175 results about "Large networks" patented technology

The invention discloses a network threat deduction system and method based on Transform and a graph attention network model. The system mainly comprises four modules including a threat intelligence extraction module, a network threat entity construction module, a network threat deduction module and a deduction result application module. The method comprises the following steps: preprocessing and mining network security threat intelligence data by utilizing a graph attention network (GAT) model, constructing a complete network threat intelligence knowledge graph based on a data association relationship, and determining a vulnerability utilization weight in the graph; modeling is carried out on a reasoned path sequence based on a Transform model, a next reasoning sequence is predicted in a generative mode, and rapid and efficient network threat intelligence reasoning is achieved. According to the method, the complexity of attack deduction calculation is reduced, the deduction efficiency is improved, and security risk investigation and early warning can be carried out for a large-scale network environment.

Systems, methods, and computer readable media related to: training an encoder model that can be utilized to determine semantic similarity of a natural language textual string to each of one or more additional natural language textual strings (directly and / or indirectly); and / or using a trained encoder model to determine one or more responsive actions to perform in response to a natural language query. The encoder model is a machine learning model, such as a neural network model. In some implementations of training the encoder model, the encoder model is trained as part of a larger network architecture trained based on one or more tasks that are distinct from a “semantic textual similarity” task for which the encoder model can be used.

The invention provides a communication method and a communication device, and the method relates to the technical field of communication, and the method comprises the steps: a first UPF receives a first data message, the first data message comes from a first terminal, the first data message is a data message of a first group of services, the target IP address of the first data message is a first IP address, and the target IP address is a second IP address; the first IP address is a large network IP address of the second terminal, and both the first terminal and the second terminal sign a first group of services; and a second data message is sent to a second user plane function UPF, the second UPF is the UPF of the park where the second terminal is located, the second data message is generated based on the first data message, the target IP address of the second data message is a second IP address, and the second IP address is obtained based on the first IP address. The second IP address is a private network IP address applied by the second terminal based on the first group of services. Based on the method, the service access delay of the terminal can be reduced.

The present disclosure describes systems and methods for enabling real-time conversational dialog among a large population of networked human users while facilitating convergence on groupwise decisions, insights, and solutions, and amplifying collective intelligence. A collaboration server running a collaboration application is provided, wherein the collaboration server is in communication with the plurality of the networked computing devices and each computing device is associated with one user of the population of human participants. In some cases, the collaboration server defines a plurality of sub-groups of the population of human participants. A local chat application configured for displaying a conversational prompt received from the collaboration server is provided on each networked computing device. The local chat application enables real-time chat communication with other users of a sub-group assigned by the collaboration server. According to some embodiments, the computer mediated collaboration enables through communication between the collaboration application and the local chat applications.

The present disclosure describes systems and methods for enabling real-time conversational dialog among a large population of networked human users while facilitating convergence on groupwise decisions, insight extraction, and solutions, and amplifying collective intelligence. A plurality of computing devices associated with members of a population of participants is provided, wherein the plurality of computing devices is networked via a computer network and in communication with a central server. In some cases, the central server divides the population into a plurality of subgroups and enables an LLM-powered conversational surrogate agent associated with each subgroup. The conversational surrogate agent is configured to repeatedly observe a conversation among members of its assigned subgroup and store content of the conversation to extract insights from the conversation at appropriate intervals. The conversational surrogate agent assesses a numerical measure of conviction, confidence, or scope associated with each unique insight within the conversation, passes the insights and the numerical measure to other subgroups and modulates a strength of the insights based on the numerical measures.

The invention discloses a complex network node influence sorting method combining graph embedding and graph sampling in the field of complex networks. The complex network node influence sorting method comprises the following steps: S1, synthesizing a training data set based on different network topology models; s2, initializing the model; s3, pre-training and updating model embedding layer parameters by utilizing sorting learning; s4, model evaluation layer parameters are updated through reinforcement learning training; s5, sampling a real network by adopting random walk; s6, performing node influence sorting on each sub-network by using the trained model; and S7, calculating the node influence sequence of the original network through multi-source ranking fusion. According to the method, the model embedding layer is pre-trained through sorting learning, so that inductive graph embedding is effectively realized; reinforcement learning is used as node disconnection value learning, so that the algorithm has the capability of searching for disconnection nodes according to state iteration; the large-scale network is sampled through random walk, and the prediction efficiency and accuracy of the large-scale network are optimized.

