382 results about "Dynamical network" patented technology

The invention discloses a dynamic network access control method and system based on a zero-trust architecture, and the method comprises the steps: integrating equipment health degree evaluation through the triple dynamic binding of biological feature dynamic binding, equipment fingerprint salt value hash verification and environmental state perception, and constructing a real-time trust basis; dynamic risk quantification is realized based on a multi-source heterogeneous data fusion machine learning model, real-time upgrading and degrading self-adaptive adjustment of authority is realized through an AI driving strategy generation module according to a real-time risk score, a zero-trust sandbox limitation sensitive operation is triggered for high-risk access, and a minimum authority channel is started for low-risk access; performing fine-grained access control and intercepting an unauthorized request in real time by adopting an agent-free API gateway technology, and monitoring an operation behavior in combination with a block chain non-tampering storage access log and an anomaly detection algorithm; finally, a continuous self-adaptive evolutionary cycle is formed through a risk assessment-policy execution-abnormal feedback closed loop mechanism, and the static lag problem of traditional network access control is systematically solved.

A computerized system for dynamic cybersecurity policy using AI-based contextual adaptive learning includes an AI system that evaluates business contexts, risk tolerance, and productivity impact to generate threat intelligence assessments. The system includes a Contextual Adaptive Learning module that dynamically adjusts cybersecurity policies based on threat assessments to create security workflows. A Cybersecurity Mesh Development module that integrates policies across security frameworks. A Dynamic Scenario Catalog module that updates policy adjustments based on threat intelligence. An Automated Workflow Orchestration module that creates and refines security workflows for optimal efficiency. A Policy Recommendation and Automation module that generates prioritized security recommendations and automates policy changes based on organizational risk profiles and current security controls. This system harmonizes security policies while considering business context, risk, and productivity impacts.

The invention relates to the field of artificial intelligence cross-modal retrieval, and provides a video text cross-modal retrieval method and system based on spatio-temporal feature fusion. The method comprises the following steps: carrying out key frame sampling and time sequence partitioning on an input video, extracting static visual features through a spatial feature network, and extracting motion features through a time dynamic network; a self-adaptive gating fusion module is adopted to dynamically calculate spatial-temporal feature weights and perform weighted fusion; extracting text semantic features by using a pre-training language model; constructing a double-flow projection network to map video fusion features and text features to a unified measurement space, and optimizing a feature distance by adopting a contrast loss function containing difficult negative sample mining and intra-modal constraint; and outputting a retrieval result according to the cosine similarity sequence. The system comprises four units, wherein the gating fusion module is integrated with an FPGA acceleration circuit. According to the method, mAP (at) 10 is equal to 0.78 in a UCF-101 data set, the time sequence action retrieval accuracy rate is 92.8%, and the single video retrieval delay is 23 milliseconds.

The invention provides a dynamic network security defense method and system oriented to real-time network state adaptation, and the method comprises the steps: building a standardized state vector sequence through collecting key indexes, such as network flow rate, abnormal connection ratio, topology change frequency, protocol distribution deviation degree and the like; based on the sequence, utilizing a time sequence prediction model embedded with a structured attention mechanism to predict attack risk trends of a plurality of time windows in the future in a prospective manner; and in combination with the current state and the risk trend, dynamically selecting an optimal strategy path in a predefined defense action map, mapping the optimal strategy path into a standardized control command which can be executed by equipment, and dispatching, issuing and executing the standardized control command according to the priority. According to the method, closed-loop self-adaptive defense from state perception and risk prediction to strategy generation and execution is realized, and the real-time performance, intelligence and engineering deployability of a network security system are remarkably improved.

The invention discloses a new energy automobile battery pack thermal management system multi-target adaptive control method, which comprises the following steps: constructing a thermal resistance-thermal capacity dynamic network model of a battery module and a cooling flow channel, and constructing a reinforcement learning virtual training environment; constructing a multi-target composite reward function; constructing a neural network model based on depth deterministic strategy gradient, and guiding gradient updating of strategy network parameters by using a multi-target composite reward function until the neural network model converges; solidifying the trained and converged strategy network parameters, deploying the solidified strategy network parameters to a vehicle thermal management controller, and outputting the optimal cooling liquid flow rate under the current working condition; and mapping the optimal cooling liquid flow rate into an electronic water pump rotating speed instruction. The method can solve the problems that in the prior art, due to the fact that the calculation load is large, the requirement for millisecond-level real-time response under the extreme working condition is difficult to meet, limitation is caused by linear deduction of temperature distribution only depending on head and tail modules, and a dynamic adjustment strategy cannot be fed back in real time.

