Information technology data monitoring device and method of using the same

Abstract

The present invention relates to the field of information technology data monitoring, and discloses an information technology data monitoring device and a method for using the same. The device includes multiple heterogeneous sensor modules, which are distributed in the monitoring area to collect multiple types of data such as light intensity and electromagnetic signals. The data acquisition unit synchronizes the original data, and after pre-processing by the edge computing node, the central processing module generates comprehensive monitoring indicators through a multi-source data fusion algorithm, and the dynamic weight adjustment module adaptively optimizes the fusion weight. The anomaly detection engine uses an autoencoder model to calculate the anomaly probability, and the data transmission unit uploads data through the LoRa and 5G dual-mode communication protocols according to the network conditions. In addition, the adaptive learning module regularly updates the model parameters. When in use, the device is deployed according to the process, data is collected and processed, anomalies are detected, and the model is updated. The invention can comprehensively collect data, accurately analyze and process data, efficiently transmit data, and continuously optimize the model to improve the accuracy and reliability of monitoring.

Description

Technical Field

[0001] The present invention relates to the field of information technology data monitoring, and in particular to an information technology data monitoring device and a method for using the same. Background Art

[0002] In today's digital age, information technology data monitoring is crucial in numerous fields, with applications spanning industrial production, intelligent security, environmental monitoring, building health monitoring, and more. However, existing data monitoring technologies have numerous limitations and struggle to meet the growing demand for complex monitoring.

[0003] In terms of sensor deployment, traditional monitoring systems use a relatively limited number of sensors, often only able to monitor a specific type of data and failing to fully reflect the overall condition of the monitored area. For example, in an industrial production workshop, monitoring only a single parameter, such as temperature or pressure, makes it difficult to detect potential failure risks caused by a combination of multiple factors. Even in some systems that employ multiple sensors, their distribution lacks scientific planning, leading to mutual interference between sensors and blind spots in data collection, seriously compromising data accuracy and integrity. For example, in large-scale warehouses, if temperature and humidity sensors are poorly distributed, changes in temperature and humidity in key areas may be missed, preventing timely detection of cargo deterioration caused by abnormal temperature and humidity.

[0004] At the data processing and analysis level, the data formats, sampling frequencies, and accuracies collected by different sensors vary greatly, making multi-source data fusion difficult. Early simple weighted average fusion methods were unable to fully tap into the inherent connections between data, and the fusion results could not accurately reflect the actual situation. In complex traffic flow monitoring scenarios, when fusing multi-source data such as vehicle speed, flow, and density, traditional methods have difficulty effectively integrating information, resulting in deviations in the judgment of traffic congestion conditions. At the same time, existing anomaly detection technologies rely on manual experience to set thresholds, which cannot adapt to dynamically changing monitoring environments and are prone to false alarms or missed reports. In the operation monitoring of power equipment, since the operating conditions of the equipment change over time, the detection method with a fixed threshold cannot promptly detect early signs of equipment failure.

[0005] The stability and efficiency of data transmission also face challenges in the communication and transmission process. In areas with unstable network coverage, such as remote mountainous areas or underground mines, traditional single communication protocols cannot guarantee reliable data transmission. Relying solely on communication methods such as 4G or WiFi can easily lead to signal interruptions, resulting in the loss of large amounts of monitoring data, affecting subsequent analysis and decision-making. Furthermore, the transmission of large amounts of raw data not only consumes significant network bandwidth, but also increases the burden on data storage and processing, reducing the efficiency of the entire monitoring system.

[0006] In terms of model optimization, updating existing monitoring systems often requires centralized data collection and training. This approach is not only time-consuming and resource-intensive, but also carries the risk of data privacy leaks. In healthcare monitoring, patients' personal health data is private, and centralized data collection and training can lead to data leaks and serious security issues. Furthermore, due to the differences in environmental and data characteristics across different monitoring areas, a single global model is difficult to adapt to all scenarios, resulting in reduced monitoring accuracy. Summary of the Invention

[0007] The object of the present invention is to provide an information technology data monitoring device and a method of using the same to solve the problems raised in the above background technology.

