Natural resource intelligent monitoring integrated system and method

Abstract

The invention relates to the technical field of intelligent monitoring integrated systems, in particular to a natural resource intelligent monitoring integrated system and method, and the system comprises a resource monitoring information collection module; the resource monitoring information judgment module is used for progressively carrying out data anomaly detection, offset correction and data fusion on the basis of the multi-dimensional monitoring data acquired by the resource monitoring information acquisition module; the information modification module is connected with the resource monitoring information judgment module and is used for performing feedback adjustment on the abnormal data output by the judgment module; the resource monitoring information feedback module is used for obtaining a feedback result output by the information modification module and feeding back the feedback result to the user terminal; and the information storage module is used for storing the multi-level data correction result output by the resource monitoring information judgment module, constructing a closed-loop monitoring process from data acquisition to data feedback, and performing refined detection, correction, feedback and output on abnormal data, so that the detection accuracy, the correction precision and the output smoothness of the system are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring integrated systems, and more specifically, to a natural resource intelligent monitoring integrated system and method. Background Art

[0002] With the increasing demand for natural resource and environmental monitoring, various monitoring technologies and systems have also developed rapidly. In existing natural resource monitoring systems, multiple sensors and data acquisition devices are usually relied on to record various parameters in the environment, such as water quality, air quality, soil temperature and humidity, etc. By collecting and analyzing these parameters, governments and enterprises can achieve real-time control of environmental conditions. However, most of the current monitoring systems have significant deficiencies in data anomaly detection, correction processing, and the smoothness and consistency of the final data. Especially when the data volatility is large and abnormal data occurs frequently, the defects of traditional methods are particularly obvious.

[0003] The existing technologies usually use simple threshold detection or mean-based deviation correction methods to deal with anomalies in collected data. These methods often show obvious limitations when faced with complex natural resource monitoring environments. First, the threshold detection method has low sensitivity to data fluctuations and is prone to omissions or false alarms, resulting in low anomaly detection accuracy. At the same time, the mean correction method only performs a simple linear repair on the data and cannot effectively handle complex anomalies in multidimensional data, especially when encountering nonlinear deviations in the natural environment. The correction effect of this method is relatively limited. In addition, when dealing with multi-level data corrections, the existing technologies are difficult to avoid the problems of computational redundancy and efficiency bottlenecks, resulting in a lag in system response speed and difficulty in adapting to the needs of real-time monitoring.

[0004] Specifically, data correction in traditional methods often lacks an adaptive adjustment mechanism, making it difficult to achieve rapid and accurate correction for data with large deviations, while over-correction is prone to occur for data with small deviations, which in turn affects the authenticity of the data. The lack of a dynamic feedback mechanism also makes these methods lack effective closed-loop control between anomaly detection and correction, which ultimately leads to insufficient stability and consistency of data output. At the same time, the existing mean filter or weighted average filter model has limitations in smoothing processing, making it difficult to effectively eliminate residual noise, resulting in poor smoothness and consistency of the final data, which cannot meet high-precision monitoring requirements. In addition, traditional systems usually lack a collaborative optimization mechanism between modules, resulting in a lack of effectiveness in the transmission of data between different processing stages, and prone to data loss or incomplete information. For large-scale natural resource monitoring tasks, this lack of collaborative module design obviously cannot support the real-time monitoring needs of multi-dimensional data.

[0005] Based on the above background, the main technical problems in the existing natural resource monitoring system can be summarized as follows: First, the existing anomaly detection methods are not sensitive enough when facing complex and multi-dimensional data, resulting in a high rate of missed detection or false detection; second, the existing deviation correction methods are mostly static linear models, which are difficult to adapt to the correction needs of nonlinear and multi-level data; third, the data smoothing processing methods in the existing technology cannot effectively eliminate noise, and the smoothness and consistency of the final output data are poor; fourth, the existing monitoring system lacks collaborative optimization between modules, resulting in low overall system response efficiency and difficulty in meeting real-time requirements. In summary, the limitations of existing technologies in data detection, correction and balanced processing make them less practical and adaptable in multi-dimensional natural resource monitoring environments. A new intelligent monitoring system is urgently needed to overcome these bottlenecks. Summary of the invention

[0006] In view of the limitations of the prior art, the present invention proposes a natural resource intelligent monitoring integrated system and method to solve the above technical problems.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0008] A natural resource intelligent monitoring integrated system, comprising:

[0009] Resource monitoring information collection module, used to obtain multi-dimensional monitoring data of natural resources;

[0010] A resource monitoring information judgment module, which progressively performs data anomaly detection, offset correction and data fusion based on the multi-dimensional monitoring data obtained by the resource monitoring information collection module;

[0011] An information modification module, connected to the resource monitoring information judgment module, for performing feedback adjustment on the abnormal data output by the judgment module;

[0012] A resource monitoring information feedback module, used to obtain the feedback result output by the information modification module and feed it back to the user terminal;

[0013] The information storage module is used to store the multi-level data correction results output by the resource monitoring information judgment module to facilitate subsequent query and management.