The invention relates to the technical field of interphone communication, and discloses an interphone communication method based on a base station type relay, a base station, an interphone and a medium, and the method comprises the steps: transmitting a time frame to a network node in a first communication range based on a first voice communication channel, network nodes corresponding to all voice time slots in a time frame are broadcasted through a synchronous time slot of the time frame, the time frame comprises the synchronous time slot, a competition time slot and at least two voice time slots, and each interphone serves as one network node; acquiring voice information transmitted by the network node and other base stations through the voice time slot of the received time frame; broadcasting the received voice information to network nodes in a first communication range based on a first voice communication channel, and broadcasting the received voice information to other base stations in a second communication range based on a second voice communication channel, according to the invention, the mutual full-duplex talkback communication between the base station and the interphone in the whole large network can be realized, the communication time delay is short, the movable networking can be realized, and the networking is flexible.

A network operation and maintenance metrics question and answer method and system based on a knowledge graph and a large model, relating to the technical field of computers. According to the method, a large network model may be triggered to extract at least one type of target operation and maintenance data from entity objects, entity relationships, entity attributes, and operation and maintenance events in network operation and maintenance data, so as to construct a knowledge graph on the basis of the target operation and maintenance data; the knowledge graph can assist the large network model in responding to knowledge question and answer, and the knowledge question and answer result can further assist in enhancing a modeling process of the knowledge graph, thereby improving the response precision of the large network model to knowledge question and answer in the field of operation and maintenance; and the knowledge graph can model and represent operation and maintenance actions, thereby achieving the standardization and automation of the operation and maintenance actions. The large network model can further optimize these operation procedures by learning a large amount of operation and maintenance action data, thereby improving the efficiency of operation and maintenance.

The invention discloses an agricultural land boundary extraction method and system fusing SAM and an improved Segform model, and relates to the technical field of image processing, and the method comprises the steps: carrying out the polygonal ground feature extraction of a preprocessed image tile data set through employing the SAM model; inputting the agricultural land sample data set into an improved Segform model for optimization, and then performing agricultural land boundary extraction; the improved Segform model takes the Segform model as a basic network structure, a feature fusion module fuses high-level semantic information, a DySample ultra-light dynamic up-sampling module is adopted to generate sampling points, and a DANet dual attention mechanism and an ECA channel attention mechanism are added for feature optimization. According to the method, on the basis of high-resolution image data, refined extraction is carried out on the boundary of the remote sensing image by fusing an SAM large network model and an improved Segform model.

The present invention discloses a sharding blockchain system and a dynamic sharding method based on a repairable fountain code. According to the characteristics of the repairable fountain code, the shards in the system are divided into original shards and coded shards, and a method for storing and retrieving data in the system after adding new shards is proposed. Based on the rateless nature of the repairable fountain code, the number of shards in the system can be continuously increased. In addition, the method also solves the problem that when adding shards, the current sharding system must perform a large amount of data migration between shards, which leads to a large network bandwidth consumption, and ensures that the system throughput and security are also improved synchronously with the increase in the number of shards.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes generating, using a controller neural network, a batch of output sequences, each output sequence in the batch specifying a respective subset of a plurality of components of a large neural network that should be active during the processing of inputs by the large neural network; for each output sequence in the batch: determining a performance metric of the large neural network on the particular neural network task (i) in accordance with current values of the large network parameters and (ii) with only the subset of components specified by the output sequences active; and using the performance metrics for the output sequences in the batch to adjust the current values of the controller parameters of the controller neural network.

A method to access a device may include obtaining, at a first device, data over a short-range wireless network from a second device. The data may originate at a remote system that sends the data to the second device through a network connection over a wide area network. The method may also include in response to a fault at the second device, obtaining, at the first device from the remote system, a maintenance command for the second device. The maintenance command may be obtained by the first device over an analog voice network. The method may also include directing, from the first device to the second device, the maintenance command over the short-range wireless network to enable the second device to perform the maintenance command.

Systems and methods are provided for managing wireless devices, specifically for managing transitions between SU-MIMO pairing and MU-MIMO pairing based on group membership and signal quality. Methods include monitoring a signal quality between an access node and one or more wireless devices, determining that a signal quality metric is below a threshold, and determining that the one or more wireless devices belongs to one or more groups based at least in part on a required Quality of Service (QoS) of the one or more wireless devices. The methods further include transitioning the one or more wireless devices from SU-MIMO pairing to MU-MIMO pairing based on the determining that the one or more wireless devices belongs to the one or more groups and the determining that the signal quality metric is below the threshold.