The invention discloses a short temporary rainfall forecasting method and system based on a dynamic neural network architecture. According to the method, training sample distribution is optimized through a space-time gradient driven resampling strategy, a time-frequency double-branch dynamic network architecture is adopted, a time domain branch extracts multi-scale space features through an encoder-decoder structure, a frequency domain branch adaptively activates an FFT calculation module through a content awareness dynamic network to capture multi-scale time features, and the multi-scale time features are obtained. And two key problems of meteorological data distribution imbalance and deep learning model optimization imbalance are solved in combination with a balance regression loss function. According to the method, adaptive computing resource allocation for meteorological events with different complexities is realized, the forecasting precision and computing efficiency of heavy rainfall events are remarkably improved, and an efficient and reliable technical solution is provided for short temporary rainfall business forecasting.

The invention relates to the field of high polymer materials, and discloses a high-wear-resistance elastomer sole material and a preparation method thereof.The material comprises an elastomer matrix and surface-modified boron nitride nanosheets; the elastomer matrix comprises a first dynamic network and a second dynamic network which are formed through crosslinking of dynamic covalent bonds, and the first dynamic network and the second dynamic network are based on different types of dynamic covalent bonds and have different dissociation activation energy barriers or external stimulus response conditions. The surface-modified boron nitride nanosheet and the second dynamic network form a selective interface enhancement effect; the preparation method comprises the steps of polymer functionalization, nanosheet surface modification, melt blending reaction net forming, forming and the like. The obtained elastomer sole material not only has excellent wear resistance and mechanical properties, but also can realize self-repair of graded response aiming at damages of different degrees, and the service life of the material is remarkably prolonged.

A dynamic grid allocation system for power distribution in the development of integrated circuits in the sub-five-nanometer range, wherein the system comprises the following: a placement processor unit configured to receive a synthesized netlist comprising a variety of standard cells and macros, each associated with switching activity data derived from simulation or synthesis activity profiles, and to generate a spatial cell placement arrangement by grouping cells into microzones based on activity correlation, time sensitivity, and connection proximity; a power density calculation unit coupled to the placement processor unit and configured to calculate the local power density and instantaneous current demand for each microzone based on the spatial distribution of switching operations, capacity load, and effective switching frequencies; a dynamic network generation unit coupled to the power density calculation unit and configured to generate a multilayer power distribution network with variable network topology, where the width, spacing, via density and metal layer assignment of the power network are adaptively determined as continuous functions of the localized power density and power demand calculated for each microzone; a topology control processor configured to monitor voltage drop and electromigration data obtained from signoff analyses or predictive models in real time and dynamically adjust the power grid topology parameters to ensure compliance with predefined reliability thresholds for voltage drop and electromigration; a predictive current modeling unit configured to receive historical switching and voltage data, train a predictive model for transient current peaks, and provide predictive power boost instructions to the dynamic grid generation unit before power integrity violations occur; and A feedback synchronization controller is communicatively connected to the placement processor unit and the topology control processor, whereby the feedback synchronization controller continuously exchanges updated power density information and placement constraints, so that cell placement and network topology adapt together in real time, thereby minimizing routing congestion, ensuring a uniform voltage distribution, and guaranteeing compliance with electromigration and IR drop regulations under various activity conditions.

The invention relates to a real-time data encryption transmission method and a real-time data encryption transmission device for a weak current remote monitoring system, in particular to the field of weak current remote monitoring systems, and effectively avoids the problem of update failure caused by link fluctuation in a dynamic network environment by intelligently predicting a stable state of a network to accurately trigger key update. A lightweight distributed consensus mechanism is adopted to generate a security key block, so that the communication overhead is remarkably reduced while the Byzantine fault-tolerant capability is guaranteed; a precise distribution strategy based on topological difference identification greatly reduces redundant transmission, and efficient delivery of keys is realized; the innovative chain verification and zero knowledge synchronization mechanism ensures that the offline node safely recovers the key state, and the overall scheme significantly optimizes the transmission efficiency and the resource utilization rate while improving the system security, and is especially suitable for large-scale and high-dynamic Internet of Things monitoring scenes.