[0014] Preferably, the resource monitoring information judgment module includes a hyperbolic-logarithmic abnormal offset detection model for detecting data deviation, and the hyperbolic-logarithmic abnormal offset detection model obtains the offset value O i ,in:

[0015]

[0016] Among them, O i is the offset of sample i, Xi is the observed value of sample i, S is the preset standard value, and λ is the hyperbolic stretching coefficient, which is used to adjust the stretching effect of the hyperbolic function; the hyperbolic-logarithmic anomaly offset detection model uses the hyperbolic-logarithmic relationship to detect the initial deviation of the data, realizes the initial anomaly identification of multidimensional data, and outputs the obtained offset to the next step of offset correction.

[0017] Preferably, the resource monitoring information judgment module further includes an inverse hypergeometric adaptive offset correction model for correcting the offset, based on the offset O output by the hyperbolic-logarithmic abnormal offset detection model. i Get the correction data ΔX i ,in:

[0018]

[0019] Where ΔX i is the corrected sample i data, X i is the original sample i data, O i is the offset of sample i, η is the adaptive adjustment coefficient, and μ is the offset index, which is used to control the correction strength; the inverse hypergeometric adaptive offset correction model gradually reduces the data deviation based on the dynamic adjustment characteristics of the inverse hypergeometric function, so that the corrected data is output to the next step of frequency mapping processing.

[0020] Preferably, the resource monitoring information judgment module further includes a multivariate nested segmented Fourier mapping model for correcting the data ΔX output based on the inverse hypergeometric adaptive offset correction model. i Get the data X after Fourier mapping i ',in:

[0021]

[0022] Among them, X′ i is the data after Fourier mapping, a k and b k is the Fourier coefficient, T is the data period parameter, and N is the highest order of the Fourier series; the multivariate nested segmented Fourier mapping model reconstructs the corrected data in the frequency domain, extracts the periodic features in the data, and further eliminates the periodic error. The Fourier mapped data is output to the next step of feedback optimization.

[0023] Preferably, the resource monitoring information judgment module further includes a fractal dimension weighted Carter mapping feedback model for outputting Fourier mapping data X′ based on the multivariate nested segmented Fourier mapping model. i Get feedback data X″ i ,in:

[0024] Xi ″=α·X i ′+β·d f ·(1-tanh(O i ))

[0025] Among them, X″ i is the data after feedback, X′ i is the data after Fourier mapping, α is the data retention coefficient, β is the feedback adjustment coefficient, d f is the fractal dimension, which is used to characterize the complexity of data. i ) is a hyperbolic tangent function that suppresses deviation; the fractal dimension weighted Carter mapping feedback model is based on the description of data complexity by fractal dimension and realizes dynamic correction of data through feedback optimization.

[0026] Preferably, the resource monitoring information judgment module further includes a composite adaptive resonant state-perturbation equalization filter model for outputting feedback data X″ based on the fractal dimension weighted Carter mapping feedback model. i Get the final output data in:

[0027]

[0028] in, is the final output data, X″ i is the feedback data, ∈ is the perturbation parameter, θ i is the resonance angle; the composite adaptive resonance state-perturbation equalization filter model processes the final output data through the resonance state-perturbation mechanism equalization, eliminates noise and errors, and realizes stable output of data.

[0029] Preferably, the information modification module receives output data from the resource monitoring information judgment module, is used to perform secondary correction on the abnormal data according to the feedback result, and transmits the corrected data to the resource monitoring information feedback module.

[0030] Preferably, the resource monitoring information feedback module feeds back final monitoring information to the user terminal based on the data results output by the information modification module, and the feedback information includes the final corrected data and anomaly detection report.

[0031] Preferably, the information storage module is used to classify and store the final corrected monitoring data to facilitate subsequent query and data analysis.

[0032] According to the monitoring integration method of the natural resource intelligent monitoring integration system, the following steps are included:

[0033] Obtain multi-dimensional monitoring data of natural resources based on resource monitoring information collection module;

[0034] The acquired monitoring data are preliminarily identified for anomalies using a hyperbolic-logarithmic anomaly shift detection model;

[0035] The inverse hypergeometric adaptive offset correction model is used to correct the offset of abnormal data;

[0036] The frequency domain reconstruction of the corrected data is performed through a multivariate nested piecewise Fourier mapping model;

[0037] Feedback optimization is performed using fractal dimension weighted Carter mapping feedback model;

[0038] The feedback data is equalized by a composite adaptive resonant state-perturbation equalization filter model to obtain the final output data;

[0039] Perform secondary correction on abnormal data through information modification module;

[0040] Feedback the final revised data to the user based on the resource monitoring information feedback module;

[0041] The final corrected monitoring data is stored in the information storage module for subsequent query and analysis.