[0008] To achieve the above-mentioned object, the present invention provides the following technical solution: an information technology data monitoring device, the device comprising:

[0009] Multiple heterogeneous sensor modules are distributed at different locations in the monitoring area. The sensor modules include light intensity sensors, electromagnetic signal sensors, temperature and humidity sensors, and motion acceleration sensors.

[0010] The data acquisition unit is connected to each sensor module to obtain the raw data of each sensor in real time and synchronize the data with the timestamp;

[0011] an edge computing node, deployed in the monitoring area, receiving the synchronized data from the data acquisition unit and performing multimodal signal preprocessing;

[0012] The central processing module receives pre-processed data and generates comprehensive monitoring indicators through multi-source data fusion algorithms;

[0013] Dynamic weight adjustment module, which adaptively adjusts the fusion weight of multi-source data based on the real-time data distribution characteristics;

[0014] An anomaly detection engine, which uses an autoencoder model to calculate the anomaly probability of the comprehensive monitoring indicators;

[0015] The data transmission unit uses LoRa and 5G dual-mode communication protocols to upload anomaly detection results and raw data to the cloud server.

[0016] Preferably, the distribution of the heterogeneous sensor modules is specifically as follows: a three-dimensional coordinate system is established with the geometric center of the monitoring area as the origin, the light intensity sensor is deployed on the surface of the monitoring area, the electromagnetic signal sensor is embedded in the interior of the monitoring area at intervals, the temperature and humidity sensors are evenly distributed at the junction of the surface and the interior, and the motion acceleration sensor is fixed at the key structural point of the monitoring area.

[0017] Preferably, the multimodal signal preprocessing comprises the following steps:

[0018] Perform discrete wavelet transform on the light intensity sensor data to extract high-frequency components as light intensity fluctuation characteristics;

[0019] Fast Fourier transform is used on electromagnetic signal sensor data to extract the main frequency amplitude and harmonic energy ratio;

[0020] The temperature and humidity sensor data is filtered using a sliding window mean filter to eliminate environmental noise;

[0021] A dynamic time warping algorithm is used on motion acceleration sensor data to align time series data with different sampling frequencies.

[0022] Preferably, the multi-source data fusion algorithm is specifically:

[0023] Definition Credibility weight of sensor-like data ,in For the variance of class sensor data;

[0024] Perform weighted summation on the preprocessed multimodal features based on the credibility weight to generate the initial fusion feature vector;

[0025] The initial fused feature vector is input into the graph convolutional network, the spatial correlation between sensors is modeled through the adjacency matrix, and the spatiotemporal fusion features are output.

[0026] Preferably, the workflow of the dynamic weight adjustment module includes:

[0027] Calculate the KL divergence of each sensor data in real time and detect the data distribution offset;

[0028] When the KL divergence of a certain type of sensor data exceeds the preset threshold, its credibility weight is dynamically adjusted downward according to the exponential decay function. The calculation formula is:

[0029]

[0030] in is the credibility weight after the reduction, is the attenuation coefficient, is the KL divergence, is the current data distribution, is the historical benchmark distribution.

[0031] Preferably, the specific implementation of the anomaly detection engine is:

[0032] Construct a deep autoencoder network. The encoder part consists of a 3-layer fully connected network, and the hidden layer activation function is LeakyReLU.

[0033] The decoder part adopts a symmetrical structure, and the loss function is defined as the weighted sum of the reconstruction error and the sparse constraint of the latent space. The calculation formula is:

[0034]

[0035] in is the latent vector output by the encoder, is the original feature vector of the input data, is the reconstructed feature vector output by the autoencoder, and is a hyperparameter;

[0036] When the reconstruction error at a certain moment exceeds three times the standard deviation of the historical error distribution, it is determined to be an abnormal event.

[0037] Preferably, the working mode of the data transmission unit is: when the network coverage in the monitoring area is stable, the 5G protocol is preferentially used to transmit the original data and abnormal labels; when the 5G signal strength is lower than -90dBm, it switches to the LoRa protocol and only transmits the compressed feature vector and position code of the abnormal event.

