Government affair big data governance analysis device and method
Through pre-processing and regression analysis of massive environmental protection data, regional pollution levels are generated and monitoring strategies are matched, the existing pollution monitoring efficiency is solved, efficient and intelligent analysis of pollution control is realized, and governance efficiency and policy formulation are improved. scientific nature.
Patent Information
- Application Number
- CN202411076485.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-07
- Publication Date
- 2024-12-06
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing pollution monitoring methods are low in efficiency and cannot effectively meet the processing and analysis needs of massive data, resulting in low pollution control efficiency.
By collecting environmental protection data such as air quality, water quality, soil pollution and noise, pre-processing, regression analysis and pollution level setting, combining multiple data types to generate regional pollution levels, and matching corresponding monitoring strategies to achieve efficient use of massive data Processing and analysis.
It improves the efficiency of pollution control, makes pollution analysis more intelligent, can monitor and control pollution more accurately, and improves the efficiency of public services and the scientific nature of policy formulation.
Smart Images

Figure CN119089330A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of digital data analysis, and in particular to a device and method for government big data governance and analysis. Background Art
[0002] Big data governance of government pollution refers to the use of big data technology to collect, analyze and process the massive data generated in the process of government management, so as to improve government transparency, reduce corruption, improve the efficiency of public services, and promote the scientific and accurate formulation of policies. This concept integrates information technology, data analysis and government management, and aims to optimize government processes through data-driven methods and achieve effective monitoring and governance of "pollution" information.
[0003] Existing pollution monitoring mainly relies on data collected by data monitoring sources to monitor pollution conditions in real time. This has low work efficiency and cannot meet actual needs. Summary of the invention
[0004] The purpose of the present invention is to provide a government big data governance and analysis device and method, aiming to achieve efficient processing and analysis of massive data, making urban pollution analysis more intelligent, thereby improving pollution control efficiency.
[0005] To achieve the above-mentioned purpose, in a first aspect, the present invention provides a government affairs big data governance and analysis method, including collecting environmental protection data, wherein the types of environmental protection data include air quality, water quality, soil pollution and noise;
[0006] Preprocess environmental protection data;
[0007] Regression analysis is performed on various types of preprocessed data to predict the prediction curve of the corresponding type of data;
[0008] Set the environmental pollution level for each type of data;
[0009] Match the corresponding pollution level based on the prediction curves of each type of area to be tested;
[0010] Combine the pollution levels of all data types to generate regional pollution levels;
[0011] Match the corresponding monitoring strategy based on the regional pollution level.
[0012] The specific steps of collecting environmental protection data, where the types of environmental protection data include air quality, water quality, soil pollution and noise, include:
[0013] Install air quality monitors, water quality monitors, soil pollution monitoring equipment and noise monitors at selected monitoring sites;
[0014] Start monitoring equipment to collect environmental protection data in real time at preset intervals;
[0015] Upload environmental protection data to the host computer through wireless transmission technology.
[0016] The specific steps of preprocessing the environmental protection data include:
[0017] Check for missing records or fields in environmental protection data and delete records with missing values;
[0018] Use Z-score to identify outliers in environmental protection data and delete outlier records;
[0019] Check and delete duplicate records in environmental protection data.
[0020] The specific steps of performing regression analysis on the preprocessed data of various types to predict the prediction curve of the corresponding type of data include:
[0021] Select the polynomial regression model and fit the polynomial regression model using the training set data;
[0022] Evaluate the model’s predictive accuracy on the test set;
[0023] Adjust model parameters based on evaluation results;
[0024] The final generated regression model is used to predict future time points and generate a prediction curve.
[0025] The specific steps of setting the environmental pollution level of each type of data include:
[0026] Obtain standard documents corresponding to the type of environmental protection data;
[0027] Generate multiple safety thresholds based on standard documents;
[0028] The pollution level of each data type is divided based on the safety threshold.
[0029] The specific steps of matching the corresponding pollution levels based on the prediction curves of various types of the area to be tested include:
[0030] Compare the predicted curve of each indicator with the pollution level standard;
[0031] Determine the pollution level corresponding to each indicator at each predicted time point.