The invention discloses a time sequence and congestion collaborative optimization-oriented GPU (Graphics Processing Unit) parallel acceleration global wiring method, which comprises the following steps of: according to a given netlist, dividing a super-large network by adopting a Kruskal algorithm in combination with a lookup set, and constructing a time sequence propagation path of the super-large network; performing network decomposition based on the timing margin estimation of the pins; calculating the time sequence weight of the two-pin network by adopting a time sequence weight calculation method based on an Elmore delay model; performing path cost calculation by adopting a cost function which comprehensively considers the time sequence and the congestion cost; executing two-level GPU parallel kernel acceleration mode wiring; optimizing the network topology by adopting a delay-aware pin connection improvement technology; the invention relates to a congestion-driven GPU (Graphics Processing Unit) accelerated routing and routing strategy for executing non-critical networks. According to the method, a high-quality wiring result with balanced time sequence congestion can be quickly obtained, the time sequence performance is effectively improved, and the requirement of a current super-large-scale high-performance circuit design wiring stage can be met.

The invention relates to the technical field of multi-element network equipment topological optimization, in particular to a multi-element network equipment topological optimization method based on clustering analysis. Comprising the following steps: setting a plurality of network nodes based on historical network topology data, and generating a communication evaluation value of each network node; setting a plurality of center nodes according to all the communication evaluation values, and establishing a communication topological structure according to all the center nodes; the method comprises the following steps: acquiring a feedback data packet according to a preset update time node, judging whether to update a communication topological structure according to the feedback data packet, establishing a plurality of network nodes based on historical network topological data, analyzing communication path information among the network nodes, effectively clustering the network nodes, and updating the communication topological structure according to the network nodes. According to the method, a large-scale network is divided into a plurality of small areas and clusters, and each cluster is iteratively optimized to construct a communication topological structure, so that an optimal communication path between network nodes is generated, and the communication efficiency between the network nodes is improved.

Systems, methods, and computer readable media related to: training an encoder model that can be utilized to determine semantic similarity of a natural language textual string to each of one or more additional natural language textual strings (directly and / or indirectly); and / or using a trained encoder model to determine one or more responsive actions to perform in response to a natural language query. The encoder model is a machine learning model, such as a neural network model. In some implementations of training the encoder model, the encoder model is trained as part of a larger network architecture trained based on one or more tasks that are distinct from a “semantic textual similarity” task for which the encoder model can be used.

A personal area network that includes a wearable electronic device, a system and methods of using the personal area network that includes a wearable electronic device. The wearable electronic device can act as an aggregator of the data that is being acquired by the one or more sensors and from other devices that are within wireless signal range of the personal area network in order to send some or all of the data over a wireless low power wide area network to remote locations within a larger network for subsequent processing, user notification, analysis of location-determination, contact tracing or the like. Data may flow in a bidirectional manner between the wearable electronic device and at least some of the other devices within the personal area network. In one form, the aggregated data may be used to provide information related to one or more operational parameters of an industrial asset and, if necessary, take control-based action in order to adjust one or more such operational parameters. In one form, a communication network formed by the wearable electronic device is used within an industrial setting in order to perform such data acquisition, processing and related control.

The invention discloses a forest fire smoke monitoring method and related device based on false detection feedback and model self-evolution, and the method comprises the steps: obtaining a video stream of a monitoring region, carrying out the preprocessing, inputting a target detection model and a scene understanding model, and judging whether a candidate alarm event is generated or not through consistency analysis; when a candidate alarm event is generated, a work order is generated for manual judgment, a real alarm executes a disposal process, and a false alarm is stored in a database; screening high-value false detection samples based on an information entropy priority strategy, storing the samples into a dynamic memory bank, selecting the samples to form an incremental training set, performing incremental training on a pre-training teacher model, and introducing low-rank constraint stability parameters; migrating the discrimination ability of the teacher model to the student model through knowledge distillation, wherein alignment of a channel dimension and a multi-scale space dimension is carried out; and redeploying the updated student model to execute target detection. The invention aims to solve the problems that the current monitoring system depends on manpower, the coverage capability is limited, the response is slow and the cost is high, and the traditional method is high in false alarm rate, easy to leak and misjudge, difficult in large-scale network edge deployment, limited in light-weight model discrimination capability, lack of linkage between alarm processing and model updating and the like, and more accurate and efficient forest fire smoke monitoring is realized.

