216 results about "Network domain" patented technology

The invention provides an SDN (Software Defined Network) inter-domain traffic engineering method based on reinforcement learning, which comprises the following steps of: deploying a data traffic demand monitoring platform and a control system, and constructing a global network topological graph; calculating a short link identifier for the link in the network and distributing the short link identifier to each network device; flow judgment is carried out, upward notification is carried out according to requirements, and pre-operation of intelligent routing is cooperatively completed; deploying a reinforcement learning model in the total intelligent body, outputting an optimal cross-domain path strategy to the cooperative controller, disassembling the optimal cross-domain path strategy into flow table rules which can be executed by each domain, and issuing the flow table rules to local controllers of related domains; and each local controller pushes the flow table configuration to the domain switching equipment to complete the forwarding decision of the flow. According to the method, a complete closed-loop process of flow measurement, intelligent decision making, cross-domain control and path issuing is realized, feasible reference is provided for actual deployment of an intelligent network, and the method has good engineering popularization value and is suitable for intelligent scheduling scenes such as an operator backbone network, an industrial internet and metro edge cloud.

The invention discloses a causal chain tracking method and system for cross-space APT attack behaviors, and relates to the technical field of network security. The method comprises the following steps: collecting heterogeneous device logs crossing multiple network domains, extracting original attack data, performing spatial-temporal feature extraction, and generating a device behavior spatial-temporal vector; analyzing the original attack data to obtain attack tactical semantic features, fusing the equipment behavior space-time vector and the attack tactical semantic features, and constructing a three-dimensional association map; and performing attack path reasoning on the three-dimensional association map based on a causal discovery algorithm, identifying a causal dependency relationship, performing data tracking according to the causal dependency relationship, reconstructing an APT attack causal chain, and obtaining an attack logic path. The technical problem that in the prior art, comprehensive and accurate traceability analysis on cross-space APT attacks is difficult is solved, and the technical effects of efficient reconstruction of APT attack causal chains and accurate identification of attack paths are achieved.

Methods and apparatus for biometric data maintenance, access and distribution across two or more experiential and / or network domains. In one embodiment, a 5G NR-based network architecture is provided which allows ultra-low latency and effectively user-imperceptible biometric data use for e.g., authentication and maintenance of user state across multiple domains via multiple constituent user devices (e.g., UEs). The network architecture includes both (i) a distributed biometric database (BDB) model wherein relevant biometric data for individuals / UEs is intelligently cached in various portions of the distributed database, and (ii) centralized and local BAEs (biometric analytics entities) which manage the aforementioned intelligent caching, as well as network configuration using one or both of 5G NR network “slicing” and CU / DU split options to optimize end-user biometric-related applications such as those providing identification / authentication, AR functions, VR functions or yet others.

The invention discloses a network attack tracing method, device and equipment and a medium, and the method comprises the steps: obtaining a plurality of network flow data packets, a plurality of pieces of weblog data and a plurality of equipment state parameters of a plurality of monitoring nodes in a target network domain; determining an abnormal node with a network attack behavior in the plurality of monitoring nodes based on the plurality of network flow data packets, the plurality of pieces of network log data and the plurality of equipment state parameters; and tracing the network attack behavior based on the abnormal data packet of the abnormal node, the abnormal weblog data and the abnormal equipment state parameter to obtain an attack type, an initial attack node and an attack path of the network attack behavior. The collaborative analysis value of data packet deep features and multi-source equipment information is fully utilized, real threats and normal network activities are accurately distinguished, and the traceability accuracy and reliability are remarkably improved. Meanwhile, through correlation analysis of multi-dimensional data, an attack source positioning range can be converged step by step, and an attack path can be completely reconstructed.

