2157 results about "Networked system" patented technology

A neural network system is provided. The system includes an autoencoder configured to encode input data into a latent space representation; a generator neural network configured to receive a noise vector and the latent space representation and output a set of routing coefficients; a discriminator neural network configured to evaluate the effectiveness of the routing coefficients by measuring the performance of a capsule network utilizing said routing coefficients; and a capsule network comprising a first capsule layer and a second capsule layer, wherein the routing coefficients are used to dynamically route outputs from the first capsule layer to the second capsule layer.

The invention discloses a multi-dimensional computing power dynamic perception routing decision-making method and system based on SRv6 driving. The method comprises the following steps: firstly, screening an optimal target computing power node based on a service demand and a node real-time load; and then, based on the dynamic network topological graph fusing the service sensitivity, calculating an optimal network path reaching the computing power node by using an improved SPFA algorithm, and realizing a global collaborative decision of selecting the most suitable computing point and searching the most efficient connection path. Meanwhile, based on an SRv6 driving service chain dynamic generation and closed loop execution method, a target computing power node and necessary network functions are abstracted into a programmable SID, an SID sequence (service chain) is dynamically constructed according to a double-stage decision result and is packaged in an SRH head, second-level path issuing and state monitoring are achieved through a programmable controller, and a real-time monitoring result is obtained. According to the method, the problems of poor real-time performance, single dimension, weak cooperative capability and the like in the prior art are solved, and efficient, stable and intelligent development of a future-oriented distributed intelligent computing network system can be promoted.

The invention relates to the technical field of wireless communication, in particular to a wireless communication network system and method for intelligently fusing a multi-mode heterogeneous network. Comprising a multi-mode access unit; a protocol compatibility and conversion unit; the heterogeneous network intelligent fusion unit completes cross-network dynamic flow collaboration and resource optimization decision through cross-layer feature association mining, service-network two-dimensional weight calibration and a double-closed-loop feedback optimization mechanism, generates a resource scheduling instruction and transmits the resource scheduling instruction to the intelligent scheduling and resource control unit; an intelligent scheduling and resource control unit; and a system control and cooperation unit. According to the invention, the service-network two-dimensional dynamic fusion weight is constructed through the intelligent fusion unit of the heterogeneous network, and bandwidth, frequency spectrum and power resources are allocated according to the priority and margin balance principle in combination with the intelligent scheduling unit, so that the problem of insufficient two-dimensional coordination of resource scheduling is solved, the resource scheduling is matched with the service demand and the network load, and the resource scheduling efficiency is improved. And resource waste or incapability of meeting business requirements is avoided.

The invention discloses an adaptive game-driven network defense method and system, and relates to the technical field of network security. The method comprises the following steps: generating a multi-modal bait according to network context information, and screening an optimal bait through credibility evaluation; constructing a time sequence feature tensor according to the network event sequence information of the bait, and obtaining predicted attack information by adopting a pre-trained attack prediction model; combining the network event sequence information of the bait and the predicted attack information to construct a defense income matrix, and carrying out iterative equilibrium solution to obtain an optimal strategy candidate pool; and taking the defense hybrid strategy of the optimal strategy candidate pool as an initial population, performing multi-objective optimization through a non-dominated sorting genetic algorithm to obtain a Pareto optimal strategy set, and performing screening to obtain an execution strategy set for dynamic defense decision making. According to the invention, the dynamic property, intelligence and self-adaptability of network defense are realized, and the ability of a network system to cope with complex attacks is effectively improved.

A method is provided for processing data in a neural network system. The method includes receiving input data; processing the input data through a first set of neural network layers configured to perform data processing using MatMul-free techniques to produce intermediate data; further processing the intermediate data through a second set of neural network layers configured to simulate spiking neural network (SNN) functionalities using MatMul-free techniques; and outputting a result based on the processed data from the second set of neural network layers.