The invention belongs to the technical field of image reconstruction and classification, and particularly relates to a radar image adaptive reconstruction and classification method based on intelligent hierarchical learning, and the method comprises the steps: obtaining an original radar image and radar platform parameters, and obtaining a standardized preprocessing image; outputting a high-fidelity reconstructed image through hierarchical processing; carrying out Sobel gradient calculation to obtain a gradient image and carrying out region division, carrying out differential dynamic window local enhancement, and then carrying out global gray balance and secondary filtering to obtain an enhanced and optimized image; carrying out local / global feature extraction, carrying out weighted fusion by utilizing semantic association, and outputting a multi-layer fusion feature map; outputting a high-confidence identification result by utilizing candidate region acquisition and difficulty evaluation, dynamic network switching identification and confidence closed-loop verification; and integrating the original radar image, the high-fidelity reconstructed image and the high-confidence identification result, and outputting a structured report. According to the method, the optimal balance of radar image speckle noise suppression and detail reservation can be realized.

The invention discloses a heterogeneous network embedding method based on dynamic heterogeneous network decomposition and a hierarchical space-time attention mechanism. The method comprises the following steps: dynamic network decomposition: decomposing a heterogeneous network sequence into independent subgraph sets according to edge types; multi-order node attention aggregation: for each sub-graph, fusing information of nodes and different edge types; semantic level attention is embedded, wherein global semantic embedding is generated in combination with global relation type weight and meta-path long-short-term memory network coding; time dynamic modeling: respectively calculating a time attention weight and a Monte Carlo sampling approximate Horkes intensity, and then aggregating and splicing results of the time attention weight and the Monte Carlo sampling approximate Horkes intensity to obtain a final embedding result. According to the method, through cross-granularity semantic modeling and efficient time sequence dependence learning, an innovative solution is provided for node representation of the dynamic heterogeneous network.

The invention belongs to the technical field of Internet of Vehicles control, and discloses an Internet of Vehicles channel congestion distributed closed-loop control method. According to the method, a closed-loop feedback channel resource congestion control strategy is provided, and a closed-loop feedback control framework adopted by the strategy is composed of reference model construction and adaptive feedback control model construction. And constructing a data packet acceptance rate model and a network effect maximization model in the reference model, and solving an optimal data packet reception probability as an ideal state of the Internet of Vehicles. In the adaptive closed-loop feedback control model, an error between an ideal state and an actual network state of the Internet of Vehicles is adjusted through a PI controller, so that the actual network state infinitely approaches the ideal network state. Network parameters are dynamically adjusted based on model reference adaptive control, the reliability of communication between vehicles in a dynamic network environment is ensured, and expected stability and robustness of a system can be kept in a dynamically changing environment.

A kind of image classification method based on class incremental learning of multi-normalization and dynamic network, comprising the following steps;Step 1: build new base network;Step 2: based on the initial image classification task D 1 of class incremental learning training of new base network, obtain initialization model, and freeze initialization model as the old model of next stage image classification task D 2 of class incremental learning;Step 3: when processing new class incremental learning image classification task, build feature enhancement model;Step 4: the size of feature enhancement model is controlled by model distillation technology, and the target compression model is obtained by distilling feature enhancement model;Target compression model is used as the old model when processing the next class incremental task;Step 5: on test sample, using target compression model carries out image classification precision detection.The present application is aimed at image classification task in the field of class incremental learning, used to relieve model catastrophic forgetting problem, improve the accuracy of model downstream image classification task.

Systems and methods are described for automated anomaly detection in computer networks using a dynamic network graph. Network data describing communications among computing entities are received, and a dynamic graph is constructed and maintained whose nodes represent the entities and whose edges represent observed communications. Behavior characteristics are computed for the nodes, and the nodes are clustered using a clustering algorithm to obtain cluster assignments. Anomalies are detected by identifying nodes whose behavior characteristics deviate from those of their assigned clusters, and alerts or security actions are generated in response. The system supports incremental updates to graph structure and cluster assignments as network conditions evolve, improving detection latency and accuracy.

