CN116684878B - 5G information transmission data safety monitoring system - Google Patents
5G information transmission data safety monitoring system Download PDFInfo
- Publication number
- CN116684878B CN116684878B CN202310836452.2A CN202310836452A CN116684878B CN 116684878 B CN116684878 B CN 116684878B CN 202310836452 A CN202310836452 A CN 202310836452A CN 116684878 B CN116684878 B CN 116684878B
- Authority
- CN
- China
- Prior art keywords
- data
- data flow
- time sequence
- vector
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 53
- 230000005540 biological transmission Effects 0.000 title claims abstract description 39
- 230000002159 abnormal effect Effects 0.000 claims abstract description 15
- 238000001514 detection method Methods 0.000 claims abstract description 13
- 239000013598 vector Substances 0.000 claims description 186
- 238000000605 extraction Methods 0.000 claims description 27
- 239000011159 matrix material Substances 0.000 claims description 27
- 230000004927 fusion Effects 0.000 claims description 20
- 238000012937 correction Methods 0.000 claims description 19
- 238000013527 convolutional neural network Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 12
- 230000009466 transformation Effects 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 8
- 230000014759 maintenance of location Effects 0.000 claims description 8
- 230000005856 abnormality Effects 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 238000012098 association analyses Methods 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 4
- 238000011176 pooling Methods 0.000 claims description 4
- 238000012300 Sequence Analysis Methods 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000009545 invasion Effects 0.000 abstract description 5
- 230000007123 defense Effects 0.000 abstract description 4
- 238000000034 method Methods 0.000 description 20
- 230000006870 function Effects 0.000 description 11
- 230000000875 corresponding effect Effects 0.000 description 9
- 230000007613 environmental effect Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 8
- 238000012806 monitoring device Methods 0.000 description 7
- 238000004422 calculation algorithm Methods 0.000 description 6
- 238000010219 correlation analysis Methods 0.000 description 5
- 238000007726 management method Methods 0.000 description 5
- 238000007781 pre-processing Methods 0.000 description 5
- 238000010801 machine learning Methods 0.000 description 4
- 210000002569 neuron Anatomy 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000007405 data analysis Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 239000002689 soil Substances 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000005311 autocorrelation function Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 206010033799 Paralysis Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 238000013144 data compression Methods 0.000 description 1
- 238000013079 data visualisation Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000007477 logistic regression Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 230000003442 weekly effect Effects 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W12/00—Security arrangements; Authentication; Protecting privacy or anonymity
- H04W12/12—Detection or prevention of fraud
- H04W12/121—Wireless intrusion detection systems [WIDS]; Wireless intrusion prevention systems [WIPS]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1408—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic by monitoring network traffic
- H04L63/1425—Traffic logging, e.g. anomaly detection
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D30/00—Reducing energy consumption in communication networks
- Y02D30/70—Reducing energy consumption in communication networks in wireless communication networks
Landscapes
- Engineering & Computer Science (AREA)
- Computer Security & Cryptography (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Computer Hardware Design (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The application discloses a 5G information transmission data safety monitoring system, which monitors data traffic in a network by using a data packet detection and defense system so as to timely discover and prevent abnormal data packets to prevent malicious attacks and invasion. In this way, the transmitted data can be monitored and analyzed in real time, and corresponding measures can be taken to protect the security of the network.
Description
Technical Field
The application relates to the field of intelligent monitoring, and more particularly, to a 5G information transmission data security monitoring system.
Background
With the wide application of 5G networks, data security of information transmission becomes an important issue. Malicious attacks and intrusions can lead to serious consequences such as data leakage, system paralysis, and network service interruption. Therefore, it is necessary to build a 5G information transmission data security monitoring system.
However, the conventional data transmission security monitoring system requires a lot of manpower resources and time to analyze and detect security events in the network, resulting in low monitoring efficiency, and difficulty in meeting practical application requirements. Moreover, conventional monitoring systems fail to respond in real-time to security events, resulting in an increase in security issues and loss. Moreover, existing transmission data security monitoring systems lack sufficient reliability in handling large-scale data transmissions. That is, in the case of high load, the existing monitoring system may have problems such as delay, packet loss or data error, which affect the integrity and accuracy of the data.
Accordingly, an optimized 5G information transfer data security monitoring system is desired.
Disclosure of Invention
The present application has been made in order to solve the above technical problems. The embodiment of the application provides a 5G information transmission data security monitoring system, which monitors data traffic in a network by using a data packet detection and defense system, so that abnormal data packets are timely found and prevented to prevent malicious attacks and invasion. In this way, the transmitted data can be monitored and analyzed in real time, and corresponding measures can be taken to protect the security of the network.
According to one aspect of the present application, there is provided a 5G information transmission data security monitoring system, comprising:
the data flow acquisition module is used for acquiring data flow values transmitted by the 5G network at a plurality of preset time points in a preset time period;
the data flow time sequence analysis module is used for performing time sequence association analysis on the data flow values transmitted by the 5G network at a plurality of preset time points to obtain data flow absolute-fluctuation time sequence feature vectors; and
and the data flow abnormality detection module is used for determining whether the data flow is normal or not based on the data flow absolute-fluctuation time sequence feature vector.
According to another aspect of the present application, there is provided a 5G information transmission data security monitoring method, including:
acquiring data flow values transmitted by a 5G network at a plurality of preset time points in a preset time period;
performing time sequence association analysis on the data flow values transmitted by the 5G network at a plurality of preset time points to obtain data flow absolute-fluctuation time sequence feature vectors; and
and determining whether the data traffic is normal or not based on the data traffic absolute-fluctuation time sequence feature vector.
Compared with the prior art, the 5G information transmission data security monitoring system monitors data traffic in a network by using the data packet detection and defense system, so that abnormal data packets are timely found and prevented, and malicious attacks and invasion are prevented. In this way, the transmitted data can be monitored and analyzed in real time, and corresponding measures can be taken to protect the security of the network.
