unit, which is responsible for storing historical environmental data, historical agricultural data and historical infrastructure data, storing encrypted link information in the static data pool, and storing real-time data that meets the conditions in the static data pool regularly according to a set static data pool data extraction time threshold; A data integration unit, wherein the data integration unit is used to associate and integrate historical data type information according to historical time dimension information and control sub-area number information based on a data integration framework, and to determine association information between the historical time dimension information, historical data type information and control sub-area number information.

10. The rural digital governance and control system based on cloud platform sharing according to claim 8 is characterized in that: The region division and model building module includes: A regional division unit, the regional division unit is used to determine the rural latitude and longitude coordinate information, topographic information and village layout information based on the rural geographical location information, and calculate the first division coefficient, the second division coefficient and the third division coefficient in combination with the real-time agricultural data, the real-time environmental data and the real-time infrastructure data, so as to obtain the control area division index, accurately divide the control area, obtain the control sub-area information, and assign a unique number to each control sub-area; An impact index prediction model construction unit is used to calculate the first historical impact index of historical environmental data on historical agricultural data, the second historical impact index of historical environmental data on historical infrastructure data, the first historical joint impact index of historical agricultural data on historical environmental data and historical infrastructure data, and the second historical joint impact index of historical infrastructure data on historical environmental data and agricultural data based on the correlation information between historical time dimension information, historical data type information and control sub-area number information; according to the predicted sub-data, the proportion of historical environmental data, the proportion of historical agricultural data and the proportion of historical infrastructure data in the corresponding control sub-area are obtained, and a first impact index prediction model, a second impact index prediction model and a third impact index prediction model are constructed; and the first impact index prediction model, the second impact index prediction model and the third impact index prediction model are concatenated into an impact index prediction stacking model.

Images