Digital rural visual data supervision system based on big data analysis

Abstract

The invention discloses a digital rural visual data supervision system based on big data analysis, and relates to the technical field of data analysis, and the system comprises a data collection and transmission module which is used for collecting and stably transmitting the pollution emission data of rural enterprises and families in real time; the data preprocessing and storage module is used for cleaning, compressing and locally storing the original data; the trend modeling module is used for performing time sequence analysis on historical and real-time data and generating a pollution emission trend model; the emission source tracing and positioning module is used for tracing a main pollution source and positioning a high-risk area. According to the method, the pollution emission trend can be accurately predicted, peak positioning and change trend analysis can be supported, and powerful data support is provided for a supervision department to formulate a scientific treatment strategy.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a digital village visualization data supervision system based on big data analysis. Background Art

[0002] As an important part of the social economy, the development of rural economy is accompanied by the expansion of agricultural and rural enterprise activities, but it also brings increasingly serious environmental problems, such as water pollution, air quality decline and soil degradation. In response to these problems, environmental supervision technology has gradually introduced digital tools. The application of related technologies has not only improved the efficiency of environmental data collection, but also provided strong support for decision makers.

[0003] However, most of the current technologies focus on the realization of a single function, such as monitoring, transmission or storage of pollution data, and lack comprehensive data processing and systematic analysis capabilities. In addition, many existing systems still have obvious limitations in terms of the continuity of data transmission, the processing of data anomalies, and the accuracy of pollution tracing, and cannot meet the comprehensive needs of modern rural environmental supervision. Summary of the invention

[0004] In view of the low reliability of existing methods in locating high-risk emission sources, the present invention proposes a digital village visualization data supervision system based on big data analysis.

[0005] Therefore, the problem to be solved by the present invention is how to solve the problem of unstable data transmission in weak signal areas and accurately predict the trend of pollution emissions.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions:

[0007] In the first aspect, the present invention provides a digital rural visualization data supervision system based on big data analysis, which includes a data acquisition and transmission module, including a data acquisition submodule and a data transmission submodule, for real-time acquisition and stable transmission of pollution emission data of rural enterprises and households; the data acquisition submodule monitors pollutant concentrations and environmental parameters according to a low-power sensor group; the data transmission submodule includes a multi-hop communication unit based on LPWAN technology, which is used for optimizing data transmission in weak signal areas; a data preprocessing and storage module, which is used to clean, compress and locally store raw data, including a data preprocessing submodule, which is used to clean noise in the collected data, correct abnormal data, and compress the amount of transmitted data; a local storage submodule is used to temporarily store the collected pollution The module can collect pollution emission data and support breakpoint resumption and regular synchronization; the trend modeling module is used to perform time series analysis on historical and real-time data and generate pollution emission trend models, including a data analysis submodule for extracting the main changing patterns of the data; the trend modeling submodule is used to generate a prediction model for future emission trends and support peak positioning and changing trend analysis; the emission source tracing and positioning module is used to track the main pollution sources and locate high-risk areas, including a tracing analysis submodule for combining the output data of trend modeling with geographic distribution information, and accurately identifying abnormal emission behaviors through the calculation of comprehensive abnormal factors and path weight analysis of feature maps; the spatial positioning submodule is used to combine GIS data to accurately mark the geographical locations of high-risk emission sources and display them visually.

[0008] As a preferred solution of the digital rural visualization data supervision system based on big data analysis described in the present invention, the data acquisition submodule specifically includes: initializing the sensor group, including gas sensors, water quality sensors and particulate matter sensors, through a microcontroller to complete the calibration of the sensors; loading the sensor driver, setting the sampling frequency and measurement range, and each sensor synchronously collects the air pollutant concentration, water quality indicators and particulate matter concentration according to the preset sampling period; the collected sensor raw data is converted into a digital signal through an ADC and stored in a local cache.

[0009] As a preferred solution of the digital village visual data supervision system based on big data analysis described in the present invention, the data transmission submodule specifically includes: real-time classification of nodes based on network node parameters, dividing them into high-priority nodes and low-priority nodes:

[0010]

[0011] Among them, RSSI is the signal strength of the network node, E r is the remaining energy of the network nodes, R tx is the transmission rate, E max is the maximum energy capacity of the network node, R maxis the maximum transmission rate in the network; when P ≥ P th , it is classified as a high-priority node; otherwise, it is classified as a low-priority node, where P th It divides the threshold into priorities; builds priority transmission links between nodes through multiple routing tables; adjusts the transmission path in real time according to the link stability parameter; during the transmission path optimization process, calculates the link quality parameter Q in real time link , and dynamically select the highest Q link The optimized transmission path is used to update the routing table. When sending data packets, a redundant coding mechanism based on erasure codes is introduced. The data transmission submodule groups the data packets and adds redundant check information.