Systems and methods for providing dynamic network slicing resource reselection for wireless communication are described. User equipments (UEs) may determine that network slicing resources utilized with respect to one or more applications are to be changed in run time, such as for more efficient operation in light of a change in power mode, throughput mode, latency mode, etc. A message indicating a cause for reselection of a current packet data unit (PDU) session association with an application may be provided to a UE route selection policy (URSP) manager. The URSP manager may reevaluate a current PDU session association with the application to determine if it is a best match with the cause. If no, a switch to a new PDU session association with the application may be made. If yes, the current PDU session association with the application may be maintained. Other aspects and features are also claimed and described.

Systems and methods for configuring and managing a network device with a transformer model under control of a network control function (NCF) are disclosed. A processor of the NCF receives a request that identifies a network management task and associated service targets. The processor forms a token set of schema-defined tokens that represent network context, applies positional encodings to generate an ordered token sequence, and invokes the transformer model to produce a configuration patch. The configuration patch is validated against a schema-constrained decoder that enforces device grammar and is applied to the target network device. Device state and telemetry are read back to obtain a read-back state, which is evaluated against the service targets. When telemetry deviates, the processor generates a further configuration patch that modifies a bounded subset of parameters relative to the read-back state to restore compliance

The invention relates to the technical field of industrial internet of things and mobile edge computing crossing, in particular to a computing task unloading and service caching collaborative optimization method, which comprises the following steps of: acquiring an IIOT equipment state, channel quality and edge server resources in real time by constructing a dynamic network awareness architecture, and analyzing a task DAG topological structure; designing a service cache delay compensation mechanism, parallelizing a cache process and task execution, predicting future required services based on a task dependency relationship, and calculating a delay compensation factor; a deep reinforcement learning algorithm based on Transform is adopted, and an unloading decision is generated in combination with a hierarchical attention mechanism and an improved DDQN network; tasks are dynamically allocated to the local, the edge or the cloud through a three-level unloading decision tree, task completion time is minimized, a resource constraint modeling and task preemption mechanism is further included, and the system response capability and the resource utilization rate are improved.

A system and method for operational and cyber risk assessment that utilizes a data-driven approach to evaluate the current security posture and identify areas for improvement based on the user's desired target profile. This process involves estimating the costs and benefits associated with various security program enhancements, increased, hiring, and control uplifts. The system and method then quantify these benefits in terms of reduction in tail value at risk, expected losses, cyber insurance premiums, and the amount of risk capital set aside. The system simulates attack paths associated with various risk scenarios and uses a risk scenario model to compute losses associated with each attack path for each risk scenario. The results of the simulation may be used to determine one or more business outcomes associated with the costs and benefits of implementing security enhancements.

The invention discloses an Internet of Vehicles cooperative unloading method based on hybrid action deep reinforcement learning, and relates to the technical field of Internet of Vehicles and mobile edge computing. In order to solve the technical problem of joint optimization of unloading target selection and resource allocation, the problem is modeled as a Markov decision process, and a mixed action soft actor-commentator (HA-SAC) algorithm is provided for solving; the core is that a multi-head strategy network outputs discrete actions and continuous actions at the same time in a decision period. A centralized training and decentralized execution architecture is adopted, and the value network receiving the global state guides the intelligent agent which only depends on the local state to make decisions to learn; compared with the prior art, the method has the advantages that the precision loss caused by action space discretization is avoided, the task completion time delay is obviously reduced, and the robustness and the adaptive decision-making capability of the system in a highly dynamic network environment are enhanced.

The invention provides an access control list configuration method and device, electronic equipment and a storage medium, and relates to the technical field of servers, and the method comprises the steps: collecting subnet information in a target containerization cluster, a configured access control list rule and security threat features in network traffic; the information is subjected to fusion analysis based on a predefined security policy so as to generate an access control list rule set containing different priorities, and then the rules are synchronized to a cluster virtual switch kernel according to the priorities so as to realize hierarchical control and dynamic protection of network traffic. The problems that a large-scale dynamic network environment is difficult to deal with, the automation level is low and malicious traffic cannot be efficiently intercepted due to the fact that manual configuration and static rule maintenance are relied on and deep integration of a containerized cluster network structure is lacked can be solved. The technical effects of improving the automation level of containerized cluster network management, enhancing the adaptability to a dynamic network environment, and realizing efficient interception of malicious traffic to guarantee network security are achieved.