[0032] The specific steps of combining the pollution levels of all data types to generate the regional pollution level include:
[0033] Set weights for each data type;
[0034] The pollution levels of each indicator at each time point are weighted and summed to obtain the comprehensive pollution value;
[0035] Match the corresponding regional pollution level based on the comprehensive pollution value.
[0036] The specific steps of matching the corresponding monitoring strategy based on the regional pollution level include:
[0037] Set corresponding monitoring strategy combinations according to different regional pollution levels;
[0038] Select the corresponding monitoring strategy from the monitoring strategy framework according to the assessed regional pollution level;
[0039] Implement the monitoring plan according to the monitoring strategy.
[0040] In a second aspect, the present invention also provides a government affairs big data governance and analysis device, including a data collection module, a preprocessing module, a prediction module, a type pollution level setting module, a type pollution level prediction module, a regional pollution level matching module and a monitoring module:
[0041] The data collection module is used to collect environmental protection data, and the types of environmental protection data include air quality, water quality, soil pollution and noise;
[0042] The preprocessing module is used to preprocess the environmental protection data;
[0043] The prediction module is used to perform regression analysis on various types of preprocessed data to predict prediction curves of corresponding types of data;
[0044] The type pollution level setting module is used to set the environmental pollution level of each type of data;
[0045] The type pollution level prediction module is used to match the corresponding pollution level based on the prediction curves of each type of the area to be tested;
[0046] The regional pollution level matching module is used to generate a regional pollution level by combining the pollution levels of all data types;
[0047] The monitoring module is used to match the corresponding monitoring strategy based on the regional pollution level.
[0048] A government big data governance and analysis device and method of the present invention collects real-time and historical data from various environmental monitoring stations, covering but not limited to air quality index (AQI), water quality indicators (such as pH value, dissolved oxygen content, chemical oxygen demand COD, etc.), soil pollution degree (heavy metal content, organic pollutants, etc.) and noise level. The data source can be a ground monitoring station, remote sensing satellite, drone, Internet of Things sensor network, etc., to ensure that the data coverage is comprehensive and updated in a timely manner. Then clean the data to remove outliers, missing values and duplicate data to ensure data quality. Then use statistical methods such as linear regression, multivariate regression or more advanced machine learning algorithms to model each type of environmental protection data and predict future trends. The prediction model outputs prediction curves for each type of data, which reflect the changing trend of environmental quality in the future. According to national or local standards, the environmental pollution level threshold of each type of data is set. For example, air quality can be divided into excellent, good, light pollution, moderate pollution, heavy pollution, etc. Each level corresponds to a certain numerical range, which is used to evaluate the pollution state of the data point. Each data point on the prediction curve is compared with the set pollution level threshold to determine the pollution level to which it belongs. This process is performed for each type of data to obtain the distribution of pollution levels of each type. The pollution levels of all data types are combined, and the comprehensive pollution level of a region is generated using weighted average, fuzzy logic or other composite evaluation methods. The comprehensive pollution level reflects the overall environmental health of a region, provides a basis for policy formulation, and automatically matches corresponding monitoring strategies based on regional pollution levels, such as increasing monitoring frequency, expanding monitoring scope, and initiating emergency response measures. This can achieve efficient processing and analysis of massive data, making urban pollution analysis more intelligent, thereby improving the efficiency of pollution control. BRIEF DESCRIPTION OF THE DRAWINGS
[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0050] Figure 1 It is a flow chart of a government big data governance and analysis method according to the first embodiment of the present invention.
[0051] Figure 2 It is a flow chart of collecting environmental protection data according to the first embodiment of the present invention, wherein the types of environmental protection data include air quality, water quality, soil pollution and noise.
[0052] Figure 3It is a flowchart of preprocessing environmental protection data according to the first embodiment of the present invention.
[0053] Figure 4 It is a flowchart of the first embodiment of the present invention for performing regression analysis on various types of preprocessed data to predict prediction curves of corresponding types of data.
[0054] Figure 5 4 is a flowchart of setting the environmental pollution level of each type of data according to the first embodiment of the present invention.