[0012] As a preferred solution of the digital village visual data supervision system based on big data analysis described in the present invention, the link quality parameter Q link The calculation formula is as follows:

[0013]

[0014] Among them, RSSI avg is the average signal strength of the link, PDR is the packet delivery rate, that is, the proportion of successfully transmitted packets, PLR is the packet loss rate, Latency is the link delay, and α1~α3 are the weight coefficients of each indicator.

[0015] As a preferred solution of the digital village visualization data supervision system based on big data analysis of the present invention, the data analysis submodule specifically includes: dividing the original data into multiple spatiotemporal subsets according to the timestamp and geographical distribution characteristics of the pollution emission data; extracting frequency domain features of the spatiotemporal subsets by fast Fourier transform, calculating the main frequency components and power spectrum density, and further generating feature data; constructing the pollution factor correlation matrix C according to the extracted feature data ij :

[0016]

[0017] Among them, C ij is the linear correlation between pollution factors i and j, x i and x j is the feature data set of pollution factors i and j, where each feature data set contains the feature data in its corresponding spatiotemporal subset, Conv(x i ,x j ) The covariance of pollution factors i and j, and are the standard deviations of pollution factors i and j respectively.

[0018] As a preferred solution of the digital village visualization data supervision system based on big data analysis described in the present invention, the trend modeling submodule specifically includes: organizing the pollution factor characteristic data in chronological order into a multidimensional time series X = {x1(t), x2(t), ..., x m (t)}, where x i (t) represents the characteristic value of pollution factor i at time t, and m is the number of dimensions of the pollution factor; the time series decomposition method is used to decompose x i (t) is decomposed into the trend term T i (t) and the periodic term S i (t); based on the decomposed trend term T i (t) and the periodic term S i (t), define the multi-factor dynamic regression model:

[0019]

[0020] in, is the pollution emission value at time k predicted at time t, β0 is a constant term, β i and γ i is the regression coefficient, ε(t) is the random error term, and n is the number of contamination factors included in the regression analysis.

[0021] In a second aspect, the present invention provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, the steps of the digital rural visualization data supervision system based on big data analysis as described in the first aspect of the present invention are implemented.

[0022] In a third aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, the steps of the digital rural visualization data supervision system based on big data analysis as described in the first aspect of the present invention are implemented.

[0023] The beneficial effects of the present invention are as follows: the present invention utilizes a low-power sensor group to realize real-time monitoring of the concentrations of multiple types of pollutants and environmental parameters, and combines a multi-hop communication unit based on LPWAN technology to effectively solve the problem of unstable data transmission in weak signal areas of traditional systems, and significantly improves the continuity and reliability of data transmission; secondly, the present invention combines time series analysis with correlation mining of multi-dimensional feature data, which can not only accurately predict the trend of pollution emissions, but also support peak positioning and change trend analysis, providing strong data support for regulatory authorities to formulate scientific governance strategies, and combining source tracing analysis with GIS spatial positioning to achieve accurate positioning and real-time monitoring of high-risk pollution sources, overcoming the problem of insufficient positioning accuracy of traditional methods in complex terrain environments. Through this comprehensive and systematic design, the present invention effectively solves the problems of discontinuous data collection, low trend prediction accuracy, and insufficient reliability of pollution source positioning in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0025] Figure 1 This is the structural diagram of the digital village visualization data supervision system based on big data analysis. DETAILED DESCRIPTION

[0026] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0027] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0028] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0029] Example 1

[0030] Reference Figure 1, which is the first embodiment of the present invention, and provides a digital village visualization data supervision system based on big data analysis, such as Figure 1 As shown, including,

[0031] The data acquisition and transmission module includes a data acquisition submodule and a data transmission submodule, which are used to collect and stably transmit pollution emission data of rural enterprises and households in real time; the data acquisition submodule monitors pollutant concentrations and environmental parameters based on a low-power sensor group (such as gas sensors, water quality sensors, particulate matter sensors, etc.); the data transmission submodule includes a multi-hop communication unit based on LPWAN technology, which is used to optimize data transmission in weak signal areas to ensure data continuity and stability.