The invention discloses a soft network system capable of expanding a transmission mode and an implementation method, and the system comprises an equipment resource mapping management unit which automatically generates a unique channel code based on a native hardware interface and establishes a multi-dimensional mapping relation; the heterogeneous interface data acquisition unit is used for monitoring various hardware interfaces in a kernel space in parallel and realizing zero-copy data transmission through a three-buffer lockless annular buffer area; the transmission abstraction and dynamic expansion unit realizes transmission mode modularization in a plug-in form and supports atomic hot plug during operation; the protocol analysis and service processing unit is used for realizing unified scheduling and fault isolation in a single process through a dynamic link mechanism; and the cross-layer monitoring and self-healing unit realizes automatic switching based on a session state machine and a redundant channel. According to the method, the code complexity is reduced from O (N * M) to O (N + M), and the time lt is extended; fault switching is carried out at 1s; and the hardware cost is reduced by more than 40%, so that the method is particularly suitable for power and environment monitoring scenes with more than 1000 devices and more than 15 protocols, and has high creativity.

The invention relates to the technical field of network management, and discloses an intent-driven network management method and system based on a large language model (LLM). The method comprises the following steps: receiving a natural language intention of a network administrator, analyzing the intention by utilizing a pre-trained large language model, extracting a key target and constraint, generating a configuration scheme of a TCP / IP or QUIC protocol based on an analysis result and a network protocol knowledge base, and ensuring the effectiveness and safety of configuration through a network constraint verification module. And the configuration passing the verification is applied to the network system. The system comprises an intention input module, an LLM analysis module, a configuration generation module, a verification module, an application module and the like. According to the invention, through conversion from automation intention to configuration, the network management process is simplified, the management efficiency and flexibility are improved, the method is especially suitable for multi-parameter optimization scenes of protocols such as TCP / IP and QUIC, and intelligent network management is realized.

The invention discloses a flow field video generation method based on a policy value architecture and online physical exploration, and belongs to the technical field of crossing of artificial intelligence and computational fluid dynamics (CFD), and the method comprises the following steps: step 1, constructing an unsteady flow field multi-modal training data set, step 2, constructing a generative network system based on an Actor-Critic architecture, step 3, constructing an unsteady flow field multi-modal training data set, and step 4, constructing an unsteady flow field multi-modal training data set. Step 4, supervised fine tuning training is carried out in the first stage; step 5, online physical exploration of a generator is carried out in the second stage; step 6, feedback co-evolution of a physical encoder is carried out in the third stage; and step 7, reasoning generation of an unsteady flow field video is carried out. According to the method, a reinforcement learning architecture containing an Actor and a Critic is constructed, a physical equation is packaged into a digital environment, and a training strategy of basic supervision fine tuning, online physical exploration of a generator and coevolution feedback of an encoder is adopted.

The invention relates to the technical field of geological early warning, in particular to a dangerous rock mass instability analysis method, system and equipment based on a space-time diagram neural network, by fusing unmanned aerial vehicle LiDAR, multispectral data, meteorological radar data and the space-time diagram neural network (ST-GNN), the system realizes sub-meter spatial resolution and minute-level time response, and the stability of dangerous rock mass instability analysis is improved. The four-dimensional (time and space) analysis result of the instability probability of the dangerous rock mass is obtained through high-precision space-time modeling, the problems that a traditional geological disaster early warning system is low in resolution ratio, slow in response and high in misinformation are solved, the comprehensiveness, accuracy and reliability of instability prediction of the dangerous rock mass are improved, and the early warning effect is good. And full-chain intelligent closed-loop management of real-time data acquisition-dynamic prediction-early warning push-feedback optimization is supported, the emergency decision time is shortened by real-time rainfall superposition risk thermodynamic diagrams, and the attenuation rate of long-term prediction precision is reduced by dynamically fusing newly added geological data and instability events through incremental learning.