The invention discloses a robot group real-time control method based on edge computing in the field of robots, and the method comprises the following steps: 1), deploying an edge computing node on each robot through employing a distributed edge computing architecture, and carrying out the real-time processing of local sensor data and the generation of a control instruction, communication and collaboration are carried out among the edge computing nodes through a wireless network, so that distributed decision and control are realized; and step 2), enabling each robot to autonomously learn a cooperative control strategy according to self sensor data and state information of the surrounding robots by using a cooperative control algorithm based on deep reinforcement learning. Through a distributed edge computing architecture, a deep reinforcement learning algorithm and a data compression transmission optimization technology, the problems of poor real-time performance, large network bandwidth pressure, low system reliability and the like existing in a traditional method are effectively solved, and the method has important application value and development prospect.

The invention provides a topological structure, a routing method and a routing device of a multi-dimensional hypercube interconnection network, and the multi-dimensional hypercube interconnection network comprises 2N network nodes. Target network nodes included by each sub-network in 2N-3 sub-networks of the multi-dimensional hypercube interconnection network as a target sub-network are divided into a first node set and a second node set, and four target network nodes in the first node set are connected with four target network nodes in the second node set in a one-to-one correspondence manner; the four target network nodes in the first node set are connected into a ring, the first network node in the second node set is connected with the third network node and the fourth network node, and the second network node is connected with the third network node and the fourth network node. According to the method and the device, the problem that the network communication time delay of the multi-dimensional hypercube interconnection network is relatively large is solved, and the effect of reducing the network communication time delay of the multi-dimensional hypercube interconnection network is achieved.

The invention discloses a partition calculation method of an undirected graph reachable matrix, and relates to the technical field of data mining. According to the method, the undirected graph is divided into a plurality of sub-graphs through a partitioning algorithm, and the reachable matrix of each sub-graph is independently calculated, so that the complexity and resource requirements of global calculation are reduced, and the calculation efficiency is improved. In addition, a multi-core and distributed computing environment is utilized, so that network topology analysis scenes, such as power grid operation analysis, dynamic traffic scheduling and the like, with high requirements on real-time performance of a large-scale network can be efficiently processed. For network dynamic changes, a boundary equivalent data updating mechanism is introduced, rapid adjustment of a local matrix is achieved, global recalculation is not needed, the response speed of the system in a frequent topology change scene is remarkably improved, and the method is suitable for the business fields of power grid operation analysis, dynamic traffic scheduling and the like. And efficient operation and real-time response capability of the system are effectively guaranteed.

Efficient scaling of in-network compute operations to large numbers of compute nodes is disclosed. Each compute node is connected to a same plurality of network compute nodes, such as compute-enabled network switches. Compute processes at the compute nodes generate local gradients or other vectors by, for instance, performing a forward pass on a neural network. Each vector comprises values for a same set of vector elements. Each network compute node is assigned to, based on the local vectors, reduce vector data for a different a subset of the vector elements. Each network compute node returns a result chunk for the elements it processed back to each of the compute nodes, whereby each compute node receives the full result vector. This configuration may, in some embodiments, reduce buffering, processing, and / or other resource requirements for the network compute node or network at large.

The invention provides a network router management method and system. The method comprises the following steps: collecting a target routing address of a target router through an address collector in a routing interface circuit; when the target router exits the network, the routing interface circuit is triggered to send routing exit information to other routers, and the routing exit information comprises the target routing address; and searching other routing tables of other routers based on the target routing address, and marking and / or deleting entries including the target routing address in the other routing tables, so that when the router exits the network, routing exit information can be sent through the routing interface circuit. The problem that the accuracy of the routing table of each router is ensured by sending the routing table at present, resulting in a large network load and affecting the network transmission speed can be solved, the network load is reduced, and the network transmission speed is improved.

The application relates to the technical field of network communication, and discloses a network self-healing device based on node state data, which aims to improve the stability and self-healing ability of network communication. By monitoring the network state in real time, combining the extended Kalman filtering algorithm to perform state estimation and filtering, and combining the ant colony algorithm and the simulated annealing algorithm to perform fault prediction, path selection and resource allocation, the potential fault can be predicted and quickly recovered. The device comprises five modules of state monitoring, state estimation and filtering, fault prediction and prevention, fault recovery and resource reallocation, forms a closed-loop optimization mechanism, and is especially suitable for complex large network environments, such as data center networks.