The invention relates to the technical field of information security, in particular to a cluster self-discovery method suitable for a cloud server cipher machine, which comprises the following steps: when physical equipment of the cloud server cipher machine leaves a factory, a certificate management module generates an equipment certificate and a root CA certificate in combination with an enterprise CA system, and stores the equipment certificate and the root CA certificate; after the virtual cipher machine is created and started, the key management service module combines with the certificate management module to generate a virtual machine certificate, and stores the virtual machine certificate, the storage device certificate and the root CA certificate together; the cluster management service module enables the master node of the virtual cipher machine to discover the slave node of the virtual cipher machine in the same network domain through UDP broadcast, and executes three-level verification on the slave node of the virtual cipher machine from three aspects of an equipment certificate, a virtual machine certificate and an authentication signature; and the virtual cipher machine master node synchronizes the cluster master key to the virtual cipher machine slave node passing verification. According to the invention, hierarchical identity isolation and verification of the cloud server cipher machine host and the virtual cipher machine can be realized, and the security of cluster self-discovery and authentication stages is ensured.

The invention relates to the technical field of wireless communication, and provides an ultra-low time delay cooperative communication method and system, and the method comprises the steps: constructing an end-to-end network slice strategy model which comprises a wireless access network, a bearer network and a core network based on a service level protocol; fusing vehicle-mounted and roadside heterogeneous sensing data, constructing surrounding environment situation sensing data, and generating an uplink data packet with a service type identifier; a dynamic decision is made according to a service type identifier in the uplink data packet, a collaborative scheduling logic mechanism is triggered, end-to-end transmission is completed in each network domain, and a multi-access edge computing data packet is output; and performing real-time analysis on the multi-access edge computing data packet, generating a final control instruction or early warning information, and completing closed-loop issuing through a downlink. According to the invention, end-to-end network resource hard isolation and cloud end-to-end integrated cooperative intelligence are cooperatively fused, and a whole-process deterministic service system from multi-source sensing, guarantee communication and cooperative decision-making to closed-loop control is constructed.

The invention discloses a decentralized AI service credible management system and a decentralized AI service credible management method. According to the method, the client and the server of each network domain are constructed through the credible AI model based on federal learning, so that the credibility of the AI model obtained by training can be ensured; the block chain node in each network domain can evaluate the credibility of the AI model uploaded to the block chain by the server of each network domain through the AI model credibility evaluation based on logistic regression and clustering, thereby supporting the subsequent personalized AI service. Through on-chain registration, under-chain storage and authorization access control of the AI model realized based on the client, the server and the block chain network, block chain-based AI service management is realized, and decentralized management of the whole life cycle of the AI service can be realized.

A system and method for privilege assurance protection of computer networks that remedies the deficiencies of the current directory service structure. The system uses a software agent to collect and store snapshots of all network resources on a computer network by identifying network domains, searching the directory service of each domain for network resources, and periodically querying the network resources for changes. The software agent communicates with a backend server which provides searching, querying, storage, administrative and other functionality to the agent via remote procedure calls.

The invention relates to a link planning method based on cross-domain heterogeneous network intelligent fusion, and the method comprises the steps: collecting heterogeneous data from a network, and carrying out the preprocessing of the data; fusing the features of different network domains; evaluating the importance of each link in the heterogeneous network according to the low-dimensional feature matrix; initializing a link population, calculating population fitness, and constructing a population dynamic model; calculating a link resource allocation proportion, updating a link topology according to the link resource allocation proportion, increasing the bandwidth of a high-proportion link or reducing the load of a low-proportion link, and generating an optimized topology; and obtaining a link planning decision by using reinforcement learning according to the optimized topology, and evaluating the link planning decision and performing adaptive adjustment through a feedback mechanism. According to the invention, the data transmission efficiency is improved, and seamless integration and extended application of a multi-domain network are supported.