[0032] The data preprocessing and storage module includes a data preprocessing submodule and a local storage submodule, which are used to clean, compress and locally store the original data; the data preprocessing submodule is used to clean the noise in the collected data, correct abnormal data, and compress the amount of transmitted data; the local storage submodule is used to temporarily store the collected pollution emission data, and supports breakpoint resumption and regular synchronization.

[0033] The trend modeling module includes a data analysis submodule and a trend modeling submodule, which are used to perform time series analysis on historical and real-time data and generate a pollution emission trend model; the data analysis submodule is used to extract the main changing patterns of the data; the trend modeling submodule is used to generate a prediction model for future emission trends and support peak location and change trend analysis.

[0034] The emission source tracing and positioning module includes a source tracing analysis submodule and a spatial positioning submodule, which are used to track the main pollution sources and locate high-risk areas; the source tracing analysis submodule is used to combine the output data of trend modeling and geographic distribution information, and accurately identify abnormal emission behaviors through the calculation of comprehensive abnormal factors and path weight analysis of characteristic maps; the spatial positioning submodule combines GIS data to accurately mark the geographical locations of high-risk emission sources and display them visually.

[0035] Specifically, the data acquisition submodule includes:

[0036] When the system starts, the microcontroller (MCU) initializes the sensor group, including the gas sensor, water quality sensor, and particle sensor, and completes the sensor calibration.

[0037] Load the sensor driver, set the sampling frequency and measurement range, and according to the preset sampling period (such as sampling every 5 minutes), each sensor synchronously collects air pollutant concentrations (such as CO2, NOx), water quality indicators (such as pH value, dissolved oxygen) and particulate matter concentrations (such as PM2.5, PM10).

[0038] The collected raw data from the sensors are converted into digital signals through ADC (Analog-to-Digital Converter) and stored in the local cache, awaiting further processing.

[0039] Specifically, the data transmission submodule includes:

[0040] The data transmission submodule uses a built-in dynamic classification algorithm based on the signal strength RSSI of the network node and the remaining energy E of the network node. r , transmission rate R tx Nodes are graded in real time based on parameters such as QoS, and divided into high-priority nodes and low-priority nodes. Priority transmission links between nodes are constructed through multiple routing tables. The specific calculation formula is as follows:

[0041]

[0042] Among them, E max is the maximum energy capacity of the network node, R max is the maximum transmission rate in the network; when P ≥ P th , divided into high-priority nodes; otherwise, divided into low-priority nodes, where P th Assign thresholds to the priorities.

[0043] It can be seen that the introduction of a dynamic classification mechanism gives priority to nodes with stable signals and sufficient energy as transmission links through comprehensive evaluation of signal strength and energy, thus avoiding the problem of low transmission efficiency of weak signal nodes caused by traditional fixed routing tables.

[0044] Furthermore, after the routing table is constructed, the transmission unit selects high-priority nodes for priority relaying according to the transmission requirements of the target node and real-time environmental changes, and dynamically adjusts the routing path to optimize the stability of the data transmission link.

[0045] The transmission path is adjusted in real time according to link stability parameters (such as packet loss rate and delay) to ensure that the transmission link maintains high stability in weak signal environments.

[0046] During the transmission path optimization process, the link quality parameter Q is calculated in real time link :

[0047]

[0048] Among them, RSSI avg is the average signal strength of the link, PDR is the packet delivery rate, that is, the proportion of successfully transmitted packets, PLR is the packet loss rate, Latency is the link delay, α1~α3 are the weight coefficients of each indicator; and the highest Q is dynamically selected. link The transmission path is updated in the routing table.

[0049] Furthermore, when sending data packets, the optimized transmission path introduces a redundant coding mechanism based on erasure codes. The data transmission submodule groups the data packets, adds redundant check information, and adjusts the redundancy ratio R according to the link feedback information. f .

[0050] Specifically, the redundancy ratio R is dynamically adjusted according to the link feedback packet loss rate. f as follows:

[0051]

[0052] Among them, R base is the basic redundancy ratio, PLR c is the packet loss rate of the current path, PLR max is the maximum allowed packet loss rate.

[0053] It can be seen that the present invention adopts a dynamic redundancy adjustment mechanism to avoid the problem of bandwidth waste caused by the traditional fixed redundancy ratio, while improving the data transmission integrity and recovery capability in a weak signal environment.