The present application relates to a method for individual identification of electromagnetic signals using open set semi-supervised learning technology, belonging to the field of electromagnetic signal identification processing. The technical scheme of the present application trains a large classification network as a first model through self-supervised pre-training, so that it can more fully learn the internal relationship of unlabeled data and improve the network feature extraction capability; a small-scale classification network model closer to the characteristics of the identification sample is used as a second model, and in semi-supervised learning, the feature extraction capability of the pre-trained model is used to filter out unlabeled data other than the target classification, reducing the negative impact of out-of-distribution unlabeled data, and at the same time, model distillation is used to enable the small-scale classification network model to learn the generalization and robustness of the large network model for data features. Through the above three aspects, the influence of data other than the target classification on the semi-supervised learning network recognition accuracy in real situations is reduced, and robust identification of electromagnetic signals is achieved.

The present invention discloses a method and device for controlling false information on a social network, and relates to the technical field of network information analysis. Large networks can be decomposed quickly and efficiently, thereby controlling the spread of false information in a timely manner and reducing the losses caused by it. The method comprises: determining the first sequence with the smallest network resilience among multiple first sequences as the optimal sequence; deleting multiple third nodes with the highest probability from the coarse-grained network and adding them to a second set of removed nodes; placing the newly occupied nodes at the beginning of the removed sequence according to the sequence number, placing the unoccupied nodes included in the unoccupied node set at the middle of the removed sequence according to the node sequence number, and placing the removed nodes at the end of the removed sequence to form a removed sequence, and connecting the optimal sequence and the removed sequence to obtain a final sequence.

The application belongs to the field of FPGA-based hardware accelerator design, and proposes a point cloud target detection neural network accelerator and an acceleration method based on FPGA. The convolution accelerator comprises an instruction decoding module, a convolution module, an accumulation module, a truncation module and an activation function. The intermediate value cache only temporarily stores the channels of one feature map, consumes less BRAM, and is suitable for accelerating the point cloud target detection neural network with large feature map size, large number of channels and large network size. The application has flexible configurability and excellent reusability, so the application can accelerate different convolution layers of the point cloud target detection neural network, and is suitable for being integrated as an IP into a large design, reducing FPGA resource consumption and improving resource utilization. Moreover, the weight and the input feature map share one data input channel, and the convolution intermediate value is temporarily stored on-chip BRAM, reducing the feature map carrying frequency and saving the FPGA interface bandwidth.

The invention discloses a statistical QoS (Quality of Service)-based transmission link selection method and system, and the method comprises the following steps: constructing a multi-service transmission link selection scene, constructing communication terminal services with different service quality requirements in the scene, and supporting different types of network resources; the maximum reachable rate is calculated according to different service types, and then the effective capacity of the service is obtained; according to the current service type, a network transmission link j with the maximum effective capacity ECi is selected for transmission; the system comprises a high-orbit satellite, a low-orbit satellite and a plurality of communication terminals, and a single communication terminal sends a plurality of traffic flows. According to the method, the statistical QoS requirements of different services can be considered, different application scenes are adapted by adjusting the statistical QoS constraints of different service types, the requirements of various services are flexibly met, and environmental changes are dynamically adapted.

The present application is a kind of lightweight target detection method for embedded platform, which overcomes the problems of large network parameter quantity, slow detection speed and poor precision index in the prior art. The present application not only solves the problems of slow speed and low accuracy of the current detection method in the deployment of embedded devices, but also optimizes the computation graph for specific operators from the hardware level, enabling fast and accurate target detection on limited resource devices. The present application comprises the following steps: step 1: obtaining basic data and making data set; step 2: data enhancement preprocessing; step 3: constructing a benchmark network model and pre-training; step 4: building a lightweight detection network model; step 5: reparameterization operation and pruning on the overall network structure; step 6: knowledge distillation to restore accuracy; step 7: deployment and acceleration of embedded platform.

The invention discloses a sensor network time synchronization method based on local bidirectional correction and related equipment, relates to the technical field of sensor networks, and solves the problem of high overhead of a bidirectional message time synchronization network. According to the method, the communication range is reduced through local bidirectional correction, and the synchronization hop count is reduced through hierarchical division of a topological structure, so that the network overhead is reduced while the overall time synchronization of the sensor network is realized: the reference nodes are dynamically elected to adapt to the network communication quality change, and the time synchronization accuracy is ensured while the network communication quality is improved. And the robustness of the time synchronization method is improved.