[0042] Compared with the prior art, the beneficial effects of the present invention are embodied in the following aspects:

[0043] The system of the present invention constructs a closed-loop monitoring process from data collection to data feedback through the collaborative work of the resource monitoring information collection module, the resource monitoring information judgment module, the information modification module, the resource monitoring information feedback module and the information storage module. The system designs a multi-layer progressive innovative algorithm system to perform refined detection, correction, feedback and output for abnormal data, significantly improving the detection accuracy, correction precision and output smoothness of the system.

[0044] Specifically, the present invention can accurately identify abnormal data in the data collection stage by constructing a hyperbolic-logarithmic abnormal offset detection model in the resource monitoring information judgment module, and dynamically adjust the sensitivity of offset detection according to the joint effect of hyperbolic and logarithmic functions, thereby ensuring the detection reliability in complex environments. Then, the inverse hypergeometric adaptive offset correction model performs adaptive correction on the deviation data, and by introducing hypergeometric functions, the data can quickly approach the standard value and adapt to nonlinear and highly complex environmental data. In addition, the frequency decomposition and reconstruction of the data are realized through the multivariate nested segmented Fourier mapping model, high-frequency noise is eliminated, and the periodic characteristics of the data are extracted, so that the data maintains high smoothness and consistency after multi-layer correction. Next, the fractal dimension weighted Carter mapping feedback model uses the fractal dimension of the data to perform feedback weighting processing, and performs refined feedback adjustment on highly complex data to ensure that the feedback effect of the system is more dynamically adaptable. Finally, the feedback result is smoothed by the composite adaptive resonant state-perturbation equalization filter model to eliminate the residual tiny noise of the data after multi-layer processing, so that the output data has higher stability and smoothness.

[0045] From the overall perspective of the system architecture, the modules of the present invention are closely connected to each other to form a synergistic closed-loop structure. After collection, the data is processed by the judgment module, and then enters the feedback correction module for closed-loop feedback. Finally, the smoothed data is fed back to the user and stored in the information storage module. Through the data flow transmission between modules, the present invention effectively avoids the problem of information loss. The functional design of each module complements each other, so that the detection, correction and feedback links are complementary and superimposed, which significantly improves the overall response speed and data processing accuracy of the system.

[0046] Therefore, the present invention solves the problems of insensitive abnormal data detection, inaccurate deviation correction, uneven output data and lack of inter-module coordination in existing monitoring systems through innovative data detection and correction algorithms. It can realize efficient and accurate intelligent monitoring in complex natural resource monitoring environments and provide a reliable foundation for real-time monitoring and subsequent data analysis. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flowchart of the overall system of the present invention.

[0048] Figure 2 It is a detailed flow chart of the resource monitoring information judgment module of the present invention.

[0049] Figure 3 It is a closed-loop feedback flow chart of the information modification module of the present invention.

[0050] Figure 4 This is a flow chart of resource monitoring information feedback and storage in the present invention. DETAILED DESCRIPTION

[0051] The scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. The embodiments in the present invention and all other embodiments obtained by ordinary persons in the art without making creative work are within the scope of protection of the present invention.

[0052] Example 1

[0053] like Figure 1-4 As shown, the present invention relates to a natural resource intelligent monitoring integrated system and method, which mainly includes a resource monitoring information collection module 1, a resource monitoring information judgment module 2, an information modification module 3, a resource monitoring information feedback module 4 and an information storage module 5. The modules work together to ensure that natural resource information can achieve efficient abnormal data processing and dynamic data correction in the collection, judgment, correction and feedback links, with strong adaptability and accuracy, and meet the natural resource monitoring needs in different scenarios.

[0054] Preferably, in one embodiment of the present invention, a natural resource intelligent monitoring integrated system of the present invention includes a resource monitoring information acquisition module 1, which is mainly used to obtain multi-dimensional monitoring data of natural resources. The acquisition module may include multiple terminal devices (such as sensors, monitors, etc.) to collect data on water quality, air, soil, etc. in the natural resource environment. The collected data is transmitted to the resource monitoring information judgment module 2, and the resource monitoring information judgment module 2 progressively performs data anomaly detection, offset correction and data fusion processing based on the collected multi-dimensional monitoring data. This module can detect in real time whether the collected data meets the preset standards, thereby screening out abnormal data that needs further processing.