The invention discloses systems and methods for privacy-preserving digital communications compliant with frameworks such as GDPR, DPDPA, HIPAA, and PSD2. A Virtual Identity (VI) is instantiated within a secure enclave and bound to one or more Compliance Jurisdiction Tokens (CJTs). Unlike conventional tokenisation limited to payment or aliasing, the invention enables multiple concurrent VIs (Multi-VI), each scoped to a declared purpose, jurisdiction, subnet, or session. Communication is permitted only if all bound CJTs validate inline, including Multi-CJT bindings where jurisdiction, purpose, and consent must all succeed, and Multi-Purpose CJTs (MCJTs) where multiple lawful purposes must be simultaneously satisfied. Each validation produces a Ledger-Anchored Validation Receipt (LAVR) containing pseudonymised metadata, anchored into tamper-evident ledgers for transparency. Regulators access receipts through a Regulator Query Interface (RQI), enabling filtered oversight without exposure of raw identifiers. The technical effect is to transform privacy and compliance into cryptographic enforcement across device, telecom, and network layers

Artificial intelligence techniques for connections networking are described. In one embodiment, for example, a method comprises receiving a natural language query to group a set of entities by a first machine learning model trained on a public dataset, generating a set of entity groups by the first machine learning model based on the natural language query and the set of entities, generating a set of connections entity groups based on the set of entity groups by a second machine learning model trained on a private dataset, selecting a member identifier (ID) representing a member of a connections networking system associated with an entity from a connections entity group of the set of connections entity groups, and sending a recommendation for a networking service to an electronic device based on the member ID. Other embodiments are described and claimed.

The invention discloses a synchronization method and device for time synchronization of a network system, and relates to the technical field of computers, and the method comprises the following steps: when a master station sends a dynamic compensation synchronization frame, recording a compensation sending timestamp in a sensing identification field of a sending end; when the frame is received and transmitted from the station, the identification field is sensed at the port to determine a compensation receiving timestamp and a compensation transmitting timestamp. And the slave station identifies the dynamic compensation synchronization frame after reverse return, calculates dynamic compensation time information based on the compensation receiving timestamp and the compensation sending timestamp corresponding to the slave station, and reads and writes the dynamic compensation time information to a corresponding field. And the master station analyzes the returned dynamic compensation synchronization frame, aggregates the dynamic compensation time information of each slave station, and solves the dynamic compensation values of the master and slave stations in combination with the fixed link delay. And the master station corrects a local high-precision clock according to the data, and writes a compensation value into a local time correction register of the slave station to trigger a hardware counter to correct so as to complete synchronization of the master and slave clocks. By realizing dynamic residence separation, the problem of overlarge error is solved.

An all-binary neural network system and method for processing and analyzing multi-source time series data is disclosed. The system employs a shared codebook to encode input streams into binary codewords, which are then processed through a series of binary convolutional layers, binary LSTM layers, and binary fully connected layers. The system maintains binary representations throughout, enabling efficient computation and reduced memory requirements while effectively capturing temporal and inter-source relationships in the data.

The invention discloses a hydropower station operation state intelligent prediction method and system based on multi-source data fusion. The method comprises the steps that heterogeneous data including but not limited to water level, flow, generating capacity, equipment operation parameters, environmental meteorological data, hydrological data and the like are collected in real time from multiple data sources of a sensor network, an SCADA system, a meteorological station and a hydrological station of a hydropower station; the method comprises the following steps of: preprocessing collected original data, extracting time sequence features, fusing multi-source data, taking a fused multi-dimensional feature vector as input, and learning and training through an encoder-decoder architecture of a model so as to capture a complex dynamic mode of an operation state of a hydropower station; and inputting the data acquired and preprocessed in real time into the trained AI prediction model, and generating prediction results of key operation parameters, equipment states, residual life and potential risks of the hydropower station. The method can more accurately capture the complex nonlinear relation in the operation of the hydropower station, and significantly improves the prediction precision of key parameters and risks.

