327results about How to "Reduce false negative rate" patented technology

The invention belongs to the field of network security, and discloses a network security evaluation system and method based on a dynamic attack and defense game model, and the evaluation system comprises four functional modules of attack and defense game construction, risk prediction, dynamic defense optimization and security situation awareness. According to the method, the idea of dynamic attack and defense game is introduced, multi-level and multi-scene attack and defense simulation is carried out according to historical states, strategy data and real-time data, and the optimal attack path and attack strategy are calculated and analyzed through a game equilibrium solution; according to the method, network resources and network security resources are dynamically adjusted by relying on reinforcement learning and deep learning technologies and a defense rule base generated by pre-training, network configuration is optimized according to a real-time evaluation result, and waste of system resources is reduced. By implementing the system and the method provided by the invention, the security of the target network can be dynamically evaluated, the security defense strategy of the network can be adjusted in real time, and unknown attacks such as advanced persistent threat (APT) and zero-day attack can be effectively resisted.

The invention provides a network attack risk mapping assessment method and system, and relates to the technical field of network attack risks, and the method comprises the steps: collecting a network flow data packet to extract a multi-dimensional attack feature vector, employing a deep neural network to carry out feature learning to obtain an attack type recognition result and an attack intensity assessment value, and constructing an attack feature standard model; based on the attack type identification result and the attack strength evaluation value, combining an asset weight coefficient, a vulnerability hazard level and a vulnerability utilization difficulty coefficient to construct an asset vulnerability evaluation model; and performing association analysis on the real-time attack feature data and the asset vulnerability assessment score, constructing a risk mapping matrix, calculating a comprehensive risk score, and generating risk early warning information. According to the invention, accurate identification, dynamic assessment and timely early warning of the network attack risk are realized, and the accuracy and real-time performance of risk assessment are improved.

The invention provides a satellite measurement and control data anomaly detection and intelligent diagnosis early warning method and system, and relates to the technical field of satellite measurement and control, and the method comprises the steps: obtaining multi-source heterogeneous data in a satellite measurement and control system, and carrying out the preprocessing of the multi-source heterogeneous data; constructing a multi-level space-time fusion network model, inputting the preprocessed multi-source heterogeneous data into the multi-level space-time fusion network model, and extracting high-dimensional space-time features; based on the extracted high-dimensional spatial-temporal features, designing a dynamic adaptive anomaly detection algorithm, and performing anomaly detection on the satellite measurement and control data; according to an anomaly detection result, performing intelligent diagnosis by using a pre-constructed multi-level satellite system knowledge graph; based on the intelligent diagnosis result, multi-level early warning information is generated; a distributed edge computing architecture is designed, and partial data processing and anomaly detection tasks are deployed to a ground station and a satellite end; and presenting the generated multi-level early warning information through a visual interface, and automatically triggering a corresponding emergency plan according to the early warning level.

The invention relates to the technical field of user behavior analysis, and discloses a method for analyzing abnormal user behaviors based on logs and flow data, and the method comprises the steps: collecting user behavior data, including historical user behavior data and real-time user behavior data; based on historical user behavior data, constructing a group behavior baseline and an individual behavior baseline, and obtaining key behavior characteristics of the user; the deviation degree DEV of the key behavior characteristics of the user deviating from the group behavior baseline and the matching degree SimScore of the real-time behavior sequence of the user and the personal behavior baseline are calculated; according to the deviation degree DEV and the matching degree SimScore, whether the user behavior is abnormal or not is judged, and the risk level of the abnormal behavior is determined; triggering corresponding abnormal alarm and response measures according to the risk level; according to the method, the abnormal behavior of the user can be identified more accurately by fusing the log and the flow data and combining group and individual behavior baselines, and the accuracy and efficiency of anomaly detection are improved.

The invention discloses a network fault adaptive detection system based on machine learning, which relates to the technical field of network security and comprises a data acquisition module, a feature extraction and selection module, a model training and updating module, a fault detection module, a fault positioning and diagnosis module and an adaptive optimization module. According to the network fault adaptive detection system based on machine learning, by generating new features, the expression ability of a feature space is significantly enhanced, and the detection precision of a machine learning model is improved; the deep learning model based on the causal relationship is combined with the graph neural network and time sequence analysis, so that the complex causal relationship in the network is effectively processed, and the fault diagnosis is more accurate; through the combination of the multi-objective evolutionary algorithm and the fuzzy logic control algorithm, the network optimization strategy is more flexible and efficient, the network performance is improved, the weight of the optimization objective can be dynamically adjusted according to the actual demand, and the performance of the system in a complex network environment is remarkably improved.