[0038] Preferably, it also includes an adaptive learning module for:

[0039] Regularly download the latest monitoring data from the cloud server to update the parameters of the autoencoder model;

[0040] A federated learning framework is used to aggregate the local model gradients of multiple edge computing nodes, generate global model parameters, and then synchronize them to each node.

[0041] Preferably, the execution steps of the federated learning framework include:

[0042] Each edge node calculates the model gradient based on local data and adds differential privacy noise;

[0043] The central processing module aggregates gradients through a secure multi-party computing protocol and updates the global model;

[0044] The updated model parameters are encrypted and distributed to each edge node, replacing the original model.

[0045] Preferably, the present invention further includes a method for using the information technology data monitoring device, comprising the following steps:

[0046] Deploy the aforementioned information technology data monitoring device in the monitoring area and initialize the coordinate system and communication protocol of the sensor module;

[0047] The multimodal sensor data is synchronously collected at a preset frequency by the data acquisition unit and marked with time and space stamps;

[0048] Perform multimodal signal preprocessing at the edge computing node to generate standardized feature vectors; call the dynamic weight adjustment module to update the fusion weight according to the real-time data distribution;

[0049] The multi-source data fusion algorithm of the central processing module is used to generate comprehensive monitoring indicators, which are then input into the anomaly detection engine to calculate anomaly probabilities;

[0050] When the abnormal probability exceeds 0.95, the data transmission unit is triggered to upload the alarm information and related data to the cloud;

[0051] The global model parameters are downloaded every month through the adaptive learning module to complete the incremental update of the edge node model.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] The present invention realizes the comprehensive collection of multi-dimensional data of the monitoring area by deploying multiple heterogeneous sensor modules such as light intensity sensors, electromagnetic signal sensors, temperature and humidity sensors, and motion acceleration sensors, and scientifically planning their distribution positions. A three-dimensional coordinate system is established with the geometric center of the monitoring area as the origin. The light intensity sensor is deployed on the surface and can accurately capture the instantaneous changes in light intensity. It is of great significance for scenarios such as agricultural greenhouse light monitoring and intelligent lighting system control. The electromagnetic signal sensor is embedded inside at intervals to effectively avoid interference and accurately monitor electromagnetic signals. It plays a key role in electromagnetic radiation monitoring in areas with dense electronic equipment. The temperature and humidity sensors are evenly distributed at the junction of the surface and the interior to fully grasp the changes in temperature and humidity and ensure the temperature and humidity stability of the storage environment and production workshop. The motion acceleration sensor is fixed at the key structural point to monitor the movement state of the structure in real time. It is indispensable in the safety monitoring of structures such as bridges and buildings. This multi-sensor collaborative and scientific distribution method greatly improves the accuracy and comprehensiveness of data collection, and provides a rich and reliable data foundation for subsequent analysis. During data processing, multimodal signal preprocessing is performed using discrete wavelet transforms, fast Fourier transforms, sliding window mean filters, and dynamic time warping algorithms, targeting the characteristics of different sensor data. This effectively extracts features, eliminates noise, and aligns time series data. The multi-source data fusion algorithm, by defining credibility weights and incorporating a graph convolutional network, fully considers the stability and spatial correlation of sensor data to generate accurate spatiotemporal fusion features. The dynamic weight adjustment module adaptively adjusts fusion weights based on the real-time data distribution characteristics. When the data distribution changes, the weight of abnormal data is promptly lowered to ensure the reliability of the fusion results. In industrial equipment fault monitoring, this system can accurately fuse multiple data sources, such as vibration, temperature, and pressure, to accurately determine the equipment's operating status and identify potential faults in advance. Compared to traditional fusion methods, this significantly improves fault diagnosis accuracy, reducing equipment downtime and repair costs.