Drawings
The foregoing and other objects, features and advantages of the present application will become more apparent from the following more particular description of embodiments of the present application, as illustrated in the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
FIG. 1 is a block diagram of a 5G information transmission data security monitoring system according to an embodiment of the present application;
FIG. 2 is a system architecture diagram of a 5G information delivery data security monitoring system according to an embodiment of the present application;
FIG. 3 is a block diagram of a data traffic timing analysis module in a 5G information transmission data security monitoring system according to an embodiment of the present application;
FIG. 4 is a block diagram of a data traffic anomaly detection module in a 5G information transmission data security monitoring system according to an embodiment of the present application;
fig. 5 is a flowchart of a method for monitoring security of 5G information transmission data according to an embodiment of the present application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative, and different aspects of the systems and methods may use different modules.
Flowcharts are used in this application to describe the operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
The traditional data transmission safety monitoring system needs a large amount of human resources and time to analyze and detect the safety event in the network, so that the monitoring efficiency is low, and the actual application requirements are difficult to meet. Moreover, conventional monitoring systems fail to respond in real-time to security events, resulting in an increase in security issues and loss. Moreover, existing transmission data security monitoring systems lack sufficient reliability in handling large-scale data transmissions. That is, in the case of high load, the existing monitoring system may have problems such as delay, packet loss or data error, which affect the integrity and accuracy of the data. Accordingly, an optimized 5G information transfer data security monitoring system is desired.
In the technical scheme of the application, a 5G information transmission data safety monitoring system is provided. Fig. 1 is a block diagram of a 5G information transfer data security monitoring system according to an embodiment of the present application. Fig. 2 is a system architecture diagram of a 5G information transmission data security monitoring system according to an embodiment of the present application. As shown in fig. 1 and 2, a 5G information transmission data security monitoring system 300 according to an embodiment of the present application includes: a data traffic acquisition module 310, configured to acquire data traffic values transmitted by the 5G network at a plurality of predetermined time points within a predetermined time period; a data traffic timing analysis module 320, configured to perform timing correlation analysis on the data traffic values transmitted by the 5G network at the plurality of predetermined time points to obtain data traffic absolute-fluctuation timing feature vectors; and a data traffic anomaly detection module 330 for determining whether the data traffic is normal based on the data traffic absolute-fluctuation timing feature vector.
Specifically, the data traffic acquisition module 310 is configured to acquire data traffic values transmitted by the 5G network at a plurality of predetermined time points within a predetermined time period. The data flow value refers to the amount of data transmitted through the network during a specific period of time. It is typically metered in units of bits (bits) or bytes (bytes). The data flow values may be used to measure the extent of network usage, as well as to evaluate the bandwidth and performance of the network. In mobile communications, data traffic values are often used to calculate the traffic consumption of a user to determine if package limitations are exceeded. Knowledge and management of data flow values is also an important indicator for network providers and service providers to manage network resources and optimize network performance.
Accordingly, in one possible implementation, the data flow values transmitted by the 5G network at a plurality of predetermined time points within the predetermined time period may be obtained by, for example: determining a time period and a time point: first the period of time that you want to get the data traffic is determined, e.g. from 2023, 6, 1, to 2023, 6, 30. Then determine the time points at which you want to acquire data traffic, such as 9 am, 3 pm, and 8 pm each day; configuration data traffic monitoring device: a data flow monitoring device is installed at each predetermined point in time. This may be a dedicated network traffic monitor or a device supporting network traffic monitoring functions, such as a router or switch. Ensuring that these devices are already connected to the 5G network; setting a data flow monitor: entering a management interface of each data flow monitoring device and setting up a monitor to start monitoring data flow at a predetermined point in time. You can specify the time period and point of monitoring and select the monitored network interface (typically the interface to connect to the 5G network); acquiring a data flow value: after each predetermined point in time has ended, a data flow value is obtained from the data flow monitoring device. This may be accomplished by accessing a management interface of the monitoring device or using an associated API. Ensuring that the data flow value at each time point is recorded; analyzing and sorting data: and sorting and analyzing the obtained data flow value. You can use spreadsheet software or data analysis tools to process the data, calculate the average, maximum, or other statistical indicator of the data flow at each point in time.
Specifically, the data traffic timing analysis module 320 is configured to perform timing correlation analysis on the data traffic values transmitted by the 5G network at the plurality of predetermined time points to obtain data traffic absolute-fluctuation timing feature vectors. In particular, in one specific example of the present application, as shown in fig. 3, the data traffic timing analysis module 320 includes: a data traffic timing arrangement unit 321, configured to arrange data traffic values transmitted by the 5G network at the plurality of predetermined time points into data traffic timing input vectors according to a time dimension; a data flow fluctuation unit 322, configured to calculate a difference between data flow values of every two adjacent predetermined time points in the data flow timing input vector to obtain a data flow fluctuation timing input vector; a multi-dimensional data fusion unit 323, configured to fuse the data traffic timing input vector and the data traffic fluctuation timing input vector to obtain a data traffic absolute-fluctuation timing input matrix; and a data traffic timing variation feature extraction unit 324 for performing feature extraction on the data traffic absolute-fluctuation timing input matrix to obtain the data traffic absolute-fluctuation timing feature vector.
More specifically, the data traffic timing arrangement unit 321 is configured to arrange the data traffic values transmitted by the 5G network at the plurality of predetermined time points into data traffic timing input vectors according to a time dimension. Considering that the data flow value has a dynamic change rule in the time dimension, when malicious attack and invasion occur, the data flow can be abnormal. Therefore, analysis of the time sequence change condition of the data flow value can monitor the abnormality of the data flow, so that the safety of the network is ensured. Based on this, in the technical solution of the present application, the data traffic values transmitted by the 5G network at the plurality of predetermined time points need to be arranged into the data traffic timing input vector according to the time dimension, so as to integrate the distribution information of the data traffic values on the timing, so as to facilitate the subsequent analysis of the timing change situation of the data traffic values.