[0055] The abnormal data output by the judgment module 2 will be transmitted to the information modification module 3 for feedback adjustment; the function of the information modification module 3 is to further adjust the abnormal data according to the feedback results, so that the data is more in line with the actual situation and the deviation is reduced. Then, the data is fed back to the user terminal through the resource monitoring information feedback module 4 to form a closed loop of the data flow. The data report provided by the feedback module can be used as a reference for users to understand the status of natural resources in real time. Finally, the information storage module 5 stores the final data results in categories for future query and analysis. This classified storage facilitates system management and is also conducive to the efficient retrieval and use of data during the monitoring process.

[0056] Preferably, in one embodiment of the present invention, the resource monitoring information judgment module 2 adopts a hyperbolic-logarithmic anomaly offset detection model, which is intended to identify nonlinear anomalies in natural resource monitoring data. The model uses a combination of hyperbolic and logarithmic functions to sensitively capture small deviations in the data to ensure the accuracy of detection. The offset value O obtained by the model calculation i The formula is as follows:

[0057]

[0058] Among them, O i is the offset of sample i, X i is the observed value of sample i, S is the corresponding preset standard value, and λ is the hyperbolic stretch coefficient used to adjust the stretching effect of the hyperbolic function. Through this model, the system can quickly determine which data deviates from the preset standard value, which is particularly suitable for detecting natural resource information with complex environments and large data fluctuations. Preferably, the offset threshold can be set to an empirical value O i >0.5, that is, the monitoring data with an offset exceeding 0.5 will be identified as abnormal data. This threshold can be adjusted according to the discrete degree and error tolerance of the specific environmental data. i It will serve as input for subsequent correction steps.

[0059] Preferably, in one embodiment of the present invention, the resource monitoring information determination module 2 further includes an inverse hypergeometric adaptive offset correction model. The model is based on the offset O obtained in the hyperbolic-logarithmic abnormal offset detection model. i , and adaptively correct the offset to ensure that the abnormal data can better approach the preset standard. The correction formula of the inverse hypergeometric model is:

[0060]

[0061] Where ΔX i is the corrected sample i data, X i is the original sample i data, O i is the offset of sample i, ηη is the adaptive adjustment coefficient, preferably set to 0.8, so as to gradually approach the standard during the correction process; μ is the offset index, usually set to 1.2 to adapt to the complexity of natural resource data. Through this model, the system adaptively adjusts the correction amplitude according to the offset size, so that the data gradually approaches the standard value. The inverse hypergeometric correction mechanism can converge quickly when the data deviation is large, and provide smooth correction when the deviation is small, avoiding the shock effect caused by over-adjustment. The corrected data ΔX i It is passed to the multivariate nested piecewise Fourier mapping model for subsequent processing.

[0062] Preferably, in one embodiment of the present invention, the resource monitoring information determination module 2 further includes a multivariate nested segmented Fourier mapping model for determining the resource monitoring information based on the correction data ΔX i Perform frequency decomposition and reconstruction to capture the periodic characteristics in the data. The purpose of Fourier mapping is to extract the potential periodic deviation of abnormal data from the frequency domain perspective and reduce high-frequency noise by multivariate segmented Fourier processing of the data. This will achieve further smoothing and correction of the data. The Fourier mapping formula is as follows:

[0063]

[0064] Among them, X′ i is the data after Fourier mapping, a k and b k are Fourier coefficients, representing the weight of each frequency component; T is the period parameter of the data, which is usually set according to the stability of the monitoring period, preferably set to 24 hours or longer to meet the needs of different monitoring scenarios; N is the highest order of the Fourier series, preferably set to 5 to ensure a balance between computational efficiency and accuracy. The segmented Fourier mapping model preserves the frequency domain characteristics of the corrected data while removing the high-frequency noise of the abnormal data, providing accurate data input for subsequent feedback optimization.

[0065] Preferably, in one embodiment of the present invention, the resource monitoring information judgment module 2 further includes a fractal dimension weighted Carter mapping feedback model. The model uses fractal dimension to weight the complexity of multidimensional data, so that different data dimensions obtain different weights in the feedback, and can realize feedback correction in a refined manner. The fractal weighted model of Carter mapping is:

[0066] X i ″=α·X i ′+β·d f ·(1-tanh(O i ))

[0067] Among them, X″ i is the data after feedback, X′ i is the data after Fourier mapping, α is the data retention coefficient, preferably set to 0.9, used to maintain the original characteristics of the modified data in the feedback; β is the feedback adjustment coefficient, preferably set to 0.1, so as to apply appropriate correction in the feedback optimization; d f is the fractal dimension, which reflects the complexity of the sample and is usually set between 1.5 and 2 to match the complexity of natural resource monitoring data; tanh(O i) is a hyperbolic tangent function, which can suppress the extreme value of the deviation. The fractal dimension weighted model combines the feedback characteristics of Carter mapping and fractal theory. In the feedback process, it can provide stronger feedback correction for highly complex data, realize dynamic regulation and smooth transition of abnormal data, and provide reliable data input for subsequent output.