[0054] The anomaly detection engine builds a deep autoencoder network. By properly configuring the encoder and decoder structures and loss function, it effectively learns normal patterns in the data. Anomalies are identified when the reconstruction error exceeds three standard deviations of the historical error distribution. This model-based anomaly detection method is more accurate and adaptive than traditional manual threshold setting. In intelligent security monitoring, it can promptly detect abnormal behavior, such as unauthorized intrusions and unusual gatherings of people, and quickly issue alerts, providing strong support for security prevention and reducing the risk of safety incidents. The data transmission unit uses LoRa and 5G dual-mode communication protocols, intelligently switching based on network coverage. When network coverage is stable, it leverages the high speed and low latency of the 5G protocol to quickly upload raw data and anomaly labels. When the 5G signal strength drops below -90dBm, it automatically switches to the LoRa protocol, transmitting only the compressed feature vectors and position codes of the anomaly event, reducing data volume and ensuring stable data transmission in harsh network environments. In scenarios such as environmental monitoring in remote areas and data transmission from field operations, it effectively prevents data loss and ensures the continuity and integrity of monitoring data.

[0055] The adaptive learning module updates the autoencoder model parameters by regularly downloading the latest monitoring data from the cloud server, improving the model's adaptability and accuracy to new data. Using a federated learning framework, each edge node calculates model gradients based on local data and adds differential privacy noise. The central processing module aggregates the gradients through a secure multi-party computing protocol to update the global model and then distributes the encrypted model parameters to each node. This approach not only enables collaborative model optimization and improves monitoring accuracy, but also protects local data privacy. In areas with extremely high data privacy requirements, such as financial risk monitoring and medical health data monitoring, this approach can fully utilize data from various parties to improve monitoring effectiveness while ensuring data security and compliance with strict privacy regulations.

[0056] The information technology data monitoring device of the present invention is simple and convenient to use, covering a series of processes including device deployment, data acquisition, preprocessing, fusion analysis, anomaly detection, data transmission, and model updating. Multimodal sensor data is synchronously collected at a preset frequency and marked with time and space stamps to ensure the spatiotemporal consistency of the data. Incremental updates are completed monthly by downloading global model parameters through an adaptive learning module, ensuring that the device always maintains good performance. In practical applications, this reduces the user's usage threshold and maintenance costs, improves the operating efficiency and reliability of the monitoring system, and can be quickly deployed and applied to various monitoring scenarios, providing efficient data monitoring solutions for different industries. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 This is a working principle diagram of the information technology data monitoring device of the present invention;

[0058] Figure 2 This is the workflow diagram of the dynamic weight adjustment module;

[0059] Figure 3 This is the workflow diagram of the anomaly detection engine;

[0060] Figure 4 This is a step diagram of the method for using the information technology data monitoring device of the present invention. DETAILED DESCRIPTION

[0061] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0062] See also Figure 1-4 The present invention provides a technical solution: an information technology data monitoring device. The information technology data monitoring device is primarily used to monitor multi-dimensional data in a monitoring area and process, analyze, and transmit the data. The device includes multiple heterogeneous sensor modules, a data acquisition unit, an edge computing node, a central processing module, a dynamic weight adjustment module, an anomaly detection engine, a data transmission unit, and an adaptive learning module.

[0063] Multiple heterogeneous sensor modules are distributed across the monitoring area. These include light intensity sensors, electromagnetic signal sensors, temperature and humidity sensors, and motion acceleration sensors. They collect different types of environmental data within the monitoring area, acquiring raw data from multiple dimensions, including light intensity, electromagnetic signals, temperature and humidity, and motion acceleration.

[0064] The data acquisition unit is connected to each sensor module. Its main function is to obtain raw data from each sensor in real time and synchronize the timestamps of this data. This ensures that the data collected by different sensors is consistent in time, facilitating subsequent data analysis and processing.

[0065] Edge computing nodes are deployed within the monitoring area and receive time-stamped data from the data acquisition units. They perform multimodal signal preprocessing on this synchronized data, converting the raw data into standardized feature vectors that are easier to analyze and process.

[0066] The central processing module receives pre-processed data from the edge computing nodes and, using a multi-source data fusion algorithm, fuses the multimodal data collected by different sensors to generate comprehensive monitoring indicators. These comprehensive monitoring indicators can more comprehensively and accurately reflect the overall status of the monitored area.

[0067] The dynamic weight adjustment module adaptively adjusts the fusion weights of multi-source data based on the real-time data distribution characteristics. This module can reasonably adjust the importance of different sensor data in the fusion process according to real-time data changes, making the fusion results more accurate.