The invention relates to a meteorological-based dynamic graph network photovoltaic power station group ultra-short-term prediction method, which is characterized in that a dynamic space-time graph network is constructed, photovoltaic power stations in a region are regarded as a complex network system connected by meteorological fluctuations, each power station is taken as a node, and the propagation relationship of the meteorological fluctuations among the power stations is represented by edges of a graph. The weight and time delay of the edge are dynamically adjusted according to real-time meteorological data, and dynamic interaction between power stations, the overall trend under the stable meteorological condition and rapid fluctuation caused by sudden weather events are accurately captured in combination with a mixed model of a graph neural network and a recurrent neural network. Compared with a traditional method, the method has the advantages that the prediction precision, the real-time response capability and the physical interpretability are remarkably improved, scattered photovoltaic power stations are integrated into a mutually associated dynamic system, an efficient and reliable solution is provided for power prediction of a power station group, and the operation stability and the power grid dispatching efficiency of a large-scale photovoltaic system are enhanced.

The application relates to the field of wireless communication, in particular to a communication method, device and system for resource indication in a wireless communication system. In the method, a network device determines a plurality of resource blocks, the plurality of resource blocks being used by a terminal device; the network device sends resource indication information to the terminal device, the resource indication information indicating the plurality of resource blocks; the terminal device acquires the resource indication information and determines index information of the plurality of resource blocks, the index information of the plurality of resource blocks being determined according to resource block indexes of a common index region or according to resource block indexes of a bandwidth region. Through the method, the network device efficiently allocates or reallocates uplink or downlink resources to the terminal device, and the communication efficiency of the network system is improved.

The invention discloses a deep sea mineral lifting unmanned transportation system. According to the system, an unmanned carrier-intelligent execution-elastic scheduling framework is constructed, and the system comprises four modules including unmanned carrying equipment, a communication network system, a scheduling control center and a support safeguard system. The unmanned carrying equipment realizes mineral transportation based on buoyancy driving; the communication network adopts a layered redundant architecture of underwater sound OFDM and a laser emergency link, and high-reliability communication and centimeter-level positioning are guaranteed; the scheduling control center improves the operation efficiency through intelligent task allocation and trajectory planning; the support and guarantee system integrates energy management, digital twin monitoring and emergency response mechanisms. The operation process adopts a mode of mainly unmanned autonomous and assisted by remote monitoring, and the links of ballast diving, acousto-optic docking, buoyancy regulation and control, mother ship dynamic unloading and the like are covered. The deep-sea mineral lifting efficiency, maneuverability and reliability are remarkably improved, and core technical support is provided for deep-sea resource development.

The present invention provides a data network, a data ingestion system and a method of data ingestion in the data network for a supply chain management enterprise application. The data network includes one or more data objects of different data types received from different data sources structured on multiple distinct architecture, connected to each other for executing multiple functions in the enterprise application.

A computer-implemented method for training an anomaly detection neural network system comprising an encoder and a decoder is described. The method includes receiving training data comprising a plurality of training examples, each training example including a training audio waveform and a machine identity (ID); processing the training audio waveform to extract training audio features; receiving an environmental noise audio waveform; processing the environmental noise audio waveform to extract noise features; generating augmented features by combining the extracted training audio features and the noise features; processing, using the encoder, the augmented features to generate latent embeddings; processing, using the decoder, the latent embeddings to generate reconstructed audio features; processing, using a convolutional neural network, the augmented features to generate a predicted machine ID probability distribution; and adjusting, through backpropagation, the current values of the parameters of the encoder and the decoder to minimize an objective function.

The invention discloses a network system security monitoring device, which comprises an intelligent sensing layer for scanning network traffic, logs and user behaviors by deploying AI-driven detection nodes; when a potential threat is detected, a structured alarm is generated immediately and pushed to a trusted transmission layer; the trusted transmission layer is used for generating a unique block identifier by adopting a Hash algorithm after the data integrity is verified through a consensus node; automatically triggering a repair process by using an intelligent contract; the self-adaptive decision-making layer is used for synchronizing configuration, flow and vulnerability states of physical equipment; after the vulnerability information is received, simulating various repair schemes in a virtual environment, evaluating the influence of the schemes on services, dynamically adjusting the priority, generating an optimal strategy, and pushing the optimal strategy to the automatic execution layer; the automatic execution layer is used for automatically executing and monitoring the repair progress through an agency-free technology after receiving the repair instruction of the self-adaptive decision-making layer, and triggering a rollback mechanism and generating a fault report if abnormity is detected; and after repairing is completed, a verification script is automatically generated.

A user equipment (UE) is configured to request connection to a selected one of a plurality of available network slices of a network system. The UE implements a permission control framework that allows individual applications to request connection to the selected network slice, but establishes the connection only when the framework determines, based on any of a variety of permission criteria, that the application is permitted to access the requested network slice. The UE also supports user selection of the network slice via a graphical user interface that presents a selectable list of available network slices.

Embodiments here in disclose a method and system for network configuration generation using a network digital twin (NDT) comprising a spatio-temporal graph neural network (STGNN) for performance-based simulation in a communication network system is disclosed. A simulation request is received from a management service (MnS) consumer, including network parameters related to live network nodes. Performance data is retrieved from a management server, and performance is assessed against a performance threshold. Multi-domain telecom data is processed using a spatio-temporal graph neural network (STGNN) by a feature fusion attention mechanism, trained via a hybrid feedback loop with real and synthetic data. Upon meeting performance thresholds, a configuration recommendation is generated by a configuration recommendation engine, including an explanation and confidence value. The configuration recommendation is transmitted to the MnS consumer, enabling network automation without altering the live network directly.

Systems and methods for dynamic buffer management in switches that facilitate a data-driven intelligent networking system are provided. The system can accommodate dynamic traffic with fast, effective congestion control while providing efficient use of internal input buffer space.

The invention relates to a distributed model reasoning method, device and equipment and a storage medium, the method is applied to center equipment of a distributed network system, and the distributed network system comprises one piece of center equipment and a plurality of pieces of edge equipment; comprising the following steps: dividing a to-be-distributed model according to structure information of the to-be-distributed model to obtain a plurality of sub-models, and distributing each sub-model to at least one edge device; wherein the structure information represents a hierarchical structure between the model layers, and the plurality of sub-models form a to-be-distributed model; if the model reasoning request is responded, obtaining resource information of each edge device; wherein the resource information represents the operation state of the edge device; determining a target device from the at least one edge device allocated by the sub-model according to the resource information of each edge device; and controlling the target equipment to execute the corresponding sub-model according to the execution sequence among the sub-models. The operation efficiency of the model is improved, and full utilization of resources is realized.

The invention provides an intelligent computing center path distribution method, a data transmission method and a network system. According to the technical scheme, based on the time sequence characteristics of the AI training data flow and the characteristic that each set communication library only selects one communication algorithm to drive data flow transmission in the same communication period, the data flow identification capable of identifying the data flow and the communication algorithm corresponding to the data flow identification are obtained, and path planning is carried out based on the communication algorithm. In this way, during actual communication, data streams driven by different communication algorithms on the same path cannot be transmitted at the same time, the link congestion risk is reduced, and idle links are reserved for subsequent data streams of the same communication algorithm; different links are allocated to data flow identifiers with the same source IP address or the same destination IP address corresponding to the same communication algorithm in the same set communication domain, multi-path load sharing is carried out, data flow dispersed transmission based on the same communication algorithm drive is ensured, the congestion risk of a single link is further reduced, and the transmission efficiency is improved. The communication efficiency of an intelligent computing center network is expected to be improved.

The embodiment of the invention provides an emergency rescue wireless communication network topology prediction method based on deep learning. According to the method, an emergency rescue wireless communication network system is constructed, initial system parameters are generated, and the emergency rescue wireless communication network system comprises a plurality of nodes; acquiring node positions, environment information and inter-node signal strength in real time, and updating node states in the emergency rescue wireless communication network system according to the node positions, the environment information and the inter-node signal strength; the node state of the current time step is input into the trained prediction model to be analyzed and processed, a prediction result is output, the prediction model is composed of a graph convolutional network and a generative adversarial network, and the prediction result is used for indicating the topology connection condition of the emergency rescue wireless communication network in the next time step; and determining a corresponding emergency rescue strategy in the target rescue area according to the prediction result. According to the method, the reliability of a communication network is improved, and efficient and orderly development of rescue actions is guaranteed.

The invention discloses a hot patch management method in a passive optical network system, a storage medium and an electronic device, in a Linux system, a patch management process running in a user mode and a patch management unit running in a kernel mode cooperatively execute, and the method comprises the steps that after the patch management process completes loading of a patch pack, the patch pack is loaded in the user mode; acquiring a patch function address and an original function address in the patch pack to obtain a corresponding relation, and configuring the corresponding relation to a patch management unit; when the original function is called, the original function determines to execute the original function logic or jump to the address indicated by the hook parameter by judging the value of the hook parameter; and the patch management unit registers a corresponding probe for each patch function according to the corresponding relationship so as to trigger a processing function of the probe to execute an operation of modifying the value of the hook parameter into a corresponding patch function address before the original function is executed, so that an execution process is skipped to the patch function when the original function is called, and the original function is called. And managing the function-level hotfix of the kernel mode and the user mode in the same framework.

The embodiment of the application provides an optical amplifier, an optical assembly, an optical module, an optical communication network system and a detection device, relates to the technical field of semiconductors, and is used for solving the problem of one-way light emission of the optical amplifier. The optical amplifier comprises a waveguide and a photonic crystal. The waveguide comprises a core region and a cladding region arranged at the periphery of the core region. The waveguide further comprises an incident light side, a first light emission side and a second light emission side. The photonic crystal is arranged in the cladding region of the waveguide. The core region is located between the incident light side and the first light emission side, and the photonic crystal is located between the second light emission side and the core region. The photonic crystal is used for receiving incident light from the incident light side and emitting first emitted light and second emitted light. The first emitted light is emitted from the first light emission side, and the second emitted light is emitted from the second light emission side.

The invention provides a network security protection method and device based on persistent attack simulation. The method comprises the following steps: S1, generating a plurality of types of simulation attack traffic; s2, sending the simulated attack traffic to a target network system; s3, collecting performance index data of the target network system in real time by a plurality of monitoring points deployed in the target network system; s4, sending the performance index data of the target network system to the trained machine learning model to obtain the effectiveness of the protection measures of the target network system; s5, adjusting the protection strategy of the target network system according to the effectiveness of the protection measures of the target network system; and S6, resending the simulated attack traffic to the target network system with the updated protection strategy, and executing the step S3. By simulating different types of persistent attacks, the defense capability of the system is monitored in real time, and a protection strategy is automatically adjusted according to a simulation result, so that the overall network security level is improved.

The invention relates to a cross-domain three-dimensional feature collaborative dynamic gating fusion network system and a detection method, belongs to the technical field of generative model detection, solves the problems of insufficient utilization of multi-dimensional features and lack of cross-domain feature fusion in the prior art, and comprises the following steps: S1, obtaining a to-be-detected image and adjusting the to-be-detected image into a preset model input size, performing normalization processing to obtain a preprocessed image; s2, performing three-branch feature extraction to obtain gradient features, frequency features and spatial domain features; s3, performing cross-domain feature alignment and fusion to obtain features after channel compression; s4, performing dynamic gating fusion to obtain a final fusion feature; and S5, inputting the obtained final fusion features into a classifier, carrying out AI generated graph dichotomy detection to obtain the probability that the to-be-detected image is the AI generated graph, comparing the probability with a discrimination threshold, if the probability is greater than the discrimination threshold, determining that the to-be-detected image is the AI generated graph, otherwise, determining that the to-be-detected image is not the AI generated graph, and outputting a determination result as a detection result.