[0068] The integrated system and method for intelligent monitoring of natural resources of the present invention adopts a multi-layer progressive innovative algorithm model, which effectively improves the ability of data anomaly identification, deviation correction and frequency domain feature extraction, so that the system can achieve efficient and accurate data processing and feedback in a complex and changeable natural resource monitoring environment. Each module and algorithm link described in the present invention is interconnected with specific functional modules, from collection to judgment to feedback, to achieve a complete data flow, ensuring that the final output data can stably and reliably reflect the natural resource monitoring situation.

[0069] Preferably, in one embodiment of the present invention, the resource monitoring information judgment module 2 further includes a composite adaptive resonance state-perturbation equalization filter model, which is specifically used to perform final equalization processing on the feedback data \(X_i”\). The model achieves noise elimination and subtle correction of the data through a resonance state perturbation mechanism, thereby outputting smooth and stable data as the final result.

[0070] The specific formula of the composite adaptive resonant state-perturbation equalization filter is:

[0071]

[0072] in, is the final corrected data, X″ i is the data after feedback, ∈ is the perturbation parameter, which is used to introduce a subtle oscillation balance effect, preferably set between 0.001-0.01 to ensure the smoothness of data output; θ i is the resonance angle, which represents the phase angle of the data. The direction and frequency of the perturbation can be controlled by appropriate phase adjustment. The main purpose of this model design is to further eliminate the accumulated errors caused by multi-level data processing before outputting the data, to ensure that the final output data has high stability and meets the accuracy requirements of the natural resource monitoring system. Especially in complex environmental data, this model can effectively reduce the impact of noise and is suitable for long-term data monitoring.

[0073] Preferably, in one embodiment of the present invention, the information modification module 3 receives the feedback result data from the resource monitoring information judgment module 2, and performs secondary correction on the data according to the feedback result. Specifically, the information modification module 3 and the judgment module 2 form a closed-loop feedback structure to achieve readjustment of abnormal data. This secondary correction mechanism is of great significance in the present invention because it provides a fault-tolerant mechanism to ensure that the system can adapt to the natural resource monitoring environment with high real-time requirements.

[0074] For example, when there is a sudden change in the environmental monitoring data (such as sudden pollutants or abnormal climatic conditions), the secondary correction process can make the data more accurately reflect the actual environmental changes, avoiding the accumulation of data deviations in a single correction mode. Preferably, the feedback adjustment parameter in the information modification module 3 can be set to a low value, such as 0.1-0.3, to ensure that the data fluctuations in the secondary correction process are within a controllable range. After the modified data is fed back, it is transmitted to the resource monitoring information feedback module 4 for further feedback to the user terminal. The closed-loop feedback adjustment mechanism improves the stability and response speed of the system, and helps to improve the timeliness and accuracy of the data.

[0075] Preferably, in one embodiment of the present invention, the resource monitoring information feedback module 4 is used to feed back the data processed by the information modification module 3 to the user terminal. The main function of the feedback module 4 is to form a visual report or data result of the data that has undergone multiple layers of correction and final filtering, so that users can quickly understand the current status of the monitored natural resources. Specifically, the feedback information includes the final corrected data and the anomaly detection report. The anomaly detection report records in detail the reasons, correction process and correction results of each data correction, so that users can verify the rationality and effectiveness of the data correction.

[0076] Preferably, in one embodiment of the present invention, the feedback module 4 displays the data in the form of a chart, and indicates the data offset, correction parameters and the effect of each layer of algorithm in the anomaly detection report. The feedback report can also generate a historical data curve to track the long-term trend of natural resource data. This module is designed to improve the user experience, so that the monitoring data is not only timely, but also has a certain degree of interpretability, which is convenient for different users (such as researchers, environmental engineers, etc.) to obtain the required information more quickly during the natural resource monitoring and analysis process, and improve the intuitiveness and reliability of data feedback.

[0077] Preferably, in one embodiment of the present invention, the information storage module 5 is used to classify and store the final corrected monitoring data. By classifying and storing data of different categories, the module facilitates the subsequent calling and management of data. For example, water quality monitoring data, air quality monitoring data and soil monitoring data can be stored in different databases respectively to ensure the independence and traceability of the data.