[0068] The anomaly detection engine uses an autoencoder model to calculate anomaly probabilities based on the comprehensive monitoring indicators generated by the central processing module. By comparing the current data with historical data, it determines whether anomalies have occurred in the monitored area.

[0069] The data transmission unit uses LoRa and 5G dual-mode communication protocols to upload anomaly detection results and raw data to the cloud server. Selecting the appropriate communication protocol in different network environments ensures stable and efficient data upload.

[0070] The adaptive learning module regularly downloads the latest monitoring data from the cloud server and updates the parameters of the autoencoder model to improve the model's accuracy and adaptability. At the same time, a federated learning framework is used to aggregate local model gradients from multiple edge computing nodes, generate global model parameters, and synchronize them to each node to achieve collaborative model optimization.

[0071] The present invention will be further described below in conjunction with Examples 1 to 5:

[0072] Example 1:

[0073] This embodiment clarifies the specific distribution of heterogeneous sensor modules within the monitoring area to improve the accuracy and comprehensiveness of data collection.

[0074] In practical applications, a specific distribution pattern is employed to ensure that heterogeneous sensor modules can effectively collect data of varying types and locations within the monitoring area. A three-dimensional coordinate system is established with the geometric center of the monitoring area as the origin. This coordinate system provides a spatial reference for precise sensor deployment.

[0075] Light intensity sensors are deployed on the surface of the monitoring area. Because light intensity changes significantly at the surface of the monitoring area, this deployment method can maximize the acquisition of real-time light intensity change data. For example, in outdoor monitoring scenarios, changes in light intensity can be detected in a timely manner, which is important for monitoring some light-sensitive equipment or environments.

[0076] Electromagnetic signal sensors are embedded at intervals within the monitoring area. Electromagnetic signals propagate through space with a certain degree of penetration and complexity. This inter-sensor embedding method avoids mutual interference between sensors while enabling comprehensive monitoring of electromagnetic signal conditions at different locations within the monitoring area. For example, in areas with dense electronic equipment, it can accurately monitor electromagnetic radiation intensity and other data.

[0077] Temperature and humidity sensors are evenly distributed at the interface between the surface and the interior. This location allows for monitoring both surface and internal temperature and humidity. For storage environments or production workshops with stringent temperature and humidity requirements, comprehensive and accurate temperature and humidity data can be obtained to ensure environmental stability.

[0078] Motion accelerometers are fixed to key structural points within the monitoring area. These points are often crucial support points for the structural stability of the entire monitoring area. Fixing motion accelerometers at these points allows for timely monitoring of changes in the structural state. This plays a crucial role in assessing structural safety in scenarios such as building and bridge monitoring.

[0079] Example 2:

[0080] This embodiment elaborates on the specific steps of multimodal signal preprocessing, performs targeted processing on the data collected by different sensors, and provides more effective features for subsequent data fusion and analysis.

[0081] A discrete wavelet transform is performed on the light intensity sensor data to extract high-frequency components as a signature of light intensity fluctuations. Light intensity in real-world environments fluctuates due to a variety of factors. The discrete wavelet transform effectively decomposes the light intensity signal into components of varying frequencies. By extracting the high-frequency components, rapid changes in light intensity can be highlighted. For example, when monitoring areas with frequent lighting changes, such as stage lighting, high-frequency components can accurately reflect transient changes in light intensity, which is crucial for lighting control and monitoring in these scenarios.

[0082] Fast Fourier transform (FFT) is used to extract the main frequency amplitude and harmonic energy percentage from electromagnetic signal sensor data. Electromagnetic signals contain multiple frequency components, and FFT can convert electromagnetic signals from the time domain into the frequency domain, allowing clear analysis of their main frequency amplitude and harmonic energy percentage. In power system monitoring, analyzing these characteristics can determine whether power equipment is operating properly. An abnormal harmonic energy percentage may indicate a potential equipment failure.

[0083] Temperature and humidity sensor data is susceptible to interference from environmental noise. Sliding window mean filtering is used to eliminate this noise. Sliding window mean filtering is a common signal filtering method that averages temperature and humidity data within a specific time window, removing noise interference and making the data smoother and more accurate. For example, in indoor environmental monitoring, this method can more accurately reflect the actual temperature and humidity conditions in a room.

