25 results about "Evolving networks" patented technology

The invention discloses a physical layer fusion network construction method, which comprises the following steps of: acquiring physical layer feature data and preprocessing the physical layer feature data; constructing a node feature matrix and an edge feature matrix, and generating an initial graph structure; generating a position coding matrix by using the adjacent matrix; constructing a view pair, executing self-supervised graph pre-training, and generating a communication node initial representation; executing a local message passing operation, and obtaining a local context node representation of the communication node; performing global attention modeling; calculating a connection weight between the communication nodes, updating a graph connection relationship, and generating a dynamically evolved network graph structure; and performing optimal path planning and communication link selection to form a networking connection scheme. According to the method, physical layer multi-mode features and a graph neural network modeling method are fused, a self-adaptive high-stability topological structure is constructed, and the method has the advantages of being high in generalization, fast in response and accurate in perception.

The invention relates to the technical field of computers, in particular to a network security operation method, device and equipment and a storage medium, and is used for providing a network security operation scheme which can give consideration to efficiency and precision and is adaptive to a current dynamically evolved network threat environment. The method comprises the steps of obtaining to-be-processed operation data, wherein the operation data is obtained by preprocessing network flow data and log data; processing the operation data by using a lightweight model to generate initial alarm data; based on the initial alarm data, carrying out alarm authenticity discrimination and threat level determination through a heavy model, and outputting confirmed threat event information; the threat event information indicates alarm data and threat levels corresponding to threat events confirmed by the heavy model; based on the threat event information, risk disposal is executed, affected asset information is obtained, a traceability evidence obtaining tool is matched, and a standardized evidence obtaining report is generated; and based on the standardized evidence obtaining report, executing vulnerability repair.

The invention provides an environmental protection planning dynamic generation method and system based on man-machine interaction and iterative feedback, and the method comprises the steps: firstly collecting an initial environmental protection planning element set of a target region, constructing an initial association network, and calculating the edge association strength; receiving interactive operation data through the human-computer interaction interface, and updating the associated network to obtain an updated network; collecting a feedback data set in a preset interaction period and performing semantic annotation; inputting the feedback data with the semantic label into the element evolution model, driving the node expansion of the association network and the reconstruction of the edge association relationship, generating an evolved network, and identifying element conflicts; and calling a planning scheme generation model to execute multi-target constraint optimization according to the evolved network and conflict analysis report, generating a dynamic environmental protection planning scheme, feeding back the dynamic environmental protection planning scheme to a human-computer interaction interface, and outputting a scheme evolution trajectory diagram. According to the method, dynamic generation and optimization of environmental protection planning are realized, and the scientificity and feasibility of planning are improved.

The invention discloses an encrypted traffic detection method based on small sample self-supervised learning, and relates to the field of network security. The method innovatively constructs a double-branch self-supervised pre-training architecture, deeply mines the time sequence dynamic characteristics of encrypted traffic through a comparison predictive coding module, and improves the detection accuracy of the encrypted traffic. Capturing structural features of head bytes by using a sub-graph multi-level mask auto-encoder module, so as to learn robust feature representation with strong discrimination from mass label-free data; on the basis, the method designs a dynamic confidence false label mechanism, realizes intelligent self-adaptive adjustment of a false label threshold value through a dual adjustment strategy of fusing a time decay function and a category balance factor, effectively screens high-quality false labels and remarkably relieves negative effects caused by category imbalance. According to the method, the dependence on the annotated data can be obviously reduced, the method can more quickly adapt to a continuously evolved network threat environment, and a key technical support is provided for constructing a next-generation adaptive network security defense system.

An evolutionary AutoML framework called LEAF optimizes hyperparameters, network architectures and the size of the network. LEAF makes use of both evolutionary algorithms (EAs) and distributed computing frameworks. A multiobjective evolutionary algorithm is used to maximize the performance and minimize the complexity of the evolved networks simultaneously by calculating the Pareto front given a group of individuals that have been evaluated for multiple objectives.