[0078] Preferably, in one embodiment of the present invention, the information storage module 5 adopts a hierarchical storage structure to classify the data in multiple dimensions according to time, location and monitoring type. This structure not only facilitates efficient call and rapid retrieval of data, but also provides flexibility for the expansion of the system in a big data environment. The information storage module 5 also has a data backup function so that it can quickly restore to the latest monitoring state when a system failure occurs. At the same time, the classified stored historical data facilitates subsequent trend analysis and abnormal monitoring, providing data support for natural resource management. The design of the information storage module 5 effectively improves the orderliness of data storage and reduces the complexity of data retrieval and calling, and is suitable for efficient storage and management of massive data.

[0079] The monitoring integration method of the natural resource intelligent monitoring integration system of the present invention covers the complete process from data collection to data feedback and storage, ensuring the efficiency and practicality of the entire system in practical applications. The following is a detailed description of each step:

[0080] First, the resource monitoring information acquisition module 1 acquires multi-dimensional monitoring data of natural resources. Preferably, the acquisition module 1 includes a series of highly sensitive sensing devices to ensure the real-time and accuracy of the collected data. The collected multi-dimensional data is then transmitted to the resource monitoring information judgment module 2 for processing.

[0081] In the judgment module 2, the data is firstly preliminarily identified for abnormality by using the hyperbolic-logarithmic abnormal offset detection model to obtain the offset value O of each data sample. i , in order to filter out data samples that deviate from the standard value. Next, the inverse hypergeometric adaptive offset correction model is used to adaptively correct the detected offset data to ensure that the offset of the data gradually approaches the preset standard. Then, the corrected data is reconstructed in the frequency domain through the multivariate nested piecewise Fourier mapping model to extract the periodic characteristics of the data and further reduce the high-frequency noise of the abnormal data. Next, the fractal dimension weighted Carter mapping feedback model performs weighted feedback on the data after Fourier mapping, and makes fine corrections to the data according to the complexity of the data (ie, the fractal dimension) to ensure that the high-dimensional data maintains a high degree of accuracy in the feedback. Finally, the composite adaptive resonant state-perturbation equalization filter model is used to perform final equalization processing on the feedback data to obtain smooth final corrected data.

[0082] The information modification module 3 receives the data feedback results output by the judgment module 2, and performs secondary correction on the abnormal data to further reduce the data deviation and ensure that the data is more in line with the actual situation. The data corrected by the information modification module 3 is transmitted to the resource monitoring information feedback module 4, which provides the final monitoring results to the user through the feedback module 4, and generates an abnormal detection report for subsequent data analysis.

[0083] Finally, the information storage module 5 stores the final corrected data by category for subsequent query and call, which is convenient for management and retrieval in a large-scale data environment. Through this method and steps, the system realizes multi-level and high-precision processing of natural resource monitoring data, ensuring the application of the system in different monitoring scenarios.

[0084] In summary, the natural resource intelligent monitoring integrated system and method of the present invention realizes efficient collection, accurate judgment, dynamic feedback and reasonable storage of natural resource monitoring data through progressive processing of multi-level algorithm models. The functional structure and data flow between each module are complete, which can meet the real-time monitoring needs in complex natural environments and improve the accuracy of data processing and the stability of the system.

[0085] In order to verify the superiority of the present invention in the intelligent monitoring of natural resources, especially the multi-level data processing and anomaly correction capabilities achieved through innovative algorithms, the present invention designed an embodiment (Example 1) and a comparative example (Comparative Example 1), and conducted detailed tests on various indicators on the same data set. The detection data set is derived from environmental monitoring data in a certain area, including continuous monitoring results of multi-dimensional indicators such as water quality, air and soil. The data collection interval is once an hour for 30 days to simulate the complex environmental fluctuations in natural resource monitoring. The test results revolve around the innovative points of the present invention, using special detection standards and detection methods to fully reflect the system advantages of the present invention.

[0086] In order to ensure the objectivity and effectiveness of the test results, the present invention sets the following test standards:

[0087] 1. Anomaly detection rate: Indicates the system's ability to detect anomalies in monitoring data, expressed as the accuracy of anomaly detection (True Positive Rate, TPR), calculated as the ratio of the amount of detected anomaly data to the actual amount of anomaly data. The higher the TPR, the stronger the system's detection capability.

[0088] 2. Post-correction deviation reduction rate: indicates the reduction in the deviation of abnormal data from the standard value after the system correction, calculated as the difference between the deviation of the data from the standard value before and after correction divided by the deviation before correction. The higher the deviation reduction rate, the better the correction effect of the system.

[0089] 3. Balance index: detect the smoothness and consistency of the final output data, and use the mean square error (MSE) to measure. The lower the MSE, the smoother the data and the smaller the error.