[0084] Motion acceleration sensors may have inconsistent sampling frequencies due to different deployment locations and acquisition devices. A dynamic time warping algorithm is used to align time series data with different sampling frequencies. This algorithm aligns motion acceleration data with different sampling frequencies on the time axis without changing the data characteristics, facilitating subsequent unified analysis of motion status. This ensures data consistency and comparability in scenarios where multiple sensors collaborate to monitor moving objects.

[0085] Example 3:

[0086] In the multi-source data fusion algorithm, we first define Credibility weight of sensor-like data Here For the The variance of sensor data can reflect the degree of data dispersion. The smaller the variance, the higher the credibility of the data, and the greater the corresponding credibility weight. In this way, the importance of each sensor data in the fusion process is determined based on its stability.

[0087] The preprocessed multimodal features are weighted and summed based on the credibility weights to generate an initial fused feature vector. The preprocessed features of different sensors are weighted and summed according to their respective credibility weights to obtain a preliminary fused feature vector that integrates the information of multiple sensor data.

[0088] The initial fused feature vector is fed into a graph convolutional network (GCN), which models the spatial correlation between sensors using an adjacency matrix to output spatiotemporal fusion features. GCNs account for the spatial relationships between sensors and describe their connectivity using an adjacency matrix. This allows the fusion process to incorporate not only the characteristics of the data itself but also spatial information, resulting in a more accurate reflection of the actual conditions in the monitored area.

[0089] The dynamic weight adjustment module calculates the KL divergence of each sensor data in real time to detect data distribution shifts. KL divergence measures the difference between two probability distributions. By calculating the KL divergence between the current data distribution and the historical baseline distribution, it is possible to detect any data distribution shifts in a timely manner.

[0090] When the KL divergence of a certain type of sensor data exceeds the preset threshold, its credibility weight is dynamically adjusted downward according to the exponential decay function. The calculation formula is: .

[0091] in is the credibility weight after the reduction, is the attenuation coefficient, which can be adjusted according to actual conditions. is the KL divergence, is the current data distribution, is the historical benchmark distribution. When the distribution of a certain type of sensor data changes significantly, its weight in the fusion process is reduced to avoid abnormal data from having a significant impact on the fusion result and ensure the reliability of the fusion result.

[0092] Example 4:

[0093] This embodiment describes in detail the specific implementation of the anomaly detection engine and the working mode of the data transmission unit to achieve accurate anomaly detection and efficient data transmission.

[0094] The anomaly detection engine builds a deep autoencoder network. The encoder consists of a three-layer fully connected network, with the hidden layer activation function using LeakyReLU. The LeakyReLU function effectively addresses the vanishing gradient problem, enabling the network to better learn data features during training. The encoder extracts and compresses the input comprehensive monitoring indicator data, converting it into a low-dimensional latent vector.

[0095] The decoder part adopts a symmetrical structure, corresponding to the encoder, and reconstructs the latent vector into an approximate representation of the original data. The loss function is defined as the weighted sum of the reconstruction error and the sparse constraint of the latent space, and the calculation formula is: .in is the latent vector output by the encoder, is the original feature vector of the input data, is the reconstructed feature vector output by the autoencoder, and are hyperparameters. By adjusting these two hyperparameters, the importance of reconstruction error and latent space sparsity constraint can be balanced.

[0096] When the reconstruction error at a given moment exceeds three standard deviations of the historical error distribution, it is considered an anomaly. This is based on statistical principles. Under normal circumstances, the reconstruction error of data should fluctuate within a certain range. When the reconstruction error exceeds three standard deviations, it indicates that there is a significant difference between the current data and the historical data, and an anomaly is likely occurring.

[0097] The data transmission unit operates by prioritizing the 5G protocol to transmit raw data and anomaly labels when network coverage in the monitoring area is stable. The 5G protocol, with its high speed and low latency, can quickly and accurately upload large amounts of raw data and anomaly labels to the cloud server, facilitating subsequent data analysis and processing.