Accordingly, in one possible implementation, the data traffic values transmitted by the 5G network at the plurality of predetermined time points may be arranged into data traffic timing input vectors according to a time dimension, for example, by: determining a data acquisition time point: and determining a plurality of preset time points for data acquisition according to the crop growth period and the key stage to be monitored. These time points may be hourly, daily or weekly, etc.; mounting the sensor and the device: sensors and devices are installed in farmlands or planting areas for acquiring environmental parameters and crop height values. The sensors may include temperature sensors, humidity sensors, illumination sensors, wind speed sensors, rain sensors, barometric pressure sensors, and soil PH sensors. In addition, a height sensor is installed for measuring the growth height of crops; connect to 5G network: ensuring that the sensors and devices can connect to the 5G network for real-time data transmission. The high speed transmission and low delay characteristics of the 5G network will ensure that data can be transferred and processed in time; data acquisition and transmission: at a predetermined point in time, the sensor will collect data of environmental parameters and crop height values and transmit to a data processing center or cloud server via a 5G network. The data of each time point is transmitted according to the time sequence to form a data flow time sequence; data processing and analysis: and processing and analyzing the received data on a data processing center or a cloud server. A data analysis algorithm may be used to calculate the average environmental parameter value and crop height value for each time point. These data can be used to assess the growth status of crops and optimize planting conditions; data visualization and reporting: the processed and analyzed data are visually displayed and can be presented in a chart, curve and the like. Therefore, crop management personnel can intuitively know the growth condition of crops, and make decisions and adjust planting strategies according to the data report.
More specifically, the data flow fluctuation unit 322 is configured to calculate a difference between data flow values of every two adjacent predetermined time points in the data flow timing input vector to obtain the data flow fluctuation timing input vector. In consideration of the fact that the characteristic of the change in the data flow rate value in time series is weak, that is, when a data flow rate abnormality occurs, the change information on the data flow rate value in an abnormal state is a minute small-amplitude change characteristic, and it is difficult to sufficiently capture. Therefore, in the technical scheme of the application, the difference value between the data flow values of every two adjacent preset time points in the data flow time sequence input vector is further calculated to obtain the data flow fluctuation time sequence input vector, so that the relative fluctuation information of the data flow values in the time dimension is represented, and the monitoring of the abnormal change of the data flow values is facilitated.
Accordingly, in one possible implementation, the data flow fluctuation time sequence input vector may be obtained by calculating a difference between data flow values of each adjacent two predetermined time points in the data flow time sequence input vector, for example: defining a predetermined point in time: a predetermined point in time is determined at which the data flow value needs to be acquired. This may be at a plurality of time points within the crop growth cycle, for example a fixed time point per day or a fixed time point per week; acquiring a data flow value: at each predetermined point in time, a data flow value is acquired by a sensor or other data acquisition device. This may be obtained by a network traffic monitoring device, sensor or other related device; calculating a difference value: for each adjacent two predetermined time points of the data flow values, the difference between them is calculated. The difference may be obtained by subtracting the data flow value from the previous time point; constructing a time sequence input vector: and taking the calculated difference value as an element of a time sequence input vector of the data flow fluctuation. Each element represents the difference between the data flow values of two adjacent time points; analysis was performed using the time-ordered input vector: the constructed timing input vector is used for further data analysis and processing. Various machine learning algorithms, statistical methods, or other analysis techniques may be used to analyze patterns, trends, or anomalies in data flow fluctuations.
More specifically, the multidimensional data fusion unit 323 is configured to fuse the data traffic timing input vector and the data traffic fluctuation timing input vector to obtain a data traffic absolute-fluctuation timing input matrix. In particular, in one specific example of the present application, the multi-dimensional data fusion unit 323 is configured to: the data traffic timing input vector and the data traffic fluctuation timing input vector are fused using a gaussian density map to obtain the data traffic absolute-fluctuation timing input matrix. It should be understood that, in order to further improve the capturing and describing sufficiency of the time sequence change characteristics of the data flow value, so as to more accurately perform anomaly monitoring on the data flow, so as to protect the security of the network, in the technical scheme of the application, a gaussian density chart is used to fuse the data flow time sequence input vector and the data flow fluctuation time sequence input vector to obtain a data flow absolute-fluctuation time sequence input matrix, so that the absolute change characteristics and the relative fluctuation characteristics of the data flow value are used to comprehensively perform anomaly monitoring on the data flow.
Gaussian fusion (Gaussian fusion) is a common method of data fusion for combining information from multiple sensors or multiple data sources into a more accurate and reliable estimate. Based on the probability theory of Gaussian distribution, the method obtains a more accurate estimation result by carrying out weighted average on the measured values of different data sources. Gaussian fusion has found wide application in many fields, such as robot navigation, object tracking, sensor networks, etc. By fusing the information of the plurality of sensors, the robustness and accuracy of the system can be improved, so that the environment can be better understood and perceived.
It should be noted that, in other specific examples of the present application, the data traffic timing input vector and the data traffic fluctuation timing input vector may be fused in other manners to obtain a data traffic absolute-fluctuation timing input matrix, for example: collecting data traffic timing input vectors: environmental parameter data including temperature, humidity, illumination time, wind speed, rainfall, air pressure and soil PH value at a plurality of time points in the crop growth period are collected. The data at each time point is taken as an element of a vector; collecting data flow fluctuation time sequence input vectors: crop height values are collected at various time points during the crop growth cycle. The height value of each time point is taken as an element of a vector; merging the data traffic timing input vector and the data traffic fluctuation timing input vector: and fusing the data flow time sequence input vector and the data flow fluctuation time sequence input vector according to the time corresponding positions. Fusion can be performed using matrix operations or element-by-element; obtaining a data flow absolute-fluctuation time sequence input matrix: the fused vectors are converted into a matrix form, wherein each row represents data at one point in time. The matrix thus obtained is the absolute-fluctuation time sequence input matrix of the data flow.