[0090] 4. Computational efficiency: The efficiency of the system in data processing is expressed by the average computing time, which is the average time for processing each set of data during the test cycle. The shorter the computing time, the higher the system efficiency.

[0091] The above indicators are tested on the same data set. Example 1 and Comparative Example 1 use the same data input, and compare and test their performance in terms of anomaly detection rate, deviation reduction rate, balance and computational efficiency item by item. Example 1 processes data based on the five-layer progressive algorithm of the present invention, while Comparative Example 1 uses the traditional anomaly detection and mean correction method to facilitate the detection of the superiority of the present invention in terms of innovative algorithms and system collaboration.

[0092] The test results are shown in the following table:

[0093] Detection indicators Embodiment 1 (present invention) Comparative Example 1 (Traditional Method) Anomaly Detection Rate (TPR) 92.5％ 78.3％ Deviation reduction rate after correction 85.7％ 60.2％ Mean squared error index (MSE) 0.0045 0.0128 Average calculation time (seconds) 0.75 1.20

[0094] It can be clearly seen from the test results that Example 1 shows significant advantages in all indicators.

[0095] First, in terms of anomaly detection rate, Example 1 reached 92.5%, which is significantly higher than 78.3% of Comparative Example 1. This shows that the multi-layer progressive algorithm of the present invention has strong adaptability in abnormal data identification, especially through the hyperbolic-logarithmic anomaly offset detection model, it effectively identifies deviations of complex and volatile natural resource data, ensuring detection accuracy. This result further verifies that the present invention has high anomaly detection capabilities in different data dimensions.

[0096] Secondly, in terms of the deviation reduction rate after correction, Example 1 is 85.7%, which is significantly better than 60.2% of Comparative Example 1. This is mainly due to the synergy of the inverse hypergeometric adaptive offset correction model and the fractal dimension weighted Carter mapping feedback model, which ensures that the abnormal data gradually approaches the standard value in multiple corrections, further reducing the data deviation. This result shows that the correction mechanism of the present invention can not only quickly adapt to abnormal data with large deviations, but also maintain efficient data approximation capabilities in complex data environments.

[0097] Furthermore, in terms of the balance index, Example 1 of the present invention shows a mean square error (MSE) of 0.0045, which is much lower than 0.0128 of Comparative Example 1. This shows that the composite adaptive resonant state-perturbation equalization filter model of the present invention effectively eliminates the residual noise caused by multi-layer correction before data output, making the final data smoother and more consistent, reflecting the outstanding performance of the present invention in noise control and data stability. This is particularly important for data processing systems that monitor changes in natural resources in real time, because the smoothness and consistency of the data directly affect the reliability of user decisions.

[0098] Finally, in terms of computational efficiency, the average computational time of Example 1 is 0.75 seconds, which is better than 1.20 seconds of Comparative Example 1. Although the present invention adopts a multi-layer progressive algorithm, the synergy between the algorithms improves the computational efficiency, especially through the multiple parallel processing in the Fourier mapping and feedback model, which reduces computational redundancy. This result shows that the present invention has unique advantages in efficiently processing a large amount of monitoring data, making the system suitable for natural resource monitoring application scenarios with high real-time requirements.

[0099] In summary, the test results show that Example 1 of the present invention is significantly superior to the control example in terms of anomaly detection, deviation correction, data balance and computing efficiency, verifying the innovation and effectiveness of the system of the present invention.

[0100] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto; any person familiar with the art who, within the scope disclosed by the present invention, makes substitutions or changes based on the scheme and improved concepts of the present invention shall be covered within the protection scope of the present invention.

Claims

1. A natural resource intelligent monitoring integrated system, characterized in that: include: Resource monitoring information collection module, used to obtain multi-dimensional monitoring data of natural resources; A resource monitoring information judgment module, which progressively performs data anomaly detection, offset correction and data fusion based on the multi-dimensional monitoring data obtained by the resource monitoring information collection module; An information modification module, connected to the resource monitoring information judgment module, for performing feedback adjustment on the abnormal data output by the judgment module; A resource monitoring information feedback module, used to obtain the feedback result output by the information modification module and feed it back to the user terminal; The information storage module is used to store the multi-level data correction results output by the resource monitoring information judgment module to facilitate subsequent query and management.