The present invention discloses a method for constructing a physical layer fusion network, comprising the following steps: collecting physical layer feature data and performing preprocessing; constructing a node feature matrix and an edge feature matrix to generate an initial graph structure; using an adjacency matrix to generate a position encoding matrix; constructing view pairs, performing self-supervised graph pre-training, and generating an initial representation of a communication node; performing a local message passing operation to obtain a local context node representation of a communication node; performing global attention modeling; calculating the connection weights between communication nodes, and updating the graph connection relationship to generate a dynamically evolving network graph structure; performing optimal path planning and communication link selection to form a network connection plan. The present invention integrates physical layer multi-mode features with a graph neural network modeling method to construct an adaptive and highly stable topological structure with the advantages of strong generalization, fast response, and accurate perception.

The present invention discloses a method for generating a regionally constrained parallel self-evolving network topology map, comprising the following steps: Step 1: Performing topology detection on the target area to obtain an IP-level topology; Step 2: Performing topology recovery to obtain router-level topology data; Step 3: Classifying the router-level topology data into three hierarchical categories: access layer routers, convergence layer routers, and backbone layer routers; Step 4: Using a neural network classification method to obtain key network nodes and set them as anchor points; Step 5: Dividing a complex network into multiple sub-regions based on administrative regions or interactive optimization requirements; Using a divide-and-conquer approach to perform a parallel layout for each sub-region; and Further dividing the layout evolution results into a core layer, convergence layer, and access layer. The present invention divides a complex network into multiple sub-regions and adopts a divide-and-conquer strategy to perform a parallel self-evolving layout for each sub-region, thereby achieving balanced node distribution and adaptability to geographical constraints.

Disclosed are computerized systems and methods for a decision intelligence (DI)-based framework that automatically and / or dynamically provides mechanisms for managing, optimizing and configuring a WiFi network at a location. The framework provides network management utilizing edge processing capabilities to bridge local WiFi and cloud systems. The framework implements comprehensive device typing through multi-layered analysis combining passive monitoring, deep packet inspection and hybrid deterministic-probabilistic classification methods. State synchronization between local and cloud networks can be achieved through hierarchical data modeling and differential synchronization algorithms. The framework can implement advanced features that include automated channel optimization, QoS management, and security monitoring. The framework incorporates self-healing capabilities using reinforcement learning techniques and maintains operational efficiency through intelligent resource management and workload distribution. The framework can operate autonomously while requiring minimal cloud connectivity, featuring extensible architecture through a plugin system that enables adaptation to evolving network requirements while maintaining stable operation of existing capabilities.

The invention provides a multi-level process node prediction method and device, equipment and a storage medium, and relates to the technical field of process management.The method comprises the steps that firstly, operation data of all levels in a target level process is obtained, an initial data set is constructed, the comprehensiveness and accuracy of model input are ensured, and a data foundation is laid for subsequent analysis; secondly, constructing a multi-level process comprehensive matrix based on the data set, systematically quantifying the incidence relation among the levels, breaking through the limitation of traditional single-level analysis, and remarkably improving the understanding ability of a complex process structure; then, through designing an improved self-evolution network architecture and integrating a game theory optimization strategy, the model realizes dynamic game and adaptive adjustment of parameters in a hidden layer, and a prediction strategy is continuously optimized in an iteration process; and finally, a stable and convergent fusion model is obtained after multiple rounds of iteration, the evolution law of a multi-level process can be accurately captured, and panoramic prediction of a future path is realized.

The application relates to a network security management method and system. The method comprises the following steps: performing digital antibody analysis on network behavior data and host behavior data of a target network to obtain suspicious behavior data packets; performing environment isolation simulation on the suspicious behavior data packets to obtain a dynamic behavior label set; analyzing an infection defense mechanism of a network attack according to the suspicious behavior data packets and the dynamic behavior label set to obtain a network security attack behavior graph; and inputting historical network antibody performance data into the network security attack behavior graph to obtain current network security immune strategy information. The method can effectively eliminate the limitations of reaction delay and defense blind area when facing rapidly evolving network attacks and advanced persistent threats.