[0054] Specifically, the local storage submodule includes:

[0055] Receive the pollution emission data transmitted from the data acquisition submodule and make preliminary classification according to the data source (such as enterprise, household) and data type (gas, water quality, particulate matter, etc.).

[0056] Parse the received pollution emission data packets and extract key parameters (such as sensor ID, timestamp, data type, concentration value, etc.); classify and store the parsed data in a temporary cache area and perform logical partitioning by data type (gas data, water quality data, etc.).

[0057] Furthermore, the integrity of the data packets is checked to ensure that there is no packet loss or error during transmission, and the correct stored data is de-redundanted and compressed to save local storage space.

[0058] Furthermore, the current storage progress is recorded regularly, including the number and transmission status of the data packet. When a breakpoint (such as network interruption) is detected, a retransmission request is sent to the data transmission submodule, and data is continued to be received based on the breakpoint position.

[0059] Specifically, the data analysis submodule includes:

[0060] First, the data analysis submodule divides the original data into multiple spatiotemporal subsets based on the pollution emission data provided by the local storage submodule and according to the timestamp and geographical distribution characteristics of the pollution emission data.

[0061] For the spatiotemporal subsets, fast Fourier transform (FFT) is used to extract frequency domain features, calculate the main frequency components and power spectrum density, and further generate characteristic data, including mean, variance, and rate of change.

[0062] Furthermore, based on the historical pollution emission database, anomaly detection is performed on the spatiotemporal subsets of feature extraction. The standardized residual is calculated. When the residual exceeds the adaptive threshold, it is judged as an outlier, and the possible true value is predicted through a multidimensional regression model. The determined abnormal data enters the anomaly analysis queue for further classification and tracing.

[0063] The correction and classification results of feature data by data anomaly detection directly affect the factor selection of association analysis, ensuring the robustness of correlation analysis.

[0064] Furthermore, based on the extracted feature data, the pollution factor correlation matrix C is constructed. ij :

[0065]

[0066] Among them, C ij is the linear correlation between pollution factors i and j, x i and x j is the characteristic data set of pollution factors i and j, where each x i Contains the feature data in its corresponding space-time subset, Cov(x i ,x j ) The covariance of pollution factors i and j, and are the standard deviations of pollution factors i and j respectively.

[0067] It should be noted that the introduction of the pollution factor correlation matrix provides a multi-dimensional and dynamic factor analysis basis for trend modeling and tracing.

[0068] Specifically, the trend modeling submodule includes:

[0069] Using the feature data (such as mean, variance, and rate of change) extracted by the data analysis submodule as input, the specific steps are as follows:

[0070] The pollution factor characteristic data are organized in chronological order into a multidimensional time series X = {x1(t), x2(t(,..., x m (t)}, where x i (t) represents the characteristic value of pollution factor i at time t, and m is the number of dimensions of the pollution factor;

[0071] Use the time series decomposition method to convert x i (t) is decomposed into the trend term Ti (t) and the periodic term S i (t).

[0072] Based on the decomposed trend term T i (t) and the periodic term S i (t), define the multi-factor dynamic regression model:

[0073]

[0074] in, is the pollution emission value at time k predicted at time t, β0 is a constant term, β i and γ i is the regression coefficient, ε(t) is the random error term, and n is the number of contamination factors included in the regression analysis;

[0075] According to the correlation matrix C ij , screen highly correlated pollution factors as regression model input.

[0076] Optionally, a dynamic weight adjustment mechanism is set to perform online optimization of the model's weight parameters according to the environmental characteristics of real-time data collection.

[0077] Furthermore, the pollution factor is z-score standardized using the mean of the time series to obtain z i (t), if |z i (t)|>T z , generally T z =3, then the x i (t) is regarded as an outlier.

[0078] Specifically, the traceability analysis submodule includes:

[0079] Preferably, the real-time pollution factor characteristic value x is integrated i (t), correlation matrix C ij , construct a feature association graph G = (V, E), where V represents the pollution factor node and E represents the association relationship; perform cluster analysis on the feature graph to identify high-correlation factor groups.

[0080] Furthermore, the output of the trend modeling submodule and the geographical distribution information are combined to define the comprehensive anomaly factor:

[0081] A i (t)=w1|Z t |+w2d s

[0082]

[0083] Among them, Z tis the time series residual (calculated by the dynamic regression model), w1 and w2 are weight coefficients used to balance the contribution of time and space information, d s is the spatial location distance weight, reflecting the geographical relationship between the node and the pollution source, r is the adjustment parameter, d is the actual distance between the node and the suspected pollution source, and d min is the shortest distance.