[0055] Figure 6 It is a flow chart of matching corresponding pollution levels based on prediction curves of various types of areas to be tested according to the first embodiment of the present invention.
[0056] Figure 7 It is a flow chart of generating a regional pollution level by combining the pollution levels of all data types according to the first embodiment of the present invention.
[0057] Figure 8 It is a flow chart of the monitoring strategy corresponding to the regional pollution level matching according to the first embodiment of the present invention. DETAILED DESCRIPTION
[0058] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and should not be construed as limiting the present invention.
[0059] First embodiment
[0060] See also Figures 1 to 8 The present invention provides a government affairs big data governance and analysis method, comprising:
[0061] S101 collects environmental protection data, where the types of environmental protection data include air quality, water quality, soil pollution and noise;
[0062] The specific steps include:
[0063] S201 Install air quality monitors, water quality monitors, soil pollution monitoring equipment and noise monitors at selected monitoring points;
[0064] Various advanced environmental monitoring instruments are installed at pre-determined key monitoring points, such as urban parks, industrial areas, rivers and lakes, farmland areas and residential areas. These include air quality monitors (used to detect the concentration of pollutants such as PM2.5, PM10, sulfur dioxide SO2, nitrogen oxides NOx), water quality monitors (which can measure various physical, chemical and biological indicators in water bodies), soil pollution monitoring equipment (which can analyze the type and concentration of pollutants in soil samples) and noise monitors (used to record decibel levels and evaluate the quality of the acoustic environment). These devices should have high precision, high stability and good environmental adaptability to ensure the accuracy and reliability of the data.
[0065] S202 starts the monitoring equipment to collect environmental protection data in real time at every preset period;
[0066] After starting all monitoring equipment, set a reasonable data collection frequency, such as hourly, daily or weekly, depending on the monitoring objectives and resource constraints. The equipment will automatically perform continuous monitoring and capture changes in environmental parameters in real time. In order to ensure the timeliness and consistency of the data, the power supply and operating status of the monitoring equipment should be ensured to be good, and calibration and maintenance should be performed regularly to prevent data deviation or interruption.
[0067] S203 uploads the environmental protection data to the host computer through wireless transmission technology.
[0068] The collected environmental protection data is securely transmitted to the host computer or cloud server through the built-in wireless communication module, such as Wi-Fi, Bluetooth, GPRS or dedicated wireless sensor network (WSN). This step requires ensuring encryption and integrity during data transmission to prevent data tampering or loss. The host computer software is responsible for receiving, parsing and storing the raw data from each monitoring point, while performing preliminary data quality control and preprocessing to prepare for subsequent data analysis and visualization.
[0069] S102 pre-processes environmental protection data;
[0070] The specific steps include:
[0071] S301 checks for missing records or fields in the environmental protection data, and deletes records with missing values;
[0072] Check for missing records or fields in environmental protection data, and delete records with missing values. During the data collection process, some monitoring data may be missing due to equipment failure, human error, or environmental interference. First, you need to write a script or use data processing software (such as Python's Pandas library, R language's dplyr package, etc.) to scan the entire data set and identify rows or columns containing missing values. Then, based on the proportion and importance of the missing values, decide whether to delete the entire record. If the proportion of missing values is small and the missing values are not systematic, delete them directly; if there are many missing values or key data are missing, you may need to use interpolation methods (such as mean interpolation, nearest neighbor interpolation, or regression interpolation) to fill the gaps instead of simply deleting them.
[0073] S302 uses Z-score to identify outliers in environmental protection data and deletes outlier records;
[0074] Use Z-score to identify outliers in environmental protection data and delete outlier records. Outliers are observations that deviate significantly from the normal range. They may be caused by measurement errors, data entry errors, or extreme environmental events. Calculate the Z-score for each data point (that is, the value minus the sample mean and then divided by the sample standard deviation). Generally, if the absolute value of the Z-score is greater than 3, the data point is considered an outlier. After identifying the outliers, further analyze their causes. If they are confirmed to be erroneous or unrepresentative data, they should be removed from the data set to avoid misleading subsequent analysis.
[0075] S303 checks and deletes duplicate records in the environmental protection data.