The invention discloses a 5G message video monitoring method based on artificial intelligence. The method comprises the following steps: S1, constructing a multi-modal data set; s2, multi-modal fusion features are generated by using a joint convolutional neural network; s3, generating a target behavior trend curve and a target behavior prediction result by using the 3D convolutional neural network; s4, generating a target threshold curve by using an adaptive algorithm based on variable domain search, and obtaining behavior abnormality warning information; s5, generating comprehensive alarm information by using a method of combining fuzzy logic reasoning and a Bayesian network; s6, cross-camera data space-time correlation reasoning is carried out by using the graph neural network; s7, constructing an event severity curve by using a multivariable regression analysis and analytic hierarchy process, and generating a severity level and an event response measure of the event; and S8, pushing alarm information and event response measures to related personnel or equipment through the 5G message platform. The invention provides an efficient video monitoring method in combination with artificial intelligence and a 5G network.

The invention relates to the technical field of program exception positioning, in particular to an AI-based data interface program exception fault pre-positioning algorithm, which comprises the following steps: S1, data stream pre-analysis; s2, capturing an abnormal signal; s3, performing abnormal clustering and feature extraction; s4, interface behavior modeling is carried out; s5, abnormal traceability positioning; s6, generating a self-adaptive repair suggestion; s7, performing feedback circulation and continuous learning; and S8, performing visualization and report generation. Through the steps of data stream classification, key field extraction, behavior modeling and the like, the system can accurately capture abnormal signals in mass data, meanwhile, an abnormal mode is visually displayed through clustering analysis and a dimension reduction technology, a reliable foundation is laid for subsequent positioning and repairing, and in addition, the method has the advantages of being high in practicability and easy to popularize. The abnormal source is quickly positioned by adopting methods such as topological sorting and causal network reasoning, the false alarm rate and the missing report rate in the positioning process are effectively reduced by combining a sliding window and time sequence analysis, and the problem solving efficiency is greatly improved.

The invention discloses an AI-driven abnormal transaction intelligent monitoring and analysis system and method, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining structured features and unstructured features, carrying out the feature fusion, and constructing an account feature vector; constructing a cross-domain heterogeneous graph, learning an embedded vector of an account node in the cross-domain heterogeneous graph based on a time sequence heterogeneous graph neural network, and generating an account portrait vector; training an abnormal transaction detection model, and predicting the abnormal probability of the current real-time transaction record of the account by taking the account portrait vector and the transaction record as input data; dividing all accounts into account groups based on the account portrait vectors, calculating a group abnormal transaction threshold value, and calculating an adaptive abnormal transaction threshold value based on the group abnormal transaction threshold value and the similarity between the account portrait vectors and the center vectors of the account groups to which the account portrait vectors belong; and if the abnormal probability is greater than a self-adaptive abnormal transaction threshold, marking the transaction of the account as an abnormal transaction, triggering risk control measures, and regularly updating the self-adaptive abnormal transaction threshold.

The invention relates to the technical field of Internet of Things monitoring, and particularly discloses a monitoring method and system based on an Internet of Things architecture, and the method comprises the steps: collecting environment data in real time through deploying a plurality of temperature and humidity sensors in a monitoring region, and transmitting the data to a central processing unit or a cloud end through a wireless network for storage and preliminary processing; the system establishes a prediction model by fitting historical data, evaluates the accuracy of sensor data, and calibrates or replaces an abnormal sensor to ensure the reliability of the data; the system comprehensively analyzes the calibrated sensor data, calculates a temperature abnormal coefficient and a humidity abnormal coefficient, and evaluates the overall environment condition of the monitoring area; when an abnormal condition is detected, the system immediately starts an early warning mechanism, sends alarm information to a monitoring center or related personnel, and records the detailed condition of the abnormal event for subsequent analysis and processing.