The invention discloses a multi-channel integrated radio frequency system based on double-threshold interference detection and dynamic spectrum aggregation. A radio frequency front-end unit is used for realizing broadband spectrum access and performing analog-to-digital conversion; the digital channel processing unit is used for realizing channelized segmentation through up-conversion and down-conversion, carrying out band elimination filtering to shield unavailable channels and outputting filtering parameters to support dynamic channel recombination; the digital signal parallel processing unit performs parallel access by using the divided channels; the spectrum sensing unit is used for carrying out double-threshold channel interference detection and real-time spectrum analysis according to the parallel access signals; and the frequency spectrum decision-making unit is used for judging the channel state and fusion detection judgment according to the interference detection result, judging the availability of a specific channel in the data link network and carrying out cooperative dynamic frequency spectrum aggregation. According to the method, a consistent spectrum access decision is realized by adopting a spectrum monitoring, sensing convergence and fusion decision mechanism, and consistent understanding of an available frequency set and high-reliability network domain dynamic spectrum aggregation are guaranteed.

The invention discloses a 6G-oriented cross-domain knowledge-driven network intelligent scheduling system and a 6G-oriented cross-domain knowledge-driven network intelligent scheduling method. The architecture comprises a cross-domain knowledge collaborative evolution module, a network closed-loop management module and a multi-normal-form learning decision module, the cross-domain knowledge collaborative evolution module is used for disassembling a network state into an environment domain, a network domain and a user behavior domain, and online incremental fusion of three-domain knowledge is realized through a graph neural network; dynamically updating the global knowledge base based on knowledge distillation; the network closed-loop management module is used for constructing a function closed loop of perception-reasoning-knowledge generation-decision issuing-verification optimization-memory retrieval; and the multi-normal-form learning decision module is used for fusing meta learning, reinforcement learning, federal learning and self-supervised learning to realize rapid migration and continuous evolution of the strategy. According to the method, the network data throughput, the fault recovery speed, the flow prediction precision, the resource fairness, the path efficiency and the task success rate are improved, and the method is suitable for complex 6G scenes such as air-ground integration and low-altitude traffic control.

The invention relates to the technical field of network space security, and provides a cross-domain honey array collaborative deployment method, device and equipment based on federated learning, and the method comprises the steps: dividing a plurality of network domains into a plurality of autonomous domains, and deploying a local honey array agent module in each autonomous domain; collecting local honey point interaction information in the autonomous domain according to each local honey array agent module; training a local honey spot decoy effectiveness evaluation model according to the local honey spot interaction information, and outputting local model parameters corresponding to each autonomous domain; according to the local model parameters corresponding to each autonomous domain, generating a global honey point deployment strategy through weighted aggregation of a federated learning aggregator; based on the global honey point deployment strategy, a local honey point deployment strategy of each autonomous domain is generated through a cross-domain scheduling mechanism module; according to the local honey point deployment strategy of each autonomous domain, deployment configuration of honey points in each autonomous domain is dynamically adjusted, and joint modeling and dynamic optimization of a multi-organization honey array deployment strategy are realized on the premise of guaranteeing data privacy.

A cyber security system includes an importance node module to compute and use graphs to compute an importance of a node based on factors including a hierarchy and a job title of the user, aggregated account privileges from network domains and a level of shared resource access for the user. The graphs are supplied into an attack path modeling component to understand an importance of the network nodes and determine key pathways within the network that a cyber-attack would use, via a modeling the cyber-attack on a simulated and a virtual device version of the network. The cyber security system provides an intelligent prioritization of remediation action to a remediation suggester module to analyze results of the modeling the cyber-attack for each node and suggest how to perform intelligent prioritization of remediation action on a network node in one of a report and an autonomous remediation action.

The invention discloses a power distribution equipment state detection method and device based on multi-modal data fusion, terminal equipment and a storage medium, and belongs to the field of power distribution equipment. Performing feature analysis on the acquired multi-modal data by using a time sequence convolutional network, a residual neural network and a Transform network to obtain a local abnormal fluctuation feature, an infrared temperature spatial distribution feature and a video global feature representation; performing feature splicing on the local abnormal fluctuation feature, the infrared temperature spatial distribution feature and the video global feature representation to obtain a fusion feature, and inputting the fusion feature to a long-short term memory network to obtain a historical hidden state sequence; and determining the equipment state of the to-be-detected power distribution equipment according to the historical hidden state sequence, the fusion features and edge equipment deployed in the local network domain of the equipment. By implementing the application, the problem of low accuracy of state analysis of the power distribution equipment caused by only depending on single modal data in the prior art can be solved.