[0084] By integrating the abnormal factors and combining the path information of the feature map, the path weight is redefined according to the weighted average calculation. According to the path weight, the path with the largest weight is selected, and the node with the highest weight is marked as a suspected pollution source.

[0085] This embodiment also provides a computer device, which is suitable for the digital village visualization data supervision system based on big data analysis, including a memory and a processor; the memory is used to store computer executable instructions, and the processor is used to execute computer executable instructions to realize the digital village visualization data supervision system based on big data analysis as proposed in the above embodiment.

[0086] The computer device may be a terminal, and the computer device includes a processor, a memory, a communication interface, a display screen and an input device connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, an operator network, NFC (near field communication) or other technologies. The display screen of the computer device may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device may be a touch layer covering the display screen, or a key, trackball or touchpad provided on the housing of the computer device, or an external keyboard, touchpad or mouse, etc.

[0087] This embodiment also provides a storage medium on which a computer program is stored. When the program is executed by a processor, a digital village visualization data supervision system based on big data analysis as proposed in the above embodiment is implemented.

[0088] In summary, the present invention uses a low-power sensor group to achieve real-time monitoring of multiple types of pollutant concentrations and environmental parameters, and combines a multi-hop communication unit based on LPWAN technology to effectively solve the problem of unstable data transmission in weak signal areas of traditional systems, and significantly improves the continuity and reliability of data transmission; secondly, the present invention combines time series analysis with correlation mining of multi-dimensional feature data, which can not only accurately predict pollution emission trends, but also support peak positioning and change trend analysis, providing strong data support for regulatory authorities to formulate scientific governance strategies, and combining source tracing analysis with GIS spatial positioning to achieve accurate positioning and real-time monitoring of high-risk pollution sources, overcoming the problem of insufficient positioning accuracy of traditional methods in complex terrain environments. Through this comprehensive and systematic design, the present invention effectively solves the problems of discontinuous data collection, low trend prediction accuracy, and insufficient reliability of pollution source positioning in the prior art.

[0089] Example 2

[0090] The second embodiment of the present invention provides a digital village visual data supervision system based on big data analysis. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through simulation experiments.

[0091] This embodiment conducts a two-week monitoring experiment on the pollution emissions of rural enterprises and households in a certain area. The experiment covers 10 pilot sites, including 4 rural factories (A1, A2, A3, A4) and 6 households (H1, H2, H3, H4, H5, H6). The monitoring equipment includes gas sensors (monitoring CO2 and NOx concentrations, unit: ppm), water quality sensors (monitoring dissolved oxygen DO and pH value, unit: mg / L and dimensionless) and particulate matter sensors (monitoring PM2.5 concentration, unit: μg / m 3 )'s low-power sensor group.

[0092] At the beginning of the experiment, each sensor device is calibrated, and the sampling frequency and threshold value are set (such as the CO2 alarm threshold is set to 1000ppm). The sensor at each sampling point is connected to the data acquisition submodule through a microcontroller. The data transmission submodule uses LPWAN technology to optimize the transmission efficiency in weak signal areas to ensure that the data is uploaded to the local storage module in real time and stably. The storage module regularly denoises and compresses the data, and ensures data integrity based on the breakpoint resume mechanism.

[0093] The data analysis module uses fast Fourier transform (FFT) to extract the frequency characteristics of pollution factors based on the collected spatiotemporal data, and predicts future trends through a multi-factor dynamic regression model. Combined with GIS geographic data, the source tracing analysis module locates high-risk emission sources and analyzes abnormal emission behaviors through a comprehensive abnormal factor model, ultimately generating emission source tracing paths and location markers.

[0094] It can be seen from the experiment that the dynamic classification algorithm and multi-hop communication mechanism of the system of the present invention effectively solve the problem of data transmission loss in the traditional system under weak signal environment.