The invention belongs to the field of network decision optimization, relates to a data analysis technology, and particularly relates to a network intelligent decision optimization system based on dynamic feature extraction, which is used for solving the problem that stage correlation analysis cannot be carried out according to a single performance parameter in a dynamic network in the prior art. Comprising a network test module, a feature extraction module, a performance monitoring module and a decision analysis module, and the network test module, the feature extraction module and the performance monitoring module are all in communication connection with a database; according to the method and the device, dynamic association analysis of the network performance parameters and the operation parameters is realized, and the system can accurately identify key factors causing performance abnormity in a complex and changeable network environment. Compared with a traditional static threshold judgment method, the dynamic feature extraction mechanism of the invention significantly improves the accuracy of anomaly diagnosis, and through the separate design of the test period and the monitoring period, the system can perform comprehensive feature analysis while ensuring the real-time monitoring efficiency.

Systems and methods enable dynamic network function management, including obtaining user input data identifying network slice provisioning parameters for a creation of a network slice in a network; sending a request for a network repository function (NRF) instance for the network slice, to an orchestrator; receiving, from the NRF instance, a verification message of the creation of the network slice; sending, to the orchestrator, a request for a creation of multiple network function (NF) instances according to the network slice provisioning parameters; receiving, from the orchestrator, a verification message of the creation of the NF instances for the network slice; receiving, from the NRF, a confirmation message of a registration of the NF instances for the network slice; sending slice-specific subscriber provisioning data to a user data instance provisioned for the network slice; and generating a network slice creation confirmation message identifying the network slice.

The invention provides a network boundary extension sensing method and system based on an AI model. The method comprises the following steps: acquiring multi-modal data such as physical fingerprints, protocol characteristics and flow modes of equipment through an edge sensing agent; generating a device-behavior joint representation vector through a feature decoupling encoder; constructing a dynamic time sequence topological graph sequence by using a space-time diagram neural network to map boundary evolution; threat reasoning is carried out by adopting three channels of rule matching, unsupervised anomaly detection and semi-supervised threat hunting; fusing decisions through a dynamic weighted voting mechanism and triggering an automatic response; and realizing closed-loop self-optimization based on incremental learning. The system correspondingly comprises an edge sensing layer, a central analysis layer, a strategy execution layer, a knowledge evolution module and a model credibility guarantee unit. According to the method, through cloud-edge-end collaborative reasoning and causal attribution analysis, the sensing and handling capability of unknown threats and APT attacks in a dynamic network boundary is remarkably improved.

The invention discloses a firewall dynamic policy adaptation method and system based on big data, and the method comprises the steps: collecting multi-source heterogeneous data in a network, and constructing a dynamic network entity map in real time; processing the time sequence of the atlas by using a preset time sequence diagram attention network model to obtain a behavior fingerprint vector representing the behavior state of the entity, and calculating the risk score of the entity; when the risk score exceeds a risk threshold value, automatically generating a temporary security policy for managing and controlling the access behavior of the entity; and managing the life cycle of the temporary security policy, and automatically updating, renewing or cancelling according to the entity risk state change. According to the method, the network entity behavior baseline is constructed and the risk prediction is carried out, so that the conversion from passive defense to active defense is realized, the security policy can be automatically and accurately generated and managed, advanced persistent threats and zero-day attacks can be effectively coped with, and the self-adaptability and the intelligent level of network defense are improved.

The invention discloses a dynamic trapping network deployment method and system fusing attack behavior preferences, and relates to the technical field of network security. The method comprises the following steps: modeling a network topology into a directed acyclic graph, and constructing a dynamic trapping network topology structure fused with attack behavior preference based on attacker behavior preference analysis in combination with situation awareness; modeling an attack and defense confrontation process as a Markov multi-stage dynamic game process, and solving Nash equilibrium to obtain an optimal strategy of each stage; the behavior preference of an attacker is updated in real time by using Bayesian learning and a sliding window mechanism, and the adaptability of a dynamic trapping network to attack and defense situations is enhanced. According to the method, the problems of configuration stiffness and poor attack and defense situation change adaptability in dynamic trap network deployment are solved, the active defense capability aiming at attacker behaviors can be improved, and an effective solution is provided for dynamic deployment of a trap network in a dynamic network environment.