More specifically, the data traffic timing variation feature extraction unit 324 is configured to perform feature extraction on the data traffic absolute-fluctuation time sequence input matrix to obtain the data traffic absolute-fluctuation time sequence feature vector. In particular, in one specific example of the present application, the data traffic timing variation feature extraction unit 324 is configured to: and the data flow absolute-fluctuation time sequence input matrix passes through a time sequence feature extractor based on a convolutional neural network model to obtain the data flow absolute-fluctuation time sequence feature vector. That is, feature mining of the data flow absolute-fluctuation time sequence input matrix is performed using a time sequence feature extractor based on a convolutional neural network model having excellent performance in terms of implicitly associated feature extraction, thereby extracting time sequence associated feature distribution information of the absolute quantity and the relative fluctuation quantity of the data flow value in the time dimension, and thus obtaining a data flow absolute-fluctuation time sequence feature vector.
Convolutional neural network (Convolutional Neural Network, CNN for short) is a deep learning model mainly used for image processing and pattern recognition. Its design inspiration comes from the neuronal structure in the biological vision system. The core idea of CNN is to extract image features by introducing a convolution layer and a pooling layer in the network, and perform tasks such as classification or regression through a fully connected layer. The convolution layer performs feature extraction on the input image through convolution operation, and can capture local spatial information in the image. The pooling layer is used to reduce the size of the feature map and preserve the main features. CNN models are typically composed of multiple convolutional layers, pooled layers, and fully connected layers. In each convolution layer, different convolution kernels may be used to extract different features. During the training process, the CNN optimizes the network parameters through a back-propagation algorithm so that the network can learn a more efficient representation of the features.
According to an embodiment of the present application, passing the data traffic absolute-fluctuation time sequence input matrix through a time sequence feature extractor based on a convolutional neural network model to obtain the data traffic absolute-fluctuation time sequence feature vector includes: each layer of the time sequence feature extractor based on the convolutional neural network model is used for respectively carrying out input data in forward transfer of the layer: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature images based on a feature matrix to obtain pooled feature images; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the time sequence feature extractor based on the convolutional neural network model is the data flow absolute-fluctuation time sequence feature vector, and the input of the first layer of the time sequence feature extractor based on the convolutional neural network model is the data flow absolute-fluctuation time sequence input matrix.
It should be noted that, in other specific examples of the present application, the feature extraction may be performed on the data traffic absolute-fluctuation time sequence input matrix in other manners to obtain the data traffic absolute-fluctuation time sequence feature vector, for example: data preprocessing: first, the raw data is preprocessed. This may include operations to remove noise, fill in missing values, normalize the data, etc., to ensure quality and consistency of the data; time sequence slicing: the data traffic absolute-fluctuation time sequence input matrix is segmented into a plurality of time sequence slices. Each time slice corresponds to data within a time period; feature extraction: for each time slice, some features may be extracted from it. Common feature extraction methods include statistical feature extraction, frequency domain feature extraction, time domain feature extraction, and the like. The following are some common feature extraction methods: and (3) extracting statistical characteristics: statistical indicators in the time series slice are calculated, such as mean, variance, maximum, minimum, etc. Extracting frequency domain features: the time-series slice is converted into the frequency domain, and frequency domain features such as spectrum energy, spectrum peak value and the like are extracted. Extracting time domain features: analyzing the time sequence slice in the time domain, and extracting time domain features such as an autocorrelation function, a difference function and the like; feature vector construction: the features extracted from each time series slice are combined into a feature vector. The length and the combination mode of the feature vectors can be selected according to the needs; feature selection: if the feature vector is too long or contains redundant information, a feature selection method may be used to select the most representative feature subset.
It should be noted that, in other specific examples of the present application, the data traffic absolute-fluctuation timing feature vector may also be obtained by performing timing correlation analysis on the data traffic values transmitted by the 5G network at the plurality of predetermined time points in other manners, for example: and (3) data acquisition: environmental parameter data including temperature, humidity, illumination time, wind speed, rainfall, barometric pressure, soil PH are collected at various time points during the crop growth cycle using altitude and other sensors. Meanwhile, using network measurement tools or devices, such as routers, switches, etc., collecting data flow values of the 5G network at these time points; data preprocessing: preprocessing the acquired data, including data cleaning, abnormal value removal, missing value filling and the like. For the environmental parameter data, smoothing processing may be performed to reduce noise effects. For data flow values, unit conversion and normalization processing can be performed for subsequent analysis; timing correlation analysis: and carrying out time sequence association analysis on the environmental parameter data and the data flow value to explore the relationship between the environmental parameter data and the data flow value. Time series analysis methods such as autocorrelation functions, cross correlation functions, spectral analysis, etc. can be used to analyze their timing characteristics and correlations; feature extraction: based on the result of the timing correlation analysis, an absolute-fluctuation timing characteristic vector of the data traffic is extracted. These feature vectors may include averages, variances, maxima, minima, fluctuation ranges, etc. of the data traffic. Suitable characteristics can be selected according to actual requirements; feature analysis and application: and analyzing and applying the extracted characteristics. The features may be classified, clustered, predicted, etc. using machine learning algorithms, statistical analysis methods, etc. These features can be used for decision support for crop growth management, such as optimizing planting conditions, predicting yield, monitoring anomalies, and the like.
Specifically, the data traffic anomaly detection module 330 is configured to determine whether the data traffic is normal based on the data traffic absolute-fluctuation time sequence feature vector. In particular, in one specific example of the present application, as shown in fig. 4, the data traffic anomaly detection module 330 includes: the feature optimization factor calculating unit 331 is configured to perform forward propagation information retention fusion on the data traffic timing input vector and the data traffic fluctuation timing input vector to obtain a corrected feature vector; a feature weighted optimization unit 332, configured to perform linear transformation on the correction feature vector, and calculate a position-wise point multiplication between the correction feature vector after linear transformation and the data flow absolute-fluctuation time sequence feature vector to obtain an optimized data flow absolute-fluctuation time sequence feature vector; and a data traffic anomaly classification unit 333 for passing the optimized data traffic absolute-fluctuation time sequence feature vector through a classifier to obtain a classification result indicating whether the data traffic is normal.