The invention discloses an online public opinion research, judgment, analysis, classification and grading early warning method and system, and the method comprises the steps: constructing a malicious public opinion data detection and judgment model, and carrying out the iterative training of a pre-training neural network through large-scale online public opinion historical data, so as to achieve the fine adjustment and optimization of the model; after malicious public opinion data are detected, fine-grained classification of malicious public opinions is realized through deep semantic comprehension and multi-dimensional text structure analysis by adopting BERT and ERNIE deep learning models and combining semantic role labeling and dependency syntactic analysis technologies; a malicious public opinion data grading and distinguishing model is constructed, deep correlation between public opinion events is captured through multi-layer convolution operation, and the recognition capacity for public opinion sensitivity and urgency degree is improved. According to the invention, malicious public opinion data related to a specific industry field can be efficiently and accurately identified and classified, and the malicious public opinion data is subjected to severity grading, so that the accuracy and the real-time performance of network public opinion management are improved.

The invention relates to a GNSS-based water conservancy facility deformation monitoring and early warning method, system and device and a medium, and the method comprises the steps: obtaining GNSS monitoring network data of a target part of a water conservancy facility, and carrying out the real-time dynamic differential processing, and obtaining corresponding three-dimensional coordinate data; acquiring environmental factor data, and performing multi-source feature fusion on the environmental factor data and the three-dimensional coordinate data to obtain a corresponding deformation feature vector; performing prediction analysis on the deformation feature vector according to a preset whale optimization algorithm to obtain a corresponding deformation trend prediction result; setting a multi-level early warning threshold according to the deformation feature vector, and performing early warning analysis on a deformation trend prediction result to obtain a corresponding initial early warning level; and obtaining standard deformation characteristic information of the deformation rate and the acceleration of the water conservancy facility, and performing comprehensive evaluation on the standard deformation characteristic information based on a deformation trend prediction result to obtain a corresponding early warning index. Potential risks can be found and processed in time, and the possibility of hydraulic engineering accidents is reduced.

The invention relates to the technical field of fault detection for a wireless communication network, and discloses a fault detection method for the wireless communication network. By collecting data of base station signal strength, network delay, data packet loss rate and user equipment signal quality, the problem of insufficient fault detection caused by a single index is solved. Through multi-dimensional data acquisition, the system can comprehensively evaluate network performance, the fault detection accuracy is improved, and different fault types can be effectively identified especially in a complex fault mode. By storing the data according to the time sequence, the problem of time sequence chaos is avoided, and accurate detection of time-varying faults is ensured. The comprehensive data vector generated by each time of sampling comprises a plurality of network performance indexes, so that the fault detection and positioning capability is improved. Abnormal values are eliminated through data preprocessing, the data quality is ensured, an accurate basis is provided for subsequent analysis, and the reliability of a detection result is ensured.

The invention provides a subway pedestrian anomaly detection method and system based on an improved yov8 network and a clip model, and relates to the technical field of subway pedestrian detection, and the method comprises the steps: obtaining a video frame in a subway scene, and carrying out the preprocessing of the video frame; inputting the preprocessed frame data into an improved yolov8 neural network model to obtain an abnormal behavior target detection frame, and performing target candidate tracking on the target detection frame by using a target tracking algorithm to obtain a candidate image of a target area of a specific behavior; the method comprises the following steps: inputting a candidate image containing a target area into a clip model, inputting a set detection text into the clip model, mapping the detection text and the candidate image of the target area, performing text-image similarity matching, and optimizing a similarity matching threshold by adopting a Q-Learning reinforcement learning immune algorithm to obtain a similarity matching result; and the abnormal behavior detection accuracy is improved.

The invention discloses a fan blade icing monitoring system and method, and relates to the technical field of wind power generation, and the system collects temperature, humidity and vibration signals in real time through a multi-sensor module installed on a fan blade, fuses multi-parameter data through an edge calculation unit, and calculates a blade icing risk factor # imgabs0 #. The risk factors are calculated by adopting a dynamic weighting model, and the icing state of the blade is accurately evaluated in combination with normalized characteristic values # imgabs1 #, # imgabs2 # and # imgabs3 #. And when the risk factor exceeds a set threshold value, the system triggers an alarm and transmits data to the cloud through the wireless communication module. The cloud platform predicts the future icing risk based on a long-short term memory (LSTM) neural network model in combination with historical data and real-time monitoring data, the accuracy and real-time performance of icing monitoring are improved, the method is suitable for operation in cold regions and high-altitude wind fields, and reliable guarantee is provided for safe and efficient operation of fans.

The invention discloses a box-type substation monitoring data processing method and system, and relates to the technical field of monitoring data processing, and the method comprises the steps: determining the type of monitoring data, constructing a monitoring data set and an abnormal fault set, and determining the correlation between the monitoring data set and the abnormal fault set; the method comprises the following steps: calculating a correlation index between monitoring data and an abnormal type, and a weight of each associated monitoring data in the abnormal type; a periodic monitoring strategy is adopted, data changes are captured in real time, abnormal values are screened out, and data fluctuation interference is eliminated through analysis; aiming at the quantity of initial monitoring data, adjusting and executing an anomaly detection strategy: comprehensively considering all anomaly types associated with the data when the data is single, and predicting a future anomaly risk by utilizing buffer time; when multiple data exist, completely matched anomaly judgment is preferentially carried out, and then whether anomaly judgment of single data needs to be carried out or not is judged; comprehensive and real-time monitoring and efficient abnormity early warning of the operation state of the box-type substation are realized, and the safe and stable operation capability of the substation is improved.

The invention discloses an intelligent tightening tool capacity allocation system and method based on deep learning, and relates to the technical field of tightening tools, multi-modal data is captured in real time, the data weight is dynamically adjusted by using an attention mechanism, the capacity is predicted in combination with a deep learning algorithm, and dynamic production requirements and sudden tasks are quickly responded; in the aspect of exception handling, dual indexes of a variational auto-encoder VAE model, reconstruction error and distribution deviation are introduced, an exception mode is captured, a probability distribution model of normal operation data is established in combination with unsupervised learning, and the false alarm rate and the missing report rate are remarkably reduced; abnormal data are fed back to the productivity prediction module in real time through a closed-loop mechanism, and deep learning model parameters are dynamically optimized, so that the system can adapt to changes of production tasks and attenuation of tool performance; and the allocation module is adopted to allocate tool types and optimize paths through task priorities, so that the resource utilization efficiency is improved, and tool conflicts and station waiting time are reduced.

The invention relates to the technical field of power failure troubleshooting, and discloses a single-phase earth fault rapid positioning method based on multi-source data fusion, and the method comprises the steps: collecting historical fault data, power system operation data and environment data through employing a plurality of monitoring devices, such as a power system monitoring device, a fault recorder and a distributed sensor; and forming a basic data set. By performing fault feature analysis on the data set, a dual machine learning model is constructed, including a fault prediction model and a positioning model. A training data set is used to train a model, model parameters are optimized, then the trained model is used to predict real-time data, potential fault risks are identified, and a targeted troubleshooting plan and a rapid positioning strategy are formulated. According to the invention, through data fusion and a machine learning algorithm, the accuracy of fault positioning is improved, the positioning time is shortened, and the power failure time and the influence on users are reduced.

The invention provides a substation safety management and control method and system based on a three-dimensional reconstruction model, and relates to the technical field of safety management and control, and the method comprises the steps: obtaining real-time point cloud data inputted by a laser point cloud sensor and a real-time image collected by a camera; comparing the real-time point cloud data with a background point cloud model, and extracting a changed dynamic region by using a background difference algorithm; the dynamic reconstruction module is used for identifying a first position of a first dynamic target in the dynamic region based on the real-time point cloud data; calculating a second position of a second dynamic target contained in the real-time image; if the first position is successfully matched with the second position and the sparse structure of the real-time point cloud data is successfully matched with dense pixels of the real-time image, determining that the first dynamic target and the second dynamic target are both dynamic flight targets; and determining the position of the dynamic flight target according to the first position and the second position, and marking in the three-dimensional model. The safety management and control precision of the transformer substation can be improved.

The invention discloses a chromogenic culture medium for detecting gram-negative bacteria in bovine mastitis and a test plate thereof, the culture medium comprises a nutritional ingredient mixture, a composite inhibitor, a composite chromogenic enzyme substrate and cold water gel, the compound chromogenic enzyme substrate is red tetrazole, 5-bromo-6-chloro-3-indole-beta-D-galactoside, and 5-bromo-4-chloro-3-indole-beta-D-glucopyranoside, and the compound chromogenic enzyme substrate is a compound chromogenic enzyme substrate, and the compound chromogenic enzyme substrate is 5-bromo-6-chloro-3-indole-beta-D-glucopyranoside. The chromogenic culture medium and the test board prepared from the chromogenic culture medium can effectively inhibit the growth of non-gram negative bacteria, have the characteristics of strong specificity, high sensitivity, short detection period, easy observation and low detection cost, and have huge development potential and wide application prospects in microbiological detection.

The invention is suitable for the technical field of load identification, and relates to an electric bicycle home-entry charging identification method, a medium and a terminal, and the method comprises the steps: S10, carrying out the real-time data collection of a voltage u (t) and a current i (t) of a wire inlet of a main ammeter, and calculating the time sequence of an active power P and a reactive power Q; s20, through an inverted Z-shaped window sliding event detection method, the maximum active power difference value of the left window and the right window is calculated through the sliding window, whether the difference value exceeds a set threshold value or not is judged, and therefore the starting event of the electric equipment is determined; s30, identifying a maximum active power difference value, a maximum reactive power difference value and a ratio of the maximum active power difference value to the maximum reactive power difference value by adopting a characteristic increment threshold value, and if the three values meet conditions at the same time, executing the step S40; and S40, analyzing the output data by using a one-dimensional convolutional neural network model, and identifying a charging starting event of the electric bicycle. According to the invention, the electric bicycle battery charging identification accuracy is improved, and the false alarm rate and the missing report rate are reduced.

The invention discloses an automatic information collection method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the chat content of a target group, and carrying out the preprocessing of the chat content; the preprocessed chat content comprises a chat record of each chat object in the target group; performing subject extraction on the chat record of each chat object, and screening based on a subject extraction result in combination with a target word to obtain a target user; performing an automatic session with a target user by using a pre-trained large model to obtain a target intelligence session; and performing risk assessment on the response content of the target user in the target intelligence session to obtain a risk rating. According to the method, automatic conversation with the target user is carried out in a large model mode, the limitation of only depending on passive monitoring is avoided, intelligence information can be effectively identified through deep analysis of conversation content, the false alarm rate and the missing report rate are reduced, and the method can be widely applied to the technical field of data processing.

The invention discloses a training method and system for an abnormal transaction recognition model of an e-commerce platform, and particularly relates to the field of e-commerce. According to the method, multi-source transaction data are integrated, the accuracy of labeling is judged through cross validation, data labeling is divided into accurate labeling and inaccurate labeling, and after the inaccurate labeling is recognized, the similarity between prediction and an actual result is calculated and the performance stability of a model is evaluated by analyzing the sample proportion fluctuation condition of the model influenced by labeling errors; according to an evaluation result, the models are divided into a stable performance type and an unstable performance type, and different training strategies are adopted: for the stable performance model, the labeled data set is continuously used for training; and for the model with unstable performance, training is carried out in stages, pre-training is carried out by using accurate annotation data, then inaccurate annotation data is introduced, and optimization adjustment is carried out through an adaptive learning algorithm, so that the negative influence of annotation deviation on the model is effectively reduced, and the accuracy of the model in practical application is improved.

The invention provides a safety monitoring method and system based on artificial intelligence. The method comprises the steps that firstly, real-time video data and environment data are collected through a camera and a sensor which are installed at a preset position; secondly, splicing the preprocessed video data and environment data to form an input vector; then, the change amplitude of the preprocessed video data and the change amplitude of the normalized environment data in the time period T are calculated respectively; thirdly, outputting a danger degree value by adopting a first convolutional neural network or a second convolutional neural network or a third convolutional neural network; finally, the danger degree value output by the convolutional neural network is sent to a manager terminal to be displayed, and an alarm is pulled. According to the invention, different types of convolutional neural network algorithms are adopted to carry out danger degree calculation, so that the accuracy and efficiency of safety accident reminding are greatly improved.

The invention relates to the technical field of traffic control, in particular to a navigational light monitoring method and system based on fail-safe. The method comprises the following steps: collecting light operation data through a distributed sensor array, and carrying out key parameter extraction on the light operation data to obtain light operation characteristic data; performing real-time state modeling according to the light operation characteristic data to obtain an operation state model; performing anomaly detection according to the operation state model to obtain operation anomaly detection data; and according to the operation abnormity detection data, performing insurance strategy intelligent matching to obtain insurance strategy execution data so as to perform navigation-aid light monitoring auxiliary operation. According to the invention, the fault detection capability and the resource utilization efficiency of the monitoring system can be improved, and a new possibility is provided for intelligent development of the navigation-aid lighting system.

The invention relates to the technical field of remote maintenance of a power distribution cabinet, in particular to a remote maintenance system of an intelligent power distribution cabinet, which constructs a component operation parameter matrix by collecting current, voltage, component temperature, starting time and internal and external environment data of the power distribution cabinet in real time, and combines environment parameters of the power distribution cabinet to maintain the power distribution cabinet. And carrying out deep learning training by using a residual neural network algorithm. The method not only can detect common fault modes, but also can identify abnormal conditions caused by component aging, so that the problems of false alarm and missing alarm in a traditional fault detection method are solved. Through the residual neural network, the system can automatically learn normal and abnormal operation modes from historical data, and the accuracy of fault detection is improved. And the exception type is further pushed to the operation and maintenance personnel and is visually displayed, so that the judgment time and the round-trip times of the operation and maintenance personnel on the maintenance component are saved, and the maintenance efficiency is improved.

The invention discloses a database abnormal behavior detection method and device, electronic equipment and a storage medium, and relates to the technical field of database security analysis, the method comprises the following steps: obtaining an operation log of a target database, and generating an operation embedding feature based on an operation record of the operation log; generating an operation feature sequence based on a recording sequence of operation records corresponding to the operation embedding features; processing the operation feature sequence according to an attention model to obtain a semantic feature sequence after intention weight adjustment; and determining an abnormal semantic proportion in the semantic feature sequence based on the abnormal behavior detection model, and generating an abnormal behavior detection result of the target database based on the abnormal semantic proportion. According to the embodiment of the invention, the operation feature sequence is generated based on the record sequence, the attention model is utilized to focus on the important features of the operation feature sequence, the recognition precision of the abnormal behaviors is improved, and the false alarm rate and the missing report rate are reduced by calculating the abnormal semantic proportion and accurately quantifying the proportion of the abnormal behaviors.

The invention relates to the field of icing prediction, in particular to an icing prediction model verification method, system, device, medium and product, and the method comprises the steps: obtaining a first meteorological sample set and inputting the first meteorological sample set to a neural network for iterative calculation, the input ends being T, RH, P, Qcloud, Qrain, IWC, LWC, W, Qice, Nice and Nrain; the output end is the probability value of the MVD; combining the meteorological samples of which the probability values belong to the set probability interval to form a second meteorological sample set, and inputting the second meteorological sample set into the convolutional neural network for updating iterative calculation; calculating a first verification index including a first ratio of the number of samples correctly classified as large droplets to the actual number of samples of large droplets, and a second ratio of the number of samples correctly classified as large droplets to the actual number of samples of small droplets; and judging whether updating needs to be continued according to the first verification index. According to the invention, the accuracy of icing prediction under the condition of small samples is improved.

The invention discloses an intelligent monitoring platform and method based on AI vision, and relates to the technical field of security monitoring, the intelligent monitoring platform comprises a video acquisition module, an intelligent calculation module, an AI vision analysis module, an alarm module and a comprehensive management platform, the video acquisition module is used for acquiring video data of a monitoring area in real time; the intelligent calculation module comprises intelligent equipment deployed in a monitoring area, and the intelligent equipment is responsible for performing feature extraction and preliminary analysis on the video data; the AI visual analysis module is used for using a cloud server and is responsible for further performing feature extraction and analysis classification on the video data processed by the intelligent calculation module, and the alarm module is used for triggering an alarm when the intelligent calculation module and the AI visual analysis module cooperatively detect abnormal behaviors of the video data. According to the invention, the real-time performance and the accuracy of monitoring are improved, and the false alarm rate and the missing report rate are reduced; and the specific environment is monitored in a customized manner, so that the pertinence and effectiveness of monitoring are improved.

The invention relates to the field of network security monitoring, in particular to a network security threat monitoring method based on deep learning, which comprises the following steps: collecting flow data on a network node, and preprocessing the collected flow data; constructing a deep neural network model to analyze the flow data, and adjusting model parameters through an optimization algorithm to minimize a loss function; evaluating the network security threat according to an output result of the deep learning model; determining response measures according to the threat assessment result, and taking corresponding response operations for different threat levels; according to the method, the timeliness of the response is evaluated according to the time interval from threat detection to response measure implementation, the deep neural network is utilized, the deep features can be automatically extracted from the network flow, and the recognition precision of the complex attack mode is remarkably improved. Compared with a traditional rule-based detection method and a simple machine learning algorithm, the scheme can effectively reduce the false report rate and the missing report rate, and improve the accuracy of network threat monitoring.