2. The natural resource intelligent monitoring integrated system according to claim 1 is characterized in that: The resource monitoring information judgment module includes a hyperbolic-logarithmic abnormal offset detection model for detecting data deviation, and the hyperbolic-logarithmic abnormal offset detection model obtains the offset value. i ,in: Among them, O i is the offset of sample i, X i is the observed value of sample i, S is the preset standard value, and λ is the hyperbolic stretching coefficient, which is used to adjust the stretching effect of the hyperbolic function; the hyperbolic-logarithmic anomaly offset detection model uses the hyperbolic-logarithmic relationship to detect the initial deviation of the data, realizes the initial anomaly identification of multidimensional data, and outputs the obtained offset to the next step of offset correction.

3. The natural resource intelligent monitoring integrated system according to claim 2 is characterized in that: The resource monitoring information judgment module further includes an inverse hypergeometric adaptive offset correction model for correcting the offset, based on the offset output by the hyperbolic-logarithmic abnormal offset detection model. i Get the correction data ΔX i ,in: Where ΔX i is the corrected sample i data, X i is the original sample i data, O i is the offset of sample i, η is the adaptive adjustment coefficient, and μ is the offset index, which is used to control the correction strength; the inverse hypergeometric adaptive offset correction model gradually reduces the data deviation based on the dynamic adjustment characteristics of the inverse hypergeometric function, so that the corrected data is output to the next step of frequency mapping processing.

4. The natural resource intelligent monitoring integrated system according to claim 3 is characterized in that: The resource monitoring information judgment module further includes a multivariate nested segmented Fourier mapping model for correcting the data ΔX output based on the inverse hypergeometric adaptive migration correction model. i Get the data X′ after Fourier mapping i ,in: Among them, X′ i is the data after Fourier mapping, a k and b k is the Fourier coefficient, T is the data period parameter, and N is the highest order of the Fourier series; the multivariate nested segmented Fourier mapping model reconstructs the corrected data in the frequency domain, extracts the periodic features in the data, and further eliminates the periodic error. The Fourier mapped data is output to the next step of feedback optimization.

5. The natural resource intelligent monitoring integrated system according to claim 4 is characterized in that: in, The resource monitoring information judgment module further includes a fractal dimension weighted Carter mapping feedback model for outputting Fourier mapping data X′ based on the multivariate nested segmented Fourier mapping model. i Get feedback data X″ i ,in: X i ″=α·X i ′+β·d f· (1-tanh(O i )) Among them, X″ i is the data after feedback, X′ i is the data after Fourier mapping, α is the data retention coefficient, β is the feedback adjustment coefficient, d f is the fractal dimension, which is used to characterize the complexity of data. i ) is a hyperbolic tangent function that suppresses deviation; the fractal dimension weighted Carter mapping feedback model is based on the description of data complexity by fractal dimension and realizes dynamic correction of data through feedback optimization.

6. The natural resource intelligent monitoring integrated system according to claim 5, wherein: The resource monitoring information judgment module further includes a composite adaptive resonant state-perturbation equalization filter model for outputting feedback data X″ based on the fractal dimension weighted Carter mapping feedback model. i Get the final output data in: in, is the final output data, X″ i is the feedback data, ∈ is the perturbation parameter, θ i is the resonance angle; the composite adaptive resonance state-perturbation equalization filter model processes the final output data through the resonance state-perturbation mechanism equalization, eliminates noise and errors, and realizes stable output of data.

7. The natural resource intelligent monitoring integrated system according to claim 6 is characterized in that: The information modification module receives the output data of the resource monitoring information judgment module, is used to perform secondary correction on the abnormal data according to the feedback result, and transmits the corrected data to the resource monitoring information feedback module.

8. The natural resource intelligent monitoring integrated system according to claim 7 is characterized in that: The resource monitoring information feedback module feeds back final monitoring information to the user terminal based on the data results output by the information modification module, and the feedback information includes the final corrected data and anomaly detection report.

9. The natural resource intelligent monitoring integrated system according to claim 8, characterized in that: The information storage module is used to classify and store the final corrected monitoring data to facilitate subsequent query and data analysis.

10. The monitoring integration method of the natural resource intelligent monitoring integration system according to any one of claims 1 to 9, characterized in that: The following steps are involved: Obtain multi-dimensional monitoring data of natural resources based on resource monitoring information collection module; The acquired monitoring data are preliminarily identified for anomalies using a hyperbolic-logarithmic anomaly shift detection model; The inverse hypergeometric adaptive offset correction model is used to correct the offset of abnormal data; The frequency domain reconstruction of the corrected data is performed through a multivariate nested piecewise Fourier mapping model; Feedback optimization is performed using fractal dimension weighted Carter mapping feedback model; The feedback data is equalized by a composite adaptive resonant state-perturbation equalization filter model to obtain the final output data; Perform secondary correction on abnormal data through information modification module; Feedback the final revised data to the user based on the resource monitoring information feedback module; The final corrected monitoring data is stored in the information storage module for subsequent query and analysis.

Images