Disclosed are computerized systems and methods for a decision intelligence (DI)-based framework that automatically and / or dynamically provides mechanisms for managing, optimizing and configuring a WiFi network at a location. The framework provides network management utilizing edge processing capabilities to bridge local WiFi and cloud systems. The framework implements comprehensive device typing through multi-layered analysis combining passive monitoring, deep packet inspection and hybrid deterministic-probabilistic classification methods. State synchronization between local and cloud networks can be achieved through hierarchical data modeling and differential synchronization algorithms. The framework can implement advanced features that include automated channel optimization, QoS management, and security monitoring. The framework incorporates self-healing capabilities using reinforcement learning techniques and maintains operational efficiency through intelligent resource management and workload distribution. The framework can operate autonomously while requiring minimal cloud connectivity, featuring extensible architecture through a plugin system that enables adaptation to evolving network requirements while maintaining stable operation of existing capabilities.

The invention relates to a self-evolution network flow data security protection method and system, and the method comprises the steps: obtaining network flow data with a label, carrying out the preprocessing, and extracting a flow-level feature; calculating contribution degrees between the flow-level features and the labels and contribution degrees among the flow-level features, and selecting the flow-level features according to the contribution degrees to obtain a feature index set; updating the old intrusion detection model according to the feature index set and the new data set to obtain a new intrusion detection model; inputting to-be-detected network flow data into the flow length prediction model to obtain a prediction length; and selecting a corresponding new intrusion detection model according to the prediction length, inputting the network flow data to be detected into the selected new intrusion detection model, obtaining and outputting a corresponding label, and triggering a real-time defense measure according to the label. According to the method, the calculation and storage cost is effectively reduced while the detection performance is ensured, and the method is suitable for safety protection requirements in various complex network environments.

The invention provides a malicious traffic dynamic detection method capable of being continuously updated, incremental continuous learning of multiple sub-graphs in a continuous time period is realized, and finally threat detection on dynamically evolved network traffic is realized, and the method specifically comprises the following steps of: 1) mapping traffic interaction behaviors among physical equipment into a topological graph; a quintuple sequence is used as input, each quintuple is identified as a unique node, and the repetition degree of the quintuple is used as an initial graph weight. And 2) providing a detection framework with a continuous updating mechanism, wherein an incremental dynamic graph learner continuously learns topological information of the traffic graph through a playback mechanism. In the mechanism, an elastic topological memory buffer area is arranged to reserve a historical flow graph, so that a continuously updated dynamic graph learning device is generated. And 3) designing a classification model based on the graph deep neural network, realizing accurate malicious node identification through a multi-layer cascaded graph neural network architecture, balancing historical knowledge consolidation and new attack mode learning through a multi-task loss function, and ensuring long-term effectiveness of the model in a dynamic network environment.

The invention relates to a network security management method and system. The method comprises the following steps: performing digital antibody analysis on network behavior data and host behavior data of a target network to obtain a suspicious behavior data packet; performing environment isolation simulation on the suspicious behavior data packet to obtain a dynamic behavior tag set; analyzing an infection defense mechanism of the network attack according to the suspicious behavior data packet and the dynamic behavior label set to obtain a network security attack behavior map; and inputting the historical network antibody expression data into the network security attack behavior map to obtain current network security immune strategy information. By adopting the method, the limitations of slow response and defense blind areas can be effectively eliminated in the face of quickly evolved network attacks and advanced persistent threats.