More specifically, the feature optimization factor calculating unit 331 is configured to perform forward propagation information preserving fusion on the data traffic timing input vector and the data traffic fluctuation timing input vector to obtain a corrected feature vector. In the technical solution of the present application, the data flow timing input vector and the data flow fluctuation timing input vector express the distribution of the data flow value along the timing and the fluctuation thereof along the timing direction, respectively, when the data flow timing input vector and the data flow fluctuation timing input vector are fused by the gaussian density map, the gaussian density map is considered to effectively fuse the distribution of the data flow value and the fluctuation thereof under the timing based on the distribution relationship between the data flow timing input vector and the data flow fluctuation timing input vector from the point of gaussian probability distribution, but due to the random characteristic when the gaussian discretization, the loss of absolute timing information is inevitably caused. Thus, when the data flow absolute-fluctuation time sequence input matrix is used for obtaining the data flow absolute-fluctuation time sequence characteristic vector through the time sequence characteristic extractor based on the convolution neural network model, the loss of absolute time sequence information can generate the loss of characteristic information when the model propagates forwards, thereby influencing the expression effect of the data flow absolute-fluctuation time sequence characteristic vector on local time sequence associated characteristics And thus the accuracy of the classification result obtained by the classifier is affected. Based on this, in one specific example of the present application, the data traffic is clocked into the vector, e.g., denoted asAnd the data flow fluctuation timing input vector, for example, denoted as +.>Performing forward propagation information preserving fusion to obtain correction feature vector, e.g. marked +.>Wherein->Expressed as:
wherein,is the data traffic timing input vector, +.>Is the data traffic fluctuation timing input vector,and->Respectively represent the left shift of the feature vector +.>Bit and right shift->Bit (s)/(s)>For rounding function, ++>Is the average of all eigenvalues of the data traffic timing input vector and the data traffic fluctuation timing input vector, +.>Representing a norm of the feature vector, +.>Is the distance between the data traffic timing input vector and the data traffic fluctuation timing input vector, and +.>Is a logarithmic function value based on 2 +.>And->Respectively representing subtraction and addition by position, +.>And->For weighting superparameters, < >>Is the correction feature vector. Here, the timing input vector is +_ for the data traffic>And the data flow fluctuation time sequence input vector +. >During forward propagation in a network model, an on-vector ruler generated due to local timing correlation feature extraction operationsFloating point distribution errors in degree and characteristic information loss, quantization errors and information loss in forward propagation are balanced and normalized by introducing a bitwise displacement operation of vectors from the viewpoint of uniformizing information, and distribution diversity is introduced by reshaping the distribution of characteristic parameters before feature extraction, thereby information retention (reproduction) is performed in a manner of expanding information entropy. Thus, the correction feature vector +.>And performing linear transformation and then performing dot multiplication on the absolute-fluctuation time sequence feature vector of the data flow, so that the information loss of the absolute-fluctuation time sequence feature vector of the data flow on the expression of the absolute time sequence correlation feature of the data flow value and the fluctuation value thereof can be reduced, and the accuracy of a classification result obtained by a classifier is improved. Therefore, the transmitted data can be monitored and analyzed in real time to effectively detect abnormal flow data, so that abnormal data packets can be found and prevented in time, malicious attacks and invasion can be prevented, and the network security can be protected.
It should be noted that, in other specific examples of the present application, the data traffic timing input vector and the data traffic fluctuation timing input vector may be further subjected to forward propagation information retention fusion by other manners to obtain a correction feature vector, for example: preparing data: first, data that needs to be fused is collected and prepared. This includes a data traffic timing input vector and a data traffic fluctuation timing input vector. These vectors contain data flow values and fluctuations at different points in time; feature extraction: for each input vector, a feature extraction operation is performed. This may include extracting useful features from the input vector using Convolutional Neural Network (CNN) or Recurrent Neural Network (RNN) methods, etc.; information retention fusion: and carrying out information retention fusion on the feature vectors. This can be achieved by different methods, for example using gating mechanisms (such as gating loop units GRU or long and short memory networks LSTM) to control retention and forgetting of features; correcting the feature vector: and correcting the fused characteristic vector. This may be done by adding a correction layer or using other methods to adjust the values of the feature vectors so that they more accurately represent the input data; outputting a result: finally, the corrected feature vector is used as an output result, which may be used for further analysis, prediction or other applications.
More specifically, the feature weighted optimization unit 332 is configured to perform linear transformation on the correction feature vector, and calculate a position-wise point multiplication of the correction feature vector after linear transformation and the data traffic absolute-fluctuation time sequence feature vector to obtain an optimized data traffic absolute-fluctuation time sequence feature vector.
Linear transformation refers to the operation of mathematically mapping elements of one vector space to another vector space. It has the property of preserving vector addition and scalar multiplication operations, i.e. satisfying the linearity property. Linear transforms have found wide application in many fields including linear algebra, computer graphics, signal processing, and the like. They can be used to describe the behavior of a physical system, solve a system of linear equations, perform data compression and feature extraction tasks, and the like.
The per-position point multiplication is a vector operation, also known as Hadamard product (Hadamard product) or element correspondence product. It multiplies the corresponding elements of two vectors with the same dimension to obtain a new vector. The point-wise multiplication is applied in many fields, such as pixel-level operation in image processing, filter design in signal processing, vectorization calculation, and the like. It can be used to operate on vectors on an element-by-element basis without changing the dimensions and structure of the vector.