[0076] Check and delete duplicate records in environmental protection data. Duplicate records may be generated due to data import errors, repeated sampling of equipment, or problems with data processing software. The presence of duplicate data will distort statistical data, such as mean, variance, etc., thus affecting the accuracy of analysis results. Duplicate records are identified by comparing unique identifiers in the data set (such as timestamps, geographic location coordinates, etc.), and one version is selected to be retained and the rest are deleted. When dealing with large data sets, use the deduplication function of database queries or data processing software to automate this process.
[0077] S103 performs regression analysis on the various types of preprocessed data to predict prediction curves of corresponding types of data;
[0078] The specific steps include:
[0079] S401 selects a polynomial regression model and fits the polynomial regression model using training set data;
[0080] Select a polynomial regression model and fit it using the training set data. Polynomial regression allows the model to capture nonlinear relationships in the data and fit complex data forms more accurately by adding power terms of independent variables. First, the data set needs to be divided into a training set and a test set. The training set is used to build the model, while the test set is used to verify the generalization ability of the model. Using the training set data, determine the optimal coefficients of the polynomial regression equation through the least squares method or other optimization algorithms, that is, find the parameter combination that minimizes the sum of squared errors between the predicted value and the actual value.
[0081] S402 evaluates the prediction accuracy of the model on the test set;
[0082] Evaluate the prediction accuracy of the model on the test set. After the model is trained, it is necessary to verify the performance of the model on a test set that was not used in the training. This usually involves calculating the difference between the predicted value and the true value. Common evaluation indicators include mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R 2 These metrics help determine whether a model is overfitting (i.e., the model is too complex and overfits to the training data, and performs poorly on new data) or underfitting (i.e., the model is too simple and cannot capture complex patterns in the data).
[0083] S403 adjusts model parameters according to the evaluation results;
[0084] Adjust model parameters based on the evaluation results. If the model performs poorly on the test set, you may need to adjust the order of the polynomial, regularization parameters, or feature selection strategies to improve the model. This may involve multiple iterations, retraining the model and evaluating after each parameter adjustment until the best model configuration is found.
[0085] S404 uses the finally generated regression model to predict future time points and generate a prediction curve.
[0086] The resulting regression model is used to make predictions for future time points and generate prediction curves. Once the model has been fully trained and optimized, it is applied to predict values at future time points. This usually involves inputting future time points as independent variables into the model and obtaining corresponding predicted values. By connecting these predicted values, a prediction curve is generated to show the trend of data over time. Prediction curves are particularly important in fields such as environmental monitoring, economic forecasting, and market analysis, helping decision makers understand possible future trends and formulate corresponding strategies accordingly.
[0087] S104 sets the environmental pollution level of each type of data;
[0088] The specific steps include:
[0089] S501 obtains a standard file corresponding to the type of environmental protection data;
[0090] Obtain standard documents corresponding to the type of environmental protection data. This step involves collecting and organizing all relevant environmental quality standard documents, which are issued by national environmental protection departments, international organizations or professional institutions, and stipulate the allowable concentration limits of different pollutants. For example, air pollution may refer to the "Air Quality Standards"; water pollution may be based on the "Surface Water Environmental Quality Standards". Each type of pollutant has its own specific standards, covering multiple indicators such as particulate matter, sulfur dioxide, nitrogen oxides, heavy metals, organic pollutants, etc.
[0091] S502 generates multiple safety thresholds based on the standard file;
[0092] After obtaining the standard documents, it is necessary to extract key information from them and determine the safety thresholds for each monitoring data. These thresholds are usually set based on scientific evidence and risk assessments to protect human health and the ecological environment from harmful effects. Safety thresholds may include but are not limited to:
[0093] Maximum allowable concentration (MAC) is the maximum concentration of a pollutant that should not be exceeded in an environmental medium.
[0094] Daily average exposure limit (DAEL), the concentration level at which long-term exposure will not cause adverse effects on human health.
[0095] Short-term exposure limit (STEL) refers to the concentration of a pollutant at which short-term exposure will not cause acute health effects.
[0096] Background concentration, the background level of pollutants in the natural environment, can be used as a benchmark for assessing the extent of pollution.
[0097] S503 classifies the pollution level of each data type based on the safety threshold.
[0098] Once the safety thresholds are determined, environmental pollution is classified into different levels based on the comparison of monitoring data with these thresholds. Pollution levels may include "clean", "slightly polluted", "moderately polluted", "heavily polluted" and "extremely polluted", etc. The specific classification standards will be based on the characteristics of the pollutants and their potential harm to human health and ecosystems. For example, in the Air Quality Index (AQI), the value range is divided into several intervals, each corresponding to a pollution level, such as green represents good air quality, and red means that the air quality is very poor and urgent measures need to be taken to reduce exposure.
[0099] S105 matches the corresponding pollution level based on the prediction curves of each type of the area to be tested;
[0100] The specific steps include:
[0101] S601 compares the prediction curve of each indicator with the pollution level standard;
[0102] Compare the prediction curve of each indicator with the pollution level standard. In this step, we will compare the prediction curve of each environmental monitoring indicator (such as PM2.5, sulfur dioxide SO2, nitrogen oxides NOx, etc.) with the pre-set pollution level standard point by point. The prediction curve reflects the concentration of pollutants changing over time, while the pollution level standard is the pollution severity level defined according to the concentration range. By comparison, we determine in which pollution level range the concentration of the pollutant will be at a certain point in the future.
[0103] S602 determines the pollution level corresponding to each indicator at each prediction time point.
[0104] Determine the pollution level corresponding to each indicator at each forecast time point. After completing the comparison, we will record the pollution level of each monitoring indicator at each time point. For example, for a certain day's forecast, we may find that the PM2.5 concentration in the morning belongs to the light pollution level, while it rises to the moderate pollution level in the afternoon. This process helps us build a detailed pollution level time series for subsequent analysis.
[0105] S106 combines the pollution levels of all data types to generate a regional pollution level;
[0106] The specific steps include:
[0107] S701 sets a weight for each data type;
[0108] Set weights for each data type. First, we need to determine the relative importance of each pollutant's impact on overall environmental quality. This is usually based on scientific consensus and policy guidance. For example, some pollutants may be given higher weights due to their toxicity or carcinogenicity. The weights are set to reflect the potential impact of pollutants on human health, ecosystems, and climate.
[0109] S702 performs weighted summation of pollution levels of various indicators at each time point to obtain a comprehensive pollution value;
[0110] The pollution levels of each indicator at each time point are weighted and summed to obtain a comprehensive pollution value. Next, we multiply the pollution levels of all pollutants at each time point by their corresponding weights and then sum them to calculate a comprehensive pollution value. This value comprehensively considers the pollution conditions of multiple pollutants and more comprehensively reflects the overall quality of the environment.
[0111] S703 matches the corresponding regional pollution level based on the comprehensive pollution value.
[0112] The corresponding regional pollution level is matched based on the comprehensive pollution value. Finally, we compare the calculated comprehensive pollution value with the preset regional pollution level standard to determine the overall pollution level of the area at a certain point in time. This level classification may include "excellent", "lightly polluted", "moderately polluted", "heavily polluted" and "extremely heavily polluted", which helps local governments and the public understand and respond to environmental problems and take necessary preventive or mitigation measures.
[0113] S107 matches the corresponding monitoring strategy based on the regional pollution level.
[0114] The specific steps include:
[0115] S801 sets corresponding monitoring strategy combinations according to different regional pollution levels;
[0116] Set up corresponding monitoring strategy combinations according to different regional pollution levels. This step involves establishing a dynamic monitoring strategy system, in which different levels of pollution correspond to monitoring requirements of different intensities and frequencies. For example, in areas with low pollution levels, only regular routine monitoring may be required; while in areas with high pollution levels, it may be necessary to increase monitoring points, increase monitoring frequency, or even introduce more advanced monitoring technologies to obtain more accurate data. In addition, consideration should be given to initiating emergency monitoring responses under specific conditions, such as when extreme weather events are predicted or when a sudden increase in pollution levels is detected.
[0117] S802 selects a corresponding monitoring strategy from the monitoring strategy framework according to the assessed regional pollution level;
[0118] Select the corresponding monitoring strategy from the monitoring strategy framework based on the assessed regional pollution level. Once the pollution level of the region is determined, select the most appropriate monitoring plan from the pre-designed monitoring strategy framework. This may involve adjusting the layout of the monitoring network, such as adding temporary or permanent monitoring stations in pollution hotspots, or changing the monitoring frequency and items of existing stations. At the same time, it is also necessary to ensure that the selected monitoring strategy matches the existing infrastructure and technical capabilities for efficient implementation.
[0119] S803 executes the monitoring plan according to the monitoring strategy.
[0120] Execute the monitoring plan according to the monitoring strategy. After determining the specific monitoring strategy, the next step is to organize and execute the monitoring activities. This includes preparing the required equipment, arranging personnel, planning the schedule for data collection, and ensuring that all monitoring operations meet the established quality control standards. The data collected during the monitoring process will be used to continuously evaluate the regional pollution status and verify the accuracy of the prediction model. If the monitoring data shows that the actual pollution level is not in line with expectations, it may be necessary to re-evaluate the pollution level and adjust the monitoring strategy accordingly.
[0121] Second embodiment
[0122] The present invention also provides a government big data governance and analysis device, including a data collection module, a preprocessing module, a prediction module, a type pollution level setting module, a type pollution level prediction module, a regional pollution level matching module and a monitoring module: the data collection module is used to collect environmental protection data, and the types of environmental protection data include air quality, water quality, soil pollution and noise; the preprocessing module is used to preprocess the environmental protection data; the prediction module is used to perform regression analysis on various types of preprocessed data to predict prediction curves of corresponding types of data; the type pollution level setting module is used to set the environmental pollution level of each type of data; the type pollution level prediction module is used to match the corresponding pollution level based on the prediction curves of each type of the area to be tested; the regional pollution level matching module is used to generate regional pollution levels in combination with the pollution levels of all data types; the monitoring module is used to match the corresponding monitoring strategy based on the regional pollution level.
[0123] In this embodiment, the data collection module collects environmental protection data from multiple sources, which covers a wide range of environmental indicators, including but not limited to air quality (such as PM2.5, PM10 concentration), water quality (such as dissolved oxygen, chemical oxygen demand COD), soil pollution (such as heavy metal content) and noise pollution, etc. This module uses the Internet of Things (IoT) sensor network, satellite remote sensing data, ground monitoring stations and other data collection systems to ensure the comprehensiveness and real-time nature of the data.
[0124] The preprocessing module cleans and preprocesses the collected raw data to remove invalid or erroneous data points, unify the data format, and fill in missing values. This step is crucial to ensure the accuracy and reliability of subsequent data analysis.
[0125] The prediction module uses statistical and machine learning algorithms, such as linear regression, support vector machine (SVM) or deep learning, to analyze the pre-processed data and predict future trends. Each environmental indicator will generate its own prediction curve to help identify potential pollution change patterns.
[0126] The type pollution level setting module defines and sets the pollution level thresholds of different environmental indicators, which reflect different levels from slight pollution to severe pollution. For example, the air quality index (AQI) can be divided into multiple levels, each level represents a different health risk.
[0127] The type pollution level prediction module evaluates the current pollution level of each type of data based on the prediction curve and predicts the future pollution status. This module can provide early warning of possible environmental deterioration and provide a basis for taking preventive measures.
[0128] The regional pollution level matching module comprehensively considers the pollution levels of all environmental indicators and generates an overall regional pollution level. This comprehensive assessment guides the government and relevant departments to formulate more comprehensive environmental protection policies and emergency response plans.
[0129] The monitoring module intelligently matches and adjusts the corresponding monitoring strategy according to the pollution level of the region. For example, in areas with higher pollution levels, it may be necessary to increase the monitoring frequency, expand the monitoring scope, or adopt more advanced monitoring technology. The dynamic adjustment of the monitoring strategy helps to optimize resource allocation and ensure the efficiency and effectiveness of monitoring work.
[0130] This government big data governance and analysis device provides strong support for environmental management by integrating multi-source data, intelligent analysis and prediction, helping decision makers to understand environmental conditions in a timely manner, scientifically plan environmental protection measures, and improve the accuracy and response speed of environmental governance.
[0131] What is disclosed above is only a preferred embodiment of the present invention, and it certainly cannot be used to limit the scope of rights of the present invention. A person skilled in the art understands that all or part of the processes of the above embodiment and equivalent changes made according to the claims of the present invention still fall within the scope of the invention.
Claims
1. A governance and analysis method for government big data , It is characterized in that Including: collecting environmental protection data, the types of which include air quality, water quality, soil pollution and noise; Preprocess environmental protection data; Regression analysis is performed on various types of preprocessed data to predict the prediction curve of the corresponding type of data; Set the environmental pollution level for each type of data; Match the corresponding pollution level based on the prediction curves of each type of area to be tested; Combine the pollution levels of all data types to generate regional pollution levels; Match the corresponding monitoring strategy based on the regional pollution level.
2. A government affairs big data governance and analysis method as claimed in claim 1, It is characterized in that The specific steps of collecting environmental protection data, wherein the types of environmental protection data include air quality, water quality, soil pollution and noise, include: Install air quality monitors, water quality monitors, soil pollution monitoring equipment and noise monitors at selected monitoring sites; Start monitoring equipment to collect environmental protection data in real time at preset intervals; Upload environmental protection data to the host computer through wireless transmission technology.
3. A government affairs big data governance and analysis method as claimed in claim 2, It is characterized in that The specific steps of preprocessing the environmental protection data include: Check for missing records or fields in environmental protection data and delete records with missing values; Use Z-score to identify outliers in environmental protection data and delete outlier records; Check and delete duplicate records in environmental protection data.
4. A government affairs big data governance and analysis method as claimed in claim 3, It is characterized in that The specific steps of performing regression analysis on the preprocessed data of various types to predict the prediction curve of the corresponding type of data include: Select the polynomial regression model and fit the polynomial regression model using the training set data; Evaluate the model’s predictive accuracy on the test set; Adjust model parameters based on evaluation results; The final generated regression model is used to predict future time points and generate a prediction curve.
5. A government affairs big data governance and analysis method as claimed in claim 4, It is characterized in that The specific steps of setting the environmental pollution level of each type of data include: Obtain standard documents corresponding to the type of environmental protection data; Generate multiple safety thresholds based on standard documents; The pollution level of each data type is divided based on the safety threshold.
6. A government affairs big data governance and analysis method as claimed in claim 5, It is characterized in that The specific steps of matching the corresponding pollution level based on the prediction curves of various types of the area to be tested include: Compare the predicted curve of each indicator with the pollution level standard; Determine the pollution level corresponding to each indicator at each predicted time point.
7. A government affairs big data governance and analysis method as claimed in claim 6, It is characterized in that The specific steps of combining the pollution levels of all data types to generate the regional pollution level include: Set weights for each data type; The pollution levels of each indicator at each time point are weighted and summed to obtain the comprehensive pollution value; Match the corresponding regional pollution level based on the comprehensive pollution value.
8. A government affairs big data governance and analysis method as claimed in claim 7, It is characterized in that The specific steps of matching the corresponding monitoring strategy based on regional pollution levels include: Set corresponding monitoring strategy combinations according to different regional pollution levels; Select the corresponding monitoring strategy from the monitoring strategy framework according to the assessed regional pollution level; Implement the monitoring plan according to the monitoring strategy.
9. A government big data governance and analysis device, It is characterized in that It includes data collection module, preprocessing module, prediction module, type pollution level setting module, type pollution level prediction module, regional pollution level matching module and monitoring module: The data collection module is used to collect environmental protection data, and the types of environmental protection data include air quality, water quality, soil pollution and noise; The preprocessing module is used to preprocess the environmental protection data; The prediction module is used to perform regression analysis on various types of preprocessed data to predict prediction curves of corresponding types of data; The type pollution level setting module is used to set the environmental pollution level of each type of data; The type pollution level prediction module is used to match the corresponding pollution level based on the prediction curves of each type of the area to be tested; The regional pollution level matching module is used to generate a regional pollution level by combining the pollution levels of all data types; The monitoring module is used to match the corresponding monitoring strategy based on the regional pollution level.