The invention discloses a heterogeneous deterministic network cross-domain periodic mapping method, a heterogeneous deterministic network cross-domain periodic mapping system and a related device, and belongs to the technical field of power system communication, and the method comprises the following steps: for a power service end-to-end deterministic network formed by a plurality of different sub-network domains, monitoring a buffer queue state through an edge gateway node of the heterogeneous deterministic network; performing queue management on the data packets of the service flow through the edge gateway node according to the queue state monitoring result of the buffer area, and obtaining queuing and queue offset distribution results of the data packets in the buffer area; the edge gateway node calculates and distributes a mapping period of the cross-domain network; and in combination with queuing and queue offset allocation results of the data packets in the buffer area, the edge gateway node feeds back and optimizes the time delay determinacy guarantee condition of the service flow, and the allocation of network resources and the routing strategy of the service flow are adjusted. According to the method, dynamic mapping of different network periods in a heterogeneous deterministic network scene can be realized, and scene requirements of dynamic changes of services and networks can be better met.

The invention discloses a cross-network collaborative alarm noise reduction method based on a knowledge distillation large model, and belongs to the technical field of network security. Comprising the following steps: deploying a server in a first network domain for operating a teacher model; a lightweight device is deployed in a second network domain needing to be protected and is used for operating a student model; a knowledge distillation module is established as a communication bridge between two networks. In the first network domain, training a teacher model by using the alarm data; after training is completed, the teacher model generates a knowledge data packet; the teacher model writes the generated knowledge data packet back to the knowledge distillation module and associates the knowledge data packet with the original reference alarm data; and the student model deployed in the second network domain simultaneously reads the reference alarm data and the corresponding knowledge data packet generated by the teacher model from the knowledge distillation module. According to the invention, the efficiency and accuracy of cross-network cooperative security alarm noise reduction are improved, and an efficient alarm noise reduction method is provided for the technical field of network security.

The application discloses a data ferrying method, device, system, equipment and storage medium, relates to the technical field of communication, and splits the data ferrying process into flexibly defined ferrying states and state transitions through a ferrying state machine, can efficiently control the transmission of data between different network domains while meeting the isolation requirements, and effectively avoids data leakage and external attacks. The method comprises the following steps: constructing a network topology structure of data ferrying in advance, wherein the network topology structure comprises a network domain set and a ferrying network set; defining a ferrying state machine on the basis of the network topology structure, wherein the ferrying state machine is a state model for describing the data transmission of the ferrying network between at least two network domains, and the ferrying state machine comprises at least one ferrying state and state transition logic; and changing the connection state combination formed by the ferrying network and the at least two network domains according to the state transition logic, so as to control the data transmission of the ferrying network between the at least two network domains.

The invention relates to the technical field of data transmission, and discloses a cross-domain model communication method, device and equipment and a computer readable storage medium. The method is applied to a cross-domain model communication system, the system comprises a user domain, a data domain and a gatekeeper, and the method comprises the following steps: sending request information of a model in the data domain to the gatekeeper through the user domain, and performing security auditing on the request information through the gatekeeper; when the security check is passed, sending the request information to a data domain through a gatekeeper, and generating response information based on the request information through a model; sending the response information to a gatekeeper through the data domain, and performing security auditing on the response information through the gatekeeper; and when the security check is passed, the response information is sent to the user domain through the gatekeeper. When the model carries out data transmission between the user domain and the data domain, the transmitted data is subjected to security auditing through the gatekeeper, and the data transmission is carried out only when the security auditing is passed, so that the security of cross-domain communication of the model is improved.