Cybersecurity mission planning and analysis uses artificial intelligence systems to make red and blue team exercises more comprehensive and effective by supplementing individual expertise, reducing reliance on intuition, and eliminating gaps in knowledge. In an embodiment, a platform for cyberattack missions planning and analysis by red and blue teams is coordinated by a control center. An incident generator generates cyberattack scenarios and events using data from external databases and an internal attack knowledge manager having a knowledge graph of data about the network under attack in conjunction with one or more machine learning algorithms configured to identify potential network vulnerabilities. Red are guided by a machine learning algorithm configured to provide suggestions as to potential successful attack paths. Blue teams are guided by a machine learning algorithm configured to provide suggestions as to potential successful attack paths.

The invention discloses a dynamic network access control system under a zero-trust architecture, which relates to the technical field of network security, and comprises a multi-dimensional trust evaluation module, a self-adaptive micro-segmentation engine, a strategy decision execution module and a risk perception feedback module, the multi-dimensional trust evaluation module calculates a comprehensive trust score based on five-dimensional features of identity, equipment, network, application and data; the self-adaptive micro-segmentation engine dynamically generates network micro-segments based on a graph diffusion algorithm; the strategy decision execution module adopts deep reinforcement learning to generate an access decision; the risk perception feedback module identifies abnormity based on the LSTM network and adjusts trust parameters through closed-loop feedback, the four modules are deeply coupled and cooperated, refined dynamic access control is realized, the occurrence rate of security events is reduced by more than 85%, and an innovative solution is provided for enterprise network security.

The invention relates to the technical field of data processing, in particular to a localized low-power-consumption computing power aggregation scheduling system and method based on a heterogeneous SoC, and the system comprises a local networking module, a modeling module, a scheduling distribution module, an execution module, a result aggregation module and an optimization scheduling module. According to the method, a technical chain from dynamic perception to intelligent decision and then to closed-loop control is constructed, multi-dimensional parameters of computational nodes are deeply coupled with demand parameters such as the calculated amount of tasks and the data dependency relationship, the coupled parameters are input into a scheduling model with the total energy consumption of a system as an optimization target, and in a local dynamic network with power supplied by a battery, the optimal energy consumption of the system is obtained. The system can adaptively select the node combination with the lowest energy consumption cost and the task decomposition mode, and the problem that reliable and efficient persistent computing power aggregation cannot be realized in the scene due to the fact that an optimization target and a resource sensing model do not conform to the real constraint of a low-power-consumption dynamic network is effectively solved.

The invention discloses a channel routing optimization system based on a graph neural network, and the system comprises the following modules: a dynamic network graph construction module which is used for collecting network topology and link state data, and constructing a dynamic network graph model; the node embedding generation module is used for inputting the data into an improved MTGNN model and generating a high-quality node embedding vector by introducing a contrast learning mechanism; the candidate path discovery module adopts a greedy neural network algorithm based on beam search, carries out parallel extension and retains high-score candidate paths according to node embedding vector scores, and generates a candidate path set; the optimal path selection module is used for calculating the comprehensive utility value of each path, sorting the comprehensive utility values and outputting an optimal path; and the routing configuration and optimization module is used for generating and issuing a routing configuration instruction according to the optimal path. According to the invention, the accuracy and efficiency of routing decision and the utilization rate of network resources are improved, and intelligent path optimization in a complex dynamic network environment is realized.

The invention discloses a Mesh network-based cluster radio station state sensing and visual early warning system, which comprises a hardware layer, a data layer, a service layer and an application layer, and is characterized in that the hardware layer is used for establishing and maintaining a wireless link by taking a Mesh radio station as a network communication main body, and the data layer is used as an information hub; the data layer is responsible for receiving, integrating and storing real-time and historical data from the hardware layer and synchronizing radio station state data and environment sensing data through a standardized interface, and the service layer is used for processing original information provided by the data layer, converting the original data into valuable insight and automatic control instructions and sending the control instructions to the data layer. The application layer is used for displaying the analysis result and the control capability in a graphical and operable manner; according to the invention, a collaborative management system integrating a hardware layer, a data layer, a service layer and an application layer is constructed, so that centralized monitoring, automatic operation and maintenance, real-time perception and visual early warning of the dynamic Mesh network are realized, and the efficiency of network management is remarkably improved.