[0095] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A digital rural visual data supervision system based on big data analysis, characterized by: include: The data collection and transmission module includes a data collection submodule and a data transmission submodule, which is used to collect and stably transmit the pollution emission data of rural enterprises and households in real time; The data acquisition submodule monitors pollutant concentration and environmental parameters based on the low-power sensor group; The data transmission submodule includes a multi-hop communication unit based on LPWAN technology for optimizing data transmission in weak signal areas; The data preprocessing and storage module is used to clean, compress and locally store the raw data, including a data preprocessing submodule, which is used to clean the noise in the collected data, correct abnormal data, and compress the amount of transmitted data; The local storage submodule is used to temporarily store the collected pollution emission data and supports breakpoint resuming and regular synchronization; The trend modeling module is used to perform time series analysis on historical and real-time data and generate pollution emission trend models, including a data analysis submodule to extract the main change patterns of the data; trend The modeling submodule is used to generate a prediction model for future emission trends and support peak location and change trend analysis; The emission source tracing and location module is used to track the main pollution sources and locate high-risk areas, including the source tracing analysis submodule, which is used to compare units and emission correlation analysis based on historical data, and identify abnormal emission behavior by comparing real-time data with historical trends; The spatial positioning submodule is used to combine GIS data to accurately mark the geographical locations of high-risk emission sources and display them visually.

2. The digital village visualization data supervision system based on big data analysis according to claim 1 is characterized by: The data acquisition submodule specifically includes: Initialize the sensor group, including gas sensor, water quality sensor and particle sensor, through the microcontroller and complete the sensor calibration; Load the sensor driver, set the sampling frequency and measurement range, and use each sensor to synchronously collect air pollutant concentrations, water quality indicators, and particulate matter concentrations according to the preset sampling period; The collected raw data from the sensor is converted into digital signals through ADC and stored in the local cache.

3. The digital village visual data supervision system based on big data analysis as claimed in claim 2 is characterized by: The data transmission submodule specifically includes: Nodes are graded in real time based on network node parameters and divided into high-priority nodes and low-priority nodes: Among them, RSSI is the signal strength of the network node, E r is the remaining energy of the network nodes, R tx is the transmission rate, E max is the maximum energy capacity of the network node, R max is the maximum transmission rate in the network; When P ≥ P th , it is classified as a high-priority node; otherwise, it is classified as a low-priority node, where P th Assign thresholds for priority; And build priority transmission links between nodes through multiple routing tables; The transmission path is adjusted in real time according to the link stability parameter. During the transmission path optimization process, the link quality parameter Q is calculated in real time. link , and dynamically select the highest Q link Transmission path, update routing table; The optimized transmission path introduces a redundant coding mechanism based on erasure codes when sending data packets. The data transmission submodule groups the data packets and adds redundant check information.

4. The digital village visual data supervision system based on big data analysis as claimed in claim 3 is characterized by: The link quality parameter Q link The calculation formula is as follows: Among them, RSSI avg is the average signal strength of the link, PDR is the packet delivery rate, that is, the proportion of successfully transmitted packets, PLR is the packet loss rate, Latency is the link delay, and α1~α3 are the weight coefficients of each indicator.

5. The digital village visual data supervision system based on big data analysis as claimed in claim 4 is characterized by: The data analysis submodule specifically includes: According to the timestamp and geographical distribution characteristics of pollution emission data, the original data is divided into multiple spatiotemporal subsets; For the spatiotemporal subset, fast Fourier transform is used to extract frequency domain features, calculate main frequency components and power spectrum density, and further generate feature data; According to the extracted characteristic data, the pollution factor correlation matrix C is constructed. ij : Among them, C ij is the linear correlation between pollution factors i and j, x i and x j is the characteristic data set of pollution factors i and j, where each characteristic data set contains the characteristic data in its corresponding spatiotemporal subset, Cov(x i , x j ) The covariance of pollution factors i and j, and are the standard deviations of pollution factors i and j respectively.

6. The digital village visual data supervision system based on big data analysis as claimed in claim 5 is characterized by: The trend modeling submodule specifically includes: The pollution factor characteristic data are organized in chronological order into a multidimensional time series X = {x1(t), x2(t), ..., x m (t)}, where x i (t) represents the characteristic value of pollution factor i at time t, and m is the number of dimensions of the pollution factor; Use the time series decomposition method to convert x i (t) is decomposed into the trend term T i (t) and the periodic term S i (t); Based on the decomposed trend term T i (t) and the periodic term S i (t), define the multi-factor dynamic regression model: in, is the pollution emission value at time k predicted at time t, β0 is a constant term, β i and γ i is the regression coefficient, ε(t) is the random error term, and n is the number of contamination factors included in the regression analysis.

7. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the digital village visualization data supervision system based on big data analysis are implemented as described in any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the digital village visualization data supervision system based on big data analysis described in any one of claims 1 to 6 are implemented.

Images