The present invention discloses an adaptive cyber threat detection system and method implemented through a computing device configured to perform multi-layer behavioral analysis of network and system activities. The system receives network traffic data and system activity data, conditions the received data into structured behavioral event records, and generates multi-dimensional behavioral profiles associated with identities, devices, and temporal sequences. The behavioral profiles are compared against adaptive behavioral baseline profiles across multiple analytical layers to identify deviations indicative of anomalous behavior. Identified deviations are subjected to staged validation by correlating behavioral evidence across independent dimensions to confirm malicious activity. Upon confirmation, the system initiates appropriate security response actions based on determined threat severity and records detection outcomes in a secure event log. The adaptive behavioral baselines are continuously updated using validated non-malicious behavioral outcomes, enabling the system to dynamically adjust to evolving network conditions while maintaining accurate and reliable cyber threat detection.

Disclosed are computerized systems and methods for a decision intelligence (Dl)-based framework that automatically and / or dynamically provides mechanisms for managing, optimizing and configuring a WiFi network at a location. The framework provides network management utilizing edge processing capabilities to bridge local WiFi and cloud systems. The framework implements comprehensive device typing through multi-layered analysis combining passive monitoring, deep packet inspection and hybrid deterministic-probabilistic classification methods. State synchronization between local and cloud networks can be achieved through hierarchical data modeling and differential synchronization algorithms. The framework can implement advanced features that include automated channel optimization, QoS management, and security monitoring. The framework incorporates self-healing capabilities using reinforcement learning techniques and maintains operational efficiency through intelligent resource management and workload distribution. The framework can operate autonomously while requiring minimal cloud connectivity, featuring extensible architecture through a plugin system that enables adaptation to evolving network requirements while maintaining stable operation of existing capabilities.

An evolutionary AutoML framework called LEAF optimizes hyperparameters, network architectures and the size of the network. LEAF makes use of both evolutionary algorithms (EAs) and distributed computing frameworks. A multiobjective evolutionary algorithm is used to maximize the performance and minimize the complexity of the evolved networks simultaneously by calculating the Pareto front given a group of individuals that have been evaluated for multiple objectives.

The embodiment of the invention discloses a model training set generation method and related equipment, and is used for the technical field of data processing. In the embodiment of the invention, a corresponding threat data template is generated based on original network threat data; generalizing variables in the threat data template to generate first network threat data; confusing the first network threat data to obtain confused second network threat data; performing data assembly on the second network threat data and the normal network data to obtain model training data; therefore, the obtained model training data has diversity, and a continuously evolved network attack mode can be comprehensively reflected.

Disclosed are computerized systems and methods for a decision intelligence (DI)-based framework that automatically and / or dynamically provides mechanisms for managing, optimizing and configuring a WiFi network at a location. The framework provides network management utilizing edge processing capabilities to bridge local WiFi and cloud systems. The framework implements comprehensive device typing through multi-layered analysis combining passive monitoring, deep packet inspection and hybrid deterministic-probabilistic classification methods. State synchronization between local and cloud networks can be achieved through hierarchical data modeling and differential synchronization algorithms. The framework can implement advanced features that include automated channel optimization, QoS management, and security monitoring. The framework incorporates self-healing capabilities using reinforcement learning techniques and maintains operational efficiency through intelligent resource management and workload distribution. The framework can operate autonomously while requiring minimal cloud connectivity, featuring extensible architecture through a plugin system that enables adaptation to evolving network requirements while maintaining stable operation of existing capabilities.

The application provides an environmental protection planning dynamic generation method and system based on human-computer interaction and iterative feedback, first collects an initial environmental protection planning element set of a target area and constructs an initial correlation network, calculates edge correlation strength; receives interactive operation data through a human-computer interaction interface, updates the correlation network to obtain an updated network; collects a feedback data set within a preset interaction period and performs semantic labeling; inputs the feedback data with semantic labels into an element evolution model, drives correlation network node expansion and edge correlation relationship reconstruction, generates an evolved network and identifies element conflicts; according to the evolved network and a conflict analysis report, calls a planning scheme generation model to perform multi-objective constraint optimization, generates a dynamic environmental protection planning scheme and feeds back to the human-computer interaction interface, and simultaneously outputs a scheme evolution trajectory diagram. The application realizes dynamic generation and optimization of environmental protection planning, and improves the scientificity and feasibility of the planning.