[0098] When the 5G signal strength falls below -90dBm, indicating unstable 5G network coverage, the LoRa protocol is switched to. The LoRa protocol offers the advantages of low power consumption and long-distance transmission. In this case, only the compressed feature vector and location code of the abnormal event are transmitted, reducing the amount of data transmitted and ensuring successful data upload in poor network conditions.

[0099] Example 5:

[0100] This embodiment describes in detail the working process of the adaptive learning module and the method of using the information technology data monitoring device to achieve continuous optimization of the model and effective operation of the device.

[0101] The adaptive learning module regularly downloads the latest monitoring data from the cloud server and updates the parameters of the autoencoder model. As time passes and the monitoring environment changes, new data can provide more information to the model. By updating the parameters, the autoencoder model can better adapt to the new data distribution and improve the accuracy of anomaly detection.

[0102] The adaptive learning module utilizes a federated learning framework to aggregate local model gradients from multiple edge computing nodes, generate global model parameters, and synchronize them to all nodes. During the execution of the federated learning framework, each edge node calculates model gradients based on local data and adds differential privacy noise. This addition of differential privacy noise allows the node to participate in model training and optimization while protecting local data privacy, preventing data leakage.

[0103] The central processing module aggregates gradients through a secure multi-party computing protocol to update the global model. The secure multi-party computing protocol ensures that the privacy of each party's data is protected during the gradient aggregation process, while accurately calculating the update direction of the global model.

[0104] The updated model parameters are encrypted and distributed to each edge node, replacing the original model. Encrypted distribution ensures the security of the model parameters during transmission. Each edge node uses the updated model parameters to achieve collaborative model optimization and improve the performance of the entire monitoring system.

[0105] The method for using the information technology data monitoring device includes the following steps: first, deploying the device of the present invention in the monitoring area and initializing the coordinate system and communication protocol of the sensor module to ensure that the sensor module can accurately collect data and communicate with other modules.

[0106] The data acquisition unit synchronously collects multimodal sensor data at a preset frequency and marks it with time and space stamps. The preset frequency is set according to the actual monitoring needs, and the time and space stamps ensure the temporal and spatial consistency of the data.

[0107] Multimodal signal preprocessing is performed at the edge computing node to generate standardized feature vectors. Preprocessed data is more convenient for subsequent analysis and processing.

[0108] Call the dynamic weight adjustment module to update the fusion weight according to the real-time data distribution to improve the accuracy of multi-source data fusion.

[0109] The central processing module uses a multi-source data fusion algorithm to generate comprehensive monitoring indicators, which are then fed into the anomaly detection engine to calculate anomaly probabilities. By calculating these comprehensive monitoring indicators and anomaly probabilities, it is determined whether anomalies exist in the monitored area.

[0110] When the probability of anomaly exceeds 0.95, the data transmission unit is triggered to upload the alarm information and related data to the cloud. The abnormal situation is promptly notified to relevant personnel for processing.

[0111] The global model parameters are downloaded monthly through the adaptive learning module to complete the incremental update of the edge node model. Regular model updates ensure that the performance of the monitoring device is always in good condition.

[0112] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "includes," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0113] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. An information technology data monitoring device, characterized in that: include: Multiple heterogeneous sensor modules are distributed at different locations in the monitoring area. The sensor modules include light intensity sensors, electromagnetic signal sensors, temperature and humidity sensors, and motion acceleration sensors. The data acquisition unit is connected to each sensor module to obtain the raw data of each sensor in real time and synchronize the data with the timestamp; an edge computing node, deployed in the monitoring area, receiving the synchronized data from the data acquisition unit and performing multimodal signal preprocessing; The central processing module receives pre-processed data and generates comprehensive monitoring indicators through multi-source data fusion algorithms; Dynamic weight adjustment module, which adaptively adjusts the fusion weight of multi-source data based on the real-time data distribution characteristics; An anomaly detection engine, which uses an autoencoder model to calculate the anomaly probability of the comprehensive monitoring indicators; The data transmission unit uses LoRa and 5G dual-mode communication protocols to upload anomaly detection results and raw data to the cloud server; The multi-source data fusion algorithm is specifically as follows: Definition Credibility weight of sensor-like data ,in For the variance of class sensor data; Perform weighted summation on the preprocessed multimodal features based on the credibility weight to generate the initial fusion feature vector; The initial fusion feature vector is input into the graph convolutional network, the spatial correlation between sensors is modeled through the adjacency matrix, and the spatiotemporal fusion features are output; The workflow of the dynamic weight adjustment module includes: Calculate the KL divergence of each sensor data in real time and detect the data distribution offset; When the KL divergence of a certain type of sensor data exceeds the preset threshold, its credibility weight is dynamically adjusted downward according to the exponential decay function. The calculation formula is: ； in is the credibility weight after the reduction, is the attenuation coefficient, is the KL divergence, is the current data distribution, is the historical benchmark distribution.