Accordingly, in one possible implementation, the correction feature vector may be linearly transformed, and then the position-wise point multiplication of the linearly transformed correction feature vector and the data traffic absolute-fluctuation time sequence feature vector may be calculated to obtain an optimized data traffic absolute-fluctuation time sequence feature vector, for example: correcting the feature vector: first, the correction feature vector is subjected to linear transformation. Assuming that the correction eigenvector is a, the linear transformation matrix is M, and the correction eigenvector after linear transformation is b=m×a; data traffic absolute-fluctuation timing eigenvector: assuming the absolute-fluctuation time sequence feature vector of the data flow is C; multiplying by the position point: and (3) multiplying the corrected characteristic vector B after linear transformation and the absolute-fluctuation time sequence characteristic vector C of the data flow according to the position points. This means that the elements of the corresponding positions are multiplied. The resulting vector is D, where di=bi×ci, where i represents the index of the vector; optimizing data traffic absolute-fluctuation time sequence eigenvector: and the absolute-fluctuation time sequence characteristic vector of the finally obtained optimized data flow is D.
More specifically, the data traffic anomaly classification unit 333 is configured to pass the optimized data traffic absolute-fluctuation time sequence feature vector through a classifier to obtain a classification result, where the classification result is used to indicate whether the data traffic is normal. In particular, in one specific example of the present application, the data traffic abnormality classification unit 333 includes: the full-connection coding subunit is used for carrying out full-connection coding on the absolute-fluctuation time sequence feature vector of the optimized data flow by using a plurality of full-connection layers of the classifier so as to obtain a coding classification feature vector; and a classification result generation subunit, configured to pass the encoded classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
And the full-connection coding subunit is used for performing full-connection coding on the absolute-fluctuation time sequence feature vector of the optimized data flow by using a plurality of full-connection layers of the classifier so as to obtain a coding classification feature vector. It is worth mentioning that the classifier is a machine learning model for classifying input data into different categories or labels. The classifier can learn according to the characteristics of the input data and classify the new unlabeled data according to the learned patterns and rules.
Full-join encoding (Fully Connected Encoding) is a common neural network encoding method, also known as full-join layer or dense-join layer. In full-join coding, each neuron is joined to all neurons of the previous layer, each join having a weight. The coding mode can map the characteristics of the input data to a hidden layer or an output layer, and nonlinear combination and conversion of the characteristics are realized. The process of full-concatenated coding can be described simply as: the input data is mapped to either the hidden layer or the output layer by a series of linear transforms and nonlinear activation functions. The output of each neuron is weighted by its input and the corresponding weight and non-linearly transformed by an activation function. In this way, each neuron can learn different features and patterns in the input data. Full-connection coding is widely applied to tasks such as image recognition, natural language processing, voice recognition and the like in deep learning. Through the superposition of multiple full-connection layers, the neural network can learn the higher-level characteristic representation, and the expression capacity and performance of the model are improved.
And the classification result generation subunit is used for passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result. Notably, the Softmax classification function is a commonly used classification function, typically used for multi-class classification problems. It converts the input vector into a probability distribution, where each element represents the probability that the input belongs to a certain class. The output of the Softmax function is a probability distribution, with values of all elements between 0 and 1, and the sum of all elements is 1. This makes it suitable for multi-class classification problems, where the input vector can be mapped onto probabilities of different classes.
It should be noted that, in other specific examples of the present application, the optimized data traffic absolute-fluctuation time sequence feature vector may also be passed through a classifier in other manners to obtain a classification result, where the classification result is used to indicate whether the data traffic is normal, for example: collecting data: data is collected for training and testing the classifier. These data should include samples of normal data traffic and abnormal data traffic; feature extraction: the collected data is feature extracted to be represented as feature vectors. In this case, the optimized data traffic absolute-fluctuation timing characteristic vector is used as an input characteristic; dividing data: the data set is divided into a training set and a test set. Typically, most of the data is used to train the classifier, and a small portion of the data is used to evaluate the performance of the classifier; training a classifier: the classifier is trained using the training set. Common classifiers include decision trees, support vector machines, logistic regression, etc. The goal of the classifier is to learn how to associate input features with corresponding categories (normal or abnormal); evaluation classifier: the trained classifier is evaluated using the test set. By comparing the prediction result of the classifier with the actual label, the performance indexes such as the accuracy, the precision, the recall rate and the like of the classifier can be calculated; tuning and improvement: based on the evaluation results, the classifier can be tuned and improved. This may include adjusting super parameters of the classifier, adding more training data, improving feature extraction methods, etc.; deployment and application: when the classifier reaches a satisfactory level of performance, it can be deployed into a practical application. By inputting the new data traffic into the classifier, a classification result of whether the data traffic is normal can be obtained.
It should be noted that, in other specific examples of the present application, it may also be determined whether the data traffic is normal based on the absolute-fluctuation timing feature vector of the data traffic in other manners, for example: and (3) data acquisition: first, real-time information of data traffic needs to be collected by sensors or monitoring devices. The sensors can be arranged at the positions of network nodes, servers, routers and the like so as to acquire accurate data flow information; data preprocessing: the raw data collected typically requires preprocessing to remove noise, smooth the data, and perform format conversion. Common pretreatment methods include filtering, downsampling, data normalization and the like; feature extraction: extracting features from the preprocessed data is a key step in determining whether the data traffic is normal. The features may be statistical properties of the data, such as mean, variance, maximum and minimum, or may be frequency domain features, time domain features, or other domain-specific features; feature vector construction: the extracted features are combined into feature vectors. The feature vector is a mathematical representation describing the data flow and can be used to characterize fluctuations in the data flow; feature selection: for the constructed feature vectors, a feature selection algorithm can be used to select the most representative feature subset to reduce the feature dimension and improve classification or anomaly detection performance; normal/abnormal classification: feature vectors are trained and classified using machine learning, statistical models, or other classification algorithms. In the training stage, a marked data sample is required to be used for model training, then an unknown data sample is input into a model for classification, and whether the data flow is normal or not is judged; abnormality detection and alarm: if the classification results indicate that the data traffic is abnormal, the system may trigger an alarm or take corresponding action, such as notifying a network administrator, automatically adjusting the network configuration, or taking other emergency action.