The present disclosure relates to the technical field of computer, and particularly relates to a network security operation method and device, equipment and storage medium, to provide a network security operation scheme which can balance efficiency and accuracy and adapt to the current dynamic evolving network threat environment. The method comprises the following steps: obtaining running data to be processed, wherein the running data is obtained by preprocessing network flow data and log data; processing the running data by using a lightweight model to generate initial alarm data; based on the initial alarm data, performing alarm authenticity discrimination and threat level determination by using a heavy model to output confirmed threat event information; the threat event information indicates alarm data and threat level corresponding to the threat event confirmed by the heavy model; based on the threat event information, performing risk disposal, obtaining affected asset information and matching a trace evidence tool to generate a standardized evidence report; and based on the standardized evidence report, performing vulnerability repair.

Disclosed are computerized systems and methods for a decision intelligence (DI)-based framework that automatically and / or dynamically provides mechanisms for managing, optimizing and configuring a WiFi network at a location. The framework provides network management utilizing edge processing capabilities to bridge local WiFi and cloud systems. The framework implements comprehensive device typing through multi-layered analysis combining passive monitoring, deep packet inspection and hybrid deterministic-probabilistic classification methods. State synchronization between local and cloud networks can be achieved through hierarchical data modeling and differential synchronization algorithms. The framework can implement advanced features that include automated channel optimization, QoS management, and security monitoring. The framework incorporates self-healing capabilities using reinforcement learning techniques and maintains operational efficiency through intelligent resource management and workload distribution. The framework can operate autonomously while requiring minimal cloud connectivity, featuring extensible architecture through a plugin system that enables adaptation to evolving network requirements while maintaining stable operation of existing capabilities.

The invention provides a webshell detection system based on behavior characteristics, which belongs to the technical field of network security protection, and can discover potential vulnerabilities in an early stage after a file is uploaded by analyzing the behavior characteristics in file uploading and access processes and combining other judgment standards, thereby blocking the possibility of vulnerability utilization. By adopting the network security protection method based on the behavior characteristics, the overall security is remarkably enhanced, and the dependence on an outdated signature method is reduced. This technique marks that more effective protection is provided for continuously evolving network threats in a dynamic network environment.

Disclosed are computerized systems and methods for a decision intelligence (DI)-based framework that automatically and / or dynamically provides mechanisms for managing, optimizing and configuring a WiFi network at a location. The framework provides network management utilizing edge processing capabilities to bridge local WiFi and cloud systems. The framework implements comprehensive device typing through multi-layered analysis combining passive monitoring, deep packet inspection and hybrid deterministic-probabilistic classification methods. State synchronization between local and cloud networks can be achieved through hierarchical data modeling and differential synchronization algorithms. The framework can implement advanced features that include automated channel optimization, QoS management, and security monitoring. The framework incorporates self-healing capabilities using reinforcement learning techniques and maintains operational efficiency through intelligent resource management and workload distribution. The framework can operate autonomously while requiring minimal cloud connectivity, featuring extensible architecture through a plugin system that enables adaptation to evolving network requirements while maintaining stable operation of existing capabilities.

The invention discloses an Ethereum phishing detection method and system based on dynamic feature fusion, and aims to accurately evaluate phishing risks in Ethereum transactions in real time. According to the system, a graph structure analysis technology, a graph embedding method and a Transform model are combined, a unified and flexible transaction data graph is constructed, multi-source features are dynamically extracted and fused, and a multi-head attention mechanism is utilized to realize adaptive adjustment of feature weights. The system can process transaction data of different scales, has a dynamic updating mechanism, and can timely adapt to and identify continuously evolved phishing attack modes. The method has high detection accuracy and robustness, and an effective technical scheme is provided for guaranteeing the security of the Ethereum block chain network.