2. The device according to claim 1, characterized in that The distribution method of the heterogeneous sensor modules is specifically as follows: a three-dimensional coordinate system is established with the geometric center of the monitoring area as the origin, the light intensity sensor is deployed on the surface of the monitoring area, the electromagnetic signal sensor is embedded in the interior of the monitoring area at intervals, the temperature and humidity sensors are evenly distributed at the junction of the surface and the interior, and the motion acceleration sensor is fixed at the key structural point of the monitoring area.

3. The device according to claim 2, characterized in that The multimodal signal preprocessing comprises the following steps: Perform discrete wavelet transform on the light intensity sensor data to extract high-frequency components as light intensity fluctuation characteristics; Fast Fourier transform is used on electromagnetic signal sensor data to extract the main frequency amplitude and harmonic energy ratio; The temperature and humidity sensor data is filtered using a sliding window mean filter to eliminate environmental noise; A dynamic time warping algorithm is used on motion acceleration sensor data to align time series data with different sampling frequencies.

4. The device according to claim 1, characterized in that The specific implementation of the anomaly detection engine is as follows: Construct a deep autoencoder network. The encoder part consists of a 3-layer fully connected network, and the hidden layer activation function is LeakyReLU. The decoder part adopts a symmetrical structure, and the loss function is defined as the weighted sum of the reconstruction error and the sparse constraint of the latent space. The calculation formula is: ； in is the latent vector output by the encoder, is the original feature vector of the input data, is the reconstructed feature vector output by the autoencoder, and is a hyperparameter; When the reconstruction error at a certain moment exceeds three times the standard deviation of the historical error distribution, it is considered an abnormal event.

5. The device according to claim 1, characterized in that The working mode of the data transmission unit is: When the network coverage in the monitoring area is stable, the 5G protocol is preferred to transmit raw data and abnormal labels; When the 5G signal strength is lower than -90dBm, it switches to the LoRa protocol and only transmits the compressed feature vector and position code of the abnormal event.

6. The device according to claim 1, characterized in that Also includes adaptive learning modules for: Regularly download the latest monitoring data from the cloud server to update the parameters of the autoencoder model; A federated learning framework is used to aggregate the local model gradients of multiple edge computing nodes, generate global model parameters, and then synchronize them to each node.

7. The device according to claim 6, characterized in that The execution steps of the federated learning framework include: Each edge node calculates the model gradient based on local data and adds differential privacy noise; The central processing module aggregates gradients through a secure multi-party computing protocol and updates the global model; The updated model parameters are encrypted and distributed to each edge node, replacing the original model.

8. A method for using an information technology data monitoring device, characterized in that: The following steps are involved: Deploy the device according to any one of claims 1 to 5 in the monitoring area, and initialize the coordinate system and communication protocol of the sensor module; The multimodal sensor data is synchronously collected at a preset frequency by the data acquisition unit and marked with time and space stamps; Perform multimodal signal preprocessing at the edge computing node to generate standardized feature vectors; Call the dynamic weight adjustment module to update the fusion weight according to the real-time data distribution; The multi-source data fusion algorithm of the central processing module is used to generate comprehensive monitoring indicators, which are then input into the anomaly detection engine to calculate anomaly probabilities; When the abnormal probability exceeds 0.95, the data transmission unit is triggered to upload the alarm information and related data to the cloud; The global model parameters are downloaded every month through the adaptive learning module to complete the incremental update of the edge node model.

Images