In summary, a 5G messaging data security monitoring system 300 is illustrated that monitors data traffic in a network using a packet detection and defense system to discover and block abnormal packets in time to prevent malicious attacks and intrusions. In this way, the transmitted data can be monitored and analyzed in real time, and corresponding measures can be taken to protect the security of the network.
As described above, the 5G information transmission data security monitoring system 300 according to the embodiment of the present application may be implemented in various wireless terminals, for example, a server or the like having a 5G information transmission data security monitoring algorithm. In one possible implementation, the 5G information transmission data security monitoring system 300 according to embodiments of the present application may be integrated into a wireless terminal as a software module and/or hardware module. For example, the 5G information transfer data security monitoring system 300 may be a software module in the operating system of the wireless terminal or may be an application developed for the wireless terminal; of course, the 5G information transmission data security monitoring system 300 may also be one of a plurality of hardware modules of the wireless terminal.
Alternatively, in another example, the 5G information transmission data security monitoring system 300 and the wireless terminal may be separate devices, and the 5G information transmission data security monitoring system 300 may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information in a agreed data format.
Further, a 5G information transmission data security monitoring method is also provided.
Fig. 5 is a flowchart of a method for monitoring security of 5G information transmission data according to an embodiment of the present application. As shown in fig. 5, a method for monitoring security of 5G information transmission data according to an embodiment of the present application includes: s110, acquiring data flow values transmitted by a 5G network at a plurality of preset time points in a preset time period; s120, performing time sequence association analysis on the data flow values transmitted by the 5G network at a plurality of preset time points to obtain data flow absolute-fluctuation time sequence feature vectors; and S130, determining whether the data traffic is normal or not based on the absolute-fluctuation time sequence feature vector of the data traffic.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (4)
1. A 5G information transmission data security monitoring system, comprising:
the data flow acquisition module is used for acquiring data flow values transmitted by the 5G network at a plurality of preset time points in a preset time period;
the data flow time sequence analysis module is used for performing time sequence association analysis on the data flow values transmitted by the 5G network at a plurality of preset time points to obtain data flow absolute-fluctuation time sequence feature vectors; and
the data flow abnormality detection module is used for determining whether the data flow is normal or not based on the data flow absolute-fluctuation time sequence feature vector;
wherein, the data traffic timing analysis module includes:
a data traffic timing arrangement unit, configured to arrange data traffic values transmitted by the 5G network at the plurality of predetermined time points into data traffic timing input vectors according to a time dimension;
the data flow fluctuation unit is used for calculating the difference value between the data flow values of every two adjacent preset time points in the data flow time sequence input vector to obtain the data flow fluctuation time sequence input vector;
the multidimensional data fusion unit is used for fusing the data flow time sequence input vector and the data flow fluctuation time sequence input vector to obtain a data flow absolute-fluctuation time sequence input matrix; and
The data flow time sequence change feature extraction unit is used for carrying out feature extraction on the data flow absolute-fluctuation time sequence input matrix to obtain the data flow absolute-fluctuation time sequence feature vector;
wherein, the multidimensional data fusion unit is used for: fusing the data traffic timing input vector and the data traffic fluctuation timing input vector using a gaussian density map to obtain the data traffic absolute-fluctuation timing input matrix;
the data traffic time sequence change feature extraction unit is used for: the data flow absolute-fluctuation time sequence input matrix passes through a time sequence feature extractor based on a convolutional neural network model to obtain the data flow absolute-fluctuation time sequence feature vector;
the data traffic time sequence change feature extraction unit is used for: each layer of the time sequence feature extractor based on the convolutional neural network model is used for respectively carrying out input data in forward transfer of the layer:
carrying out convolution processing on input data to obtain a convolution characteristic diagram;
pooling the convolution feature images based on a feature matrix to obtain pooled feature images; and
non-linear activation is carried out on the pooled feature map so as to obtain an activated feature map;
The output of the last layer of the time sequence feature extractor based on the convolutional neural network model is the data flow absolute-fluctuation time sequence feature vector, and the input of the first layer of the time sequence feature extractor based on the convolutional neural network model is the data flow absolute-fluctuation time sequence input matrix.
2. The 5G information transmission data security monitoring system of claim 1, wherein the data traffic anomaly detection module comprises:
the characteristic optimization factor calculation unit is used for carrying out forward propagation information retention fusion on the data flow time sequence input vector and the data flow fluctuation time sequence input vector so as to obtain a correction characteristic vector;
the characteristic weighting optimization unit is used for carrying out linear transformation on the correction characteristic vector, and then calculating the position-based point multiplication of the correction characteristic vector after the linear transformation and the data flow absolute-fluctuation time sequence characteristic vector to obtain an optimized data flow absolute-fluctuation time sequence characteristic vector; and
and the data flow abnormal classification unit is used for enabling the optimized data flow absolute-fluctuation time sequence feature vector to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the data flow is normal or not.
3. The 5G information transmission data security monitoring system according to claim 2, wherein the feature optimization factor calculating unit is configured to: carrying out forward propagation information retention fusion on the data flow time sequence input vector and the data flow fluctuation time sequence input vector by using the following fusion optimization formula to obtain the correction feature vector;
the fusion optimization formula is as follows:
wherein V is 1 Is the data traffic timing input vector, V 2 Is the data flow fluctuation time sequence input vector"s and > s represent shifting the feature vector left by s bits and right by s bits, respectively, round (·) is a rounding function,is the average of all eigenvalues of the data traffic timing input vector and the data traffic fluctuation timing input vector, |·|| 1 Represents a norm, d (V) 1 ,V 2 ) Is the distance between the data traffic timing input vector and the data traffic fluctuation timing input vector, and log is a logarithmic function value based on 2, < ->And->Respectively represent subtraction and addition by position, alpha and beta are weighted super parameters, and V' is the correction feature vector.