The application discloses a botnet domain name determination method and device and electronic equipment. It relates to the technical field of data processing, the field of network security and other related technical fields. The method comprises the following steps: constructing a target network relationship graph according to target DNS data; performing community division on the target network relationship graph according to a community discovery algorithm to obtain multiple community structure information; and determining a target botnet domain name from the target DNS data according to the multiple community structure information. Through the application, the problem that the determination accuracy of the botnet domain name is relatively low in the related art, which is caused by calculating the similarity between the target domain name and the historical botnet domain name to determine whether the target domain name is a botnet domain name, is solved.

The invention relates to the technical field of communication, and discloses a reinforcement learning-based cross-space resource autonomous configuration method, which comprises the following steps of: performing joint modeling on network resources and physical resources by using a unified heterogeneous graph, and expressing a cross-space resource comprehensive configuration problem as a random and time-varying mixed integer nonlinear programming problem in a rolling time domain; introducing reinforcement learning to convert the nonlinear programming problem into a constrained Markov decision process; a resource configuration language instruction output by the policy network is mapped into a specific network domain and physical domain control instruction through a domain specific compiler, the specific network domain and physical domain control instruction is transactionally issued and executed, and an execution receipt is collected and fed back to the policy network to form closed-loop learning; according to the method, the engineering feasibility and the theoretical interpretability are unified. By means of a resource configuration language and triple masks, strategy output naturally falls in a compilable and rollback instruction subspace, and invalid exploration and configuration conflicts are remarkably reduced.

The present disclosure provides a network configuration verification acceleration method based on network domain knowledge, an electronic device and a readable storage medium. The method of the present disclosure comprises: screening the first configuration information in the network configuration information irrelevant to the network invariant to be verified, ignoring the first configuration information in the network configuration information, and obtaining the second configuration information; encoding the network invariant to be verified to obtain the first encoded information; encoding the second configuration information to obtain the second encoded information, wherein the numerical attribute information in the second configuration information is abstracted in the encoding process; combining the first encoded information and the second encoded information to obtain the encoded information; determining the search order of the first variable in the encoded information, and determining the assignment order of the first variable in the encoded information; selecting the first variable in the encoded information according to the search order, and then assigning the selected first variable according to the assignment order to verify the encoded information.

A method performed by performed by an exposure node having a first identity in a first network domain in a telecommunications network is provided. The method includes initiating a request towards a first network node for a subscription to an event of a communication device. The request includes subscription information for a common network exposure in at least two network domains. The method further includes receiving a response from the first network node. The response includes at least one of: a first confirmation that the event will be reported to the exposure node for a second network domain for the common network exposure and a second confirmation that the event will be reported to the exposure node for the first network domain. The second confirmation omits an indication of the common network exposure. Methods performed by a first network node are also provided.

A resource event sensing method and system based on computing network fusion relates to the technical field of computing network fusion resource sensing, and comprises the following steps: decomposing an application into a computing task and a connection task to generate application information; generating task information including a task ID, a task type, a resource type, a corresponding resource ID and resource context information for each task; constructing a unified computing network resource information topological graph based on the task information, taking computing resources corresponding to the computing tasks as nodes, and taking connection resources corresponding to the connection tasks as edges; a unified clock source is adopted to ensure the time consistency of sensing data, and the resource state is sensed; and carrying out aggregation and correlation analysis on the sensing events according to the resource dependency chain. Through the unified event model, the computing network topology and the resource association mechanism, the problems of sensing fragmentation, fault positioning difficulty and low resource scheduling efficiency caused by sensing separation of the computing power domain and the network domain are solved, a precise end-to-end resource view is provided for AI application, and the operation and maintenance efficiency of the AI cluster is remarkably improved.

A method, a network element, a system and a storage medium for processing a quality of service (QoS) parameter, the method comprising: a control plane network element obtaining a first QoS parameter between a terminal device and a user plane function network element; obtaining capability information of a first network domain, determining a second QoS parameter of the first network domain according to the capability information of the first network domain and the first QoS parameter, and sending first information of the second QoS parameter to the first network domain. The first network domain comprises at least one of a radio access network, a backhaul network and the user plane function network element. By adopting the scheme, the accuracy of data packet scheduling and user experience can be improved.

Prediction and prevention of cybersquatting events include receiving a first input by a computer associated with a first trademark term. A first set of features associated with the first trademark term is determined based on the received first input. Based on application of a first machine learning (ML) model on the determined first set of features, the first confidence score is predicted. The first confidence score is indicative of at least one cybersquatting event associated with the first trademark term. A first alert is rendered based on the predicted first confidence score.

This invention relates to the field of waste-to-energy incineration technology and provides an artificial intelligence-based combustion control method for waste-to-energy boilers. The method includes: collecting data from a distributed control system, flue gas monitoring, and feed metering, aligning these data with a unified time frame, and generating combustion condition data; calculating drift residuals and missing rates, classifying and labeling them to obtain confidence weights; calculating equivalent lower heating value and moisture content from steam flow and feed flow based on energy balance, updating parameters only during the stable steam and carbon monoxide windows; identifying the equivalent time delay from control quantities to steam and emissions based on cross-correlation peak values, writing this information into the prediction model after stabilization, and performing shift compensation; constructing hard constraints for steam and emissions based on aligned predictions, writing confidence into the cost function, using MPC to calculate the feasible region, selecting incremental deployments within the policy network domain, and backing down and auditing for low confidence levels.

The invention discloses a recognition method of a reversely-installed fastener, a storage medium and equipment, and the method comprises the steps: firstly obtaining an original image of a track, carrying out the data enhancement and domain extension of the original image, inputting the enhanced track image and a domain extension image into a fastener recognition model, and carrying out the iterative training, thereby obtaining a trained fastener recognition model; inputting a track image to be recognized to obtain a fastener recognition result of the track image; the fastener identification model is based on Faster R-CNN and comprises a backbone network, a region candidate network, a domain comparison module and a detection head, the domain comparison module introduces a class-level domain comparison learning mechanism to encourage a detector to understand correlation and difference between fasteners in different fields on the class level, the model is guided to mine fastener class-level domain invariant features, and the detection head is used for identifying the fasteners in the class-level domain. According to the method, the problem that the reversely-installed fastener is difficult to recognize in multiple scenes is solved, the generalization and accuracy of track fastener recognition are greatly improved, the cost is saved, and the method has important practical application significance.

The invention discloses an SDN (Software Defined Network) controller network domain division method based on an MPLS (Multi-Protocol Label Switching) network, which comprises the following steps: (1) MPLS configuration item resource static planning: carrying out static range division according to a hardware resource condition, the number of actually required domain division and an actual condition of an actual multi-department network management monitoring permission; (2) deploying controllers according to domains: the SDN controller obtains whole network topology data through equipment directly connected with the SDN controller, the equipment directly connected with each domain controller is different, and the controllers between the domains do not influence each other and work independently; (3) deploying network management software: each piece of network management software is only allowed to issue an instruction to the controller in the respective domain, and the network management software running in the network does not influence each other and independently works; and (4) realizing network domain division. According to the invention, in the SDN architecture, a domain-divided networking mode is provided for centralized networking, so that the requirements of multi-department network management monitoring or different services and authority are met, and the network stability and the operation and maintenance efficiency are improved.

The invention discloses a vulnerability analysis processing method and device for an electric power information physical fusion system, and relates to the field of electric power systems. Comprising the steps of 1, constructing a holographic mapping relation graph, and identifying vulnerable points / dependency points; 2, simultaneously monitoring network intrusion and equipment abnormity in real time: if an alarm source belongs to a candidate node, starting cross-domain collaborative protection; otherwise, entering single-domain quick response of the network domain or the physical domain respectively; step 3, network domain vulnerability protection; step 4, physical domain vulnerability protection; 5, cross-domain collaborative protection adopts a recursive subtraction traversal mode to carry out recursive depth defense; through holographic mapping, cross-domain influence quantization and hierarchical recursive protection, the method can realize accurate, rapid and controllable safety guarantee of the electric power information physical fusion system.