4. The 5G information transmission data security monitoring system of claim 3, wherein the data traffic anomaly classification unit comprises:
The full-connection coding subunit is used for carrying out full-connection coding on the absolute-fluctuation time sequence feature vector of the optimized data flow by using a plurality of full-connection layers of the classifier so as to obtain a coding classification feature vector; and
and the classification result generation subunit is used for passing the coding classification feature vector through a Softmax classification function of the classifier to obtain the classification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310836452.2A CN116684878B (en) | 2023-07-10 | 2023-07-10 | 5G information transmission data safety monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310836452.2A CN116684878B (en) | 2023-07-10 | 2023-07-10 | 5G information transmission data safety monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116684878A CN116684878A (en) | 2023-09-01 |
| CN116684878B true CN116684878B (en) | 2024-01-30 |
Family
ID=87783859
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310836452.2A Active CN116684878B (en) | 2023-07-10 | 2023-07-10 | 5G information transmission data safety monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116684878B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117156442B (en) * | 2023-10-31 | 2024-03-12 | 深圳市中科鼎创科技股份有限公司 | Cloud data security protection method and system based on 5G network |
| CN117834256A (en) * | 2023-12-29 | 2024-04-05 | 广东云达智能物联科技有限公司 | Internet of things equipment safety monitoring system based on big data |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112968816A (en) * | 2021-03-14 | 2021-06-15 | 国网浙江省电力有限公司电力科学研究院 | Method and system for screening abnormality of Internet of things equipment through flow abnormality detection |
| WO2022113273A1 (en) * | 2020-11-27 | 2022-06-02 | 日本電信電話株式会社 | Time-series data analysis device, time-series data analysis method, and time-series data analysis program |
| WO2022142120A1 (en) * | 2020-12-31 | 2022-07-07 | 平安科技（深圳）有限公司 | Data detection method and apparatus based on artificial intelligence, and server and storage medium |
| CN114936789A (en) * | 2022-04-30 | 2022-08-23 | 宁波大学科学技术学院 | Method for monitoring state of grid-connected photovoltaic power generation system based on time sequence characteristic decomposition technology |
| CN115811440A (en) * | 2023-01-12 | 2023-03-17 | 南京众智维信息科技有限公司 | Real-time flow detection method based on network situation awareness |
| CN116015837A (en) * | 2022-12-22 | 2023-04-25 | 南阳理工学院 | Intrusion detection method and system for computer network information security |
-
2023
- 2023-07-10 CN CN202310836452.2A patent/CN116684878B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022113273A1 (en) * | 2020-11-27 | 2022-06-02 | 日本電信電話株式会社 | Time-series data analysis device, time-series data analysis method, and time-series data analysis program |
| WO2022142120A1 (en) * | 2020-12-31 | 2022-07-07 | 平安科技（深圳）有限公司 | Data detection method and apparatus based on artificial intelligence, and server and storage medium |
| CN112968816A (en) * | 2021-03-14 | 2021-06-15 | 国网浙江省电力有限公司电力科学研究院 | Method and system for screening abnormality of Internet of things equipment through flow abnormality detection |
| CN114936789A (en) * | 2022-04-30 | 2022-08-23 | 宁波大学科学技术学院 | Method for monitoring state of grid-connected photovoltaic power generation system based on time sequence characteristic decomposition technology |
| CN116015837A (en) * | 2022-12-22 | 2023-04-25 | 南阳理工学院 | Intrusion detection method and system for computer network information security |
| CN115811440A (en) * | 2023-01-12 | 2023-03-17 | 南京众智维信息科技有限公司 | Real-time flow detection method based on network situation awareness |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116684878A (en) | 2023-09-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116684878B (en) | 5G information transmission data safety monitoring system | |
| CN111178456A (en) | Abnormal index detection method and device, computer equipment and storage medium | |
| WO2022052510A1 (en) | Anomaly detection system and method for sterile filling production line | |
| CN109446804B (en) | Intrusion detection method based on multi-scale feature connection convolutional neural network | |
| CN112367303B (en) | Distributed self-learning abnormal flow collaborative detection method and system | |
| CN115080290B (en) | Abnormal data detection method and system based on intelligent algorithm | |
| US20230118175A1 (en) | Event analysis in an electric power system | |
| CN117156442B (en) | Cloud data security protection method and system based on 5G network | |
| CN117041017B (en) | Intelligent operation and maintenance management method and system for data center | |
| CN112132430A (en) | Reliability evaluation method and system for distributed state sensor of power distribution main equipment | |
| CN111949496B (en) | Data detection method and device | |
| CN116557787A (en) | Intelligent evaluation system and method for pipe network state | |
| CN114048546B (en) | Method for predicting residual service life of aeroengine based on graph convolution network and unsupervised domain self-adaption | |
| CN117671396B (en) | Intelligent monitoring and early warning system and method for construction progress | |
| CN117388893B (en) | Multi-device positioning system based on GPS | |
| CN117421994A (en) | Edge application health monitoring method and system | |
| CN114338351B (en) | Network anomaly root cause determination method and device, computer equipment and storage medium | |
| CN113807716A (en) | Network operation and maintenance automation method based on artificial intelligence | |
| YR et al. | Iot streaming data outlier detection and sensor data aggregation | |
| Lin et al. | A semi-supervised approach for abnormal event prediction on large operational network time-series data | |
| Kumar et al. | Enhanced-KNN (M-KNN) based outlier detection and sensor data aggregation for large data streams in the IoT-cloud | |
| CN117421684B (en) | Abnormal data monitoring and analyzing method based on data mining and neural network | |
| CN116660761B (en) | Lithium ion battery detection method and system | |
| CN113469247B (en) | Network asset abnormity detection method | |
| CN117579513B (en) | Visual operation and maintenance system and method for convergence and diversion equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |